diff --git a/Assignment3.ipynb b/Assignment3.ipynb
index 4a1ac34..ff36480 100644
--- a/Assignment3.ipynb
+++ b/Assignment3.ipynb
@@ -1,42 +1,21 @@
{
"cells": [
- {
- "cell_type": "markdown",
- "id": "82d0cd9f",
- "metadata": {},
- "source": [
- "# Assignment3"
- ]
- },
{
"cell_type": "code",
"execution_count": 1,
- "id": "59764a58",
+ "id": "cfda6557",
"metadata": {},
"outputs": [],
"source": [
- "import pandas as pd\n",
"import numpy as np\n",
- "import matplotlib.pyplot as plt\n",
- "from sklearn import datasets, linear_model\n",
- "from sklearn.metrics import mean_squared_error\n",
- "from sklearn.metrics import r2_score"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "id": "7b522d7d",
- "metadata": {},
- "outputs": [],
- "source": [
- "df= pd.read_csv('superheated_vapor_properties.csv')"
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
- "execution_count": 3,
- "id": "a7f6e1db",
+ "execution_count": 5,
+ "id": "1e1c9322",
"metadata": {},
"outputs": [
{
@@ -409,95 +388,377 @@
"[544 rows x 37 columns]"
]
},
- "execution_count": 3,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "df"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "id": "f62f03c4",
- "metadata": {},
- "outputs": [],
- "source": [
- "df1=df.loc[(df['Property']=='V')&(df['Pressure']<=300)]['Liq_Sat'][:-8]\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "id": "e10f35df",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 1.000\n",
- "4 1.010\n",
- "8 1.017\n",
- "12 1.022\n",
- "16 1.027\n",
- "20 1.030\n",
- "24 1.037\n",
- "28 1.043\n",
- "32 1.044\n",
- "Name: Liq_Sat, dtype: float64"
- ]
- },
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "id": "cd74ea41",
- "metadata": {},
- "outputs": [],
- "source": [
- "df2=df.loc[(df['Property']=='V')&((df['Pressure']<=1500)&(df['Pressure']>=300))]['Liq_Sat'][:-19]"
+ "df = pd.read_csv(\"superheated_vapor_properties.csv\")\n",
+ "df"
]
},
{
"cell_type": "code",
"execution_count": 7,
- "id": "b31f67c3",
+ "id": "1fac39f0",
"metadata": {},
"outputs": [
{
"data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Property \n",
+ " Liq_Sat \n",
+ " Vap_Sat \n",
+ " 75 \n",
+ " 100 \n",
+ " 125 \n",
+ " 150 \n",
+ " 175 \n",
+ " 200 \n",
+ " ... \n",
+ " 425 \n",
+ " 450 \n",
+ " 475 \n",
+ " 500 \n",
+ " 525 \n",
+ " 550 \n",
+ " 575 \n",
+ " 600 \n",
+ " 625 \n",
+ " 650 \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 \n",
+ " 1.0 \n",
+ " V \n",
+ " 1.000 \n",
+ " 129200.000 \n",
+ " 160640.0 \n",
+ " 172180.0 \n",
+ " 183720.0 \n",
+ " 195270.0 \n",
+ " 206810.0 \n",
+ " 218350.0 \n",
+ " ... \n",
+ " NaN \n",
+ " 333730.000 \n",
+ " NaN \n",
+ " 356810.000 \n",
+ " NaN \n",
+ " 379880.000 \n",
+ " NaN \n",
+ " 402960.000 \n",
+ " NaN \n",
+ " 426040.000 \n",
+ " \n",
+ " \n",
+ " 4 \n",
+ " 10.0 \n",
+ " V \n",
+ " 1.010 \n",
+ " 14670.000 \n",
+ " 16030.0 \n",
+ " 17190.0 \n",
+ " 18350.0 \n",
+ " 19510.0 \n",
+ " 20660.0 \n",
+ " 21820.0 \n",
+ " ... \n",
+ " NaN \n",
+ " 33370.000 \n",
+ " NaN \n",
+ " 35670.000 \n",
+ " NaN \n",
+ " 37980.000 \n",
+ " NaN \n",
+ " 40290.000 \n",
+ " NaN \n",
+ " 42600.000 \n",
+ " \n",
+ " \n",
+ " 8 \n",
+ " 20.0 \n",
+ " V \n",
+ " 1.017 \n",
+ " 7649.800 \n",
+ " 8000.0 \n",
+ " 8584.7 \n",
+ " 9167.1 \n",
+ " 9748.0 \n",
+ " 10320.0 \n",
+ " 10900.0 \n",
+ " ... \n",
+ " NaN \n",
+ " 16680.000 \n",
+ " NaN \n",
+ " 17830.000 \n",
+ " NaN \n",
+ " 18990.000 \n",
+ " NaN \n",
+ " 20140.000 \n",
+ " NaN \n",
+ " 21300.000 \n",
+ " \n",
+ " \n",
+ " 12 \n",
+ " 30.0 \n",
+ " V \n",
+ " 1.022 \n",
+ " 5229.300 \n",
+ " 5322.0 \n",
+ " 5714.4 \n",
+ " 6104.6 \n",
+ " 6493.2 \n",
+ " 6880.8 \n",
+ " 7267.5 \n",
+ " ... \n",
+ " NaN \n",
+ " 11120.000 \n",
+ " NaN \n",
+ " 11890.000 \n",
+ " NaN \n",
+ " 12660.000 \n",
+ " NaN \n",
+ " 13430.000 \n",
+ " NaN \n",
+ " 14190.000 \n",
+ " \n",
+ " \n",
+ " 16 \n",
+ " 40.0 \n",
+ " V \n",
+ " 1.027 \n",
+ " 3993.400 \n",
+ " NaN \n",
+ " 4279.2 \n",
+ " 4573.3 \n",
+ " 4865.8 \n",
+ " 5157.2 \n",
+ " 5447.8 \n",
+ " ... \n",
+ " NaN \n",
+ " 8340.100 \n",
+ " NaN \n",
+ " 8917.600 \n",
+ " NaN \n",
+ " 9494.900 \n",
+ " NaN \n",
+ " 10070.000 \n",
+ " NaN \n",
+ " 10640.000 \n",
+ " \n",
+ " \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " \n",
+ " \n",
+ " 524 \n",
+ " 10600.0 \n",
+ " V \n",
+ " 1.474 \n",
+ " 16.778 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 26.276 \n",
+ " 27.834 \n",
+ " 29.313 \n",
+ " 30.732 \n",
+ " 32.106 \n",
+ " 33.444 \n",
+ " 34.753 \n",
+ " 36.039 \n",
+ " 37.304 \n",
+ " 38.552 \n",
+ " \n",
+ " \n",
+ " 528 \n",
+ " 10800.0 \n",
+ " V \n",
+ " 1.481 \n",
+ " 16.385 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 25.703 \n",
+ " 27.245 \n",
+ " 28.706 \n",
+ " 30.106 \n",
+ " 31.461 \n",
+ " 32.779 \n",
+ " 34.069 \n",
+ " 35.335 \n",
+ " 36.580 \n",
+ " 37.808 \n",
+ " \n",
+ " \n",
+ " 532 \n",
+ " 11000.0 \n",
+ " V \n",
+ " 1.489 \n",
+ " 16.006 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 25.151 \n",
+ " 26.676 \n",
+ " 28.120 \n",
+ " 29.503 \n",
+ " 30.839 \n",
+ " 32.139 \n",
+ " 33.410 \n",
+ " 34.656 \n",
+ " 35.882 \n",
+ " 37.091 \n",
+ " \n",
+ " \n",
+ " 536 \n",
+ " 11200.0 \n",
+ " V \n",
+ " 1.496 \n",
+ " 15.639 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 24.619 \n",
+ " 26.128 \n",
+ " 27.555 \n",
+ " 28.921 \n",
+ " 30.240 \n",
+ " 31.521 \n",
+ " 32.774 \n",
+ " 34.002 \n",
+ " 35.210 \n",
+ " 36.400 \n",
+ " \n",
+ " \n",
+ " 540 \n",
+ " 11400.0 \n",
+ " V \n",
+ " 1.504 \n",
+ " 15.284 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 24.104 \n",
+ " 25.599 \n",
+ " 27.010 \n",
+ " 28.359 \n",
+ " 29.661 \n",
+ " 30.925 \n",
+ " 32.160 \n",
+ " 33.370 \n",
+ " 34.560 \n",
+ " 35.733 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
136 rows × 37 columns
\n",
+ "
"
+ ],
"text/plain": [
- "64 1.073\n",
- "68 1.076\n",
- "72 1.079\n",
- "76 1.081\n",
- "80 1.084\n",
- "84 1.086\n",
- "88 1.088\n",
- "92 1.091\n",
- "96 1.093\n",
- "100 1.095\n",
- "104 1.097\n",
- "108 1.099\n",
- "112 1.101\n",
- "116 1.103\n",
- "120 1.105\n",
- "124 1.106\n",
- "128 1.108\n",
- "132 1.110\n",
- "136 1.112\n",
- "140 1.113\n",
- "Name: Liq_Sat, dtype: float64"
+ " Pressure Property Liq_Sat Vap_Sat 75 100 125 \\\n",
+ "0 1.0 V 1.000 129200.000 160640.0 172180.0 183720.0 \n",
+ "4 10.0 V 1.010 14670.000 16030.0 17190.0 18350.0 \n",
+ "8 20.0 V 1.017 7649.800 8000.0 8584.7 9167.1 \n",
+ "12 30.0 V 1.022 5229.300 5322.0 5714.4 6104.6 \n",
+ "16 40.0 V 1.027 3993.400 NaN 4279.2 4573.3 \n",
+ ".. ... ... ... ... ... ... ... \n",
+ "524 10600.0 V 1.474 16.778 NaN NaN NaN \n",
+ "528 10800.0 V 1.481 16.385 NaN NaN NaN \n",
+ "532 11000.0 V 1.489 16.006 NaN NaN NaN \n",
+ "536 11200.0 V 1.496 15.639 NaN NaN NaN \n",
+ "540 11400.0 V 1.504 15.284 NaN NaN NaN \n",
+ "\n",
+ " 150 175 200 ... 425 450 475 \\\n",
+ "0 195270.0 206810.0 218350.0 ... NaN 333730.000 NaN \n",
+ "4 19510.0 20660.0 21820.0 ... NaN 33370.000 NaN \n",
+ "8 9748.0 10320.0 10900.0 ... NaN 16680.000 NaN \n",
+ "12 6493.2 6880.8 7267.5 ... NaN 11120.000 NaN \n",
+ "16 4865.8 5157.2 5447.8 ... NaN 8340.100 NaN \n",
+ ".. ... ... ... ... ... ... ... \n",
+ "524 NaN NaN NaN ... 26.276 27.834 29.313 \n",
+ "528 NaN NaN NaN ... 25.703 27.245 28.706 \n",
+ "532 NaN NaN NaN ... 25.151 26.676 28.120 \n",
+ "536 NaN NaN NaN ... 24.619 26.128 27.555 \n",
+ "540 NaN NaN NaN ... 24.104 25.599 27.010 \n",
+ "\n",
+ " 500 525 550 575 600 625 650 \n",
+ "0 356810.000 NaN 379880.000 NaN 402960.000 NaN 426040.000 \n",
+ "4 35670.000 NaN 37980.000 NaN 40290.000 NaN 42600.000 \n",
+ "8 17830.000 NaN 18990.000 NaN 20140.000 NaN 21300.000 \n",
+ "12 11890.000 NaN 12660.000 NaN 13430.000 NaN 14190.000 \n",
+ "16 8917.600 NaN 9494.900 NaN 10070.000 NaN 10640.000 \n",
+ ".. ... ... ... ... ... ... ... \n",
+ "524 30.732 32.106 33.444 34.753 36.039 37.304 38.552 \n",
+ "528 30.106 31.461 32.779 34.069 35.335 36.580 37.808 \n",
+ "532 29.503 30.839 32.139 33.410 34.656 35.882 37.091 \n",
+ "536 28.921 30.240 31.521 32.774 34.002 35.210 36.400 \n",
+ "540 28.359 29.661 30.925 32.160 33.370 34.560 35.733 \n",
+ "\n",
+ "[136 rows x 37 columns]"
]
},
"execution_count": 7,
@@ -506,630 +767,3239 @@
}
],
"source": [
- "df2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "id": "73137238",
- "metadata": {},
- "outputs": [],
- "source": [
- "df3=df.loc[(df['Property']=='V')&(df['Pressure']>=1500)]['Liq_Sat'][:-40]"
+ "V_data=df[df['Property']=='V']\n",
+ "V_data"
]
},
{
"cell_type": "code",
- "execution_count": 9,
- "id": "277025fe",
+ "execution_count": 10,
+ "id": "42175ca0",
"metadata": {},
"outputs": [
{
"data": {
- "text/plain": [
- "216 1.154\n",
- "220 1.156\n",
- "224 1.159\n",
- "228 1.161\n",
- "232 1.163\n",
- "236 1.166\n",
- "240 1.168\n",
- "244 1.170\n",
- "248 1.172\n",
- "252 1.174\n",
- "256 1.177\n",
- "260 1.181\n",
- "264 1.185\n",
- "268 1.189\n",
- "272 1.193\n",
- "276 1.197\n",
- "280 1.201\n",
- "284 1.205\n",
- "288 1.209\n",
- "292 1.213\n",
- "296 1.216\n",
- "300 1.220\n",
- "304 1.224\n",
- "308 1.227\n",
- "312 1.231\n",
- "316 1.235\n",
- "320 1.238\n",
- "324 1.242\n",
- "328 1.245\n",
- "332 1.249\n",
- "336 1.252\n",
- "340 1.256\n",
- "344 1.259\n",
- "348 1.262\n",
- "352 1.266\n",
- "356 1.269\n",
- "360 1.272\n",
- "364 1.276\n",
- "368 1.279\n",
- "372 1.282\n",
- "376 1.286\n",
- "380 1.289\n",
- "Name: Liq_Sat, dtype: float64"
- ]
- },
- "execution_count": 9,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "df3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "id": "a5512554",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_train1=list(df.loc[(df['Property']=='V')&(df['Pressure']<=300)]['Pressure'])[:-8]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "id": "e0c6dbc2",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_train1=np.array(pressure_train1)\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "id": "b194ed9b",
- "metadata": {},
- "outputs": [],
- "source": [
- "volume_train=list(df1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "id": "3c010621",
- "metadata": {},
- "outputs": [],
- "source": [
- "volume_train=np.array(volume_train)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "id": "1d920ced",
- "metadata": {},
- "outputs": [],
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Property \n",
+ " Liq_Sat \n",
+ " Vap_Sat \n",
+ " 75 \n",
+ " 100 \n",
+ " 125 \n",
+ " 150 \n",
+ " 175 \n",
+ " 200 \n",
+ " ... \n",
+ " 425 \n",
+ " 450 \n",
+ " 475 \n",
+ " 500 \n",
+ " 525 \n",
+ " 550 \n",
+ " 575 \n",
+ " 600 \n",
+ " 625 \n",
+ " 650 \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 \n",
+ " 1.000 \n",
+ " V \n",
+ " 1.000 \n",
+ " 129200.00 \n",
+ " 160640.0 \n",
+ " 172180.0 \n",
+ " 183720.00 \n",
+ " 195270.00 \n",
+ " 206810.00 \n",
+ " 218350.00 \n",
+ " ... \n",
+ " NaN \n",
+ " 333730.0 \n",
+ " NaN \n",
+ " 356810.0 \n",
+ " NaN \n",
+ " 379880.0 \n",
+ " NaN \n",
+ " 402960.0 \n",
+ " NaN \n",
+ " 426040.0 \n",
+ " \n",
+ " \n",
+ " 4 \n",
+ " 10.000 \n",
+ " V \n",
+ " 1.010 \n",
+ " 14670.00 \n",
+ " 16030.0 \n",
+ " 17190.0 \n",
+ " 18350.00 \n",
+ " 19510.00 \n",
+ " 20660.00 \n",
+ " 21820.00 \n",
+ " ... \n",
+ " NaN \n",
+ " 33370.0 \n",
+ " NaN \n",
+ " 35670.0 \n",
+ " NaN \n",
+ " 37980.0 \n",
+ " NaN \n",
+ " 40290.0 \n",
+ " NaN \n",
+ " 42600.0 \n",
+ " \n",
+ " \n",
+ " 8 \n",
+ " 20.000 \n",
+ " V \n",
+ " 1.017 \n",
+ " 7649.80 \n",
+ " 8000.0 \n",
+ " 8584.7 \n",
+ " 9167.10 \n",
+ " 9748.00 \n",
+ " 10320.00 \n",
+ " 10900.00 \n",
+ " ... \n",
+ " NaN \n",
+ " 16680.0 \n",
+ " NaN \n",
+ " 17830.0 \n",
+ " NaN \n",
+ " 18990.0 \n",
+ " NaN \n",
+ " 20140.0 \n",
+ " NaN \n",
+ " 21300.0 \n",
+ " \n",
+ " \n",
+ " 12 \n",
+ " 30.000 \n",
+ " V \n",
+ " 1.022 \n",
+ " 5229.30 \n",
+ " 5322.0 \n",
+ " 5714.4 \n",
+ " 6104.60 \n",
+ " 6493.20 \n",
+ " 6880.80 \n",
+ " 7267.50 \n",
+ " ... \n",
+ " NaN \n",
+ " 11120.0 \n",
+ " NaN \n",
+ " 11890.0 \n",
+ " NaN \n",
+ " 12660.0 \n",
+ " NaN \n",
+ " 13430.0 \n",
+ " NaN \n",
+ " 14190.0 \n",
+ " \n",
+ " \n",
+ " 16 \n",
+ " 40.000 \n",
+ " V \n",
+ " 1.027 \n",
+ " 3993.40 \n",
+ " NaN \n",
+ " 4279.2 \n",
+ " 4573.30 \n",
+ " 4865.80 \n",
+ " 5157.20 \n",
+ " 5447.80 \n",
+ " ... \n",
+ " NaN \n",
+ " 8340.1 \n",
+ " NaN \n",
+ " 8917.6 \n",
+ " NaN \n",
+ " 9494.9 \n",
+ " NaN \n",
+ " 10070.0 \n",
+ " NaN \n",
+ " 10640.0 \n",
+ " \n",
+ " \n",
+ " 20 \n",
+ " 50.000 \n",
+ " V \n",
+ " 1.030 \n",
+ " 3240.20 \n",
+ " NaN \n",
+ " 3418.1 \n",
+ " 3654.50 \n",
+ " 3889.30 \n",
+ " 4123.00 \n",
+ " 4356.00 \n",
+ " ... \n",
+ " NaN \n",
+ " 6671.4 \n",
+ " NaN \n",
+ " 7133.5 \n",
+ " NaN \n",
+ " 7595.5 \n",
+ " NaN \n",
+ " 8057.4 \n",
+ " NaN \n",
+ " 8519.2 \n",
+ " \n",
+ " \n",
+ " 24 \n",
+ " 75.000 \n",
+ " V \n",
+ " 1.037 \n",
+ " 2216.90 \n",
+ " NaN \n",
+ " 2269.8 \n",
+ " 2429.40 \n",
+ " 2587.30 \n",
+ " 2744.20 \n",
+ " 2900.20 \n",
+ " ... \n",
+ " NaN \n",
+ " 4446.4 \n",
+ " NaN \n",
+ " 4754.7 \n",
+ " NaN \n",
+ " 5062.8 \n",
+ " NaN \n",
+ " 5370.9 \n",
+ " NaN \n",
+ " 5678.9 \n",
+ " \n",
+ " \n",
+ " 28 \n",
+ " 100.000 \n",
+ " V \n",
+ " 1.043 \n",
+ " 1693.70 \n",
+ " NaN \n",
+ " 1695.5 \n",
+ " 1816.70 \n",
+ " 1936.30 \n",
+ " 2054.70 \n",
+ " 2172.30 \n",
+ " ... \n",
+ " NaN \n",
+ " 3334.0 \n",
+ " NaN \n",
+ " 3565.3 \n",
+ " NaN \n",
+ " 3796.5 \n",
+ " NaN \n",
+ " 4027.7 \n",
+ " NaN \n",
+ " 4258.8 \n",
+ " \n",
+ " \n",
+ " 32 \n",
+ " 101.325 \n",
+ " V \n",
+ " 1.044 \n",
+ " 1673.00 \n",
+ " NaN \n",
+ " 1673.0 \n",
+ " 1792.70 \n",
+ " 1910.70 \n",
+ " 2027.70 \n",
+ " 2143.80 \n",
+ " ... \n",
+ " NaN \n",
+ " 3290.3 \n",
+ " NaN \n",
+ " 3518.7 \n",
+ " NaN \n",
+ " 3746.9 \n",
+ " NaN \n",
+ " 3975.0 \n",
+ " NaN \n",
+ " 4203.1 \n",
+ " \n",
+ " \n",
+ " 36 \n",
+ " 125.000 \n",
+ " V \n",
+ " 1.049 \n",
+ " 1374.60 \n",
+ " NaN \n",
+ " NaN \n",
+ " 1449.10 \n",
+ " 1545.60 \n",
+ " 1641.00 \n",
+ " 1735.60 \n",
+ " ... \n",
+ " NaN \n",
+ " 2666.5 \n",
+ " NaN \n",
+ " 2851.7 \n",
+ " NaN \n",
+ " 3036.8 \n",
+ " NaN \n",
+ " 3221.8 \n",
+ " NaN \n",
+ " 3406.7 \n",
+ " \n",
+ " \n",
+ " 40 \n",
+ " 150.000 \n",
+ " V \n",
+ " 1.053 \n",
+ " 1159.00 \n",
+ " NaN \n",
+ " NaN \n",
+ " 1204.00 \n",
+ " 1285.20 \n",
+ " 1365.20 \n",
+ " 1444.40 \n",
+ " ... \n",
+ " NaN \n",
+ " 2221.5 \n",
+ " NaN \n",
+ " 2375.9 \n",
+ " NaN \n",
+ " 2530.2 \n",
+ " NaN \n",
+ " 2684.5 \n",
+ " NaN \n",
+ " 2838.6 \n",
+ " \n",
+ " \n",
+ " 44 \n",
+ " 175.000 \n",
+ " V \n",
+ " 1.057 \n",
+ " 1003.34 \n",
+ " NaN \n",
+ " NaN \n",
+ " 1028.80 \n",
+ " 1099.10 \n",
+ " 1168.20 \n",
+ " 1236.40 \n",
+ " ... \n",
+ " NaN \n",
+ " 1903.7 \n",
+ " NaN \n",
+ " 2036.1 \n",
+ " NaN \n",
+ " 2168.4 \n",
+ " NaN \n",
+ " 2300.7 \n",
+ " NaN \n",
+ " 2432.9 \n",
+ " \n",
+ " \n",
+ " 48 \n",
+ " 200.000 \n",
+ " V \n",
+ " 1.061 \n",
+ " 885.44 \n",
+ " NaN \n",
+ " NaN \n",
+ " 897.47 \n",
+ " 959.54 \n",
+ " 1020.40 \n",
+ " 1080.40 \n",
+ " ... \n",
+ " NaN \n",
+ " 1665.3 \n",
+ " NaN \n",
+ " 1781.2 \n",
+ " NaN \n",
+ " 1897.1 \n",
+ " NaN \n",
+ " 2012.9 \n",
+ " NaN \n",
+ " 2128.6 \n",
+ " \n",
+ " \n",
+ " 52 \n",
+ " 225.000 \n",
+ " V \n",
+ " 1.064 \n",
+ " 792.97 \n",
+ " NaN \n",
+ " NaN \n",
+ " 795.25 \n",
+ " 850.97 \n",
+ " 905.44 \n",
+ " 959.06 \n",
+ " ... \n",
+ " NaN \n",
+ " 1479.9 \n",
+ " NaN \n",
+ " 1583.0 \n",
+ " NaN \n",
+ " 1686.0 \n",
+ " NaN \n",
+ " 1789.0 \n",
+ " NaN \n",
+ " 1891.9 \n",
+ " \n",
+ " \n",
+ " 56 \n",
+ " 250.000 \n",
+ " V \n",
+ " 1.068 \n",
+ " 718.44 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 764.09 \n",
+ " 813.47 \n",
+ " 861.98 \n",
+ " ... \n",
+ " NaN \n",
+ " 1331.5 \n",
+ " NaN \n",
+ " 1424.4 \n",
+ " NaN \n",
+ " 1517.2 \n",
+ " NaN \n",
+ " 1609.9 \n",
+ " NaN \n",
+ " 1702.5 \n",
+ " \n",
+ " \n",
+ " 60 \n",
+ " 275.000 \n",
+ " V \n",
+ " 1.071 \n",
+ " 657.04 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 693.00 \n",
+ " 738.21 \n",
+ " 782.55 \n",
+ " ... \n",
+ " NaN \n",
+ " 1210.2 \n",
+ " NaN \n",
+ " 1294.7 \n",
+ " NaN \n",
+ " 1379.0 \n",
+ " NaN \n",
+ " 1463.3 \n",
+ " NaN \n",
+ " 1547.6 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
16 rows × 37 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Property Liq_Sat Vap_Sat 75 100 125 \\\n",
+ "0 1.000 V 1.000 129200.00 160640.0 172180.0 183720.00 \n",
+ "4 10.000 V 1.010 14670.00 16030.0 17190.0 18350.00 \n",
+ "8 20.000 V 1.017 7649.80 8000.0 8584.7 9167.10 \n",
+ "12 30.000 V 1.022 5229.30 5322.0 5714.4 6104.60 \n",
+ "16 40.000 V 1.027 3993.40 NaN 4279.2 4573.30 \n",
+ "20 50.000 V 1.030 3240.20 NaN 3418.1 3654.50 \n",
+ "24 75.000 V 1.037 2216.90 NaN 2269.8 2429.40 \n",
+ "28 100.000 V 1.043 1693.70 NaN 1695.5 1816.70 \n",
+ "32 101.325 V 1.044 1673.00 NaN 1673.0 1792.70 \n",
+ "36 125.000 V 1.049 1374.60 NaN NaN 1449.10 \n",
+ "40 150.000 V 1.053 1159.00 NaN NaN 1204.00 \n",
+ "44 175.000 V 1.057 1003.34 NaN NaN 1028.80 \n",
+ "48 200.000 V 1.061 885.44 NaN NaN 897.47 \n",
+ "52 225.000 V 1.064 792.97 NaN NaN 795.25 \n",
+ "56 250.000 V 1.068 718.44 NaN NaN NaN \n",
+ "60 275.000 V 1.071 657.04 NaN NaN NaN \n",
+ "\n",
+ " 150 175 200 ... 425 450 475 500 525 \\\n",
+ "0 195270.00 206810.00 218350.00 ... NaN 333730.0 NaN 356810.0 NaN \n",
+ "4 19510.00 20660.00 21820.00 ... NaN 33370.0 NaN 35670.0 NaN \n",
+ "8 9748.00 10320.00 10900.00 ... NaN 16680.0 NaN 17830.0 NaN \n",
+ "12 6493.20 6880.80 7267.50 ... NaN 11120.0 NaN 11890.0 NaN \n",
+ "16 4865.80 5157.20 5447.80 ... NaN 8340.1 NaN 8917.6 NaN \n",
+ "20 3889.30 4123.00 4356.00 ... NaN 6671.4 NaN 7133.5 NaN \n",
+ "24 2587.30 2744.20 2900.20 ... NaN 4446.4 NaN 4754.7 NaN \n",
+ "28 1936.30 2054.70 2172.30 ... NaN 3334.0 NaN 3565.3 NaN \n",
+ "32 1910.70 2027.70 2143.80 ... NaN 3290.3 NaN 3518.7 NaN \n",
+ "36 1545.60 1641.00 1735.60 ... NaN 2666.5 NaN 2851.7 NaN \n",
+ "40 1285.20 1365.20 1444.40 ... NaN 2221.5 NaN 2375.9 NaN \n",
+ "44 1099.10 1168.20 1236.40 ... NaN 1903.7 NaN 2036.1 NaN \n",
+ "48 959.54 1020.40 1080.40 ... NaN 1665.3 NaN 1781.2 NaN \n",
+ "52 850.97 905.44 959.06 ... NaN 1479.9 NaN 1583.0 NaN \n",
+ "56 764.09 813.47 861.98 ... NaN 1331.5 NaN 1424.4 NaN \n",
+ "60 693.00 738.21 782.55 ... NaN 1210.2 NaN 1294.7 NaN \n",
+ "\n",
+ " 550 575 600 625 650 \n",
+ "0 379880.0 NaN 402960.0 NaN 426040.0 \n",
+ "4 37980.0 NaN 40290.0 NaN 42600.0 \n",
+ "8 18990.0 NaN 20140.0 NaN 21300.0 \n",
+ "12 12660.0 NaN 13430.0 NaN 14190.0 \n",
+ "16 9494.9 NaN 10070.0 NaN 10640.0 \n",
+ "20 7595.5 NaN 8057.4 NaN 8519.2 \n",
+ "24 5062.8 NaN 5370.9 NaN 5678.9 \n",
+ "28 3796.5 NaN 4027.7 NaN 4258.8 \n",
+ "32 3746.9 NaN 3975.0 NaN 4203.1 \n",
+ "36 3036.8 NaN 3221.8 NaN 3406.7 \n",
+ "40 2530.2 NaN 2684.5 NaN 2838.6 \n",
+ "44 2168.4 NaN 2300.7 NaN 2432.9 \n",
+ "48 1897.1 NaN 2012.9 NaN 2128.6 \n",
+ "52 1686.0 NaN 1789.0 NaN 1891.9 \n",
+ "56 1517.2 NaN 1609.9 NaN 1702.5 \n",
+ "60 1379.0 NaN 1463.3 NaN 1547.6 \n",
+ "\n",
+ "[16 rows x 37 columns]"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "model = linear_model.LinearRegression()\n"
+ "dataset1=V_data[(V_data['Pressure']<300)]\n",
+ "dataset1"
]
},
{
"cell_type": "code",
- "execution_count": 15,
- "id": "ef270881",
+ "execution_count": 20,
+ "id": "0149dea0",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Property \n",
+ " Liq_Sat \n",
+ " Vap_Sat \n",
+ " 75 \n",
+ " 100 \n",
+ " 125 \n",
+ " 150 \n",
+ " 175 \n",
+ " 200 \n",
+ " ... \n",
+ " 425 \n",
+ " 450 \n",
+ " 475 \n",
+ " 500 \n",
+ " 525 \n",
+ " 550 \n",
+ " 575 \n",
+ " 600 \n",
+ " 625 \n",
+ " 650 \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 68 \n",
+ " 325.0 \n",
+ " V \n",
+ " 1.076 \n",
+ " 561.75 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 583.58 \n",
+ " 622.41 \n",
+ " 660.33 \n",
+ " ... \n",
+ " NaN \n",
+ " 1023.50 \n",
+ " NaN \n",
+ " 1095.00 \n",
+ " NaN \n",
+ " 1166.50 \n",
+ " NaN \n",
+ " 1237.90 \n",
+ " NaN \n",
+ " 1309.20 \n",
+ " \n",
+ " \n",
+ " 72 \n",
+ " 350.0 \n",
+ " V \n",
+ " 1.079 \n",
+ " 524.00 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 540.58 \n",
+ " 576.90 \n",
+ " 612.31 \n",
+ " ... \n",
+ " NaN \n",
+ " 950.11 \n",
+ " NaN \n",
+ " 1016.60 \n",
+ " NaN \n",
+ " 1083.00 \n",
+ " NaN \n",
+ " 1149.30 \n",
+ " NaN \n",
+ " 1215.60 \n",
+ " \n",
+ " \n",
+ " 76 \n",
+ " 375.0 \n",
+ " V \n",
+ " 1.081 \n",
+ " 491.13 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 503.29 \n",
+ " 537.46 \n",
+ " 570.69 \n",
+ " ... \n",
+ " NaN \n",
+ " 886.54 \n",
+ " NaN \n",
+ " 948.66 \n",
+ " NaN \n",
+ " 1010.70 \n",
+ " NaN \n",
+ " 1072.60 \n",
+ " NaN \n",
+ " 1134.50 \n",
+ " \n",
+ " \n",
+ " 80 \n",
+ " 400.0 \n",
+ " V \n",
+ " 1.084 \n",
+ " 462.22 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 470.66 \n",
+ " 502.93 \n",
+ " 534.26 \n",
+ " ... \n",
+ " NaN \n",
+ " 830.92 \n",
+ " NaN \n",
+ " 889.19 \n",
+ " NaN \n",
+ " 947.35 \n",
+ " NaN \n",
+ " 1005.40 \n",
+ " NaN \n",
+ " 1063.40 \n",
+ " \n",
+ " \n",
+ " 84 \n",
+ " 425.0 \n",
+ " V \n",
+ " 1.086 \n",
+ " 436.61 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 441.85 \n",
+ " 472.47 \n",
+ " 502.12 \n",
+ " ... \n",
+ " NaN \n",
+ " 781.84 \n",
+ " NaN \n",
+ " 836.72 \n",
+ " NaN \n",
+ " 891.49 \n",
+ " NaN \n",
+ " 946.17 \n",
+ " NaN \n",
+ " 1000.80 \n",
+ " \n",
+ " \n",
+ " 88 \n",
+ " 450.0 \n",
+ " V \n",
+ " 1.088 \n",
+ " 413.75 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 416.24 \n",
+ " 445.38 \n",
+ " 473.55 \n",
+ " ... \n",
+ " NaN \n",
+ " 738.21 \n",
+ " NaN \n",
+ " 790.07 \n",
+ " NaN \n",
+ " 841.83 \n",
+ " NaN \n",
+ " 893.50 \n",
+ " NaN \n",
+ " 945.10 \n",
+ " \n",
+ " \n",
+ " 92 \n",
+ " 475.0 \n",
+ " V \n",
+ " 1.091 \n",
+ " 393.22 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 393.31 \n",
+ " 421.14 \n",
+ " 447.97 \n",
+ " ... \n",
+ " NaN \n",
+ " 699.18 \n",
+ " NaN \n",
+ " 748.34 \n",
+ " NaN \n",
+ " 797.40 \n",
+ " NaN \n",
+ " 846.37 \n",
+ " NaN \n",
+ " 895.27 \n",
+ " \n",
+ " \n",
+ " 96 \n",
+ " 500.0 \n",
+ " V \n",
+ " 1.093 \n",
+ " 374.68 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 399.31 \n",
+ " 424.96 \n",
+ " ... \n",
+ " NaN \n",
+ " 664.05 \n",
+ " NaN \n",
+ " 710.78 \n",
+ " NaN \n",
+ " 757.41 \n",
+ " NaN \n",
+ " 803.95 \n",
+ " NaN \n",
+ " 850.42 \n",
+ " \n",
+ " \n",
+ " 100 \n",
+ " 525.0 \n",
+ " V \n",
+ " 1.095 \n",
+ " 357.84 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 379.56 \n",
+ " 404.13 \n",
+ " ... \n",
+ " NaN \n",
+ " 632.26 \n",
+ " NaN \n",
+ " 676.80 \n",
+ " NaN \n",
+ " 721.23 \n",
+ " NaN \n",
+ " 765.57 \n",
+ " NaN \n",
+ " 809.85 \n",
+ " \n",
+ " \n",
+ " 104 \n",
+ " 550.0 \n",
+ " V \n",
+ " 1.097 \n",
+ " 342.48 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 361.60 \n",
+ " 385.19 \n",
+ " ... \n",
+ " NaN \n",
+ " 603.37 \n",
+ " NaN \n",
+ " 645.91 \n",
+ " NaN \n",
+ " 688.34 \n",
+ " NaN \n",
+ " 730.68 \n",
+ " NaN \n",
+ " 772.96 \n",
+ " \n",
+ " \n",
+ " 108 \n",
+ " 575.0 \n",
+ " V \n",
+ " 1.099 \n",
+ " 328.41 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 345.20 \n",
+ " 367.90 \n",
+ " ... \n",
+ " NaN \n",
+ " 576.98 \n",
+ " NaN \n",
+ " 617.70 \n",
+ " NaN \n",
+ " 658.30 \n",
+ " NaN \n",
+ " 698.83 \n",
+ " NaN \n",
+ " 739.28 \n",
+ " \n",
+ " \n",
+ " 112 \n",
+ " 600.0 \n",
+ " V \n",
+ " 1.101 \n",
+ " 315.47 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 330.16 \n",
+ " 352.04 \n",
+ " ... \n",
+ " NaN \n",
+ " 552.80 \n",
+ " NaN \n",
+ " 591.84 \n",
+ " NaN \n",
+ " 630.78 \n",
+ " NaN \n",
+ " 669.63 \n",
+ " NaN \n",
+ " 708.41 \n",
+ " \n",
+ " \n",
+ " 116 \n",
+ " 625.0 \n",
+ " V \n",
+ " 1.103 \n",
+ " 303.54 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 316.31 \n",
+ " 337.45 \n",
+ " ... \n",
+ " NaN \n",
+ " 530.55 \n",
+ " NaN \n",
+ " 568.05 \n",
+ " NaN \n",
+ " 605.45 \n",
+ " NaN \n",
+ " 642.76 \n",
+ " NaN \n",
+ " 680.01 \n",
+ " \n",
+ " \n",
+ " 120 \n",
+ " 650.0 \n",
+ " V \n",
+ " 1.105 \n",
+ " 292.49 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 303.53 \n",
+ " 323.98 \n",
+ " ... \n",
+ " NaN \n",
+ " 510.01 \n",
+ " NaN \n",
+ " 546.10 \n",
+ " NaN \n",
+ " 582.07 \n",
+ " NaN \n",
+ " 617.96 \n",
+ " NaN \n",
+ " 653.79 \n",
+ " \n",
+ " \n",
+ " 124 \n",
+ " 675.0 \n",
+ " V \n",
+ " 1.106 \n",
+ " 282.23 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 291.69 \n",
+ " 311.51 \n",
+ " ... \n",
+ " NaN \n",
+ " 491.00 \n",
+ " NaN \n",
+ " 525.77 \n",
+ " NaN \n",
+ " 560.43 \n",
+ " NaN \n",
+ " 595.00 \n",
+ " NaN \n",
+ " 629.51 \n",
+ " \n",
+ " \n",
+ " 128 \n",
+ " 700.0 \n",
+ " V \n",
+ " 1.108 \n",
+ " 272.68 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 280.69 \n",
+ " 299.92 \n",
+ " ... \n",
+ " NaN \n",
+ " 473.34 \n",
+ " NaN \n",
+ " 506.89 \n",
+ " NaN \n",
+ " 540.33 \n",
+ " NaN \n",
+ " 573.68 \n",
+ " NaN \n",
+ " 606.97 \n",
+ " \n",
+ " \n",
+ " 132 \n",
+ " 725.0 \n",
+ " V \n",
+ " 1.110 \n",
+ " 263.77 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 270.45 \n",
+ " 289.13 \n",
+ " ... \n",
+ " NaN \n",
+ " 456.90 \n",
+ " NaN \n",
+ " 489.31 \n",
+ " NaN \n",
+ " 521.61 \n",
+ " NaN \n",
+ " 553.83 \n",
+ " NaN \n",
+ " 585.99 \n",
+ " \n",
+ " \n",
+ " 136 \n",
+ " 750.0 \n",
+ " V \n",
+ " 1.112 \n",
+ " 255.43 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 260.88 \n",
+ " 279.05 \n",
+ " ... \n",
+ " NaN \n",
+ " 441.55 \n",
+ " NaN \n",
+ " 472.90 \n",
+ " NaN \n",
+ " 504.15 \n",
+ " NaN \n",
+ " 535.30 \n",
+ " NaN \n",
+ " 566.40 \n",
+ " \n",
+ " \n",
+ " 140 \n",
+ " 775.0 \n",
+ " V \n",
+ " 1.113 \n",
+ " 247.61 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 251.93 \n",
+ " 269.63 \n",
+ " ... \n",
+ " NaN \n",
+ " 427.20 \n",
+ " NaN \n",
+ " 457.56 \n",
+ " NaN \n",
+ " 487.81 \n",
+ " NaN \n",
+ " 517.97 \n",
+ " NaN \n",
+ " 548.07 \n",
+ " \n",
+ " \n",
+ " 144 \n",
+ " 800.0 \n",
+ " V \n",
+ " 1.115 \n",
+ " 240.26 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 243.53 \n",
+ " 260.79 \n",
+ " ... \n",
+ " NaN \n",
+ " 413.74 \n",
+ " NaN \n",
+ " 443.17 \n",
+ " NaN \n",
+ " 472.49 \n",
+ " NaN \n",
+ " 501.72 \n",
+ " NaN \n",
+ " 530.89 \n",
+ " \n",
+ " \n",
+ " 148 \n",
+ " 825.0 \n",
+ " V \n",
+ " 1.117 \n",
+ " 233.34 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 235.64 \n",
+ " 252.48 \n",
+ " ... \n",
+ " NaN \n",
+ " 401.10 \n",
+ " NaN \n",
+ " 429.65 \n",
+ " NaN \n",
+ " 458.10 \n",
+ " NaN \n",
+ " 486.46 \n",
+ " NaN \n",
+ " 514.76 \n",
+ " \n",
+ " \n",
+ " 152 \n",
+ " 850.0 \n",
+ " V \n",
+ " 1.118 \n",
+ " 226.81 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 228.21 \n",
+ " 244.66 \n",
+ " ... \n",
+ " NaN \n",
+ " 389.20 \n",
+ " NaN \n",
+ " 416.93 \n",
+ " NaN \n",
+ " 444.56 \n",
+ " NaN \n",
+ " 472.09 \n",
+ " NaN \n",
+ " 499.57 \n",
+ " \n",
+ " \n",
+ " 156 \n",
+ " 875.0 \n",
+ " V \n",
+ " 1.120 \n",
+ " 220.65 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 221.20 \n",
+ " 237.29 \n",
+ " ... \n",
+ " NaN \n",
+ " 377.98 \n",
+ " NaN \n",
+ " 404.94 \n",
+ " NaN \n",
+ " 431.79 \n",
+ " NaN \n",
+ " 458.55 \n",
+ " NaN \n",
+ " 485.25 \n",
+ " \n",
+ " \n",
+ " 160 \n",
+ " 900.0 \n",
+ " V \n",
+ " 1.121 \n",
+ " 214.81 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 230.32 \n",
+ " ... \n",
+ " NaN \n",
+ " 367.39 \n",
+ " NaN \n",
+ " 393.61 \n",
+ " NaN \n",
+ " 419.73 \n",
+ " NaN \n",
+ " 445.76 \n",
+ " NaN \n",
+ " 471.72 \n",
+ " \n",
+ " \n",
+ " 164 \n",
+ " 925.0 \n",
+ " V \n",
+ " 1.123 \n",
+ " 209.28 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 223.73 \n",
+ " ... \n",
+ " NaN \n",
+ " 357.36 \n",
+ " NaN \n",
+ " 382.90 \n",
+ " NaN \n",
+ " 408.32 \n",
+ " NaN \n",
+ " 433.66 \n",
+ " NaN \n",
+ " 458.93 \n",
+ " \n",
+ " \n",
+ " 168 \n",
+ " 950.0 \n",
+ " V \n",
+ " 1.124 \n",
+ " 204.03 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 217.48 \n",
+ " ... \n",
+ " NaN \n",
+ " 347.87 \n",
+ " NaN \n",
+ " 372.74 \n",
+ " NaN \n",
+ " 397.51 \n",
+ " NaN \n",
+ " 422.19 \n",
+ " NaN \n",
+ " 446.81 \n",
+ " \n",
+ " \n",
+ " 172 \n",
+ " 975.0 \n",
+ " V \n",
+ " 1.126 \n",
+ " 199.04 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 211.55 \n",
+ " ... \n",
+ " NaN \n",
+ " 338.86 \n",
+ " NaN \n",
+ " 363.11 \n",
+ " NaN \n",
+ " 387.26 \n",
+ " NaN \n",
+ " 411.32 \n",
+ " NaN \n",
+ " 435.31 \n",
+ " \n",
+ " \n",
+ " 176 \n",
+ " 1000.0 \n",
+ " V \n",
+ " 1.127 \n",
+ " 194.29 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 205.92 \n",
+ " ... \n",
+ " NaN \n",
+ " 330.30 \n",
+ " NaN \n",
+ " 353.96 \n",
+ " NaN \n",
+ " 377.52 \n",
+ " NaN \n",
+ " 400.98 \n",
+ " NaN \n",
+ " 424.38 \n",
+ " \n",
+ " \n",
+ " 180 \n",
+ " 1050.0 \n",
+ " V \n",
+ " 1.130 \n",
+ " 185.45 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 195.45 \n",
+ " ... \n",
+ " NaN \n",
+ " 314.41 \n",
+ " NaN \n",
+ " 336.97 \n",
+ " NaN \n",
+ " 359.43 \n",
+ " NaN \n",
+ " 381.79 \n",
+ " NaN \n",
+ " 404.10 \n",
+ " \n",
+ " \n",
+ " 184 \n",
+ " 1100.0 \n",
+ " V \n",
+ " 1.133 \n",
+ " 177.38 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 185.92 \n",
+ " ... \n",
+ " NaN \n",
+ " 299.96 \n",
+ " NaN \n",
+ " 321.53 \n",
+ " NaN \n",
+ " 342.98 \n",
+ " NaN \n",
+ " 364.35 \n",
+ " NaN \n",
+ " 385.65 \n",
+ " \n",
+ " \n",
+ " 188 \n",
+ " 1150.0 \n",
+ " V \n",
+ " 1.136 \n",
+ " 169.99 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 177.22 \n",
+ " ... \n",
+ " NaN \n",
+ " 286.77 \n",
+ " NaN \n",
+ " 307.42 \n",
+ " NaN \n",
+ " 327.97 \n",
+ " NaN \n",
+ " 348.42 \n",
+ " NaN \n",
+ " 368.81 \n",
+ " \n",
+ " \n",
+ " 192 \n",
+ " 1200.0 \n",
+ " V \n",
+ " 1.139 \n",
+ " 163.20 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 169.23 \n",
+ " ... \n",
+ " NaN \n",
+ " 274.68 \n",
+ " NaN \n",
+ " 294.50 \n",
+ " NaN \n",
+ " 314.20 \n",
+ " NaN \n",
+ " 333.82 \n",
+ " NaN \n",
+ " 353.38 \n",
+ " \n",
+ " \n",
+ " 196 \n",
+ " 1250.0 \n",
+ " V \n",
+ " 1.141 \n",
+ " 156.93 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 161.88 \n",
+ " ... \n",
+ " NaN \n",
+ " 263.55 \n",
+ " NaN \n",
+ " 282.60 \n",
+ " NaN \n",
+ " 301.54 \n",
+ " NaN \n",
+ " 320.39 \n",
+ " NaN \n",
+ " 339.18 \n",
+ " \n",
+ " \n",
+ " 200 \n",
+ " 1300.0 \n",
+ " V \n",
+ " 1.144 \n",
+ " 151.13 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 155.09 \n",
+ " ... \n",
+ " NaN \n",
+ " 253.28 \n",
+ " NaN \n",
+ " 271.62 \n",
+ " NaN \n",
+ " 289.85 \n",
+ " NaN \n",
+ " 307.99 \n",
+ " NaN \n",
+ " 326.07 \n",
+ " \n",
+ " \n",
+ " 204 \n",
+ " 1350.0 \n",
+ " V \n",
+ " 1.146 \n",
+ " 145.74 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 148.79 \n",
+ " ... \n",
+ " 234.88 \n",
+ " 243.78 \n",
+ " 252.63 \n",
+ " 261.46 \n",
+ " NaN \n",
+ " 279.03 \n",
+ " NaN \n",
+ " 296.51 \n",
+ " NaN \n",
+ " 313.93 \n",
+ " \n",
+ " \n",
+ " 208 \n",
+ " 1400.0 \n",
+ " V \n",
+ " 1.149 \n",
+ " 140.72 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 142.94 \n",
+ " ... \n",
+ " 226.35 \n",
+ " 234.95 \n",
+ " 243.50 \n",
+ " 252.02 \n",
+ " NaN \n",
+ " 268.98 \n",
+ " NaN \n",
+ " 285.85 \n",
+ " NaN \n",
+ " 302.66 \n",
+ " \n",
+ " \n",
+ " 212 \n",
+ " 1450.0 \n",
+ " V \n",
+ " 1.151 \n",
+ " 136.04 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 137.48 \n",
+ " ... \n",
+ " 218.42 \n",
+ " 226.72 \n",
+ " 234.99 \n",
+ " 243.23 \n",
+ " NaN \n",
+ " 259.62 \n",
+ " NaN \n",
+ " 275.93 \n",
+ " NaN \n",
+ " 292.16 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
37 rows × 37 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Property Liq_Sat Vap_Sat 75 100 125 150 175 \\\n",
+ "68 325.0 V 1.076 561.75 NaN NaN NaN 583.58 622.41 \n",
+ "72 350.0 V 1.079 524.00 NaN NaN NaN 540.58 576.90 \n",
+ "76 375.0 V 1.081 491.13 NaN NaN NaN 503.29 537.46 \n",
+ "80 400.0 V 1.084 462.22 NaN NaN NaN 470.66 502.93 \n",
+ "84 425.0 V 1.086 436.61 NaN NaN NaN 441.85 472.47 \n",
+ "88 450.0 V 1.088 413.75 NaN NaN NaN 416.24 445.38 \n",
+ "92 475.0 V 1.091 393.22 NaN NaN NaN 393.31 421.14 \n",
+ "96 500.0 V 1.093 374.68 NaN NaN NaN NaN 399.31 \n",
+ "100 525.0 V 1.095 357.84 NaN NaN NaN NaN 379.56 \n",
+ "104 550.0 V 1.097 342.48 NaN NaN NaN NaN 361.60 \n",
+ "108 575.0 V 1.099 328.41 NaN NaN NaN NaN 345.20 \n",
+ "112 600.0 V 1.101 315.47 NaN NaN NaN NaN 330.16 \n",
+ "116 625.0 V 1.103 303.54 NaN NaN NaN NaN 316.31 \n",
+ "120 650.0 V 1.105 292.49 NaN NaN NaN NaN 303.53 \n",
+ "124 675.0 V 1.106 282.23 NaN NaN NaN NaN 291.69 \n",
+ "128 700.0 V 1.108 272.68 NaN NaN NaN NaN 280.69 \n",
+ "132 725.0 V 1.110 263.77 NaN NaN NaN NaN 270.45 \n",
+ "136 750.0 V 1.112 255.43 NaN NaN NaN NaN 260.88 \n",
+ "140 775.0 V 1.113 247.61 NaN NaN NaN NaN 251.93 \n",
+ "144 800.0 V 1.115 240.26 NaN NaN NaN NaN 243.53 \n",
+ "148 825.0 V 1.117 233.34 NaN NaN NaN NaN 235.64 \n",
+ "152 850.0 V 1.118 226.81 NaN NaN NaN NaN 228.21 \n",
+ "156 875.0 V 1.120 220.65 NaN NaN NaN NaN 221.20 \n",
+ "160 900.0 V 1.121 214.81 NaN NaN NaN NaN NaN \n",
+ "164 925.0 V 1.123 209.28 NaN NaN NaN NaN NaN \n",
+ "168 950.0 V 1.124 204.03 NaN NaN NaN NaN NaN \n",
+ "172 975.0 V 1.126 199.04 NaN NaN NaN NaN NaN \n",
+ "176 1000.0 V 1.127 194.29 NaN NaN NaN NaN NaN \n",
+ "180 1050.0 V 1.130 185.45 NaN NaN NaN NaN NaN \n",
+ "184 1100.0 V 1.133 177.38 NaN NaN NaN NaN NaN \n",
+ "188 1150.0 V 1.136 169.99 NaN NaN NaN NaN NaN \n",
+ "192 1200.0 V 1.139 163.20 NaN NaN NaN NaN NaN \n",
+ "196 1250.0 V 1.141 156.93 NaN NaN NaN NaN NaN \n",
+ "200 1300.0 V 1.144 151.13 NaN NaN NaN NaN NaN \n",
+ "204 1350.0 V 1.146 145.74 NaN NaN NaN NaN NaN \n",
+ "208 1400.0 V 1.149 140.72 NaN NaN NaN NaN NaN \n",
+ "212 1450.0 V 1.151 136.04 NaN NaN NaN NaN NaN \n",
+ "\n",
+ " 200 ... 425 450 475 500 525 550 575 \\\n",
+ "68 660.33 ... NaN 1023.50 NaN 1095.00 NaN 1166.50 NaN \n",
+ "72 612.31 ... NaN 950.11 NaN 1016.60 NaN 1083.00 NaN \n",
+ "76 570.69 ... NaN 886.54 NaN 948.66 NaN 1010.70 NaN \n",
+ "80 534.26 ... NaN 830.92 NaN 889.19 NaN 947.35 NaN \n",
+ "84 502.12 ... NaN 781.84 NaN 836.72 NaN 891.49 NaN \n",
+ "88 473.55 ... NaN 738.21 NaN 790.07 NaN 841.83 NaN \n",
+ "92 447.97 ... NaN 699.18 NaN 748.34 NaN 797.40 NaN \n",
+ "96 424.96 ... NaN 664.05 NaN 710.78 NaN 757.41 NaN \n",
+ "100 404.13 ... NaN 632.26 NaN 676.80 NaN 721.23 NaN \n",
+ "104 385.19 ... NaN 603.37 NaN 645.91 NaN 688.34 NaN \n",
+ "108 367.90 ... NaN 576.98 NaN 617.70 NaN 658.30 NaN \n",
+ "112 352.04 ... NaN 552.80 NaN 591.84 NaN 630.78 NaN \n",
+ "116 337.45 ... NaN 530.55 NaN 568.05 NaN 605.45 NaN \n",
+ "120 323.98 ... NaN 510.01 NaN 546.10 NaN 582.07 NaN \n",
+ "124 311.51 ... NaN 491.00 NaN 525.77 NaN 560.43 NaN \n",
+ "128 299.92 ... NaN 473.34 NaN 506.89 NaN 540.33 NaN \n",
+ "132 289.13 ... NaN 456.90 NaN 489.31 NaN 521.61 NaN \n",
+ "136 279.05 ... NaN 441.55 NaN 472.90 NaN 504.15 NaN \n",
+ "140 269.63 ... NaN 427.20 NaN 457.56 NaN 487.81 NaN \n",
+ "144 260.79 ... NaN 413.74 NaN 443.17 NaN 472.49 NaN \n",
+ "148 252.48 ... NaN 401.10 NaN 429.65 NaN 458.10 NaN \n",
+ "152 244.66 ... NaN 389.20 NaN 416.93 NaN 444.56 NaN \n",
+ "156 237.29 ... NaN 377.98 NaN 404.94 NaN 431.79 NaN \n",
+ "160 230.32 ... NaN 367.39 NaN 393.61 NaN 419.73 NaN \n",
+ "164 223.73 ... NaN 357.36 NaN 382.90 NaN 408.32 NaN \n",
+ "168 217.48 ... NaN 347.87 NaN 372.74 NaN 397.51 NaN \n",
+ "172 211.55 ... NaN 338.86 NaN 363.11 NaN 387.26 NaN \n",
+ "176 205.92 ... NaN 330.30 NaN 353.96 NaN 377.52 NaN \n",
+ "180 195.45 ... NaN 314.41 NaN 336.97 NaN 359.43 NaN \n",
+ "184 185.92 ... NaN 299.96 NaN 321.53 NaN 342.98 NaN \n",
+ "188 177.22 ... NaN 286.77 NaN 307.42 NaN 327.97 NaN \n",
+ "192 169.23 ... NaN 274.68 NaN 294.50 NaN 314.20 NaN \n",
+ "196 161.88 ... NaN 263.55 NaN 282.60 NaN 301.54 NaN \n",
+ "200 155.09 ... NaN 253.28 NaN 271.62 NaN 289.85 NaN \n",
+ "204 148.79 ... 234.88 243.78 252.63 261.46 NaN 279.03 NaN \n",
+ "208 142.94 ... 226.35 234.95 243.50 252.02 NaN 268.98 NaN \n",
+ "212 137.48 ... 218.42 226.72 234.99 243.23 NaN 259.62 NaN \n",
+ "\n",
+ " 600 625 650 \n",
+ "68 1237.90 NaN 1309.20 \n",
+ "72 1149.30 NaN 1215.60 \n",
+ "76 1072.60 NaN 1134.50 \n",
+ "80 1005.40 NaN 1063.40 \n",
+ "84 946.17 NaN 1000.80 \n",
+ "88 893.50 NaN 945.10 \n",
+ "92 846.37 NaN 895.27 \n",
+ "96 803.95 NaN 850.42 \n",
+ "100 765.57 NaN 809.85 \n",
+ "104 730.68 NaN 772.96 \n",
+ "108 698.83 NaN 739.28 \n",
+ "112 669.63 NaN 708.41 \n",
+ "116 642.76 NaN 680.01 \n",
+ "120 617.96 NaN 653.79 \n",
+ "124 595.00 NaN 629.51 \n",
+ "128 573.68 NaN 606.97 \n",
+ "132 553.83 NaN 585.99 \n",
+ "136 535.30 NaN 566.40 \n",
+ "140 517.97 NaN 548.07 \n",
+ "144 501.72 NaN 530.89 \n",
+ "148 486.46 NaN 514.76 \n",
+ "152 472.09 NaN 499.57 \n",
+ "156 458.55 NaN 485.25 \n",
+ "160 445.76 NaN 471.72 \n",
+ "164 433.66 NaN 458.93 \n",
+ "168 422.19 NaN 446.81 \n",
+ "172 411.32 NaN 435.31 \n",
+ "176 400.98 NaN 424.38 \n",
+ "180 381.79 NaN 404.10 \n",
+ "184 364.35 NaN 385.65 \n",
+ "188 348.42 NaN 368.81 \n",
+ "192 333.82 NaN 353.38 \n",
+ "196 320.39 NaN 339.18 \n",
+ "200 307.99 NaN 326.07 \n",
+ "204 296.51 NaN 313.93 \n",
+ "208 285.85 NaN 302.66 \n",
+ "212 275.93 NaN 292.16 \n",
+ "\n",
+ "[37 rows x 37 columns]"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "pressure_train1= pressure_train1.reshape(-1,1)"
+ "dataset2 = V_data[(V_data['Pressure']>300) & (V_data['Pressure']<1500)]\n",
+ "dataset2"
]
},
{
"cell_type": "code",
- "execution_count": 16,
- "id": "401a8f36",
+ "execution_count": 11,
+ "id": "1c8e6c68",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Property \n",
+ " Liq_Sat \n",
+ " Vap_Sat \n",
+ " 75 \n",
+ " 100 \n",
+ " 125 \n",
+ " 150 \n",
+ " 175 \n",
+ " 200 \n",
+ " ... \n",
+ " 425 \n",
+ " 450 \n",
+ " 475 \n",
+ " 500 \n",
+ " 525 \n",
+ " 550 \n",
+ " 575 \n",
+ " 600 \n",
+ " 625 \n",
+ " 650 \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 220 \n",
+ " 1550.0 \n",
+ " V \n",
+ " 1.156 \n",
+ " 127.550 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " 127.61 \n",
+ " ... \n",
+ " 204.080 \n",
+ " 211.870 \n",
+ " 219.630 \n",
+ " 227.350 \n",
+ " NaN \n",
+ " 242.720 \n",
+ " NaN \n",
+ " 258.000 \n",
+ " NaN \n",
+ " 273.210 \n",
+ " \n",
+ " \n",
+ " 224 \n",
+ " 1600.0 \n",
+ " V \n",
+ " 1.159 \n",
+ " 123.690 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 197.580 \n",
+ " 205.150 \n",
+ " 212.670 \n",
+ " 220.160 \n",
+ " NaN \n",
+ " 235.060 \n",
+ " NaN \n",
+ " 249.870 \n",
+ " NaN \n",
+ " 264.620 \n",
+ " \n",
+ " \n",
+ " 228 \n",
+ " 1650.0 \n",
+ " V \n",
+ " 1.161 \n",
+ " 120.050 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 191.480 \n",
+ " 198.820 \n",
+ " 206.130 \n",
+ " 213.400 \n",
+ " NaN \n",
+ " 227.860 \n",
+ " NaN \n",
+ " 242.240 \n",
+ " NaN \n",
+ " 256.550 \n",
+ " \n",
+ " \n",
+ " 232 \n",
+ " 1700.0 \n",
+ " V \n",
+ " 1.163 \n",
+ " 116.620 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 185.740 \n",
+ " 192.870 \n",
+ " 199.970 \n",
+ " 207.040 \n",
+ " NaN \n",
+ " 221.090 \n",
+ " NaN \n",
+ " 235.060 \n",
+ " NaN \n",
+ " 248.960 \n",
+ " \n",
+ " \n",
+ " 236 \n",
+ " 1750.0 \n",
+ " V \n",
+ " 1.166 \n",
+ " 113.380 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 180.320 \n",
+ " 187.260 \n",
+ " 194.170 \n",
+ " 201.040 \n",
+ " NaN \n",
+ " 214.710 \n",
+ " NaN \n",
+ " 228.280 \n",
+ " NaN \n",
+ " 241.800 \n",
+ " \n",
+ " \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " \n",
+ " \n",
+ " 524 \n",
+ " 10600.0 \n",
+ " V \n",
+ " 1.474 \n",
+ " 16.778 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 26.276 \n",
+ " 27.834 \n",
+ " 29.313 \n",
+ " 30.732 \n",
+ " 32.106 \n",
+ " 33.444 \n",
+ " 34.753 \n",
+ " 36.039 \n",
+ " 37.304 \n",
+ " 38.552 \n",
+ " \n",
+ " \n",
+ " 528 \n",
+ " 10800.0 \n",
+ " V \n",
+ " 1.481 \n",
+ " 16.385 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 25.703 \n",
+ " 27.245 \n",
+ " 28.706 \n",
+ " 30.106 \n",
+ " 31.461 \n",
+ " 32.779 \n",
+ " 34.069 \n",
+ " 35.335 \n",
+ " 36.580 \n",
+ " 37.808 \n",
+ " \n",
+ " \n",
+ " 532 \n",
+ " 11000.0 \n",
+ " V \n",
+ " 1.489 \n",
+ " 16.006 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 25.151 \n",
+ " 26.676 \n",
+ " 28.120 \n",
+ " 29.503 \n",
+ " 30.839 \n",
+ " 32.139 \n",
+ " 33.410 \n",
+ " 34.656 \n",
+ " 35.882 \n",
+ " 37.091 \n",
+ " \n",
+ " \n",
+ " 536 \n",
+ " 11200.0 \n",
+ " V \n",
+ " 1.496 \n",
+ " 15.639 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 24.619 \n",
+ " 26.128 \n",
+ " 27.555 \n",
+ " 28.921 \n",
+ " 30.240 \n",
+ " 31.521 \n",
+ " 32.774 \n",
+ " 34.002 \n",
+ " 35.210 \n",
+ " 36.400 \n",
+ " \n",
+ " \n",
+ " 540 \n",
+ " 11400.0 \n",
+ " V \n",
+ " 1.504 \n",
+ " 15.284 \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " NaN \n",
+ " ... \n",
+ " 24.104 \n",
+ " 25.599 \n",
+ " 27.010 \n",
+ " 28.359 \n",
+ " 29.661 \n",
+ " 30.925 \n",
+ " 32.160 \n",
+ " 33.370 \n",
+ " 34.560 \n",
+ " 35.733 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
81 rows × 37 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Property Liq_Sat Vap_Sat 75 100 125 150 175 200 ... \\\n",
+ "220 1550.0 V 1.156 127.550 NaN NaN NaN NaN NaN 127.61 ... \n",
+ "224 1600.0 V 1.159 123.690 NaN NaN NaN NaN NaN NaN ... \n",
+ "228 1650.0 V 1.161 120.050 NaN NaN NaN NaN NaN NaN ... \n",
+ "232 1700.0 V 1.163 116.620 NaN NaN NaN NaN NaN NaN ... \n",
+ "236 1750.0 V 1.166 113.380 NaN NaN NaN NaN NaN NaN ... \n",
+ ".. ... ... ... ... .. ... ... ... ... ... ... \n",
+ "524 10600.0 V 1.474 16.778 NaN NaN NaN NaN NaN NaN ... \n",
+ "528 10800.0 V 1.481 16.385 NaN NaN NaN NaN NaN NaN ... \n",
+ "532 11000.0 V 1.489 16.006 NaN NaN NaN NaN NaN NaN ... \n",
+ "536 11200.0 V 1.496 15.639 NaN NaN NaN NaN NaN NaN ... \n",
+ "540 11400.0 V 1.504 15.284 NaN NaN NaN NaN NaN NaN ... \n",
+ "\n",
+ " 425 450 475 500 525 550 575 600 \\\n",
+ "220 204.080 211.870 219.630 227.350 NaN 242.720 NaN 258.000 \n",
+ "224 197.580 205.150 212.670 220.160 NaN 235.060 NaN 249.870 \n",
+ "228 191.480 198.820 206.130 213.400 NaN 227.860 NaN 242.240 \n",
+ "232 185.740 192.870 199.970 207.040 NaN 221.090 NaN 235.060 \n",
+ "236 180.320 187.260 194.170 201.040 NaN 214.710 NaN 228.280 \n",
+ ".. ... ... ... ... ... ... ... ... \n",
+ "524 26.276 27.834 29.313 30.732 32.106 33.444 34.753 36.039 \n",
+ "528 25.703 27.245 28.706 30.106 31.461 32.779 34.069 35.335 \n",
+ "532 25.151 26.676 28.120 29.503 30.839 32.139 33.410 34.656 \n",
+ "536 24.619 26.128 27.555 28.921 30.240 31.521 32.774 34.002 \n",
+ "540 24.104 25.599 27.010 28.359 29.661 30.925 32.160 33.370 \n",
+ "\n",
+ " 625 650 \n",
+ "220 NaN 273.210 \n",
+ "224 NaN 264.620 \n",
+ "228 NaN 256.550 \n",
+ "232 NaN 248.960 \n",
+ "236 NaN 241.800 \n",
+ ".. ... ... \n",
+ "524 37.304 38.552 \n",
+ "528 36.580 37.808 \n",
+ "532 35.882 37.091 \n",
+ "536 35.210 36.400 \n",
+ "540 34.560 35.733 \n",
+ "\n",
+ "[81 rows x 37 columns]"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "volume_train=volume_train.reshape(-1,1)"
+ "dataset3=V_data[(V_data['Pressure']>1500)]\n",
+ "dataset3"
]
},
{
"cell_type": "code",
- "execution_count": 17,
- "id": "eb1d27d7",
+ "execution_count": 23,
+ "id": "deacf4d8",
"metadata": {},
"outputs": [
{
"data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Liq_Sat \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 68 \n",
+ " 325.0 \n",
+ " 1.076 \n",
+ " \n",
+ " \n",
+ " 72 \n",
+ " 350.0 \n",
+ " 1.079 \n",
+ " \n",
+ " \n",
+ " 76 \n",
+ " 375.0 \n",
+ " 1.081 \n",
+ " \n",
+ " \n",
+ " 80 \n",
+ " 400.0 \n",
+ " 1.084 \n",
+ " \n",
+ " \n",
+ " 84 \n",
+ " 425.0 \n",
+ " 1.086 \n",
+ " \n",
+ " \n",
+ " 88 \n",
+ " 450.0 \n",
+ " 1.088 \n",
+ " \n",
+ " \n",
+ " 92 \n",
+ " 475.0 \n",
+ " 1.091 \n",
+ " \n",
+ " \n",
+ " 96 \n",
+ " 500.0 \n",
+ " 1.093 \n",
+ " \n",
+ " \n",
+ " 100 \n",
+ " 525.0 \n",
+ " 1.095 \n",
+ " \n",
+ " \n",
+ " 104 \n",
+ " 550.0 \n",
+ " 1.097 \n",
+ " \n",
+ " \n",
+ " 108 \n",
+ " 575.0 \n",
+ " 1.099 \n",
+ " \n",
+ " \n",
+ " 112 \n",
+ " 600.0 \n",
+ " 1.101 \n",
+ " \n",
+ " \n",
+ " 116 \n",
+ " 625.0 \n",
+ " 1.103 \n",
+ " \n",
+ " \n",
+ " 120 \n",
+ " 650.0 \n",
+ " 1.105 \n",
+ " \n",
+ " \n",
+ " 124 \n",
+ " 675.0 \n",
+ " 1.106 \n",
+ " \n",
+ " \n",
+ " 128 \n",
+ " 700.0 \n",
+ " 1.108 \n",
+ " \n",
+ " \n",
+ " 132 \n",
+ " 725.0 \n",
+ " 1.110 \n",
+ " \n",
+ " \n",
+ " 136 \n",
+ " 750.0 \n",
+ " 1.112 \n",
+ " \n",
+ " \n",
+ " 140 \n",
+ " 775.0 \n",
+ " 1.113 \n",
+ " \n",
+ " \n",
+ " 144 \n",
+ " 800.0 \n",
+ " 1.115 \n",
+ " \n",
+ " \n",
+ " 148 \n",
+ " 825.0 \n",
+ " 1.117 \n",
+ " \n",
+ " \n",
+ " 152 \n",
+ " 850.0 \n",
+ " 1.118 \n",
+ " \n",
+ " \n",
+ " 156 \n",
+ " 875.0 \n",
+ " 1.120 \n",
+ " \n",
+ " \n",
+ " 160 \n",
+ " 900.0 \n",
+ " 1.121 \n",
+ " \n",
+ " \n",
+ " 164 \n",
+ " 925.0 \n",
+ " 1.123 \n",
+ " \n",
+ " \n",
+ " 168 \n",
+ " 950.0 \n",
+ " 1.124 \n",
+ " \n",
+ " \n",
+ " 172 \n",
+ " 975.0 \n",
+ " 1.126 \n",
+ " \n",
+ " \n",
+ " 176 \n",
+ " 1000.0 \n",
+ " 1.127 \n",
+ " \n",
+ " \n",
+ " 180 \n",
+ " 1050.0 \n",
+ " 1.130 \n",
+ " \n",
+ " \n",
+ " 184 \n",
+ " 1100.0 \n",
+ " 1.133 \n",
+ " \n",
+ " \n",
+ " 188 \n",
+ " 1150.0 \n",
+ " 1.136 \n",
+ " \n",
+ " \n",
+ " 192 \n",
+ " 1200.0 \n",
+ " 1.139 \n",
+ " \n",
+ " \n",
+ " 196 \n",
+ " 1250.0 \n",
+ " 1.141 \n",
+ " \n",
+ " \n",
+ " 200 \n",
+ " 1300.0 \n",
+ " 1.144 \n",
+ " \n",
+ " \n",
+ " 204 \n",
+ " 1350.0 \n",
+ " 1.146 \n",
+ " \n",
+ " \n",
+ " 208 \n",
+ " 1400.0 \n",
+ " 1.149 \n",
+ " \n",
+ " \n",
+ " 212 \n",
+ " 1450.0 \n",
+ " 1.151 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
- "LinearRegression()"
+ " Pressure Liq_Sat\n",
+ "68 325.0 1.076\n",
+ "72 350.0 1.079\n",
+ "76 375.0 1.081\n",
+ "80 400.0 1.084\n",
+ "84 425.0 1.086\n",
+ "88 450.0 1.088\n",
+ "92 475.0 1.091\n",
+ "96 500.0 1.093\n",
+ "100 525.0 1.095\n",
+ "104 550.0 1.097\n",
+ "108 575.0 1.099\n",
+ "112 600.0 1.101\n",
+ "116 625.0 1.103\n",
+ "120 650.0 1.105\n",
+ "124 675.0 1.106\n",
+ "128 700.0 1.108\n",
+ "132 725.0 1.110\n",
+ "136 750.0 1.112\n",
+ "140 775.0 1.113\n",
+ "144 800.0 1.115\n",
+ "148 825.0 1.117\n",
+ "152 850.0 1.118\n",
+ "156 875.0 1.120\n",
+ "160 900.0 1.121\n",
+ "164 925.0 1.123\n",
+ "168 950.0 1.124\n",
+ "172 975.0 1.126\n",
+ "176 1000.0 1.127\n",
+ "180 1050.0 1.130\n",
+ "184 1100.0 1.133\n",
+ "188 1150.0 1.136\n",
+ "192 1200.0 1.139\n",
+ "196 1250.0 1.141\n",
+ "200 1300.0 1.144\n",
+ "204 1350.0 1.146\n",
+ "208 1400.0 1.149\n",
+ "212 1450.0 1.151"
]
},
- "execution_count": 17,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "model.fit(pressure_train1,volume_train)"
+ "d1 = dataset1[['Pressure','Liq_Sat']]\n",
+ "d1\n"
]
},
{
"cell_type": "code",
- "execution_count": 18,
- "id": "df0dc41b",
+ "execution_count": 21,
+ "id": "fc230f0c",
"metadata": {},
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Weights: [[0.00038663]]\n"
- ]
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Liq_Sat \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 68 \n",
+ " 325.0 \n",
+ " 1.076 \n",
+ " \n",
+ " \n",
+ " 72 \n",
+ " 350.0 \n",
+ " 1.079 \n",
+ " \n",
+ " \n",
+ " 76 \n",
+ " 375.0 \n",
+ " 1.081 \n",
+ " \n",
+ " \n",
+ " 80 \n",
+ " 400.0 \n",
+ " 1.084 \n",
+ " \n",
+ " \n",
+ " 84 \n",
+ " 425.0 \n",
+ " 1.086 \n",
+ " \n",
+ " \n",
+ " 88 \n",
+ " 450.0 \n",
+ " 1.088 \n",
+ " \n",
+ " \n",
+ " 92 \n",
+ " 475.0 \n",
+ " 1.091 \n",
+ " \n",
+ " \n",
+ " 96 \n",
+ " 500.0 \n",
+ " 1.093 \n",
+ " \n",
+ " \n",
+ " 100 \n",
+ " 525.0 \n",
+ " 1.095 \n",
+ " \n",
+ " \n",
+ " 104 \n",
+ " 550.0 \n",
+ " 1.097 \n",
+ " \n",
+ " \n",
+ " 108 \n",
+ " 575.0 \n",
+ " 1.099 \n",
+ " \n",
+ " \n",
+ " 112 \n",
+ " 600.0 \n",
+ " 1.101 \n",
+ " \n",
+ " \n",
+ " 116 \n",
+ " 625.0 \n",
+ " 1.103 \n",
+ " \n",
+ " \n",
+ " 120 \n",
+ " 650.0 \n",
+ " 1.105 \n",
+ " \n",
+ " \n",
+ " 124 \n",
+ " 675.0 \n",
+ " 1.106 \n",
+ " \n",
+ " \n",
+ " 128 \n",
+ " 700.0 \n",
+ " 1.108 \n",
+ " \n",
+ " \n",
+ " 132 \n",
+ " 725.0 \n",
+ " 1.110 \n",
+ " \n",
+ " \n",
+ " 136 \n",
+ " 750.0 \n",
+ " 1.112 \n",
+ " \n",
+ " \n",
+ " 140 \n",
+ " 775.0 \n",
+ " 1.113 \n",
+ " \n",
+ " \n",
+ " 144 \n",
+ " 800.0 \n",
+ " 1.115 \n",
+ " \n",
+ " \n",
+ " 148 \n",
+ " 825.0 \n",
+ " 1.117 \n",
+ " \n",
+ " \n",
+ " 152 \n",
+ " 850.0 \n",
+ " 1.118 \n",
+ " \n",
+ " \n",
+ " 156 \n",
+ " 875.0 \n",
+ " 1.120 \n",
+ " \n",
+ " \n",
+ " 160 \n",
+ " 900.0 \n",
+ " 1.121 \n",
+ " \n",
+ " \n",
+ " 164 \n",
+ " 925.0 \n",
+ " 1.123 \n",
+ " \n",
+ " \n",
+ " 168 \n",
+ " 950.0 \n",
+ " 1.124 \n",
+ " \n",
+ " \n",
+ " 172 \n",
+ " 975.0 \n",
+ " 1.126 \n",
+ " \n",
+ " \n",
+ " 176 \n",
+ " 1000.0 \n",
+ " 1.127 \n",
+ " \n",
+ " \n",
+ " 180 \n",
+ " 1050.0 \n",
+ " 1.130 \n",
+ " \n",
+ " \n",
+ " 184 \n",
+ " 1100.0 \n",
+ " 1.133 \n",
+ " \n",
+ " \n",
+ " 188 \n",
+ " 1150.0 \n",
+ " 1.136 \n",
+ " \n",
+ " \n",
+ " 192 \n",
+ " 1200.0 \n",
+ " 1.139 \n",
+ " \n",
+ " \n",
+ " 196 \n",
+ " 1250.0 \n",
+ " 1.141 \n",
+ " \n",
+ " \n",
+ " 200 \n",
+ " 1300.0 \n",
+ " 1.144 \n",
+ " \n",
+ " \n",
+ " 204 \n",
+ " 1350.0 \n",
+ " 1.146 \n",
+ " \n",
+ " \n",
+ " 208 \n",
+ " 1400.0 \n",
+ " 1.149 \n",
+ " \n",
+ " \n",
+ " 212 \n",
+ " 1450.0 \n",
+ " 1.151 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Liq_Sat\n",
+ "68 325.0 1.076\n",
+ "72 350.0 1.079\n",
+ "76 375.0 1.081\n",
+ "80 400.0 1.084\n",
+ "84 425.0 1.086\n",
+ "88 450.0 1.088\n",
+ "92 475.0 1.091\n",
+ "96 500.0 1.093\n",
+ "100 525.0 1.095\n",
+ "104 550.0 1.097\n",
+ "108 575.0 1.099\n",
+ "112 600.0 1.101\n",
+ "116 625.0 1.103\n",
+ "120 650.0 1.105\n",
+ "124 675.0 1.106\n",
+ "128 700.0 1.108\n",
+ "132 725.0 1.110\n",
+ "136 750.0 1.112\n",
+ "140 775.0 1.113\n",
+ "144 800.0 1.115\n",
+ "148 825.0 1.117\n",
+ "152 850.0 1.118\n",
+ "156 875.0 1.120\n",
+ "160 900.0 1.121\n",
+ "164 925.0 1.123\n",
+ "168 950.0 1.124\n",
+ "172 975.0 1.126\n",
+ "176 1000.0 1.127\n",
+ "180 1050.0 1.130\n",
+ "184 1100.0 1.133\n",
+ "188 1150.0 1.136\n",
+ "192 1200.0 1.139\n",
+ "196 1250.0 1.141\n",
+ "200 1300.0 1.144\n",
+ "204 1350.0 1.146\n",
+ "208 1400.0 1.149\n",
+ "212 1450.0 1.151"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
}
],
"source": [
- "print(\"Weights: \",model.coef_)"
+ "d2 = dataset2[['Pressure','Liq_Sat']]\n",
+ "d2"
]
},
{
"cell_type": "code",
- "execution_count": 19,
- "id": "892b60fc",
+ "execution_count": 24,
+ "id": "f65cbbe8",
"metadata": {},
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Intercepts: [1.00719828]\n"
- ]
- }
- ],
- "source": [
- "print(\"Intercepts: \",model.intercept_)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "id": "ae4a4063",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test1=list(df.loc[(df['Property']=='V')&(df['Pressure']<=300)]['Pressure'])[-9:]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "id": "a6fe42c9",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test1=np.array(pressure_test1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "id": "6e818e97",
- "metadata": {},
- "outputs": [],
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Liq_Sat \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 220 \n",
+ " 1550.0 \n",
+ " 1.156 \n",
+ " \n",
+ " \n",
+ " 224 \n",
+ " 1600.0 \n",
+ " 1.159 \n",
+ " \n",
+ " \n",
+ " 228 \n",
+ " 1650.0 \n",
+ " 1.161 \n",
+ " \n",
+ " \n",
+ " 232 \n",
+ " 1700.0 \n",
+ " 1.163 \n",
+ " \n",
+ " \n",
+ " 236 \n",
+ " 1750.0 \n",
+ " 1.166 \n",
+ " \n",
+ " \n",
+ " ... \n",
+ " ... \n",
+ " ... \n",
+ " \n",
+ " \n",
+ " 524 \n",
+ " 10600.0 \n",
+ " 1.474 \n",
+ " \n",
+ " \n",
+ " 528 \n",
+ " 10800.0 \n",
+ " 1.481 \n",
+ " \n",
+ " \n",
+ " 532 \n",
+ " 11000.0 \n",
+ " 1.489 \n",
+ " \n",
+ " \n",
+ " 536 \n",
+ " 11200.0 \n",
+ " 1.496 \n",
+ " \n",
+ " \n",
+ " 540 \n",
+ " 11400.0 \n",
+ " 1.504 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
81 rows × 2 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Liq_Sat\n",
+ "220 1550.0 1.156\n",
+ "224 1600.0 1.159\n",
+ "228 1650.0 1.161\n",
+ "232 1700.0 1.163\n",
+ "236 1750.0 1.166\n",
+ ".. ... ...\n",
+ "524 10600.0 1.474\n",
+ "528 10800.0 1.481\n",
+ "532 11000.0 1.489\n",
+ "536 11200.0 1.496\n",
+ "540 11400.0 1.504\n",
+ "\n",
+ "[81 rows x 2 columns]"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "pressure_test1=pressure_test1.reshape(-1,1)"
+ "d3 = dataset3[['Pressure','Liq_Sat']]\n",
+ "d3"
]
},
{
"cell_type": "code",
- "execution_count": 23,
- "id": "f7fad9db",
+ "execution_count": 35,
+ "id": "41d58b24",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.00023137328921369157 1.0143878627679743\n"
+ ]
+ }
+ ],
"source": [
- "volume_pred1=model.predict(pressure_test1)"
+ "X = d1['Pressure'].values\n",
+ "Y = d1['Liq_Sat'].values\n",
+ "\n",
+ "x_mean = np.mean(X)\n",
+ "y_mean = np.mean(Y)\n",
+ "\n",
+ "n = len(X)\n",
+ "\n",
+ "num = 0\n",
+ "deno = 0\n",
+ "for i in range(n):\n",
+ " num += (X[i] - x_mean) * (Y[i] - y_mean)\n",
+ " deno += (X[i] - x_mean) ** 2\n",
+ " \n",
+ "m = num / deno\n",
+ "c = y_mean - (m * x_mean)\n",
+ "#printing the coefficient\n",
+ "print(m, c)"
]
},
{
"cell_type": "code",
- "execution_count": 24,
- "id": "586d99b9",
+ "execution_count": 36,
+ "id": "d14347e3",
"metadata": {},
"outputs": [
{
"data": {
+ "image/png": "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\n",
"text/plain": [
- "-17.26666272414709"
+ ""
]
},
- "execution_count": 24,
"metadata": {},
- "output_type": "execute_result"
+ "output_type": "display_data"
}
],
"source": [
- "r2_score(volume_train,volume_pred1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "id": "32e49847",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_train2=list(df.loc[(df['Property']=='V')&((df['Pressure']<=1500)&(df['Pressure']>=300))]['Pressure'])[:-19]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "id": "0280882d",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_train2=np.array(pressure_train2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 27,
- "id": "df9c494a",
- "metadata": {},
- "outputs": [],
- "source": [
- "volume_train=list(df2)"
+ " \n",
+ "x_max = np.max(X) + 100\n",
+ "x_min = np.min(X) - 100\n",
+ "\n",
+ "x = np.linspace(x_min, x_max, 1000)\n",
+ "y = c + m * x\n",
+ "\n",
+ "plt.plot(x, y, color='b', label='Linear Regression',)\n",
+ "\n",
+ "plt.scatter(X, Y, color='g', label='Data Point')\n",
+ "\n",
+ "plt.xlabel('Pressure')\n",
+ "\n",
+ "plt.ylabel('Liq_Sat')\n",
+ "plt.legend()\n",
+ "plt.show()"
]
},
{
"cell_type": "code",
- "execution_count": 28,
- "id": "82599518",
+ "execution_count": 39,
+ "id": "b3fb8139",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.0056557927412657525\n"
+ ]
+ }
+ ],
"source": [
- "pressure_train2= pressure_train2.reshape(-1,1)"
+ "r2 = 0\n",
+ "for i in range(n):\n",
+ " y_pred= c + m* X[i]\n",
+ " r2 += (Y[i] - y_pred) ** 2\n",
+ " \n",
+ "r2 = np.sqrt(r2/n)\n",
+ "print(r2)"
]
},
{
"cell_type": "code",
- "execution_count": 29,
- "id": "7b62a185",
+ "execution_count": 41,
+ "id": "271ac548",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.9263208134364601\n"
+ ]
+ }
+ ],
"source": [
- "volume_train=np.array(volume_train)"
+ "sumofsquares = 0\n",
+ "sumofresiduals = 0\n",
+ "for i in range(n) :\n",
+ " y_pred = c + m * X[i]\n",
+ " sumofsquares += (Y[i] - y_mean) ** 2\n",
+ " sumofresiduals += (Y[i] - y_pred) **2\n",
+ " \n",
+ "score = 1 - (sumofresiduals/sumofsquares)\n",
+ "print(score)"
]
},
{
"cell_type": "code",
- "execution_count": 30,
- "id": "124ed846",
+ "execution_count": 53,
+ "id": "ecd2a7bb",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "6.590430613134484e-05 1.0600824777644846\n"
+ ]
+ }
+ ],
"source": [
- "volume_train=volume_train.reshape(-1,1)"
+ "## second dataset\n",
+ "X = d2['Pressure'].values\n",
+ "Y = d2['Liq_Sat'].values\n",
+ "\n",
+ "x_mean = np.mean(X)\n",
+ "y_mean = np.mean(Y)\n",
+ "\n",
+ "n = len(X)\n",
+ "\n",
+ "num = 0\n",
+ "deno = 0\n",
+ "for i in range(n):\n",
+ " num += (X[i] - x_mean) * (Y[i] - y_mean)\n",
+ " deno += (X[i] - x_mean) ** 2\n",
+ " \n",
+ "m = num / deno\n",
+ "c = y_mean - (m * x_mean)\n",
+ "#printing the coefficient\n",
+ "print(m, c)"
]
},
{
"cell_type": "code",
- "execution_count": 31,
- "id": "e4e3a737",
+ "execution_count": 54,
+ "id": "4eb272ad",
"metadata": {},
"outputs": [
{
"data": {
+ "image/png": "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\n",
"text/plain": [
- "LinearRegression()"
+ ""
]
},
- "execution_count": 31,
"metadata": {},
- "output_type": "execute_result"
+ "output_type": "display_data"
}
],
"source": [
- "model.fit(pressure_train2,volume_train)"
+ "x_max = np.max(X) + 100\n",
+ "x_min = np.min(X) - 100\n",
+ "\n",
+ "x = np.linspace(x_min, x_max, 1000)\n",
+ "y = c + m * x\n",
+ "\n",
+ "plt.plot(x, y, color='b', label='Linear Regression',)\n",
+ "\n",
+ "plt.scatter(X, Y, color='g', label='Data Point')\n",
+ "\n",
+ "plt.xlabel('Pressure')\n",
+ "\n",
+ "plt.ylabel('Liq_Sat')\n",
+ "plt.legend()\n",
+ "plt.show()"
]
},
{
"cell_type": "code",
- "execution_count": 32,
- "id": "67c5c9d8",
+ "execution_count": 55,
+ "id": "78d5c25a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Weights: [[8.34887218e-05]]\n"
+ "0.0022393324406263185\n"
]
}
],
"source": [
- "print(\"Weights: \",model.coef_)"
+ "r2 = 0\n",
+ "for i in range(n):\n",
+ " y_pred= c + m* X[i]\n",
+ " r2 += (Y[i] - y_pred) ** 2\n",
+ " \n",
+ "r2 = np.sqrt(r2/n)\n",
+ "print(r2)"
]
},
{
"cell_type": "code",
- "execution_count": 33,
- "id": "c0b3f3a4",
+ "execution_count": 56,
+ "id": "38dbbc75",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Intercepts: [1.05012481]\n"
+ "0.9884088056118443\n"
]
}
],
"source": [
- "print(\"Intercepts: \",model.intercept_)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "id": "ebbf0622",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test2=list(df.loc[(df['Property']=='V')&(df['Pressure']>=300)&(df['Pressure']<=1500)]['Pressure'])[-20:]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "id": "394a93dd",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test2=np.array(pressure_test2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 36,
- "id": "c3f688b9",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test2= pressure_test2.reshape(-1,1)"
+ "sumofsquares = 0\n",
+ "sumofresiduals = 0\n",
+ "for i in range(n) :\n",
+ " y_pred = c + m * X[i]\n",
+ " sumofsquares += (Y[i] - y_mean) ** 2\n",
+ " sumofresiduals += (Y[i] - y_pred) **2\n",
+ " \n",
+ "score = 1 - (sumofresiduals/sumofsquares)\n",
+ "print(score)"
]
},
{
"cell_type": "code",
- "execution_count": 37,
- "id": "905a85c1",
+ "execution_count": 57,
+ "id": "6d5be89a",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "6.590430613134484e-05 1.0600824777644846\n"
+ ]
+ }
+ ],
"source": [
- "volume_pred2=model.predict(pressure_test2)"
+ "## third dataset\n",
+ "X = d2['Pressure'].values\n",
+ "Y = d2['Liq_Sat'].values\n",
+ "\n",
+ "x_mean = np.mean(X)\n",
+ "y_mean = np.mean(Y)\n",
+ "\n",
+ "n = len(X)\n",
+ "\n",
+ "num = 0\n",
+ "deno = 0\n",
+ "for i in range(n):\n",
+ " num += (X[i] - x_mean) * (Y[i] - y_mean)\n",
+ " deno += (X[i] - x_mean) ** 2\n",
+ " \n",
+ "m = num / deno\n",
+ "c = y_mean - (m * x_mean)\n",
+ "#printing the coefficient\n",
+ "print(m, c)"
]
},
{
"cell_type": "code",
- "execution_count": 38,
- "id": "fb5ee83e",
+ "execution_count": 58,
+ "id": "429a9e90",
"metadata": {},
"outputs": [
{
"data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkwAAAGwCAYAAABb3Do8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAABg4klEQVR4nO3deVxUddvH8c8wAm6AKyqCoplbmmuZqQmliZaaZO5b3VmWKVhamZa2at0tUt1pi7nknqKZmksmLmmZKGplpQYuhJlm4Io6c54/zsPkCMgiMMB8368Xr8dz5jdnrnNuHubqd37nuiyGYRiIiIiISKY8XB2AiIiISGGnhElEREQkC0qYRERERLKghElEREQkC0qYRERERLKghElEREQkC0qYRERERLJQwtUBFEZ2u50//vgDHx8fLBaLq8MRERGRbDAMg9OnTxMQEICHR97OCSlhysAff/xBUFCQq8MQERGRXDhy5AiBgYF5ekwlTBnw8fEBzAvu6+vr4mhEREQkO1JSUggKCnJ8j+clJUwZSLsN5+vrq4RJRESkiMmP5TRa9C0iIiKSBSVMIiIiIllQwiQiIiKSBa1hug42m41Lly65OgyRa/L09MRqtbo6DBGRIk0JUy4YhsGxY8f4559/XB2KSLaUK1eOqlWrqq6YiEguKWHKhbRkyd/fn9KlS+tLSAotwzA4d+4cx48fB6BatWoujkhEpGhSwpRDNpvNkSxVrFjR1eGIZKlUqVIAHD9+HH9/f92eExHJBS36zqG0NUulS5d2cSQi2Zf2+6o1dyIiuaOEKZd0G06KEv2+iohcHyVMIiIiIllQwiQiIiKSBSVM4mCxWFi2bJmrw3A7M2fOpFy5cq4OQ0RErkEJkxsZMmQI9913X6avJyUl0blz54ILKIcsFovjp2zZsjRp0oSZM2e6Oqzr1rt3b3777TdXhyEiUmB+/dX8KUqUMIlD1apV8fb2dmkMhmFw+fLlTF+fMWMGSUlJ7N69m969e/Pggw+yZs2afI3p4sWL+Xr8UqVK4e/vn6+fISJSWMyZAy1aQM+ecP68q6PJPiVMecAw4OxZ1/wYRt6dx5W35BISErBYLERHRxMaGkrp0qVp0qQJ27Ztc3rP1q1bueOOOyhVqhRBQUGMHDmSs2fPOl6fM2cOLVu2xMfHh6pVq9KvXz9HEUWAmJgYLBYLa9asoWXLlnh7e7N58+ZMY0yrWH3DDTfw3HPPUaFCBdauXet4PTk5mUceeQR/f398fX2588472b17t9MxXnnlFfz9/fHx8eHhhx/m2WefpWnTpo7X02biJk2aREBAAHXr1gUgMTGR3r17U758eSpWrEj37t1JSEhwOpdbb72VMmXKUK5cOdq0acOhQ4cA2L17N6Ghofj4+ODr60uLFi3YsWMHkPEtualTp3LDDTfg5eVFvXr1+Oyzz9L9b/XJJ5/Qo0cPSpcuzY033sjy5cszvW4iIq527hz85z8wcKD5/VWpEpw54+qosk8JUx44dw7KlnXNz7lz+Xtu48aNY/To0cTFxVG3bl369u3rmAHau3cvnTp1Ijw8nD179rBw4UK2bNnCE0884Xj/xYsXefnll9m9ezfLli0jPj6eIUOGpPucp59+mkmTJrFv3z5uvvnmLOOy2WwsWrSIv//+G09PT8Ccnbrnnns4duwYq1atIjY2lubNm3PXXXfx999/AzB37lxeffVVXn/9dWJjY6lRowZTp05Nd/z169ezb98+1q1bx4oVKzh37hyhoaGULVuWTZs2sWXLFsqWLUtYWBgXL17k8uXL3HfffbRv3549e/awbds2HnnkEcfj/P379ycwMJAffviB2NhYnn32WUfcV1u6dCkRERE89dRT/Pjjjzz66KM8+OCDbNiwwWnciy++SK9evdizZw9dunShf//+jvMUESlMfv4Zbr0VPv0ULBaYMAG+/hoqV3Z1ZDlgSDrJyckGYCQnJ6d77fz588bPP/9snD9/3rHvzBnDMOd6Cv7nzJnsn9fgwYON7t27Z/o6YCxdutQwDMOIj483AOOTTz5xvP7TTz8ZgLFv3z7DMAxj4MCBxiOPPOJ0jM2bNxseHh5O1+dK27dvNwDj9OnThmEYxoYNGwzAWLZsWZbxA0bJkiWNMmXKGFar1QCMChUqGPv37zcMwzDWr19v+Pr6GhcuXHB63w033GB8+OGHhmEYRqtWrYzhw4c7vd6mTRujSZMmju3BgwcbVapUMVJTUx37pk+fbtSrV8+w2+2OfampqUapUqWMNWvWGCdPnjQAIyYmJsPYfXx8jJkzZ2b42owZMww/Pz/H9u23324MHTrUacwDDzxgdOnSxelajB8/3rF95swZw2KxGF999VWGn5HR762ISH6z2w3j008No1Qp8zuralXDWL8+/z7vWt/f10szTHmgdGlzWtEVP/ldcPzK2Z60PmRpt9RiY2OZOXMmZcuWdfx06tQJu91OfHw8ALt27aJ79+7UrFkTHx8fQkJCADh8+LDT57Rs2TJb8bzzzjvExcWxbt06mjZtyjvvvEOdOnUc8Zw5c4aKFSs6xRQfH8/BgwcB+PXXX7n11ludjnn1NkDjxo3x8vJybMfGxnLgwAF8fHwcx61QoQIXLlzg4MGDVKhQgSFDhtCpUye6du1KVFQUSUlJjvc/+eSTPPzww3To0IHJkyc74snIvn37aNOmjdO+Nm3asG/fPqd9V/5vU6ZMGXx8fJxud4qIuNKZMzB4MDz0kLlWqUMHiIuDO+90dWS5o15yecBigTJlXB1F/rjytlHa7SW73e74v48++igjR45M974aNWpw9uxZ7r77bu6++27mzJlD5cqVOXz4MJ06dUq3kLpMNi9g1apVqVOnDnXq1OHzzz+nWbNmtGzZkoYNG2K326lWrRoxMTHp3nflGqGrq14bGSwEuzoeu91OixYtmDt3brqxlf9/TnnGjBmMHDmS1atXs3DhQsaPH8+6deu47bbbmDhxIv369WPlypV89dVXTJgwgQULFtCjR48MzzOjGK/ed/UtPYvF4vjfRkTElfbsgd694ZdfwMMDXnoJxo41/11UuTT0TZs20bVrVwICArJVAygpKYl+/fpRr149PDw8iIyMzHDcP//8w/Dhw6lWrRolS5akQYMGrFq1Ku9PwM01b96cn376yZHAXPnj5eXFL7/8wokTJ5g8eTLt2rWjfv36eToDUqdOHe6//37Gjh3riOfYsWOUKFEiXTyVKlUCoF69emzfvt3pOGmLr7M61/379+Pv75/u2H5+fo5xzZo1Y+zYsWzdupVGjRoxb948x2t169Zl1KhRrF27lvDwcGbMmJHhZzVo0IAtW7Y47du6dSsNGjTI3oUREXERw4CPPoJWrcxkKSAANmyAceOKdrIELk6Yzp49S5MmTXj//fezNT41NZXKlSszbtw4mjRpkuGYixcv0rFjRxISEli8eDG//vorH3/8MdWrV8/L0Ius5ORk4uLinH6uvj2WXc888wzbtm1j+PDhxMXFsX//fpYvX86IESMAc5bJy8uL9957j99//53ly5fz8ssv5+Xp8NRTT/Hll1+yY8cOOnToQOvWrbnvvvtYs2YNCQkJbN26lfHjxzuSohEjRjB9+nRmzZrF/v37eeWVV9izZ0+Wvdb69+9PpUqV6N69O5s3byY+Pp6NGzcSERHB0aNHiY+PZ+zYsWzbto1Dhw6xdu1afvvtNxo0aMD58+d54okniImJ4dChQ3z77bf88MMPmSZAY8aMYebMmUybNo39+/fz9ttvEx0dzejRo/P02omI5KWUFOjXDx59FC5cgLAw8xbcHXe4OrI8kueronKJKxYcZ0f79u2NiIiIdPunTp1q1K5d27h48WKuY8npou+iYvDgwQaQ7mfw4MGGYWS86HvXrl2O9586dcoAjA0bNjj2bd++3ejYsaNRtmxZo0yZMsbNN99svPrqq47X582bZwQHBxve3t5G69atjeXLlzsdN23R96lTp7KMP7PfkY4dOxqdO3c2DMMwUlJSjBEjRhgBAQGGp6enERQUZPTv3984fPiwY/xLL71kVKpUyShbtqzx0EMPGSNHjjRuu+02p+uU0eL4pKQkY9CgQUalSpUMb29vo3bt2sbQoUON5ORk49ixY8Z9991nVKtWzfDy8jJq1qxpvPDCC4bNZjNSU1ONPn36GEFBQYaXl5cREBBgPPHEE47foasXfRuGYXzwwQdG7dq1DU9PT6Nu3brG7Nmzs7wWfn5+xowZMzK8dkX591ZECr+dOw2jTh1zYbfVahivv24YNlvBx5Gfi74thpGXlXxyz2KxsHTp0mtWor5SSEgITZs2ZcqUKU77u3TpQoUKFShdujRffPEFlStXpl+/fjzzzDNYrdYMj5WamkpqaqpjOyUlhaCgIJKTk/H19XUae+HCBeLj46lVqxYlS5bM0TlK4dSxY0eqVq2artZRcaLfWxHJD4YBU6fCqFFw8SIEBcGCBXD77a6JJyUlBT8/vwy/v69XsVv0/fvvv/PNN9/Qv39/Vq1axf79+xk+fDiXL1/mhRdeyPA9kyZN4sUXXyzgSMUVzp07x7Rp0+jUqRNWq5X58+fz9ddfs27dOleHJiJSpCQnw8MPw+LF5nbXrjBzJlSo4NKw8k0RX4KVnt1ux9/fn48++ogWLVrQp08fxo0bl2FxwjRjx44lOTnZ8XPkyJECjFgKksViYdWqVbRr144WLVrw5ZdfsmTJEjp06ODq0EREiowffoBmzcxkydMT3n4bvvii+CZLUAxnmKpVq4anp6fT7bcGDRpw7NgxLl686FRbJ423t7fLe6hJwShVqhRff/21q8MQESmSDAPefRfGjIFLlyA4GBYuNKt4F3fFboapTZs2HDhwwKkezW+//Ua1atUyTJZEREQka3//DT16QGSkmSyFh8OuXe6RLIGLE6YzZ844Hm0HiI+Pd3rMfezYsQwaNMjpPWnjz5w5w19//UVcXBw///yz4/XHHnuMkydPEhERwW+//cbKlSt57bXXGD58eIGdl4iISHHy3XfmLbgvvgAvL3jvPfN23FV9w4s1l96S27FjB6GhoY7tJ598EoDBgwczc+ZMkpKS0tUIatasmePfsbGxzJs3j5o1azq6xgcFBbF27VpGjRrFzTffTPXq1YmIiOCZZ57J/xMSEREpRux2eOsteO45uHwZbrjBvAXXooWrIyt4Lk2YQkJCMmxLkWbmzJnp9mWnCkLr1q357rvvric0ERERt3biBAwZAitXmtu9esHHH0MeP61fZBS7NUwiIiJyfbZsgaZNzWTJ2xumTTPrK7lrsgRKmKQYmDlzplNzXRERyR27HSZNgpAQSEyEunXh++/NdidZdJAq9pQwuZEhQ4ZgsViwWCx4enpSpUoVOnbsyKeffprjLvd5maSEhIQ44vL29qZu3bq89tpr2Gy2bL2/d+/e/Pbbbzn+zMyaN4uIuKPjx6FzZ3O9ks0GAwZAbCxk0rrV7ShhciGb3UZMQgzz984nJiEGmz17CcL1CAsLIykpiYSEBL766itCQ0OJiIjg3nvv5fLly/n++ZkZOnQoSUlJ/Prrr4wcOZLx48fz5ptvZuu9pUqVwt/fP58jFBEpvmJizFtwa9dCqVIwfTrMng1ly7o6ssJDCZOLRO+LJjgqmNBZofSL7kforFCCo4KJ3hedr5/r7e1N1apVqV69Os2bN+e5557jiy++4KuvvnJaZP/222/TuHFjypQpQ1BQEI8//jhnzpwBICYmhgcffJDk5GTHzNDEiRMBmDNnDi1btsTHx4eqVavSr18/jh8/nmVcpUuXpmrVqgQHB/PEE09w1113sWzZMgBOnTrFoEGDKF++PKVLl6Zz587s37/f8d6rZ7smTpxI06ZN+eyzzwgODsbPz48+ffpw+vRpwJxp27hxI1FRUY74056yFBFxJzYbvPQS3HUXJCVBgwZmFe+HHtItuKspYXKB6H3R9FzUk6MpR532J6Yk0nNRz3xPmq5255130qRJE6Kj//1cDw8P3n33XX788UdmzZrFN998w9NPPw3A7bffzpQpU/D19SUpKYmkpCRGjx4NwMWLF3n55ZfZvXs3y5YtIz4+niFDhuQ4plKlSnHp0iXATHB27NjB8uXL2bZtG4Zh0KVLF8frGTl48CDLli1jxYoVrFixgo0bNzJ58mQAoqKiaN26tWNWKykpiaCgoBzHKCJSlB07BnffDRMmmGuXHnzQTJZuusnVkRVOxa41SmFns9uIWB2BQfryCAYGFixEro6ke73uWD2sGRwhf9SvX589e/Y4tq9c31OrVi1efvllHnvsMT744AO8vLzw8/PDYrFQtWpVp+M89NBDjn/Xrl2bd999l1tvvZUzZ85QNhtzu3a7nbVr17JmzRoiIyPZv38/y5cv59tvv+X2/29/PXfuXIKCgli2bBkPPPBApseZOXMmPj4+AAwcOJD169fz6quv4ufnh5eXl2NWS0TE3Xz9NfTvb65bKl3afApu4EBXR1W4aYapgG0+vDndzNKVDAyOpBxh8+HNBRiVWd/KcsX864YNG+jYsSPVq1fHx8eHQYMGcfLkSc6ePXvN4+zatYvu3btTs2ZNfHx8CAkJAUhXgPRqH3zwAWXLlqVkyZJ069aNAQMGMGHCBPbt20eJEiVo1aqVY2zFihWpV68e+/bty/R4wcHBjmQJzB6D2bk1KCJSnF2+DM8/b84sHT8OjRubC7uVLGVNCVMBSzqdlKfj8sq+ffuoVasWAIcOHaJLly40atSIJUuWEBsby//+9z+Aa94GO3v2LHfffTdly5Zlzpw5/PDDDyxduhQwb9VdS//+/YmLi+PgwYOcP3+e6dOnU7p06UwLlV6d4F3N09PTadtiseT4SUARkeIkMdFcq/TKK2YT3aFDzZIB9eu7OrKiQbfkClg1n2p5Oi4vfPPNN+zdu5dRo0YBZsuay5cv89Zbb+HhYebUixYtcnqPl5dXusf+f/nlF06cOMHkyZMda4J27NiRrRj8/PyoU6dOuv0NGzbk8uXLfP/9945bcidPnuS3336jQYMGOTvRLOIXESmuVq82Z5FOnDCffPvoI+jb19VRFS2aYSpg7Wq0I9A3EAsZz45YsBDkG0S7Gu3y5fNTU1M5duwYiYmJ7Ny5k9dee43u3btz7733Ohod33DDDVy+fJn33nuP33//nc8++4xp06Y5HSc4OJgzZ86wfv16Tpw4wblz56hRowZeXl6O9y1fvpyXX375uuK98cYb6d69O0OHDmXLli3s3r2bAQMGUL16dbp3757r4wYHB/P999+TkJDAiRMnNPskIsXSpUvw7LNmfaUTJ8zSATt3KlnKDSVMBczqYSUqLAogXdKUtj0lbEq+LfhevXo11apVIzg4mLCwMDZs2MC7777LF198gdVqfmbTpk15++23ef3112nUqBFz585l0qRJTse5/fbbGTZsGL1796Zy5cq88cYbVK5cmZkzZ/L555/TsGFDJk+enO1aStcyY8YMWrRowb333kvr1q0xDINVq1alu+2WE6NHj8ZqtdKwYUMqV66c5RorEZGi5vBhs2L366+b248/Dtu2wY03ujSsIstiZKebrZtJSUnBz8+P5ORkfK9qnHPhwgXi4+OpVasWJUuWzPVnRO+LJmJ1hNMC8CDfIKaETSG8QXiujyuSkbz6vRWRouHLL83GuX//bfZ/mz4devZ0dVT571rf39dLa5hcJLxBON3rdWfz4c0knU6imk812tVoV6ClBEREpHi5eBHGjoW33za3W7aEhQuhdm3XxlUcKGFyIauHlZDgEFeHISIixUB8PPTpA9u3m9uRkTB5Mnh7uzSsYkMJk4iISBG3dKlZqTs5GcqVg5kz4Tqei5EMaNG3iIhIEZWaCiNHQni4mSzddhvExSlZyg9KmHJJa+WlKNHvq0jxc+AA3H47vPeeuT16NGzaBDVrujau4kq35HIo7VH2c+fOUapUKRdHI5I9586dA9JXQBeRomnRInj4YTh9GipWhFmz4J57XB1V8aaEKYesVivlypVz9CUrXbr0NVt0iLiSYRicO3eO48ePU65cOUetLREpms6fhyefNJvlArRpAwsWQGCga+NyB0qYciGtw72auUpRUa5cOcfvrYgUTb/+Cr16wZ495vbYsfDSS1BC3+QFQpc5FywWC9WqVcPf3/+azWhFCgNPT0/NLIkUcXPnwqOPwtmzULkyfPYZdOrk6qjcixKm62C1WvVFJCIi+ebcOfMpuOnTze2QEDN5CgjI+bFsdpuKJV8HJUwiIiKF0M8/m7fgfvoJLBZ4/nl44QXIzX+nZ9SOK9A3kKiwKLXjyiaVFRARESlkZs6EW24xk6UqVeDrr+HFF3OfLPVc1NMpWQJITEmk56KeRO+LzpugizklTCIiIoXEmTMweLBZtfvcOejQAXbvhjvvzN3xbHYbEasjMEhfiy1tX+TqSGx22/WE7RaUMImIiBQCe/eas0qzZ4OHB7z8Mqxebc4w5dbmw5vTzSxdycDgSMoRNh/enPsPcRNawyQiIuJChmEu6h4xAi5cMBd0z5sH7dtf/7GTTifl6Th3poRJRETERU6fNssFzJ9vboeFmTNMlSvnzfGr+VTL03HuTLfkREREXGDXLmje3EyWrFaYPBlWrsy7ZAmgXY12BPoGYiHjjhQWLAT5BtGuRru8+9BiSgmTiIhIATIM+OADaN3abKAbFGQ2zX3mGXPtUkZsdhsxCTHM3zufmISYbC/StnpYiQqLAkiXNKVtTwmbonpM2aBbciIiIgUkOdlsmrt4sbndtSvMmGE20M3M9dZQCm8QzuJeizM8xpSwKarDlE0WwzDSP2vo5lJSUvDz8yM5ORlfX19XhyMiIsXAjh3Quzf8/rvZ/+3112HUKLMoZWbSaihdXRYgbXZoca/F2U543KHSd35+fythyoASJhERySuGAe++C2PGwKVLULMmLFwIrVpd+302u43gqOBMywJYsBDoG0h8RHyxS3xyKz+/v7WGSUREJJ+cOgXh4RAZaSZLPXqYi72zSpZANZQKGyVMIiIi+eD776FZM1i2DLy8zFmmJUugfPnsvV81lAoXJUwiIiJ5yG6Ht96Ctm3h0CGoXRu2bjULU15rvdLVVEOpcFHCJCIikkdOnoRu3WD0aLh8GXr1gp07oUWLnB9LNZQKFyVMIiIieeDbb6FpU7P4pLc3TJ0KCxaAn1/ujqcaSoWLEiYREZHrYLfDpElm77ejR6FuXXP90rBhObsFl5G0GkrVfas77Q/0DcxRSQG5fiorkAGVFRARkew4fhwGDYI1a8zt/v3NmSUfn7z9HHeooZQX8vP7W5W+RUREcmHjRujbF5KSoFQpeO89eOih9LNKeZHsWD2shASH5F3wkmNKmERERHLAZoNXX4UXXzRvxzVoAIsWQaNG6cdeb1sTKTy0hklERCSbjh2DTp1gwgQzWRoyBH74IfNkqeeinumKTyamJNJzUU+i90UXTNCSJ5QwiYiIZMP69eZTcOvXQ+nSMGuW2Ti3TJn0Y212GxGrI9L1gAMc+yJXR2Kz2/I5askrSphERESu4fJleOEF6NgR/vzTnE3ascNc7J0ZtTUpfrSGSUREJBN//GEu7N60ydweOhSiosxF3teitibFjxImERGRDKxeDQMHwokTULYsfPgh9OuXvfeqrUnxo1tyIiIiV7h8GcaOhc6dzWSpaVOIjc1+sgRqa1IcKWESERH5f0eOQEgITJ5sbj/2mJ3XF2wiNnU+MQkx2V6krbYmxY8SJhEREWDFCnM26dtvwdcXnnr7e768sSadFrSnX3Q/QmeFEhwVnO1yAGprUryoNUoG1BpFRMR9XLxo3oJ7+21zu0ULeOjVNTzxXed0ZQHSZodykvCorUnByc/vbyVMGVDCJCLiHhISoE8fs1kuQEQEvDbJRr1pwZmWBbBgIdA3kPiIeCU+hUx+fn/rlpyIiLilZcugWTMzWSpXDpYuhSlTYPufqqEk6SlhEhERt5Kaas4k9egB//wDrVrBrl1w333m66qhJBlRwiQiIm7j4EFo0wbefdfcfuopsyhlcPC/Y1RDSTKihElERNzC559D8+ZmTaUKFeDLL+HNN8HLy3mcaihJRpQwiYhIsXbhAjz+OPTqBSkp5gxTXBzce2/G41VDSTKihElERIqt336D226DqVPN7bFjISYGgoKu/T7VUJKrqaxABlRWQESk6Js3Dx59FM6cgcqV4bPPoFOnnB1DNZSKlvz8/lbzXRERKVbOnTOfgvvkE3O7fXszeQoIyPmxrB5WQoJD8jQ+KZqUMImISLGxb5+5VunHH8FiMRg44hAdh3zHbxerUsWu2SHJPSVMIiJSLMyaZS7uPncOylW8QIkHhjC7wkJmLzdfD/QNJCosSuuPJFe06FtERIq0s2dhyBDz59w5aHzbcf4ZUosTVRc6jUtMSaTnop7Zbp4rciUlTCIiUmT9+CO0bGnOLnl4wMQX7fzd8xbwOZZubFoj3cjVkdjstoIOVYo4JUwiIlLkGIa5qPuWW+CXX8wF3d98A+0HbSLxzOHM36c+cJJLLk2YNm3aRNeuXQkICMBisbBs2bJrjk9KSqJfv37Uq1cPDw8PIiMjrzl+wYIFWCwW7ktrECQiIkXe6dMwYAAMHWoWpQwLMwtRtm+vPnCSf1yaMJ09e5YmTZrw/vvvZ2t8amoqlStXZty4cTRp0uSaYw8dOsTo0aNp106l60VEiou4OPMW3Lx5YLXC5MmwcqVZZwnUB07yj0ufkuvcuTOdO3fO9vjg4GCiosxy9Z9++mmm42w2G/379+fFF19k8+bN/PPPP9c8bmpqKqmpqY7tlJSUbMckIiJ57+qCkW2D2vHxR1ZGjYLUVAgMhAULzDYnV0rrA5eYkuhYs3QlCxYCfQPVB05yrFiuYXrppZeoXLky//nPf7I1ftKkSfj5+Tl+grKqmS8iIvkmel80wVHBhM4KpV90P0I/7I5vy1U8/riZLN17rznTdHWyBOoDJ/mn2CVM3377LdOnT+fjjz/O9nvGjh1LcnKy4+fIkSP5GKGIiGQmel80PRf15GjKUXNHYgv4cCfn47qCxyUGP72H5cuhYsXMj6E+cJIfilXhytOnTzNgwAA+/vhjKlWqlO33eXt74+3tnY+RiYhIVmx2GxGrI8xbaQbw/QhY+ybYvcAvAR7owzdV/8BuxGO1XHuGKLxBON3rdVcfOMkzxSphOnjwIAkJCXTt2tWxz263A1CiRAl+/fVXbrjhBleFJyIi17D58GZzZul8OfhiOvzy/zNB9ZdC94eg1D8cSTHHZae/m/rASV4qVglT/fr12bt3r9O+8ePHc/r0aaKiorQ2SUSkEEs6nQRHb4XPF0JyMHhchLtHQ6v3uHI5kkoCiCu4NGE6c+YMBw4ccGzHx8cTFxdHhQoVqFGjBmPHjiUxMZHZs2c7xsTFxTne+9dffxEXF4eXlxcNGzakZMmSNGrUyOkzypUrB5Buv4iIFB6GAZsX3AKfbgG7J5Q/CD17Q/XYdGNVEkBcwaUJ044dOwgNDXVsP/nkkwAMHjyYmTNnkpSUxOHDzhVbmzVr5vh3bGws8+bNo2bNmiQkJBRIzCIikrdOnjT7wK1YUcfc0XARdBsKJZ1LvKgkgLiSxTCM9IUq3FxKSgp+fn4kJyfj6+vr6nBERIqtb7+Fvn3hyBHw9obBz+ziI0sLLBac6iillQTQU25yLfn5/V3sygqIiEjhZ7ebVbrbtzeTpRtvhO++gw9fbMaS3ioJIIWPZpgyoBkmEZH889dfMGgQrF5tbvfrB9OmgY/Pv2OurvStkgCSHfn5/V2snpITEZHCbdMm8xbcH39AyZLw/vvw0ENgcS7KrZIAUugoYRIRkTyV0ewQhpVJk2DCBPN2XP368PnnoAeYpahQwiQiInkmel80Easj/m1tAlSjGZVWr2bvd/4ADB4M//sflCnjqihFck4Jk4iI5Im0PnBXPt3G73eStGQuSWf98S51mQ+nlmDwYNfFKJJbekpORESum1MfOAC7B2yYCLPXwdmq4L+X8iM6MWCgzaVxiuSWEiYREblujj5wACnVYNZ62DgB8IDmH8PDrThW+hs2H97s0jhFcku35ERE5Lo5+rsduBuiP4Nz/uB1Gu59FG6en36cSBGjhElERK6bf6kA+Po12DLW3FElDh7oBZX2O41THzgpqpQwiYjIdTlyBF4Ycgd8297c0fID6PQkeKY6xqgPnBR1SphERCTXVq40q3b//beF0mUvcS5sAJZGn2fYB25K2BRV65YiS4u+RUQkxy5dgjFj4N574e+/oUUL2BPnyZKXeqsPnBRLmmESEZEcOXQIeveG7783t0eOhDfeAG9vuIFwutfrrj5wUuwoYRIREYesmt4uWwYPPgj//APlysGnn0KPHs7HUB84KY6UMImICJBxW5NA30CiwqK4p3Y4zzwDUVHm/ltvhYULITjYNbGKFDQlTCIiknFbEyAxJZH7p43hhvWhHPypPABPPQWvvQZeXq6IVMQ1lDCJiLi5dG1NrmD8FA7Lp3Mw1Y8KFQxmzbJw770uCFLExZQwiYi4Oae2JmkuecPat+CH4eZ20BamLrBy7+2tCz5AkUJAZQVERNxcunYlJ+vA9G3/JkttJ8GQUGw+CQUem0hhoRkmERE359SuZG8f+PIjuOgDpf+CHgPhxjXpx4m4GSVMIiJurl2NdlQvWYfERU/DzqHmzpob4f5+4PuH2pqIoIRJRMTt7f/NinX6DtjvB9jhjleg/Utgtamticj/0xomERE3Nnu22dbk8H4/ylW8QKVh/eHOCWC1AWprIpJGM0wiIm7o7Fl44gmYOdPcvvNOmDu3JJX957D58KNqayJyFSVMIiJu5qefoFcv+Pln8PCAiRPhuefAagVQWxORjChhEhEpJrLqA2cYZu+3ESPg/HmoVg3mzYOQENfFLFJUKGESESkGrtUHLrxBOKdPw2OPwdy55mudOpnrl/z9XRSwSBGjRd8iIkVcWh+4q6t1J6Yk0nNRT95eup6WLc1kyWqFSZNg1SolSyI5oRkmEZEi7Jp94AwDdgzjqVfawGUIDIT586FtWxcEKlLEKWESESnCMuwDB3DBB778GH7qDcBtd55kxaKKVKxYwAGKFBO6JSciUoSl6wMH8Edz+HCnmSx5XIK7n+KJt9cqWRK5DpphEhEpwpz6uxnA9idg7Ztg8wa/BOjZB4K+p7rfBleFKFIsKGESESnC2tVoR6BvIEf/PAPLP4F995sv1F8K3R/CUiqZQN8g9YETuU66JSciUoRZPaw8ETDbvAW3737wuAhhI6F3OJZSyYD6wInkBc0wiYgUUYYB77wD458JhctgrXgIW/j9UD0WMOswTQmboj5wInlACZOISBH0998wZAh8+aW53bMnfPhRIHuS31QfOJF8oIRJRKQQyKqtyZW2boU+feDIEfD2NmeZhg0Di8VKSPmQAo1bxF0oYRIRcbGs2pqksdvhv/+FcePAZoMbb4RFi6BpUxcELeJmtOhbRMSFsmprEr0vGoC//oJ774VnnzWTpb59ITZWyZJIQdEMk4iIi1yzrQkGFixEro6k/J/dGdDfyh9/QMmS8N578J//gMXigqBF3JQSJhGRfJbZ+qRM25r8P8Nu4ciXg+gw2gO7HerXN2/BNW5cgMGLCKCESUQkX11rfVLq5dTM33jGH6LnwO8dsQODBsH//gdly+Z/zCKSntYwiYjkk6zWJ+3/e3/Gb/w9FKbFwe8dwfMsz/z3F2bNUrIk4kpKmERE8kFW65MAPo79mECfQCz8/2IkuwdsmAizv4Yz1aDyj1Qd1Y1Xn7yxACMXkYwoYRIRyQdZrk/C4OjpowxtMdTckRJgJkobJwAe0PwTGNqK/w0ZruKTIoWA1jCJiOSDpNNJ2Rp3Y4UbGV99E6++WR/7mUrgdRrufZSgtluYEvaZ2pqIFBJKmERE8kE1n2pZD7JZWTHtduZ9UBOAGxqc4fHXN9K88SO0q/GZZpZEChElTCIi+aBdjXYE+gaSmJKY4TomkgPxWraEefFmsjRsGLzzTllKlry3gCMVkezQGiYRketks9uISYhh/t75xCTEYLPbsHpYiQqLAvh3UXea37rAtF1cjL8VHx9YuBCmTjWLUopI4aQZJhGR65BVH7jFvRb/+7qtBKx/FbY+DUDz5mYhyhtucFX0IpJdFsMwMpgrdm8pKSn4+fmRnJyMr6+vq8MRkUIqrc7S1bfc0maUFvdaTHiDcGx2G59v3c7zw2/kwJ5KAIwYYTbS9fYu8LBFiq38/P7WLTkRkVzITp2lyNWR2Ow2Vnxp5fFurTmwpxJ+frBkCbz7rpIlkaJEt+RERK4h133gMDjy9zF6P5zEkhmBANx6KyxYALVqFVT0IpJXcp0wWa1WkpKS8Pf3d9p/8uRJ/P39sdls1x2ciIgr5boPHMDftWDxQpb8YSZLTz0Fr70GXl75GbGI5Jdc35LLbOlTamoqXvqLICJFXK77wAH8HA4f7oI/bsG33CWWL4c331SyJFKU5XiG6d133wXAYrHwySefUPaKbpA2m41NmzZRv379vItQRKSAZbU+yYLF0Qcu8fQVdZYuecPaN+GHJwDwCt5B3IZm1AouwOBFJF/kOGF65513AHOGadq0aVit/1ai9fLyIjg4mGnTpuVdhCIiBSy7feBeDHmRiTETsWDBOHkDfL4QjjU3B7V5nc8+qEut4JYFFLWI5KccJ0zx8fEAhIaGEh0dTfny5fM8KBERV8pJH7jFvRYzdNJ6/l44GS76QOm/qNT/ST4c1YPwBj3yOVIRKSi5XvS9YcOGvIxDRKTQyFYfOKCCZ3Wi37mDvz8zG+TWb3Gcl94/QPitM9UHTqSYua6yAkePHmX58uUcPnyYixcvOr329ttvX1dgIiKuklUfOAsWqpxvz5he7di7FywWGDcOJkzwp0QJ/wyOKCJFXa4TpvXr19OtWzdq1arFr7/+SqNGjUhISMAwDJo3b56XMYqI5JvM6ixFhUXRc1FPc33SFUmTBQvG7gH8s/pTjp234O8Pc+dChw4uPAkRyXe5LiswduxYnnrqKX788UdKlizJkiVLOHLkCO3bt+eBBx7IyxhFRPJF9L5ogqOCCZ0VSr/ofoTOCiU4KpjofdGOPnDVfav/+4aLpSm9aj4snc2F8yW4806Ii1OyJOIOct1LzsfHh7i4OG644QbKly/Pli1buOmmm9i9ezfdu3cnISEhj0MtOOolJ1L85aQP3ObDm/lh11n+90wIh/aXwcMDJkwwb8NZtVRJpNAolL3kypQpQ2qqWek2ICCAgwcPOl47ceLE9UcmInKdbHYbMQkxzN87n5iEGGx2m2N/dvvAeVis/P5NCBP638Oh/WWoVg3Wr4cXXlCyJOJOcr2G6bbbbuPbb7+lYcOG3HPPPTz11FPs3buX6OhobrvttryMUUQkx67V1qRCqQpZ94FLOcLafVuZN7kdc+aY++++Gz77DPy1rlvE7eR6huntt9+mVatWAEycOJGOHTuycOFCatasyfTp07N1jE2bNtG1a1cCAgKwWCwsW7bsmuOTkpLo168f9erVw8PDg8jIyHRjPv74Y9q1a0f58uUpX748HTp0YPv27Tk9PREpwrJqa/LFr19kfZBjjfnPPU2YM8ecSXrtNfjqKyVLIu4q1zNMtWvXdvy7dOnSfPDBBzk+xtmzZ2nSpAkPPvgg999/f5bjU1NTqVy5MuPGjXNUHL9aTEwMffv25fbbb6dkyZK88cYb3H333fz0009Ur149w/eISPGRnbYmc/fMzfwABhD7CHwVRZKtJNWrw4IF0LZt/sUsIoVfrhd9X+nChQssXLiQc+fO0bFjR+rUqZPzQCwWli5dyn333Zet8SEhITRt2pQpU6Zcc5zNZqN8+fK8//77DBo0KMMxqampjvVYYC4aCwoK0qJvkSIoJiGG0FmhWY6rXLoyJ86dcE6sLvjAlx/BT30A6NLFYNYsC5Uq5Ve0IpKXCtWi7zFjxhAREeHYvnjxIq1bt2bo0KGMHTuWpk2bsm3btjwN8nqcO3eOS5cuUaFChUzHTJo0CT8/P8dPUFBQAUYoInkpu21N+jfuD/z7VBx/NIMPd5rJksclBo3ey5dfKlkSEVOOE6avvvqKu+66y7E9d+5cDh06xP79+zl16hQPPPAAr7zySp4GeT2effZZqlevTodrFEoZO3YsycnJjp8jR44UYIQikpey29ake/3uLO61mACf6vD9cJi+DU7VwVr+KJPmbmHWfxvjketVniJS3OR4DdPhw4dp2LChY3vt2rX07NmTmjVrAhAREUGXLl3yLsLr8MYbbzB//nxiYmIoWbJkpuO8vb3x9vYuwMhEJL9kp61JoG8g7Wq043SKlVu39GDpV+YsU5uOJ1g6rxqVKwUWdNgiUsjl+L+fPDw8uHLZ03fffedURqBcuXKcOnUqb6K7Dm+++SavvfYaa9eu5eabb3Z1OCKSDzKqs5TW1gSuuN32/9K2p4RNIXaHlWbNYOlSC56eMGUKbF5TicqVVFxJRNLLccJUv359vvzySwB++uknDh8+TGjovwssDx06RJUqVfIuwlz473//y8svv8zq1atp2bKlS2MRkfyR47YmmHWYPn9gMYdWh9O2LSQkQK1a8O23EBFhNtEVEclIjm/JjRkzhr59+7Jy5Up++uknunTpQq1atRyvr1q1iltvvTVbxzpz5gwHDhxwbMfHxxMXF0eFChWoUaMGY8eOJTExkdmzZzvGxMXFOd77119/ERcXh5eXl+M24RtvvMHzzz/PvHnzCA4O5tixYwCULVuWsmXL5vR0RaQQyqytSVqdpbS2Jt3rdXdqrHtT2XY8/B8ry5eb43v2hE8+AT8/F5yEiBQpuSor8PXXX7Ny5UqqVq3KiBEjKF26tOO1F198kfbt2xMSEpLlcWJiYpxmp9IMHjyYmTNnMmTIEBISEoiJifk34Az+E7BmzZqO3nXBwcEcOnQo3ZgJEyYwceLELGMC9ZITKcxsdhvBUcGZVupOW6MUHxGP1ePf22vbtkHv3nDkCHh5wTvvwGOPaVZJpDjJz+/vPKnDdC2PP/44L730EpWK0LO5SphEXC+t6W3a7FC7Gu2welizXWdpw+ANhASHYLfDm2/Cc8+BzQZ16sCiRdCsWQGchIgUqPz8/s51pe/smjNnDqNHjy5SCZOIuNa1+sClXk69xjv/lXQ6iRMnYNAgs6UJQN++8OGH4OOTH1GLSHGW71VG8nkCS0SKmaz6wO3/e3+2jvPXvvo0bWomSyVLwkcfwdy5SpZEJHdUlk1ECo2s+sABfBz7MYE+gelKBjjYPfD7/nVG9W1KYiLUqwfffw9Dh2q9kojknhImESk0Nh/enOlibjCTpqOnjzK0xVAgfZ0lzlSBOV+R/NXT2O0WBg6EHTtApdhE5HopYRKRQiO7feBurHBj+jpLv4fi8eEe+P1uSpeGGTNg9mxQNRERyQv5vuhbRCS7stsHrppPNUKCQ+herzsx8Zv54M2KLP2sEXbDwk03mU/BXdHBSUTkuuX7DNOAAQP0aL6IZEtaH7jM1idZsBDkG0S7Gu0AOP6nlVeHhhA9rTGGYeE//4Ht25UsiUjey/UM0549e7I17rHHHlNJARFJJ7M6S1FhUfRc1BMLFqfF31f2gbN6WFm3DgYMgOPHoUwZs1xA//6uOhsRKe5ynTA1bdo0w6rbVzIMA4vFgs1my+3HiEgxdK06S2l94DJ6fUrYFLrdGM748fDaa2AY5oLuRYvMp+FERPJLrit9L1u2jNGjRzNmzBhat24NwLZt23jrrbd44403aHZFGd2aNWvmTbQFRJW+RfJPZn3g0maQ0vrAZTQDlfSHlX79YPNm8z3DhsHbb0OpUgV9FiJSGBXK1ii33norEydOpEuXLk77V61axfPPP09sbGyeBOgKSphE8kdu+8ABrFplVu0+edIsPvnxx2ZvOBGRNPn5/Z3rRd979+6lVq1a6fbXqlWLn3/++bqCEpHiKTt1lo6kHGHz4c2OfZcuwdNPwz33mMlS8+awc6eSJREpWLlOmBo0aMArr7zChQsXHPtSU1N55ZVXaNCgQZ4EJyLFS3brLKWNO3wY2reH//7X3D9iBGzdajbQFREpSLle9D1t2jS6du1KUFAQTZo0AWD37t1YLBZWrFiRZwGKSPGRkzpLy5fDkCFw6hT4+cGnn0J4eP7GJyKSmVyvYQI4d+4cc+bM4ZdffsEwDBo2bEi/fv0oU6ZMXsZY4LSGSeT6ZFYyIG0NU2JKYob94ixYqF66FuGJ+3k3ypwAv+UWWLgQMlgBICLipFAu+i7OlDCJ5F5WJQPSnpID0tVZMk4FU+ebHRzYWwGAJ5+ESZPAy6tgz0FEiqZCkzAtX76czp074+npyfLly685tlu3btcdnKsoYRLJneyWDMgoqaqYMJTzS97n3GkvypeHWbOga9cCDV9EirhCkzB5eHhw7Ngx/P398fDIfL14US9WqYRJJOdyWjIg7bbdoRN/8sV7bVg6OxCA1q1hwQKoUaMgoxeR4iA/v79ztOjbbrdn+O8rHT58mAkTJlxfVCJSqGW0RiknJQNCgkOwelgJvBzCk4/Arl3mmKefhldeAU/PAjoREZFsyvVTcpk5deoUs2fPZsaMGXl9aBEpBDJbo9SzYc9svT+tZMDChTB0KJw+DZUqwezZ0LlzvoQsInLd8jxhEpHiK7M1SokpiUz5bkq2jlHBszrDhpnNcgHatYP586F69TwOVkQkDylhEpFssdltRKyOyLAcQNo+q8WK3bBnWjKgyoU7eLp3O/bsAYsFxo2DCROghP4SiUghpz9TIpItWa1RArAZ5sMeFizpSwbs7s8/q2dw7LwFf3+YMwc6dszXkEVE8kyOE6bwLErt/vPPP7mNRUQKsey2NYlsFcnifYv/Ta4ulqL01zM4u703F4DQUJg7F6plr+i3iEihkOOEyc/PL8vXBw0alOuARKRwym5bk+71u/Pm3W+y+fBmfth1lv89E8Kh/WXw8DBvv40bB1ZrPgcrIpLHcpww6ek3EffUrkY7An0Dr9nWJNA3kHY12uFhsRK/IYQJw+H8eaha1VzYHRJS8HGLiOSFzKtPiohbstltxCTEMH/vfGISYrDZzXVJVg8rUWFRwL+Vu9OkbU8Jm8L5c1YGD4aHHjKTpbvvht27lSyJSNGmRd8i4pBVH7jwBuEs7rU4wzFTwqZQ51I4LVvCr7+Chwe8/DI8+6z5bxGRokzNdzOg1ijijrLbBw7SV/puG9SOT6dbiYiACxfMmkrz55s1lkRECkqh6SXnLpQwibvJaR+4K6WkwKOPmv3fALp0MRvnVqqU31GLiDjLz+9vTZSLSI76wF1p1y5o0cJMlkqUgDfegC+/VLIkIsWP1jCJSLZrLKWNMwz44AN48km4eBFq1DCTptat8zNKERHXUcIkItmusVTNpxr//GM2zV282NzXrRvMmAEVKuRffCIirqZbciLiqLF0dbmANBYsBPkGUfLPdjRvbiZLnp4wZQosW6ZkSUSKPyVMIm4mozpLWdVYMgzocPxL7mhnJT4eatWCb7+FiAizia6ISHGnW3IibiSrOksZ1ViqZr2J6t+sYcaGAADuvx8++QTKlSvo6EVEXEdlBTKgsgJSHGW3ztKVNZb+3l+PN0Y14/BhC15e8Pbb8PjjmlUSkcJJZQVE5LrY7DYiVkdk2AMubV/k6kjH7bk7aoRwdHVfIns35/BhC3XqwHffwfDhSpZExD0pYRJxAzmps3TiBHTtCk8/DZcvQ58+EBsLzZoVYMAiIoWMEiYRN5DdOksbYi7TtCmsWgUlS8KHH8K8eaA70yLi7rToW8QNZFlnyW6BLc/yysa7sNugXj1YtAhuvrlg4hMRKeyUMIkUI1c3xW1Xox1WD6ujzlJiSmL6dUxnKsPSz+BgJ+zAwIFmFe+yZV1yCiIihZISJpFiIquSAVFhUfRc1NOsq5SWNMW3hyXz4EwAXiUvM+2DEgwZooXdIiJX0xomkWIgrWTA1Qu7E1MS6bmoJ9H7oh11lqr7Vge7B8S8ALPXw5kAAm9IYVdsCR58UMmSiEhGVIcpA6rDJEWJzW4jOCo406fgLFgI9A0kPiIeq4eVo4k2uvVKYdfW8gA8+KCd99/3oHTpgoxaRCTv5ef3t27JiRQhGa1RyknJgEv7QxgwwMrx4+UpUwamTYMBAzTRLCKSFSVMIkVEZmuUejbsmfWbbVaiXqvEF5+AYZhPvy1cCPXr52PAIiLFiG7JZUC35KSwuVZbk4yqdztJCYDF8+HwHQA8+ii88w6UKpVf0YqIuIZuyYm4sey0NbFarNgNe/ox+8Ng6Ww4VxkfH4OPPrLQp09BRC0iUrwoYRIp5LJaowRgM2zAFTNOthLwzSvw7TMA1GrwD2uXl6NOnXwPV0SkWNJqT5FCLrttTSJbRZolA/4JgpkxjmSpc7+D/LxTyZKIyPVQwiRSyGXZ1uT/da/fnfdqJ+Az4yAcaUMZn8ssWmRj1dwbKFkyn4MUESnmlDCJFHJpbU0sZFxR0oKFwNK1+eLdO+hxn5XTyZ7ccgvs3V2CBx6wFnC0IiLFkxImkULCZrcRkxDD/L3ziUmIwWY31yVZPaxEhUUBpEuaLFgwTgVT6rMfmPKO+f/Oo0bBli1Qq1bBxi8iUpxp0bdIIZBVH7i0tiZXj6mQ8DDnl7zP/tNelC8PM2dCt24uOAERkWJOdZgyoDpMUpCuVWMJYHGvxYQ3CAf+rfR9+OSfLHu3DUtnBwLQujXMnw81axZs7CIihUl+fn/rlpyIC2WnxlLk6kin23OBl0OIeqS3I1l6+mnYuFHJkohIflLCJOJCOekDB7BoETRvDjt3QsWKsHIlvP46eHoWVMQiIu5JCZOIC2W3xtKhv44zbBj07g2nT0PbthAXB1265G98IiJi0qJvERfKVo2lE3V5aVAXfv8FLBZ47jmYOBFK6P97RUQKjP7kirhQWo2lxJTEjJvo7umPZcWH/H6xDP7+MGcOdOxY8HGKiLg73ZITKSAZ1VnKtMbSxVLwxScQPQfjYhlCQ81bcEqWRERcQzNMIgUgqzpLTjWWjjeAzxfBX42wWAwmTLAwfjxYVbRbRMRlVIcpA6rDJHkpu3WWbHYb497ez5Tn65B6oQRVqxrMm2chNNQVUYuIFD2qwyRSRGW3zlJyio2HHrTy+pj6pF4oQceOEBenZElEpLDQLTmRfJStOkv7/bi5+QUOHyyDhwe8/DI8+yx46D9nREQKDZf+Sd60aRNdu3YlICAAi8XCsmXLrjk+KSmJfv36Ua9ePTw8PIiMjMxw3JIlS2jYsCHe3t40bNiQpUuX5n3wItlwzTpLBhD7MHy8ncMHy1C9OsTEmGUDlCyJiBQuLv2zfPbsWZo0acL777+frfGpqalUrlyZcePG0aRJkwzHbNu2jd69ezNw4EB2797NwIED6dWrF99//31ehi6SLZnWWbrgA0vmwZcfw+VStAo5SVwctGtXoOGJiEg2FZpF3xaLhaVLl3Lfffdla3xISAhNmzZlypQpTvt79+5NSkoKX331lWNfWFgY5cuXZ/78+RkeKzU1ldTUVMd2SkoKQUFBWvQt2ZbWFDfpdBLVfKrRrkY7rB5WbHYbwVHBznWWkpqaT8H9fSNYLuN3z+v8tfRZPEvoMTgRkeuhRd85sG3bNu6++26nfZ06dWLr1q2ZvmfSpEn4+fk5foKCgvI7TClGovdFExwVTOisUPpF9yN0VijBUcFE74t2qrOEYYHtj8En35nJkt8heOgOPn2jgZIlEZFCrtglTMeOHaNKlSpO+6pUqcKxY8cyfc/YsWNJTk52/Bw5ciS/w5RiIq1kwNULuxNTEum5qCfR+6IJbxDOrM7LKLVsOaz6AGzeUO8LAkbfy5KnRhPeINxF0YuISHYVy6fkLBaL07ZhGOn2Xcnb2xtvb+/8DkuKmaxKBliwELk6kuqnuzOhTzfOx0MJTzt9I+N48DE/7qgZh9VDM0siIkVBsUuYqlatmm426fjx4+lmnUSuV5YlAwyDI2t70PYZC5cvQXAwLFrkwS23NC+4IEVEJE8Uu1tyrVu3Zt26dU771q5dy+233+6iiKS4umbJgPPlYGE0rI7i8iUPwsNh1y645ZYCC09ERPKQS2eYzpw5w4EDBxzb8fHxxMXFUaFCBWrUqMHYsWNJTExk9uzZjjFxcXGO9/7111/ExcXh5eVFw4YNAYiIiOCOO+7g9ddfp3v37nzxxRd8/fXXbNmypUDPTYq/TEsGHGkFixdAcjBYUxn5wiGmPF+Xa9wVFhGRQs6lZQViYmIIzaD3w+DBg5k5cyZDhgwhISGBmJgYx2sZrUWqWbMmCQkJju3Fixczfvx4fv/9d2644QZeffVVwsOzv7BWveQkO9KVDLBbYNuTsH4S2D2h/AGqPDiSxP9+qbVKIiIFID+/vwtNHabCRAmTXC2zOkuOxrpnK8KyGbD/XvMNNy2Aro+yZNAMPQUnIlJA8vP7u9gt+hbJa9H7oolYHeG0wDvQN5CosCjCG4Tz8g0bmDDiRmz/BID1AnQeSWDoaqI6K1kSESkuNMOUAc0wSRrHDNJVpQMsWDDsFvqn7GbBe42w2SCo9jmGv7GRVi1KOWagRESk4GiGScQFrlln6UwlWPoZcw82AmDAAJg6tTRly3Yu6DBFRKQAFLuyAiJ5JdM6S/HtYVocHOwEJc7x9Bu/MHs2lC1b4CGKiEgBUcIkkol0dZbsHhDzPMxeD2cCoPJP8MgtNA3bpZIBIiLFnG7JiWTCqc7S6SoQPRfi7zK3m34KXUaA17nM6zGJiEixoYRJJBPtarQj0DeQo7vqQ/RncLYqeJ6Bex+DJnOwYCHQN4h2Ndq5OlQREclnSpjE7WVWY8mwW7ntt3Us/qwu4AH+e+CBXlD5VyyY9+CmhE3R03AiIm5ACZO4tcxqLL3Q7EPmTOjCpk31AShz2xzO3jUUPC84xkwJm6I6SyIibkIJk7itzGosHY1txCPjb4Fz5pNvH38MD/Tqy+bDgelmoURExD0oYRK3lGGNJVsJ+OZl+PZZADyr7+WH9Q2pX88KWAkJDnFJrCIi4noqKyBuKV2NpeRAmBnjSJa45X0uDbmFY96bXRKfiIgULpphErfkVGPp13th2Uw4XxG8/4Hu/4GG0enHiYiI21LCJG6pmk81uOwJ6yfBtqfMnQHboWcfqBDvPE5ERNyeEiYp9jIqGxBkb4fn7O+5dLiZOei2d6DDM1DiEsD/11gKVI0lEREBlDBJMZdR2YCKCQ9zIfp/XEppBiVPwX0PQv0vHK+rxpKIiFxNi76l2EorG+BIli57waooTs78mLMpXtRtcpKpX35H4K2xTu8L9A1kca/FqrEkIiIOmmGSYild2YC/a8PnCyGppbl9+38512MqQ+/cz9A7EzKs9C0iIpJGCZMUS05lA37qCcs/gVQ/KHUCegyGuqs4etYcFxIcohpLIiJyTUqYpFhKOp0El7xhzduw43FzZ43NcH9f8Et0HiciIpIFJUxSLF3+qzZ88h382RSwQ7tJEDIBrDancSobICIi2aGESYqduXPhsUdvhbMWKH0cwgdAnXVOY1Q2QEREckIJkxRpV9ZYKl+iOp+/2ZZPP/UALNx061/81K4pFp9jTu11VTZARERySgmTFFlONZb+qg+fL4LjHlgsBi+8YOH55yvzxW/vp6vDFOgbyJSwKSobICIi2aaESYqktBpLBgbEDYKVH8ClMlA2CSN8ADf3Ho7VGk54g3C61+uusgEiInJdLIZhGFkPcy8pKSn4+fmRnJyMr6+vq8ORq9jsNoKjgjl64m8zUdo92Hyh9joIH4Cl7F8E+gYSHxGvxEhExI3k5/e3Kn1LkbP58GaO7i8HH+0wkyWLDe4cBwM6QdnjGBgcSTnC5sObXR2qiIgUE7olJ0WKYcC8maXg4+1wuRT4JJq1lYLTJ0eqsSQiInlFCZMUGadPw7BhMG9eK3NHnVVm1e4yJzIcrxpLIiKSV5QwSZEQFwe9esH+/WC1GpTt/BrJzV8AD3u6saqxJCIieU1rmKRQMwyYOhVuu81MloKCYNMmC5++0QCLh+GoqZRGNZZERCQ/KGGSQis5GXr3hscfh9RU6NrVnGm6/XYIbxDO4l6Lqe5b3ek9gb6BLO61WDWWREQkT6msQAZUVsD1duwwk6XffwdPT3j9dYiMBIvzhJJTpW/VWBIRcW/5+f2tNUxSqBgGvPcejB4Nly5BcDAsXAi33prxeKuHlZDgkIIMUURE3JBuyUmhceoUhIdDRISZLIWHw45YG+f8Y5i/dz4xCTHY7DZXhykiIm5IM0xSKHz/vXkL7tAh8PKCt96CandG03RW+j5wUWFRWqMkIiIFSjNM4lKGYSZHbduaydINN8DWrRBwVzQPfN7TKVkCSExJpOeinkTvi3ZRxCIi4o6UMInLnDwJ3bqZ65UuXzZnmHbuhKbNbESsjjAb614lbV/k6kjdnhMRkQKjhElc4ttvoWlTWLECvL1h2jSYPx98ff+/V9xVM0tXUq84EREpaEqYpEDZ7TB5MrRvD0ePQt265vqlRx/9t2RAdnvAqVeciIgUFC36lgJz/DgMGgRr1pjbAwaYVbzLlnUel90ecOoVJyIiBUUJkxSIjRuhb19ISoJSpeD992HQYBtbjmwmKd656GS7Gu0I9A0kMSUxw3VM6hUnIiIFTQmT5CubDV57DSZONG/HNWgAn38Ov3pEU+vdzEsGRIVF0XNRTyxYnJIm9YoTERFX0BomyTfHjkGnTvDCC2ay9OCD8MMPZrLUc9G1SwaoV5yIiBQm6iWXAfWSu37r10P//vDnn1C6tPkU3MCBZu+34KjgTJ+CS7vdFh8Rj9XDql5xIiKSbeolJ0WGzQYvvgivvGIWpWzcGBYtgvr1zddzUjIgJDhEveJERKRQUMIkeeaPP6BfP3OBN8DQoRAVZS7yTqOSASIiUhQpYZI8sWaNWSbgxAmzTMBHH5lPxV1NJQNERKQo0qJvuS6XL8PYsRAWZiZLTZua7U0ySpYAR8mAtKfdrmbBQpBvkEoGiIhIoaKESXLtyBEICTErdwMMHw7btsGNN5rbNruNmIQY5u+dT0xCDDa7DauHlaiwKIB0SZNKBoiISGGlW3KSKytXmlW7//7b7P82fTr07Pnv69H7oolYnXmdpcW9Fmf4+pSwKSoZICIihY7KCmRAZQUyd/EiPPccvPWWud2yJSxcCLVr/zsmep9ZZ+nqKt1pM0hpdZRUMkBERPJSfn5/K2HKgBKmjCUkQJ8+ZrNcgMhI83act/e/Y3JaZ0lERCSv5Of3t9YwSbYsWwbNmpnJUrly5vY77zgnS5CzOksiIiJFhRImuabUVIiIgB494J9/4LbbIC4OunfPeLzqLImISHGkhEkydfAgtGkD775rbo8eDZs2Qc2amb9HdZZERKQ4UsIkGfr8c2jeHGJjoWJFWLEC/vtf8PS89vtUZ0lERIojJUzi5MIFePxx6NULUlKgbVvzFtw992Tv/aqzJCIixZESJnHYvx9at4apU83tsWNhwwYIDMzZcdLqLFX3re60P9A30FFSQEREpChRWYEMuGNZgfnz4ZFH4MwZqFwZPvsMOnW6vmOqzpKIiBSk/Pz+VqVvN3f+PIwcCZ98Ym6HhMDcuRAQcO33ZScZsnpYCQkOyZe4RURECpISJje2b5+5VunHH8FigeefhxdeAGsWk0BZtT0REREpbrSGyU3NmmW2NfnxR6hSBb7+Gl58MXvJUs9FPdMVp0xMSaTnop5E74vOx6hFRERcQwmTmzl7FoYMMX/OnYMOHWD3brjzzqzfa7PbiFgdka5HHODYF7k6EpvdlrdBi4iIuJgSJjfy449wyy3m7JKHB7z8Mqxebc4wZYfanoiIiLvSGiY3YBjw6afwxBNmnaWAAJg3D9q3z9lx1PZERETclUtnmDZt2kTXrl0JCAjAYrGwbNmyLN+zceNGWrRoQcmSJalduzbTpk1LN2bKlCnUq1ePUqVKERQUxKhRo7hw4UI+nEHhd/o0DBwIDz9sJkthYWYhypwmS6C2JyIi4r5cmjCdPXuWJk2a8P7772drfHx8PF26dKFdu3bs2rWL5557jpEjR7JkyRLHmLlz5/Lss88yYcIE9u3bx/Tp01m4cCFjx47Nr9MotHbvNhd2z51rLuaePBlWrjTrLOWG2p6IiIi7cuktuc6dO9O5c+dsj582bRo1atRgypQpADRo0IAdO3bw5ptvcv/99wOwbds22rRpQ79+/QAIDg6mb9++bN++PdPjpqamkpqa6thOSUnJxdkUHoYBH34IkZGQmgpBQbBgAdx+e/aPkVmdpaiwKHou6okFi9Pib7U9ERGR4qxILfretm0bd999t9O+Tp06sWPHDi5dugRA27ZtiY2NdSRIv//+O6tWreKeazRDmzRpEn5+fo6foKCg/DuJfJacDH36wGOPmclS166wa1fOkqXofdEERwUTOiuUftH9CJ0VSnBUMNH7otX2RERE3FKRWvR97Ngxqlz1SFeVKlW4fPkyJ06coFq1avTp04e//vqLtm3bYhgGly9f5rHHHuPZZ5/N9Lhjx47lySefdGynpKQUyaQpNhZ694aDB6FECXj9dRg1yixKmV1pdZauLh2QVmcpLSnqXq+72p6IiIjbKFIJE4Dlqm//tFZ4aftjYmJ49dVX+eCDD2jVqhUHDhwgIiKCatWq8fzzz2d4TG9vb7y9vfM38HxkGPD++zB6NFy8CDVrwsKF0KpVzo6TVZ0lCxYiV0fSvV53tT0RERG3UqQSpqpVq3Ls2DGnfcePH6dEiRJUrFgRgOeff56BAwfy8MMPA9C4cWPOnj3LI488wrhx4/DwKFJ3IbN06hT85z+wdKm53aMHTJ8O5cvn/Fg5qbOkZElERNxJkcoeWrduzbp165z2rV27lpYtW+Lp6QnAuXPn0iVFVqsVwzAcs1HFxfffQ/PmZrLk5QXvvgtLluQuWQLVWRIREcmMSxOmM2fOEBcXR1xcHGCWDYiLi+Pw4cOAubZo0KBBjvHDhg3j0KFDPPnkk+zbt49PP/2U6dOnM3r0aMeYrl27MnXqVBYsWEB8fDzr1q3j+eefp1u3blizapRWRBgGvP02tG0LCQlQuzZs3QojRuRsvdLVVGdJREQkYy69Jbdjxw5CQ0Md22kLrwcPHszMmTNJSkpyJE8AtWrVYtWqVYwaNYr//e9/BAQE8O677zpKCgCMHz8ei8XC+PHjSUxMpHLlynTt2pVXX3214E4sH508afaBW7HC3O7VCz76CPz8rv/YaXWWElMSM1zHZMFCoG+g6iyJiIjbsRjF7T5VHkhJScHPz4/k5GR8fX1dHY7D1q1myYAjR8DbG6ZMgUcfvb5ZpaulPSUHZFhnSaUDRESksMrP7+8itYbJXdntZomAO+4wk6W6dc31S8OG5W2yBKjOkoiISAY0w5SBwjTD9NdfMGgQrF5tbvfvD1Ongo9P/n5uZpW+RURECqv8/P4uUmUF3M2mTdC3L/zxB5QqBe+9Bw89lPezShlRnSUREZF/KWEqhGw2mDQJJkwwb8c1aACLFkGjRnl0fM0eiYiI5IgSpkLmzz9hwAD4+mtze8gQs4p3mTJ5c/zofdFErI5wKlAZ6BtIVFiU1ieJiIhkQou+C5H166FJEzNZKl0aZs2CGTPyNlnquahnumreaX3iovdF580HiYiIFDNKmAoBm828/daxoznD1KgR7NhhLvbOs8/Iok8cQOTqSGx2W959qIiISDGhhMnF/vgDOnSAl14yK3gPHQrbt5vrlvJSTvrEiYiIiDOtYXKhNWtg4ECzdEDZsmbF7r598+ez1CdOREQk9zTD5AKXL8Nzz0FYmJksNW0KsbH5lyyB+sSJiIhcDyVMBezoUQgNNcsGADz+OGzbZlbvzk9pfeLSWpxczYKFIN8g9YkTERHJgBKmArRjhzmbtGUL+PqatZX+9z8oWTL/P9vqYSUqLAogXdKUtj0lbIrqMYmIiGRACVMBqlsXypeHFi1g50544IGC/Xz1iRMREckd9ZLLQH72oomPh4AA8PbO08PmiCp9i4hIcaRecsVIrVqujkB94kRERHJKt+REREREsqCESURERCQLSphEREREsqCESURERCQLSphEREREsqCESURERCQLSphEREREsqCESURERCQLSphEREREsqCESURERCQLSphEREREsqCESURERCQLSphEREREslDC1QEURoZhAJCSkuLiSERERCS70r63077H85ISpgycPn0agKCgIBdHIiIiIjl1+vRp/Pz88vSYFiM/0rAizm6388cff+Dj44PFYsn2+1JSUggKCuLIkSP4+vrmY4RFh66JM10PZ7oeznQ9nOl6ONP1cJbR9TAMg9OnTxMQEICHR96uOtIMUwY8PDwIDAzM9ft9fX31y3wVXRNnuh7OdD2c6Xo40/Vwpuvh7OrrkdczS2m06FtEREQkC0qYRERERLKghCkPeXt7M2HCBLy9vV0dSqGha+JM18OZroczXQ9nuh7OdD2cFfT10KJvERERkSxohklEREQkC0qYRERERLKghElEREQkC0qYRERERLKghCkLkyZN4pZbbsHHxwd/f3/uu+8+fv31V6cxhmEwceJEAgICKFWqFCEhIfz0009OY1JTUxkxYgSVKlWiTJkydOvWjaNHjxbkqeSLSZMmYbFYiIyMdOxzt+uRmJjIgAEDqFixIqVLl6Zp06bExsY6Xnen63H58mXGjx9PrVq1KFWqFLVr1+all17Cbrc7xhT367Fp0ya6du1KQEAAFouFZcuWOb2eV+d/6tQpBg4ciJ+fH35+fgwcOJB//vknn88u5651PS5dusQzzzxD48aNKVOmDAEBAQwaNIg//vjD6Rjucj2u9uijj2KxWJgyZYrTfne7Hvv27aNbt274+fnh4+PDbbfdxuHDhx2vF9j1MOSaOnXqZMyYMcP48ccfjbi4OOOee+4xatSoYZw5c8YxZvLkyYaPj4+xZMkSY+/evUbv3r2NatWqGSkpKY4xw4YNM6pXr26sW7fO2LlzpxEaGmo0adLEuHz5sitOK09s377dCA4ONm6++WYjIiLCsd+drsfff/9t1KxZ0xgyZIjx/fffG/Hx8cbXX39tHDhwwDHGna7HK6+8YlSsWNFYsWKFER8fb3z++edG2bJljSlTpjjGFPfrsWrVKmPcuHHGkiVLDMBYunSp0+t5df5hYWFGo0aNjK1btxpbt241GjVqZNx7770FdZrZdq3r8c8//xgdOnQwFi5caPzyyy/Gtm3bjFatWhktWrRwOoa7XI8rLV261GjSpIkREBBgvPPOO06vudP1OHDggFGhQgVjzJgxxs6dO42DBw8aK1asMP7880/HmIK6HkqYcuj48eMGYGzcuNEwDMOw2+1G1apVjcmTJzvGXLhwwfDz8zOmTZtmGIb5R8HT09NYsGCBY0xiYqLh4eFhrF69umBPII+cPn3auPHGG41169YZ7du3dyRM7nY9nnnmGaNt27aZvu5u1+Oee+4xHnroIad94eHhxoABAwzDcL/rcfUXQF6d/88//2wAxnfffecYs23bNgMwfvnll3w+q9y7VoKQZvv27QZgHDp0yDAM97weR48eNapXr278+OOPRs2aNZ0SJne7Hr1793b8/chIQV4P3ZLLoeTkZAAqVKgAQHx8PMeOHePuu+92jPH29qZ9+/Zs3boVgNjYWC5duuQ0JiAggEaNGjnGFDXDhw/nnnvuoUOHDk773e16LF++nJYtW/LAAw/g7+9Ps2bN+Pjjjx2vu9v1aNu2LevXr+e3334DYPfu3WzZsoUuXboA7nc9rpZX579t2zb8/Pxo1aqVY8xtt92Gn59fkb9GycnJWCwWypUrB7jf9bDb7QwcOJAxY8Zw0003pXvdna6H3W5n5cqV1K1bl06dOuHv70+rVq2cbtsV5PVQwpQDhmHw5JNP0rZtWxo1agTAsWPHAKhSpYrT2CpVqjheO3bsGF5eXpQvXz7TMUXJggULiI2NZdKkSelec7fr8fvvvzN16lRuvPFG1qxZw7Bhwxg5ciSzZ88G3O96PPPMM/Tt25f69evj6elJs2bNiIyMpG/fvoD7XY+r5dX5Hzt2DH9//3TH9/f3L9LX6MKFCzz77LP069fP0UzV3a7H66+/TokSJRg5cmSGr7vT9Th+/Dhnzpxh8uTJhIWFsXbtWnr06EF4eDgbN24ECvZ6lLiOc3E7TzzxBHv27GHLli3pXrNYLE7bhmGk23e17IwpbI4cOUJERARr166lZMmSmY5zl+tht9tp2bIlr732GgDNmjXjp59+YurUqQwaNMgxzl2ux8KFC5kzZw7z5s3jpptuIi4ujsjISAICAhg8eLBjnLtcj8zkxflnNL4oX6NLly7Rp08f7HY7H3zwQZbji+P1iI2NJSoqip07d+Y47uJ4PdIeFunevTujRo0CoGnTpmzdupVp06bRvn37TN+bH9dDM0zZNGLECJYvX86GDRsIDAx07K9atSpAuiz1+PHjjv+KrFq1KhcvXuTUqVOZjikqYmNjOX78OC1atKBEiRKUKFGCjRs38u6771KiRAnH+bjL9ahWrRoNGzZ02tegQQPHExzu9vsxZswYnn32Wfr06UPjxo0ZOHAgo0aNcsxGutv1uFpenX/VqlX5888/0x3/r7/+KpLX6NKlS/Tq1Yv4+HjWrVvnmF0C97oemzdv5vjx49SoUcPx9/XQoUM89dRTBAcHA+51PSpVqkSJEiWy/BtbUNdDCVMWDMPgiSeeIDo6mm+++YZatWo5vV6rVi2qVq3KunXrHPsuXrzIxo0buf322wFo0aIFnp6eTmOSkpL48ccfHWOKirvuuou9e/cSFxfn+GnZsiX9+/cnLi6O2rVru9X1aNOmTboyE7/99hs1a9YE3O/349y5c3h4OP9ZsVqtjv9SdLfrcbW8Ov/WrVuTnJzM9u3bHWO+//57kpOTi9w1SkuW9u/fz9dff03FihWdXnen6zFw4ED27Nnj9Pc1ICCAMWPGsGbNGsC9roeXlxe33HLLNf/GFuj1yPbycDf12GOPGX5+fkZMTIyRlJTk+Dl37pxjzOTJkw0/Pz8jOjra2Lt3r9G3b98MHxMODAw0vv76a2Pnzp3GnXfeWWQek87KlU/JGYZ7XY/t27cbJUqUMF599VVj//79xty5c43SpUsbc+bMcYxxp+sxePBgo3r16o6yAtHR0UalSpWMp59+2jGmuF+P06dPG7t27TJ27dplAMbbb79t7Nq1y/HUV16df1hYmHHzzTcb27ZtM7Zt22Y0bty4UD42fq3rcenSJaNbt25GYGCgERcX5/Q3NjU11XEMd7keGbn6KTnDcK/rER0dbXh6ehofffSRsX//fuO9994zrFarsXnzZscxCup6KGHKApDhz4wZMxxj7Ha7MWHCBKNq1aqGt7e3cccddxh79+51Os758+eNJ554wqhQoYJRqlQp49577zUOHz5cwGeTP65OmNztenz55ZdGo0aNDG9vb6N+/frGRx995PS6O12PlJQUIyIiwqhRo4ZRsmRJo3bt2sa4ceOcvvyK+/XYsGFDhn8zBg8ebBhG3p3/yZMnjf79+xs+Pj6Gj4+P0b9/f+PUqVMFdJbZd63rER8fn+nf2A0bNjiO4S7XIyMZJUzudj2mT59u1KlTxyhZsqTRpEkTY9myZU7HKKjrYTEMw8j+fJSIiIiI+9EaJhEREZEsKGESERERyYISJhEREZEsKGESERERyYISJhEREZEsKGESERERyYISJhEREZEsKGESERERyYISJhEREZEsKGESEZcbMmQIFosFi8WCp6cntWvXZvTo0Zw9e9bVoYmIAFDC1QGIiACEhYUxY8YMLl26xObNm3n44Yc5e/YsU6dOdRp36dIlPD09XRRlxgpjTCKStzTDJCKFgre3N1WrViUoKIh+/frRv39/li1bxsSJE2natCmffvoptWvXxtvbG8MwSE5O5pFHHsHf3x9fX1/uvPNOdu/e7Tje7t27CQ0NxcfHB19fX1q0aMGOHTsAOHToEF27dqV8+fKUKVOGm266iVWrVgEwc+ZMypUr5xTbsmXLsFgsju3cxiQiRZdmmESkUCpVqhSXLl0C4MCBAyxatIglS5ZgtVoBuOeee6hQoQKrVq3Cz8+PDz/8kLvuuovffvuNChUq0L9/f5o1a8bUqVOxWq3ExcU5ZoGGDx/OxYsX2bRpE2XKlOHnn3+mbNmyOYovNzGJSNGlhElECp3t27czb9487rrrLgAuXrzIZ599RuXKlQH45ptv2Lt3L8ePH8fb2xuAN998k2XLlrF48WIeeeQRDh8+zJgxY6hfvz4AN954o+P4hw8f5v7776dx48YA1K5dO8cx5iYmESm6dEtORAqFFStWULZsWUqWLEnr1q254447eO+99wCoWbOmIzEBiI2N5cyZM1SsWJGyZcs6fuLj4zl48CAATz75JA8//DAdOnRg8uTJjv0AI0eO5JVXXqFNmzZMmDCBPXv25Dje3MQkIkWXZphEpFAIDQ1l6tSpeHp6EhAQ4LSIukyZMk5j7XY71apVIyYmJt1x0tYfTZw4kX79+rFy5Uq++uorJkyYwIIFC+jRowcPP/wwnTp1YuXKlaxdu5ZJkybx1ltvMWLECDw8PDAMw+mYabcGr5SbmESk6FLCJCKFQpkyZahTp062xjZv3pxjx45RokQJgoODMx1Xt25d6taty6hRo+jbty8zZsygR48eAAQFBTFs2DCGDRvG2LFj+fjjjxkxYgSVK1fm9OnTnD171pEUxcXF5VlMIlI06ZaciBQ5HTp0oHXr1tx3332sWbOGhIQEtm7dyvjx49mxYwfnz5/niSeeICYmhkOHDvHtt9/yww8/0KBBAwAiIyNZs2YN8fHx7Ny5k2+++cbxWqtWrShdujTPPfccBw4cYN68ecycOfO6YxKRok0Jk4gUORaLhVWrVnHHHXfw0EMPUbduXfr06UNCQgJVqlTBarVy8uRJBg0aRN26denVqxedO3fmxRdfBMBmszF8+HAaNGhAWFgY9erV44MPPgCgQoUKzJkzh1WrVtG4cWPmz5/PxIkTrzsmESnaLMbVN+tFRERExIlmmERERESyoIRJREREJAtKmERERESyoIRJREREJAtKmERERESyoIRJREREJAtKmERERESyoIRJREREJAtKmERERESyoIRJREREJAtKmERERESy8H/B1qpoF7fEDQAAAABJRU5ErkJggg==\n",
"text/plain": [
- "-13.52822205270276"
+ ""
]
},
- "execution_count": 38,
"metadata": {},
- "output_type": "execute_result"
+ "output_type": "display_data"
}
],
"source": [
- "r2_score(volume_train,volume_pred2)"
+ "x_max = np.max(X) + 100\n",
+ "x_min = np.min(X) - 100\n",
+ "\n",
+ "x = np.linspace(x_min, x_max, 1000)\n",
+ "y = c + m * x\n",
+ "\n",
+ "plt.plot(x, y, color='b', label='Linear Regression',)\n",
+ "\n",
+ "plt.scatter(X, Y, color='g', label='Data Point')\n",
+ "\n",
+ "plt.xlabel('Pressure')\n",
+ "\n",
+ "plt.ylabel('Liq_Sat')\n",
+ "plt.legend()\n",
+ "plt.show()"
]
},
{
"cell_type": "code",
- "execution_count": 39,
- "id": "7f05dc16",
+ "execution_count": 59,
+ "id": "1d9ab0a4",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.0022393324406263185\n"
+ ]
+ }
+ ],
"source": [
- "pressure_train3=list(df.loc[(df['Property']=='V')&((df['Pressure']>=1500))]['Pressure'])[:-40]"
+ "r2 = 0\n",
+ "for i in range(n):\n",
+ " y_pred= c + m* X[i]\n",
+ " r2 += (Y[i] - y_pred) ** 2\n",
+ " \n",
+ "r2 = np.sqrt(r2/n)\n",
+ "print(r2)"
]
},
{
"cell_type": "code",
- "execution_count": 40,
- "id": "f76d336e",
+ "execution_count": 60,
+ "id": "90798130",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.9884088056118443\n"
+ ]
+ }
+ ],
"source": [
- "pressure_train3=np.array(pressure_train3)"
+ "sumofsquares = 0\n",
+ "sumofresiduals = 0\n",
+ "for i in range(n) :\n",
+ " y_pred = c + m * X[i]\n",
+ " sumofsquares += (Y[i] - y_mean) ** 2\n",
+ " sumofresiduals += (Y[i] - y_pred) **2\n",
+ " \n",
+ "score = 1 - (sumofresiduals/sumofsquares)\n",
+ "print(score)"
]
},
{
"cell_type": "code",
- "execution_count": 41,
- "id": "afe2d612",
+ "execution_count": null,
+ "id": "9d478e69",
"metadata": {},
"outputs": [],
"source": [
- "pressure_train3= pressure_train3.reshape(-1,1)"
+ "#### sklearn implementation"
]
},
{
"cell_type": "code",
"execution_count": 42,
- "id": "a1129e87",
+ "id": "d22fbca6",
"metadata": {},
"outputs": [],
"source": [
- "volume_train=list(df3)"
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import seaborn as sns\n",
+ "import matplotlib.pyplot as plt\n",
+ "from sklearn import preprocessing, svm\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.linear_model import LinearRegression"
]
},
{
"cell_type": "code",
"execution_count": 43,
- "id": "28da041b",
+ "id": "87debd91",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Pressure \n",
+ " Liq_Sat \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 \n",
+ " 1.0 \n",
+ " 1.000 \n",
+ " \n",
+ " \n",
+ " 4 \n",
+ " 10.0 \n",
+ " 1.010 \n",
+ " \n",
+ " \n",
+ " 8 \n",
+ " 20.0 \n",
+ " 1.017 \n",
+ " \n",
+ " \n",
+ " 12 \n",
+ " 30.0 \n",
+ " 1.022 \n",
+ " \n",
+ " \n",
+ " 16 \n",
+ " 40.0 \n",
+ " 1.027 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Pressure Liq_Sat\n",
+ "0 1.0 1.000\n",
+ "4 10.0 1.010\n",
+ "8 20.0 1.017\n",
+ "12 30.0 1.022\n",
+ "16 40.0 1.027"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "volume_train=np.array(volume_train)"
+ "\n",
+ "d1.head()"
]
},
{
"cell_type": "code",
"execution_count": 44,
- "id": "1ad60b5a",
- "metadata": {},
- "outputs": [],
- "source": [
- "volume_train=volume_train.reshape(-1,1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 45,
- "id": "cd1e0c40",
+ "id": "564d00b5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "LinearRegression()"
+ ""
]
},
- "execution_count": 45,
+ "execution_count": 44,
"metadata": {},
"output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeoAAAHqCAYAAADLbQ06AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAABXsUlEQVR4nO3deVzUdf4H8Nd3hjnkvuQYT8BURETFTG2N7PDM0tzu0tqOxQ5Lsp+rtWlbq+2uHVuW7raalZXVemRlpR1ihZUoo4h4gAgoTCMiDMPAXN/v7w/Wr46AAgJz8Ho+HvP49f18vzO85/tjffH9fj+HIEmSBCIiIvJICncXQERERM1jUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwBnUTJEmCyWQC54IhIiJ3Y1A3oaamBiEhIaipqXF3KURE1MUxqImIiDwYg5qIiMiDMaiJiIg8GIOaiIjIgzGoiYiIPBiDmoiIyIMxqImIiDwYg5qIiMiDMaiJiIg8GIOaiIjIgzGoiYiIPBiDmoiIyIMxqImIiDyYn7sLICIi8nSiKCGvzIRKiw3h/mok6YKhUAid8rMZ1ERERBeQVVCBFZmFKDSaYXdKUCkFJEQFYnZaAsb0i+zwn89b30RERM3IKqjAwo25yC83IUDjh6ggDQI0fsgvr8HCjbnIKqjo8BoY1ERERE0QRQkrMgthtjoQE6yFVqWEQiFAq1IiJlgDs9WJFZmFEEWpQ+tgUBMRETUhr8yEQqMZYf5qCILr82hBEBDqr0Kh0Yy8MlOH1sGgJiIiakKlxQa7U4Ja2XRUapQK2EUJlRZbh9bh1qDesWMHpk6dCp1OB0EQsGnTpou+JzMzE6mpqdBqtYiPj8fKlStd9l999dUQBKHRa8qUKR30LYiIyBeF+6uhUgqwOcUm91udIlQKAeH+6g6tw61BXVtbi5SUFCxfvrxFxxcVFWHy5MkYO3YscnJysHDhQsyZMwfr16+Xj9mwYQPKy8vl1/79+6FUKnHLLbd01NcgIiIflKQLRkJUIE5b7JAk1+fQkiShymJHQlQgknTBHVqHW4dnTZo0CZMmTWrx8StXrkTv3r3x6quvAgASExORnZ2NZcuWYcaMGQCA8PBwl/esW7cO/v7+DGoiImoVhULA7LQELNyYC4PJilB/FTRKBaxOEVUWOwI1SsxOS+jw8dRe9Yx6586dGD9+vEvbhAkTkJ2dDbvd3uR7Vq1ahdtvvx0BAQGdUSIREfmQMf0isWR6MhJjg2CxOmA0W2GxOpAYG4Ql05M7ZRy1V014YjAYEB0d7dIWHR0Nh8OBiooKxMbGuuz79ddfsX//fqxateqCn2u1WmG1WuVtk6lje/AREZH3GNMvEqPiIzgzWUud30X+zHOD89uBhqvpwYMHY+TIkRf8zKVLl+K5555rvyKJiMinKBQCknuGuOdnu+WntlFMTAwMBoNLm9FohJ+fHyIiIlzaLRYL1q1bhwceeOCin7tgwQJUV1fLr9LS0natm4iIqK286op69OjR+Oyzz1zatm7dihEjRkClUrm0f/zxx7Barbj77rsv+rkajQYajaZdayUiImoPbr2iNpvN0Ov10Ov1ABqGX+n1epSUlABouNKdOXOmfHx6ejqKi4uRkZGB/Px8rF69GqtWrcK8efMaffaqVaswbdq0RlfaRERE3sStV9TZ2dkYN26cvJ2RkQEAmDVrFtasWYPy8nI5tAEgLi4OW7Zswdy5c/HGG29Ap9Phtddek4dmnXH48GH8+OOP2Lp1a+d8ESIiog4iSOeP4iaYTCaEhISguroawcEdO5CdiIjoQrzqGTUREXUtoii5bViUp2BQExGRR8oqqMCKzEIUGs2wOyWolAISogIxOy2hUyYa8RReNTyLiIi6hqyCCizcmIv8chMCNH6ICtIgQOOH/PIaLNyYi6yCik6vSRQlWGwOVHXwalnn4xU1ERF5FFGUsCKzEGarAzHBWnlCK61CiZhgBQwmK1ZkFmJUfESrb4M7RQmnaq2oqLGhwmxFhdmKylobqix2nLY0/F9TvR1mqwM19Q6Y6x2osztRZ3fC5mhYRat7kAa7nr6u3b93cxjURETkUfLKTCg0mhHmr24066QgCAj1V6HQaEZemanRbGH1didKKy0oPW3B8dN1KK204ERVHcqr62GoroexxgqneGl9qOttzkt6f2sxqImIyKNUWmywOyWolU0/nVUrBFQ6RGQeOYldxypRcNKMopO1KD5Vi3JTPTp6LFOdnUFNRERdWLi/GiqlAJtThBoK1NmdqLc7UW8XUe9o+G9RApZ9fajNP6ObSonIIDUiAzWICNAgzF+FsAA1QrqpENJNhSCtHwI1DS9/tR+6qRXQqpToplJCq1JCkqQm15joCAxqIiLyCFaHEwfKTNCXVMEhSjhaUdum29R+CgE9wrqhV5g/eoZ1Q4/QbtCFdkNMiBYxIVpEB2sRqPGe+POeSomIyKf8ZqrH7uLTyD52GrtLTuNAWTXszpYHc3SwBv2iAtGveyDiuweib2QA4iICoAvVwq+Z2+beiEFNRESdorTSgl+KKvHL0VP4uegUSivrWvQ+AYBSIUDtp0BsiBZ3XdEHM1J7IqSb6qLv9QUMaiIi6hCnzFZkFZ5CVmEFfiyoaFEwa/wUGNwjBEN7hSK5RwiSYoNRa3Oiut7OmcmIiIguhcMpIqe0CpmHTiLz8Enknqi+6Ht6hHZDap8wjOgbhuG9wzAgJggqH7pt3R4Y1ERE1GZVFhu2HzqJbw8akXnICFO944LHx0cG4Ir4cFwRF4GRceHQhXbrpEq9F4OaiIha5fhpC77O+w1f5xmQfawSF+qYHR2swZUJkbiyX8MrJkTbeYX6CAY1ERFdVFFFLbbklmNLbjnyykzNHqdWKjAyLhxp/bsjbUB3XBYV2GnjjX0Vg5qIiJpUfKoWn+8rx+f7ypFf3nw4RwZqcO3AKFyTGIXf9YtEgBeNUfYGPJtERCQz1tTji33l+FRfBn1pVbPHxXcPwISkGIwfFI2UnqFdrid2Z2JQExF1cfV2J7Ye+A3rdx/HD0dONvvMeWBMEKYkx2JSciz6RQV2bpFdGIOaiKgLkiQJOaVV+CS7FJ/vLUeNtene2pdFBWJqig5ThsQioTvD2R0Y1EREXcgpsxUb9pzAR9mlKDCamzxGF6LFjUN74KahOgyMCWJnMDdjUBMR+ThJkrDz6Cl88EsJvs4zNDmfdoBaicnJsbh5eE9cERfOZ84ehEFNROSjquvsWL/7ONb+UoyjJ2ubPGZ0fARuvbwnJibFopta2ckVUkswqImIfMxBgwnv7izGxj0nUGd3NtofHazBLam9cMuInugTEdDkZ4iihLwyEyotti47x7anYFATEfkAUZTw3UEjVv1YhJ1HTzXaLwjAVZd1x51X9Ma1A6MuuAxkVkEFVmQWotBoht0pQaUUkBAViNlpCRjTL7IjvwY1QZAkqfWrcvs4k8mEkJAQVFdXIzg42N3lEBE1q9bqwCfZpViTdQzHTlka7Q/1V+G2y3vh7iv6oFe4/0U/L6ugAgs35sJsdSDMXw21UgGbU8Rpix2BGiWWTE9mWHcyXlETEXkhY0093sk6hrU/l6C6zt5o/+AewZg1ui+mpuigVbXs2bMoSliRWQiz1YGYYK3c21urUCImWAGDyYoVmYUYFR/B2+CdiEFNRORFiipq8a/MQmzYcwI2p+iyTyEAEwfH4A9XxiG1T1irh1XllZlQaDQjzF/d6L2CICDUX4VCoxl5ZSYk9wy55O9CLcOgJiLyAnll1XhzeyG+zC1vNHNYgFqJ20f2xr1j+rbo9nZzKi022J0S1M08v9YoFagWJVRabG3+GdR6DGoiIg+WU3Iar39XgO8OGhvtiw7W4L4r43DHyN4I6aa65J8V7q+GSinA5hShVTS+XW51ilApBIT7qy/5Z1HLMaiJiDzQrmOVeO3bI/jhSEWjffGRAUhPS8C0YT2g9mu+93ZrJemCkRAViPzyGsQEK1xuf0uShCqLHYmxQUjSsZNtZ2JQExF5kOxjlXjlm8P4qaDxEKvBPYLx8NX9MCEpBsoO6MylUAiYnZaAhRtzYTBZEeqvgkapgNUpoup/vb5npyWwI1kn4/CsJnB4FhF1tpyS03jlmyPYcfhko33DeodizjWX4eoB3Ttl3m2XcdSiBJWC46jdiUHdBAY1EXWWgwYTln19GN/k/9Zo3+V9w/D4tf1xZb+ITl8YgzOTeQ7e+iYicoPiU7V4ZdthfLq3DOdfLg3vHYonxw/AmITOD+gzFAqBQ7A8BIOaiKgTVZiteP3bI3j/lxI4zhtnNaRnCJ4cPwBXXRbJpSVJxqAmIuoEFpsD//mhCP/KLEStzXWhjMuiAvHk+AGYkBTNgKZGGNRERB3IKUpYv/s4lm09BGON1WVfj9BuyLi+P6YN69EhvbjJNzCoiYg6yI9HKvDXLfnILze5tIf6q/DouH64Z3QfaPy4BjRdGIOaiKidFVXU4q9fHMA3+a6zian9FLj/d3FIT0todiYx9ram8zGoiYjaSU29Hcu/K8Dqn4pgd7p2FJs2VIenJg5Ej9Buzb6f60BTUziOugkcR01ErSGKEjbknMCLXx5Ehdn1OfSIPmF45oZBGNor9IKfwXWgqTm8oiYiugT7T1Tj2U/3Y09JlUu7LkSLBZMTccOQ2Iv25OY60HQhDGoiojaottjxj60H8f4vJS4TlmhVCsxO64eHropHN3XLOopxHWi6EAY1EVErSJKEDXtOYMmWfJyqdV2XeXJyDJ6eMuiCz6GbwnWg6ULab320NtixYwemTp0KnU4HQRCwadOmi74nMzMTqamp0Gq1iI+Px8qVKxsdU1VVhUceeQSxsbHQarVITEzEli1bOuAbEFFXUmCswe3//hlPfrLXJaQTugdg7f1X4M27Ulsd0oDrOtBN4TrQXZtbr6hra2uRkpKC++67DzNmzLjo8UVFRZg8eTIefPBBrF27Fj/99BMefvhhdO/eXX6/zWbD9ddfj6ioKPz3v/9Fz549UVpaiqCgoI7+OkTko+rtTrzxfQFWZha69ObuplLi8esuwx+ujLukdaG5DjRdiFuDetKkSZg0aVKLj1+5ciV69+6NV199FQCQmJiI7OxsLFu2TA7q1atXo7KyEllZWVCpGsYp9unTp91rJ6KuIaugAk9v2o+iilqX9vGDovHs1EHoGeZ/yT+D60DThbj11ndr7dy5E+PHj3dpmzBhArKzs2G32wEAmzdvxujRo/HII48gOjoagwcPxpIlS+B0Opv6SACA1WqFyWRyeRFR11ZtseOpT/bizv/84hLSPUK74T8zR+DfM0e0S0ifMaZfJJZMT0ZibBAsVgeMZissVgcSY4M4NKuL86rOZAaDAdHR0S5t0dHRcDgcqKioQGxsLI4ePYrvvvsOd911F7Zs2YIjR47gkUcegcPhwLPPPtvk5y5duhTPPfdcZ3wFIvICX+aW49nNeTh5ztzcCgH4w5VxmHt9fwRoOuafzjH9IjEqPoIzk5ELrwpqAI2GLpyZr+VMuyiKiIqKwr///W8olUqkpqairKwM//jHP5oN6gULFiAjI0PeNplM6NWrVwd9AyLyVMaaejy7KQ9f5Rlc2gf3CMbS6UM6ZWgU14Gm83lVUMfExMBgcP0fkNFohJ+fHyIiIgAAsbGxUKlUUCrPjl9MTEyEwWCAzWaDWt2416RGo4FGo+nY4onIY0mShE/1ZVi0OQ/VdXa5XeOnQMb1/XH/7+Lg18zQKaKO5lVBPXr0aHz22WcubVu3bsWIESPkjmNXXnklPvjgA4iiCIWi4X9Yhw8fRmxsbJMhTURdm9FUj4Ub9+Ob/N9c2q+IC8eLM4YgLjLATZURNXDrn4hmsxl6vR56vR5Aw/ArvV6PkpISAA23pGfOnCkfn56ejuLiYmRkZCA/Px+rV6/GqlWrMG/ePPmY2bNn49SpU3j88cdx+PBhfPHFF1iyZAkeeeSRTv1uROTZGq6iT+D6V3a4hHSAWokXpg3Ghw+OYkiTR3Drohzbt2/HuHHjGrXPmjULa9aswb333otjx45h+/bt8r7MzEzMnTsXeXl50Ol0mD9/PtLT013ev3PnTsydOxd6vR49evTA/fffj/nz57vcDr8QLspB5NtOma14ZtN+fLnf9VHa7/pF4sUZye3am5voUnH1rCYwqIl817YDv2HBhn2oMJ+dWSxArcTTUwbhjpG9LrqABlFn86pn1EREbWW2OvD8ZwfwUXapS/uo+HD84/cp6BXOq2jyTAxqIvJ5u4tPY+5HepRUWuQ2jZ8C8ycOxL1j+nKcMnk0BjUR+SyHU8Rr3xVg+XdHIJ7zkG9IzxC8fOtQ9IsKdF9xRC3EoCYin1RaacHj63Kwp6RKblMIwKPj+uGxay+DiuOiyUswqInI52zKOYFnNu2H2eqQ23qH++OV24YitU+YGysjaj0GNRH5DLPVgWc37ceGnBMu7TOG98RzNyUh8AJzdIuixDm2ySMxqInIJ+w/UY3HPsxxWekqSOuHJdOTMTVFd8H3ZhVUYEVmIQqNZtidElRKAQlRgZidlsBVq8jtOI66CRxHTeQ9JEnCmqxjWLrlIGxOUW4f0ScMr94+9KKTl2QVVGDhxlyYrQ6E+auhVipgc4o4/b91oLnEJLkbr6iJyGtVW+x46r97sfXA2SlAhf91GHv82ssuupCGKEpYkVkIs9WBmGCtPNmJVqFETLACBpMVKzILMSo+grfByW0Y1ETklfSlVXj0gz04frpObosK0uDV24diTELLroDzykwoNJoR5q9uNCOZIAgI9Veh0GhGXpmJS0+S2zCoicirSJKEt386hqVf5sPuPPvkLq1/d7x8awoiAlu+ZG2lxQa7U4K6mStvjVKBalFCpcXW5H6izsCgJiKvUVNvx5/W5+KL3HK5TakQ8OT4/ki/KqHVt6fD/dVQKQXYnCK0isaL9lidIlQKAeH+XCKX3IdBTURe4aDBhIfX7sHRc3p1Rwdr8PodwzEyLrxNn5mkC0ZCVCDyy2sQE6xwuf0tSRKqLHYkxgYhScdOpeQ+nJqHiDzexpzjmPbGTy4h/bt+kfhiztg2hzQAKBQCZqclIFCjhMFkRZ3dCVGUUGd3wmCyIlCjxOy01l+pE7UnDs9qAodnEXkGm0PEX784gHd2Fru0z7mmHx6/rj+U7RSgLuOoRQkqBcdRk+dgUDeBQU3kfr+Z6vHw+3uwu/i03Bbqr8Irtw3FuAFR7f7zODMZeSo+oyYij7PrWCVmr92DCrNVbhvcIxgr7krtsHWjFQqBQ7DIIzGoichjSJKE938pweLNeXCcsy7lLak98fy0wdCqGvfMJvJ1DGoi8ghWhxOLPs3Dul2lcptKKWDxjUm4c2TvRhOSEHUVDGoicjujqR7pa3e7rB0dFaTBirtTuSwldXkMaiJyq72lVfjje7thMNXLbcN7h2LF3amIDta6sTIiz8CgJiK3+VR/Av/3332wOs6uenX75b3w3E1J0PjxeTQRwKAmIjcQRQn/2HoIK7YXym1KhYDFUwfhntF93VcYkQdiUBNRp6q1OjD3I73L0pSh/iq8eedwTi5C1AQGNRF1mrKqOtz/Tjbyy01yW//oQPxn5uXoHdEx46OJvB2Dmog6hb60Cg++m42TNWcnMblmYBT+eftQBGlVbqyMyLMxqImow23JLcfcj/QuncYeHBuHP01KbLf5uol8FYOaiDqMJElYkVmIv391SG7zUwj46/TBuO3y3nIb59kmah6Dmog6hM0h4s+b9uOj7LMzjQVr/bDynlSMSTjbacxl5SqnBJWSK1cRnYurZzWBq2cRXRpTvR2z1+7GTwWn5LY+Ef5Yfe/lSOgeKLdlFVRg4cZcmK0OhPmroVYqYHOKOG2xI1CjxJLpyQxr6vIU7i6AiHxLWVUdblmx0yWkR/QJw8aHr3QJaVFsuC1utjoQE6yFVqWEQiFAq1IiJlgDs9WJFZmFEEVeS1DXxqAmonaTV1aN6W/+hEO/1chtU1N0WPvAFQgPUJ93rAmFRjPC/NWNFtwQBAGh/ioUGs3IKzOBqCvjM2oiahc/HDmJ9Pd2o9bmlNsevjoB88YPaLJjWKXFBrtTglrZ9PWCRqlAtSih0mLrsJqJvAGDmogu2YY9x/F//90nryGtVAh4/qbBuPOK3s2+J9xfDZVSgM0pQqtoPK+31SlCpRAQ7q9u4t1EXQdvfRNRm0mShDe+L0DGx3vlkPZXK/GfmSMuGNIAkKQLRkJUIE5b7Di/T6skSaiy2JEQFYgkHTt0UtfGoCaiNnGKEhZtzsM/vj47RjoyUI11D43CuIFRF32/QiFgdloCAjVKGExW1NmdEEUJdXYnDCYrAjVKzE5L4Hhq6vI4PKsJHJ5FdGH1difmfqTHl/sNcltcZADeuW9kq+fsdhlHLUpQKTiOmuhcDOomMKiJmmeqt+Ohd7Px89FKuS2lVyhWzxqBiEBNmz6TM5MRNY+dyYioxYw19bh39S4cOGf1q6sHdMebdw2Hv7rt/5woFAKSe4a0R4lEPodBTUQtUnLKgrtX/YKSSovcdvOwHvjb74dA1cwQKyK6dAxqIrqogwYT7ln1q8sSlX+8Kh7zJw7kLWqiDsagJqIL2l1cifve3gVTvUNuWzh5IB66KsGNVRF1HQxqImpW5uGT+ON72ai3N6wjrRCAF2cMwa0jerm5MqKug0FNRE36Mrccc9blwO5sGBiiVirw2h3DMHFwjJsrI+pa3NoDZMeOHZg6dSp0Oh0EQcCmTZsu+p7MzEykpqZCq9UiPj4eK1eudNm/Zs0aCILQ6FVfX99B34LI93ySXYpHPtgjh3SAWok1913OkCZyA7cGdW1tLVJSUrB8+fIWHV9UVITJkydj7NixyMnJwcKFCzFnzhysX7/e5bjg4GCUl5e7vLRabUd8BSKf8/ZPRXjqv/twZnXJkG4qvP/gKE4+QuQmbr31PWnSJEyaNKnFx69cuRK9e/fGq6++CgBITExEdnY2li1bhhkzZsjHCYKAmBj+5U/UWm98X+AyJWj3IA3W3n8FBsQEubEqoq7NqwY/7ty5E+PHj3dpmzBhArKzs2G32+U2s9mMPn36oGfPnrjhhhuQk5Nzwc+1Wq0wmUwuL6KuRJIkLPv6kEtI9wjthk/+OJohTeRmXhXUBoMB0dHRLm3R0dFwOByoqKgAAAwcOBBr1qzB5s2b8eGHH0Kr1eLKK6/EkSNHmv3cpUuXIiQkRH716sUerdR1SJKE5z/Px/LvC+S2+MgA/Hf2aPSNDHBjZUQEeFlQAw23tc91ZqryM+2jRo3C3XffjZSUFIwdOxYff/wx+vfvj9dff73Zz1ywYAGqq6vlV2lpacd9ASIP4nCImL12D1b/VCS3DYgOwkd/HI3YkG5urIyIzvCq4VkxMTEwGAwubUajEX5+foiIiGjyPQqFApdffvkFr6g1Gg00mrYtJkDkrX48fBJPfrIXv50z21igxg8Z11+G7kH83wORp/CqK+rRo0dj27ZtLm1bt27FiBEjoFKpmnyPJEnQ6/WIjY3tjBKJvMIPh0/ij2t3u4S01k8BtZ8CS788iKyCCjdWR0TncmtQm81m6PV66PV6AA3Dr/R6PUpKSgA03JKeOXOmfHx6ejqKi4uRkZGB/Px8rF69GqtWrcK8efPkY5577jl8/fXXOHr0KPR6Pe6//37o9Xqkp6d36ncj8lRWuxNzP9aj1uaU2wLUSsR3D4QuRAuz1YkVmYUQRa6AS+QJ3HrrOzs7G+PGjZO3MzIyAACzZs3CmjVrUF5eLoc2AMTFxWHLli2YO3cu3njjDeh0Orz22msuQ7Oqqqrw0EMPwWAwICQkBMOGDcOOHTswcuTIzvtiRB7K5hBx79u7UGG2yW0BGiX6hgfIi2uE+qtQaDQjr8zEpSeJPIAgnemNRTKTyYSQkBBUV1cjODjY3eUQtQubQ8SjH+zB1gO/yW2BGj/0ifCH4pxOmqIowWi2YtktKUjr390dpRLRObyqMxkRtY3NIeLh9/fgm/yzIR2gVjYKaQCwOkWoFALC/dWdXSYRNYFBTeTjrA4nHnl/D77JN8pt4QFqCADOX0lakiRUWexIjA1Cko53k4g8gVf1+iai1rE5xEYhff2gaLx6awqCtH4wmKyoszshihLq7E4YTFYEapSYnZYgP7MmIvfiFTWRj7I5RDzygWtIjx8UjeV3DofaT4El0xVYkVmIQqMZ1aIElUJAYmwQZqclcAEOIg/CzmRNYGcy8nZ2p4jHPsjBV3lnJwg6N6TPEEUJeWUmVFpsCPdXI0kXzCtpIg/DK2oiH+Nwinhind4lpK9LbBzSAKBQCByCReTh+IyayIc4RQlzP96LL3LL5bZrBkbhjbuGNQppIvIO/F8ukY8QRQn/9999+Gxvmdx29YDuWHH3cGj8lG6sjIguBYOayAeIooSnN+Vi/Z7jctvYyyKx8u5UhjSRl2NQE3k5SZLw3Gd5+PDXs8uzjooPx7/vGQGtiiFN5O0Y1EReTJIkvPjlQbyzs1huG9EnDKtmXY5uaoY0kS9gUBN5sX9+ewT/2nFU3k7pFYq377scARoO6CDyFQxqIi/17x2FePWbI/L2oNhgvHvfSARpm16bnYi8E4OayAu9t/MYlmw5KG/3iwrEe/ePRIg/Q5rI1zCoibzMxpzj+POnefJ273B/rL3/CkQEatxYFRF1FAY1kRf5Os+AeZ/sk7djQ7R4/4ErEBOidWNVRNSRGNREXuKnggo89kEOnGLD9PwRAWqsfeAK9Ar3d3NlRNSRGNREXmBPyWk8+G42bE4RABCk9cO7949EQvdAN1dGRB2NQU3k4Q4ZanDf27tgsTkBAN1USqy573Ik6biYBlFXwKAm8mAlpyy4Z9UvqK6zAwDUSgXemjkCqX3C3VwZEXUWBjWRhzLW1OOe1b/AWGMFACgE4LU7huJ3l0W6uTIi6kycvojITURRQl6ZCZUWG8L91UjSBUOhEAAA1XV2zFz1K4pPWeTjl96cjImDY91VLhG5CYOayA2yCiqwIrMQhUYz7E4JKqWAhKhAzE5LwPA+YXjgnV04aKiRj18waSBuu7y3GysmIncRJEmS3F2EpzGZTAgJCUF1dTWCg4PdXQ75mKyCCizcmAuz1YEwfzXUSgVsThGnLXYEqBWIDNRgd0mVfPwf0+KxYFKi+womIrfiFTVRJxJFCSsyC2G2OhATrIUgNNzq1iqUiA4SUHCyFsWVdfLxt47oiT9NHOiuconIA7AzGVEnyiszodBoRpi/Wg7pM4w1Nlgdorx9XWI0lkxPbnQcEXUtvKIm6kSVFpv8TLrO5oRDFOGnUKDWZsdJs1U+rn90IJbfOQx+Sv4tTdTVMaiJOlG4vxqiJKGowgKHKEKSAEmS4Dynp4ifQsBzUwdDq1K6r1Ai8hj8c52oE1XX2VBrc6De7oQAQBDgEtKCAAzvE4or4jmhCRE14BU1UScRRQn/2nEUaqUCoijBIUoQzxtzoVIKmHPNZfJ4aiIiXlETdZIzHcmig7WIDtbi/IGRaqUCQRo/hHRTu6dAIvJIvKIm6iRnOpIpBQHGGivOzenYYC3C/FU4WWtDpcXmthqJyPPwipqok4T7q+GnAIorLS7DsHqEdkNkkAY2UYJKISDcn1fURHQWg5qokyTGBMEhSqizO+W27kEahAeoIUkSqix2JEQFIknH2fCI6Cze+ibqJMu2HcZJ89nb2kFaP3QPUKPO7kSVxY5AjRKz0xLYkYyIXDCoiTrB2p+LsTKzUN4O7aZCN5UCJ2ttUCkEJMYGYXZaAsb04xKWROSKQU3Uwb4/aMSzn+6XtwfGBOGjh0ahpLKuySUuiYjOxaAm6kD7T1TjkQ/2yOOlY4K1ePu+yxHir0YyO40RUQuwMxlRBymrqsMf1uyCxdbQeSxQ44fV916O2JBubq6MiLwJg5qoA9TU2/GHNbtgrGlYaEOpEPDGXcMxiD26iaiVGNRE7czhFPHoBzk4aKiR2/46bTDS+nd3Y1VE5K0Y1ETtSJIkLP4sD5mHT8pts69OwO0je7uxKiLyZgxqona06scirP25RN6ekhyLp8YPcGNFROTt3BrUO3bswNSpU6HT6SAIAjZt2nTR92RmZiI1NRVarRbx8fFYuXJls8euW7cOgiBg2rRp7Vc0UTO2HfgNf92SL28P7RWKl25N4bArIrokbg3q2tpapKSkYPny5S06vqioCJMnT8bYsWORk5ODhQsXYs6cOVi/fn2jY4uLizFv3jyMHTu2vcsmaiSvrBqPr8uRV8TqGdYNb80cAa1K6d7CiMjruXUc9aRJkzBp0qQWH79y5Ur07t0br776KgAgMTER2dnZWLZsGWbMmCEf53Q6cdddd+G5557DDz/8gKqqqnaunOgso6keD7yT3WgYVvcgjZsrIyJf4FXPqHfu3Inx48e7tE2YMAHZ2dmw2+1y21/+8hd0794d999/f2eXSF1Mnc2JB9/NRnl1PQBAIQDL7xyG/tFBbq6MiHyFV81MZjAYEB0d7dIWHR0Nh8OBiooKxMbG4qeffsKqVaug1+tb/LlWqxVWq1XeNplM7VUy+TBRlDDvk73Ye7xabls0NQlXD4hyY1VE5Gu86ooaAATBtWOO9L+HgoIgoKamBnfffTfeeustREa2fHGDpUuXIiQkRH716tWrXWsm3/Tqt0fwRW65vD1zdB/MGtPXfQURkU/yqivqmJgYGAwGlzaj0Qg/Pz9EREQgLy8Px44dw9SpU+X9oigCAPz8/HDo0CEkJCQ0+twFCxYgIyND3jaZTAxruqDP9pbhtW+PyNtjL4vEszcMcmNFROSrvCqoR48ejc8++8ylbevWrRgxYgRUKhUGDhyI3Nxcl/3PPPMMampq8M9//rPZ8NVoNNBo2PGHWmbf8SrM+2SvvB3fPQDL7xwOP6XX3aAiIi/Q5qBWKpUoLy9HVJTr87hTp04hKioKTqfzop9hNptRUFAgbxcVFUGv1yM8PBy9e/fGggULcOLECbz77rsAgPT0dCxfvhwZGRl48MEHsXPnTqxatQoffvghAECr1WLw4MEuPyM0NBQAGrUTtYWhuh4PvpsNq6PhTk1INxVWzbocId1Ubq6MiHxVm4P6zLPh81mtVqjVLVu+Lzs7G+PGjZO3z9x+njVrFtasWYPy8nKUlJyd5SkuLg5btmzB3Llz8cYbb0Cn0+G1115zGZpF1FHq7U788b1s/GZq6HjopxCw4q7hiIsMcHNlROTLBKm5xG3Ga6+9BgCYO3cunn/+eQQGBsr7nE4nduzYgWPHjiEnJ6d9K+1EJpMJISEhqK6uRnAwVzuihj9Mn/hIj0/1ZXLbC9MG4+5RfdxYFRF1Ba2+on7llVcANPzDtXLlSiiVZ2deUqvV6Nu37wWn9STyRv/acdQlpO8Z1YchTUSdotVBXVRUBAAYN24cNmzYgLCwsHYvisiTfHfwN/ztq4Py9uj4CDw7lT28iahztPkZ9ffff9+edRB5pAJjDeZ8qJfn8O4V3g1v3jUcKvbwJqJOcknDs44fP47NmzejpKQENpvNZd/LL798SYURuVu1xY4H3smG2eoAAASolfjPzMsRFtCyzpJERO2hzUH97bff4sYbb0RcXBwOHTqEwYMH49ixY5AkCcOHD2/PGok6nVOUMGddDo6dsshtr9w2FANiOIc3EXWuNt+/W7BgAZ588kns378fWq0W69evR2lpKdLS0nDLLbe0Z41E7UYUJeQer0bm4ZPIPV4NUWx60MPfvz6IzMMn5e2M6/tjfFJMZ5VJRCRr9fCsM4KCgqDX65GQkICwsDD8+OOPSEpKwt69e3HTTTfh2LFj7Vxq5+HwLN+UVVCBFZmFKDSaYXdKUCkFJEQFYnZaAsb0Ozs3/Kf6E3h8nV7enpgUgzfvGg6FQmjiU4mIOlabr6gDAgLkFad0Oh0KCwvlfRUVFZdeGVE7yiqowMKNucgvNyFA44eoIA0CNH7IL6/Bwo25yCpo+J3NK6vG/PX75PcNiA7CS7emMKSJyG3a/Ix61KhR+OmnnzBo0CBMmTIFTz75JHJzc7FhwwaMGjWqPWskuiSiKGFFZiHMVgdigrXyCmxahRIxwQoYTFasyCxE/+ggPPTubtTbz04P+u+ZqQjQeNWU+ETkY9r8L9DLL78Ms9kMAFi8eDHMZjM++ugj9OvXT54UhcgT5JWZUGg0I8xf3WiZVEEQEOqvQsFvNbj/nV04UVUHAFAIwPI7h6FPBKcHJSL3anNQx8fHy//t7++PN998s10KImpvlRYb7E4J6mbGPmuUCpyoc6DcVC23zZ84EGMv695ZJRIRNatd7unV19fjo48+gsViwfXXX49+/fq1x8cStYtwfzVUSgE2pwitQtlof0WtFXX2s6u9TRkSi4euim90HBGRO7S61/dTTz0Fm82Gf/7znwAAm82GK664Anl5efD394fD4cC2bdswevToDim4M7DXt28RRQmz3v4V+eU1iAnWuNz+rrM5UHCyVt4eGBOEDQ+Pgb+az6WJyDO0utf3l19+iWuvvVbefv/991FcXIwjR47g9OnTuOWWW/DCCy+0a5FEl0KhEDA7LQGBGiUMpoarZ1GUYLY6cLTi7IQmwVo//OueVIY0EXmUVgd1SUkJBg06uyDB1q1b8fvf/x59+vSBIAh4/PHHvXqJS/JNY/pFYsn0ZCTGBsFideC3mnqUVdVB/N8NJUEA/nkHO48RkedpdVArFAqce7f8559/dhmOFRoaitOnT7dPdUTtaEy/SLxz30j8654RuKp/d1gdorxv7nX9MW5AlBurIyJqWquDeuDAgfjss88AAHl5eSgpKcG4cePk/cXFxYiOjm6/ConakUIhoKLWio05J+S26xKj8Og4doAkIs/U6odxTz31FO644w588cUXyMvLw+TJkxEXFyfv37JlC0aOHNmuRRK1l9JKC55Yd3bZyr4R/njp1qGceYyIPFarr6hnzJiBLVu2YMiQIZg7dy4++ugjl/3+/v54+OGH261AovZSb3di9vu7UV1nBwB0Uymx8p5UhHRTubkyIqLmtXlRjpZ6+OGH8Ze//AWRkZEXP9hDcHiWb/rT+n1Yt6tU3n71tqGYNqyHGysiIrq4Ni/K0VJr166FyWTq6B9DdEEf7yp1CemZo/swpInIK3R4UHfwBTvRRe0/UY1nPt0vbw/rHYpnpgy6wDuIiDxHhwc1kTtV19kx+/3dsP1vKFZ4gBpv3jUcaj/+6hORd+C/VuSzJEnCvE/2orTy7IpYr90+DLEh3dxcGRFRyzGoyWe99cNRbDvwm7ydcX1//O4y7+nUSEQEMKjJR/1aVIm/fXVI3r56QHc8fDUnNSEi79PhQX333XdziBN1qpM1Vjz6wR44xYaOjLoQLV7hpCZE5KXavEzQvn37WnTc7NmzvWoMNXk3pyjhiY9yYKyxAgBUSgFv3DUcYQFqN1dGRNQ2bQ7qoUOHuqzr2xRJkiAIApxOZ1t/DFGrvP7dEfxUcErefnpyIob1DnNjRUREl6bNt743bNiAuLg4vPnmm8jJyUFOTg7efPNNJCQkYP369Th69CiKiopw9OjR9qyXqFk/HqnAP789Im9PSY7FrDF93VcQEVE7aPMV9ZIlS/Daa69h8uTJctuQIUPQq1cv/PnPf8bu3bvbpUCiljCa6vHERzkui20snZF80bs+RESers1X1Lm5uS6rZp0RFxeHAwcOXFJRRK3hcIp47MMcVJhtAAC1nwJv3DUcwVoutkFE3q/NQZ2YmIgXXngB9fX1cpvVasULL7yAxMTEdimOqCX++e0R/FJUKW8vnpqEJF2IGysiImo/bb71vXLlSkydOhW9evVCSkoKAGDv3r0QBAGff/55uxVIdCE/HqnA8u8L5O2bhupwx8hebqyIiKh9XdIylxaLBWvXrsXBgwchSRIGDRqEO++8EwEBAe1ZY6fjMpfewVhTj8n//EG+5R0fGYDNj/0OgZo2//1JRORxOnw9am/EoPZ8TlHCPat+QVZhw1AstZ8CGx8ew1veRORzWnXpsXnzZkyaNAkqlQqbN2++4LE33njjJRVGdCHLvyuQQxoA/nzDIIY0EfmkVl1RKxQKGAwGREVFQaFovh+at09ywitqz/bz0VO4862f8b8ZQjElORbL7xzGoVhE5JNadUUtimKT/32ukpISLFq06NKqImpGZa0NT6zTyyHdO5zjpYnIt7X7ohynT5/Gu+++294fSwRJkvDUJ3thMDUMCVQpBSy/cxjHSxORT+Myl+Q1Vv90DN8eNMrb8ycOxJCeoe4riIioEzCoySvkHq/Gi1/my9vXDIzC/b9rPDMeEZGvYVCTxzNbHXjswz2wOxseTEcHa7DslhQ+lyaiLqHVM0PcfPPNF9xfVVXV1lrIh4mihLwyEyotNoT7q5GkC4ZC0bKgffbT/Th2ygIAUAjAq7cNQzjXlyaiLqLVV9QhISEXfPXp0wczZ85s0Wft2LEDU6dOhU6ngyAI2LRp00Xfk5mZidTUVGi1WsTHx2PlypUu+zds2IARI0YgNDQUAQEBGDp0KN57773Wfk1qR1kFFZj19q/443vZmPfxXvzxvWzMevtXZBVUXPS9G3OOY8OeE/L2o9dchtEJER1ZLhGRR2n1FfXbb7/dbj+8trYWKSkpuO+++zBjxoyLHl9UVITJkyfjwQcfxNq1a/HTTz/h4YcfRvfu3eX3h4eH4+mnn8bAgQOhVqvx+eef47777kNUVBQmTJjQbrVTy2QVVGDhxlyYrQ6E+auhVipgc4rIL6/Bwo25WDI9GWP6RTb53mMVtXhm4355e0SfMMy5pl9nlU5E5BE8ZgpRQRCwceNGTJs2rdlj5s+fj82bNyM//2ynovT0dOzduxc7d+5s9n3Dhw/HlClT8Pzzz7eoFk540j5EUcKst39FfrkJMcFal2fKkiTBYLIiMTYI79w3stFtcJtDxO9XZmHf8WoAQJDWD18+PhY9w/w79TsQEbmbV3Um27lzJ8aPH+/SNmHCBGRnZ8Nutzc6XpIkfPvttzh06BCuuuqqZj/XarXCZDK5vOjS5ZWZUGg0I8xf3ajjlyAICPVXodBoRl5Z4/P90rZDckgDwIs3D2FIE1GX5FVBbTAYEB0d7dIWHR0Nh8OBioqzzzurq6sRGBgItVqNKVOm4PXXX8f111/f7OcuXbrU5Tl7r15cJrE9VFpssDslqJVN/5pplArYRQmVFptL+08FFfhX5lF5+/bLe2HKkNgOrZWIyFN5VVADaHRldubO/bntQUFB0Ov12LVrF/76178iIyMD27dvb/YzFyxYgOrqavlVWlraIbV3NeH+aqiUAmzOpqebtTpFqBQCwv3P9uCurLUh42O9vJ3QPQDPTh3U0aUSEXksr1q4NyYmBgaDwaXNaDTCz88PERFnewIrFAr069fQ6Wjo0KHIz8/H0qVLcfXVVzf5uRqNBhqNpsPq7qqSdMFIiApEfnkNYoIVjZ5RV1nsSIwNQpIuWG6bv34ffjNZATRMEfrP24fBX+1Vv6ZERO3Kq66oR48ejW3btrm0bd26FSNGjIBK1fx8z5IkwWq1dnR5dB6FQsDstAQEapQwmKyoszshihLq7E4YTFYEapSYnZYgdyR7/5cSbDvwm/z++RMHYnAPLl1JRF2bW4PabDZDr9dDr9cDaBh+pdfrUVJSAqDhlvS5Y7LT09NRXFyMjIwM5OfnY/Xq1Vi1ahXmzZsnH7N06VJs27YNR48excGDB/Hyyy/j3Xffxd13392p340ajOkXiSXTk5EYGwSL1QGj2QqL1YHE2CCXoVkFxhq88MUB+X1jL4vEH67kFKFERG69p5idnY1x48bJ2xkZGQCAWbNmYc2aNSgvL5dDGwDi4uKwZcsWzJ07F2+88QZ0Oh1ee+01lzHYtbW1ePjhh3H8+HF069YNAwcOxNq1a3Hbbbd13hcjF2P6RWJUfESzM5NZHU7M+VCPenvDs+zwADVeuiWlxTOXERH5Mo8ZR+1JOI66cy3dko9/7Tjby/s/M0fgukHRF3gHEVHX4VXPqMn3ZBVW4N8/nA3pu67ozZAmIjoHg5rcpspiQ8ZHe3Hmnk589wA8M4VDsYiIzsWgJreQJAlPb9wPg6keQMNQrNduH4ZuaqWbKyMi8iwManKLjTkn8EVuubz95PgBHIpFRNQEBjV1utJKC579NE/eHhUfjgfHxruxIiIiz8Upn6hVRFFqdphVSzhFCU9+vBdmqwNAw6pYL906FEoOxSIiahKDmlosq6ACKzILUWg0w+6UoFIKSIgKxOy0hGbXlD7fv3ccxa/HKuXt528ajB6h3TqqZCIir8db39QiWQUVWLgxF/nlJgRo/BAVpEGAxg/55TVYuDEXWQUVF/2M/Seq8fK2Q/L21BQdbhqq68iyiYi8HoOaLkoUJazILITZ6kBMsBZalRIKhQCtSomYYA3MVidWZBZCFJufO6fe7sTcj/SwOxuOiQ3R4oWbBjdaDY2IiFwxqOmi8spMKDSaEeavbhSsgiAg1F+FQqMZeWWmZj/jH18fwhGjWd5edksKQvybX0iFiIgaMKjpoiotNtidEtTKpn9dNEoF7KKESoutyf1ZhRVY9WORvP2HK+NwZQufaRMRdXUMarqocH81VEoBNqfY5H6rU4RKISDcX91on6nejnkf75W3+0UF4v8mDuiwWomIfA2Dmi4qSReMhKhAnLbYcf4aLpIkocpiR0JUIJJ0jRcwWbw5D2XVDbOP+SkEvHrbUGhVnH2MiKilGNR0UQqFgNlpCQjUKGEwWVFnd0IUJdTZnTCYrAjUKDE7LaHReOqv9pdjw54T8vbj117G2ceIiFqJQU0tMqZfJJZMT0ZibBAsVgeMZissVgcSY4OwZHpyo3HUJ2usWLhxv7w9rHcoZl+d0NllExF5PU54Qi02pl8kRsVHXHRmsoYFN3JRWdvQuUyrUuClW1Lg10xnNCIiah6DmlpFoRCQ3PPCt6837DmBrQd+k7cXTEpEfPfAji6NiMgn8RKH2lVZVR0Wbz674MaV/SJwz6g+bqyIiMi7Maip3YiihP/77z7UnFlwQ+OHf/w+pVWLdhARkSsGNbWb938pxo/nzPm96MYk6LjgBhHRJWFQU7soPlWLJVsOytvXD4rGjOE93FgREZFvYFDTJRNFCU99sg91dicAIMxfhSXTk7ngBhFRO2BQ0yV7O+uYyxrTL0xLRvcgjRsrIiLyHQxquiSFJ834+1dnb3nfMCQWU4bEurEiIiLfwqCmNnOKEuZ9shdWR8NiHZGBavzlpsFuroqIyLcwqKnN/vPDUeSUVMnbS6YnIzyg8QpaRETUdgxqapMCYw1e2nZY3p4+rAfGJ8W4sSIiIt/EoKZWa7jlvQ+2/93y7h6kwaKpg9xcFRGRb2JQU6u99cNR6Eur5O2l05MR6s9b3kREHYFBTa1SYKzBy+fc8r55WA9cNyjajRUREfk2BjW12Pm3vKOCNFg0NcnNVRER+TYGNbXYqh/Pu+V9czJC/FXuK4iIqAvgetRdlChKyCszodJiQ7i/Gkm64AuucnX0pBkvbXW95X1tIm95ExF1NAZ1F5RVUIEVmYUoNJphd0pQKQUkRAVidloCxvSLbHS883/LV1rP6eX9LHt5ExF1Ct767mKyCiqwcGMu8stNCND4ISpIgwCNH/LLa7BwYy6yzlmm8ox3so4hu/i0vP3CtMHs5U1E1EkY1F2IKEpYkVkIs9WBmGAttColFAoBWpUSMcEamK1OrMgshChK8nuKT9Xi71+fnct7aooOEzixCRFRp2FQdyF5ZSYUGs0I81c3WoJSEASE+qtQaDQjr8wEoCHY56/fh3p7wy3viAA1nruRvbyJiDoTg7oLqbTYYHdKUCub/n+7RqmAXZRQabEBAD7cVYKfj55dvvIvNw3mXN5ERJ2MQd2FhPuroVIKsDnFJvdbnSJUCgHh/mqUVdVh6Zazt7wnJEVjcjJveRMRdTYGdReSpAtGQlQgTlvskCTJZZ8kSaiy2JEQFYhBsUF4ZtN+mK0OAECw1g/P3zS40e1yIiLqeAzqLkShEDA7LQGBGiUMJivq7E6IooQ6uxMGkxWBGiVmpyXgs33l+O6gUX7fn28YhKhgrRsrJyLquhjUXcyYfpFYMj0ZibFBsFgdMJqtsFgdSIwNwpLpyegfE4TnPsuTj7+qf3f8PrWnGysmIuraOOFJFzSmXyRGxUc0OTPZox/swWmLHQAQoFZiyXTe8iYicicGdRelUAhI7hni0vbNgd/w+b5yefv/Jg5EzzD/zi6NiIjO4dZb3zt27MDUqVOh0+kgCAI2bdp00fdkZmYiNTUVWq0W8fHxWLlypcv+t956C2PHjkVYWBjCwsJw3XXX4ddff+2gb+A7TPV2PLNpv7w9ok8Y7hnVx40VERER4Oagrq2tRUpKCpYvX96i44uKijB58mSMHTsWOTk5WLhwIebMmYP169fLx2zfvh133HEHvv/+e+zcuRO9e/fG+PHjceLEiY76Gj7hb18ehMFUDwBQKxV4ccaQCy7SQUREnUOQzh+n4yaCIGDjxo2YNm1as8fMnz8fmzdvRn5+vtyWnp6OvXv3YufOnU2+x+l0IiwsDMuXL8fMmTNbVIvJZEJISAiqq6sRHBzcqu/hjX4+egq3//tnefvJ6/vjsWsvc2NFRER0hlf1+t65cyfGjx/v0jZhwgRkZ2fDbrc3+R6LxQK73Y7w8PBmP9dqtcJkMrm8uop6uxMLNuTK2wNjgvDHtAQ3VkREROfyqqA2GAyIjnZdAzk6OhoOhwMVFY1XfQKAP/3pT+jRoweuu+66Zj936dKlCAkJkV+9evVq17o92evfHUFRRS0AQCEAf5sxBGo/r/q1ICLyaV73L/L5Q4XO3LlvagjR3//+d3z44YfYsGEDtNrmJ+xYsGABqqur5VdpaWn7Fu2h8stN+FfmUXn7D1fGIaVXqPsKIiKiRrxqeFZMTAwMBoNLm9FohJ+fHyIiIlzaly1bhiVLluCbb77BkCFDLvi5Go0GGo2m3ev1ZE5Rwp/W74Pjf0ta9gzrhozx/d1cFRERnc+rrqhHjx6Nbdu2ubRt3boVI0aMgEqlktv+8Y9/4Pnnn8dXX32FESNGdHaZXuGdrGPYe7xa3v7r9GT4q73q7zYioi7BrUFtNpuh1+uh1+sBNAy/0uv1KCkpAdBwS/rcntrp6ekoLi5GRkYG8vPzsXr1aqxatQrz5s2Tj/n73/+OZ555BqtXr0bfvn1hMBhgMBhgNps79bt5suOnLVi29ZC8PX1YD6T17+7GioiIqDluHZ61fft2jBs3rlH7rFmzsGbNGtx77704duwYtm/fLu/LzMzE3LlzkZeXB51Oh/nz5yM9PV3e37dvXxQXFzf6zEWLFmHx4sUtqsuXh2dJkoQ/rNmF7w+dBACE+avwTUYaIgK71q1/IiJv4THjqD2JLwf1Z3vL8NiHOfL2K7elYPowLrpBROSpvOoZNV2aaovdZWWssZdFYtrQHm6siIiILoZB3YW8+FU+Ksw2AIBWpcBfpyVzZSwiIg/HoO4ifi2qxIe/nh0f/vi1/dE7gitjERF5OgZ1F2B1OLFgwz55e2BMEB4YG+fGioiIqKU4cNYHiKKEvDITKi02hPurkaQLdln5auX2oyg82TBNqCAAL84YApWSf6MREXkDBrWXyyqowIrMQhQazbA7JaiUAhKiAjE7LQFj+kXi6Ekz3vi+QD5+1ui+GMppQomIvAYvq7xYVkEFFm7MRX65CQEaP0QFaRCg8UN+eQ0WbszFT0dO4umN+2FzigCA6GANnuQ0oUREXoVX1F5KFCWsyCyE2epATLBW7r2tVSgRE6yAwWTFc58fwOHfzs7I9tyNSQjSqpr7SCIi8kC8ovZSeWUmFBrNCPNXNxpiJQgCgrR+KDCeDenrEqMwISmms8skIqJLxKD2UpUWG+xOCepmOoWdrrXhfwtjwV+txHM3DeaYaSIiL8Sg9lLh/mqolIL8/PlctVYHqurs8nbG9f3RI7RbZ5ZHRETthEHtpZJ0wUiICsRpix3nTtcuShJOVNXJ24Nig3HvmL5uqJCIiNoDg9pLKRQCZqclIFCjhMFkRZ3dCVGUUF5dD6uj4SpbALDk5mT4ccw0EZHX4r/gXmxMv0gsmZ6MxNggWKwOlJvqUVlrk/ffPaoPx0wTEXk5Ds/ycmP6RWJUfAT2n6jGM5/ul4M6MlCDeRMGuLk6IiK6VLyi9gEKhYATVXXYd7xabvvzDYkI6cYx00RE3o5B7QPMVgee++yAvP27fpG4MUXnxoqIiKi9MKh9wCvbDsNgqgcAqP0UeH4ax0wTEfkKBrWXO1BmwpqsY/L27LQExEUGuK8gIiJqVwxqLyaKEp7ZlAvn/6Yg6xPhj9lXJ7i5KiIiak8Mai/2ye5S7CmpkrefuzEJWpXSfQUREVG7Y1B7qcpaG5Z+eVDenpwcg6sHRLmxIiIi6ggMai/1ty8PosrSMJ93gFqJZ29IcnNFRETUERjUXmh38Wl8lF0qb8+9vj9iQrRurIiIiDoKg9rLOJwi/rxpv7w9MCaIi24QEfkwBrWXef+XEhwoN8nbz08bzEU3iIh8GP+F9yIna6xYtvWQvD1jeE9c3jfcjRUREVFHY1B7kaVb8lFT7wAABGn98KdJA91cERERdTQGtZf4tagSG3JOyNtPTRiA7kEaN1ZERESdgUHtBRxOEc9+erYD2eAewbjrij5urIiIiDoLg9oLvLuzGAcNNfL28zcNhlLBRTeIiLoCBrWHM9bU45Vth+Xt20b0wrDeYW6siIiIOhOD2sO9+OVB1FgbOpAFa/3wfxMHuLkiIiLqTAxqD7brWCU27HHtQBYRyA5kRERdCYPaQ50/A1mSLhh3sgMZEVGXw6D2UO//UuLSgewv7EBGRNQlMag90CmzFS+dMwPZ71N7IrUPO5AREXVFDGoP9I+vD8F0zgxk8ydyBjIioq6KQe1h9pZWuS5heV1/zkBGRNSFMag9iChKeHZzHiSpYXtAdBBmjmYHMiKiroxB7UH+u/s49pZWyduLb0ziEpZERF0cU8BDVNfZ8bevDsrbNwyJxeiECDdWREREnoBB7SFe/eYwTtXaAADdVEo8PSXRzRUREZEncGtQ79ixA1OnToVOp4MgCNi0adNF35OZmYnU1FRotVrEx8dj5cqVLvvz8vIwY8YM9O3bF4Ig4NVXX+2Y4tvR4d9q8O7OYnl7ypBYVNTYIIqSG6siIiJP4Nagrq2tRUpKCpYvX96i44uKijB58mSMHTsWOTk5WLhwIebMmYP169fLx1gsFsTHx+PFF19ETExMR5XebiRJwnOf5cH5v1BWKgRsP2jEH9/Lxqy3f0VWQYWbKyQiIncSJEnyiMs2QRCwceNGTJs2rdlj5s+fj82bNyM/P19uS09Px969e7Fz585Gx/ft2xdPPPEEnnjiiVbVYjKZEBISgurqagQHB7fqva311f5ypK/dI2/HhmgR7q+GzSnitMWOQI0SS6YnY0y/yA6tg4iIPJNXPaPeuXMnxo8f79I2YcIEZGdnw263u6mqtqu3O/H852f/6AjUKBERoIZCIUCrUiImWAOz1YkVmYW8DU5E1EV5VVAbDAZER0e7tEVHR8PhcKCiou23iK1WK0wmk8urM/wr8yhOVNXJ27qQbhCEs/N5C4KAUH8VCo1m5JV1Tk1ERORZvCqoAbgEGdDwjLep9tZYunQpQkJC5FevXr0uqcaWOFFVhxWZBfJ2RIAaGpWy0XEapQJ2UUKlxdbhNRERkefxqqCOiYmBwWBwaTMajfDz80NERNvHHC9YsADV1dXyq7S09OJvukRLt+Sj3i4CABQCENJN1eRxVqcIlUJAuL+6w2siIiLP4+fuAlpj9OjR+Oyzz1zatm7dihEjRkClajroWkKj0UCj6bz5tH8tqsTn+8rl7YTugThtscNfrXS5MyBJEqosdiTGBiFJ17Gd2oiIyDO59YrabDZDr9dDr9cDaBh+pdfrUVJSAqDhSnfmzJny8enp6SguLkZGRgby8/OxevVqrFq1CvPmzZOPsdls8mfabDacOHECer0eBQUF8AROUcLizXny9pCeIVg0dRACNUoYTFbU2Z0QRQl1dicMJisCNUrMTkuAgmtRExF1SW4dnrV9+3aMGzeuUfusWbOwZs0a3HvvvTh27Bi2b98u78vMzMTcuXORl5cHnU6H+fPnIz09Xd5/7NgxxMXFNfrMtLQ0l8+5kI4cnvXhryVYsCFX3l4/ewxS+4Qhq6ACKzILUWg0wy5KUCkEJEQFYnZaAodmERF1YR4zjtqTdFRQV9fZcc2y7fJUodOH9cArtw2V94uihLwyEyotNoT7q5GkC+aVNBFRF+dVz6i93evfHpFD2l+txPyJA132KxQCknuGuKM0IiLyUF7V69ubFZ40Y03WMXn7kXH9EBOidV9BRETkFRjUneSvX+TD8b/ZxXqGdcP9v2v8HJ2IiOh8DOpOkHn4JL47aJS3F05OhLaJyU2IiIjOx6DuYHaniOc/PyBvj4wLx6TBnr+qFxEReQYGdQd7/+diFBjNAABBAJ69YdAlTXdKRERdC4O6A52uteGVb47I27eN6IXBPdirm4iIWo5B3YFe/eYwqusalt8M1PjhyfED3FwRERF5GwZ1B3GKEg7/Zpa3H7umH7oHdd584kRE5Bs44UkHUSoEfPDgFdiSa8AHvxbj3iv7urskIiLyQpxCtAkdOdc3ERFRa/DWNxERkQdjUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwBjUREZEHY1ATERF5MAY1ERGRB2NQExEReTAGNRERkQdjUBMREXkwP3cX4MtEUUJemQmVFhvC/dVI0gVDoRDcXRYREXkRt15R79ixA1OnToVOp4MgCNi0adNF35OZmYnU1FRotVrEx8dj5cqVjY5Zv349Bg0aBI1Gg0GDBmHjxo0dUP2FZRVUYNbbv+KP72Vj3sd78cf3sjHr7V+RVVDR6bUQEZH3cmtQ19bWIiUlBcuXL2/R8UVFRZg8eTLGjh2LnJwcLFy4EHPmzMH69evlY3bu3InbbrsN99xzD/bu3Yt77rkHt956K3755ZeO+hqNZBVUYOHGXOSXmxCg8UNUkAYBGj/kl9dg4cZchjUREbWYIEmS5O4iAEAQBGzcuBHTpk1r9pj58+dj8+bNyM/Pl9vS09Oxd+9e7Ny5EwBw2223wWQy4csvv5SPmThxIsLCwvDhhx+2qBaTyYSQkBBUV1cjODi4Vd9DFCXMevtX5JebEBOshSCcvdUtSRIMJisSY4Pwzn0jeRuciIguyqs6k+3cuRPjx493aZswYQKys7Nht9sveExWVlazn2u1WmEymVxebZVXZkKh0Ywwf7VLSAMNf4yE+qtQaDQjr6ztP4OIiLoOrwpqg8GA6Ohol7bo6Gg4HA5UVFRc8BiDwdDs5y5duhQhISHyq1evXm2usdJig90pQa1s+tRqlArYRQmVFlubfwYREXUdXhXUABpdpZ65c39ue1PHnN92rgULFqC6ulp+lZaWtrm+cH81VEoBNqfY5H6rU4RKISDcX93mn0FERF2HVw3PiomJaXRlbDQa4efnh4iIiAsec/5V9rk0Gg00Gk271JikC0ZCVCDyy2sQE6xo9Iy6ymJHYmwQknSte/ZNRERdk1ddUY8ePRrbtm1zadu6dStGjBgBlUp1wWPGjBnTKTUqFAJmpyUgUKOEwWRFnd0JUZRQZ3fCYLIiUKPE7LQEdiQjIqIWcWtQm81m6PV66PV6AA3Dr/R6PUpKSgA03JKeOXOmfHx6ejqKi4uRkZGB/Px8rF69GqtWrcK8efPkYx5//HFs3boVf/vb33Dw4EH87W9/wzfffIMnnnii077XmH6RWDI9GYmxQbBYHTCarbBYHUiMDcKS6ckY0y+y02ohIiIvJ7nR999/LwFo9Jo1a5YkSZI0a9YsKS0tzeU927dvl4YNGyap1Wqpb9++0ooVKxp97ieffCINGDBAUqlU0sCBA6X169e3qq7q6moJgFRdXd3WryZJkiQ5naK0r7RK2n7IKO0rrZKcTvGSPo+IiLoejxlH7UkuZRw1ERFRe/KqZ9RERERdDYOaiIjIgzGoiYiIPBiDmoiIyIMxqImIiDwYg5qIiMiDMaiJiIg8GIOaiIjIgzGoiYiIPBiDmoiIyIMxqImIiDwYg5qIiMiD+bm7AE90Zp0Sk8nk5kqIiMiXBQUFQRCECx7DoG5CTU0NAKBXr15uroSIiHxZS1Zp5DKXTRBFEWVlZS36S+dCTCYTevXqhdLSUi6XCZ6P8/F8uOL5OIvnwpUvnw9eUbeRQqFAz5492+3zgoODfe6X61LwfLji+XDF83EWz4Wrrno+2JmMiIjIgzGoiYiIPBiDugNpNBosWrQIGo3G3aV4BJ4PVzwfrng+zuK5cNXVzwc7kxEREXkwXlETERF5MAY1ERGRB2NQExEReTAGdQd58803ERcXB61Wi9TUVPzwww/uLqlTLF68GIIguLxiYmLk/ZIkYfHixdDpdOjWrRuuvvpq5OXlubHi9rVjxw5MnToVOp0OgiBg06ZNLvtb8v2tVisee+wxREZGIiAgADfeeCOOHz/eid+i/VzsfNx7772Nfl9GjRrlcoyvnI+lS5fi8ssvR1BQEKKiojBt2jQcOnTI5Ziu9PvRkvPRlX4/LoRB3QE++ugjPPHEE3j66aeRk5ODsWPHYtKkSSgpKXF3aZ0iKSkJ5eXl8is3N1fe9/e//x0vv/wyli9fjl27diEmJgbXX3+9PG2rt6utrUVKSgqWL1/e5P6WfP8nnngCGzduxLp16/Djjz/CbDbjhhtugNPp7Kyv0W4udj4AYOLEiS6/L1u2bHHZ7yvnIzMzE4888gh+/vlnbNu2DQ6HA+PHj0dtba18TFf6/WjJ+QC6zu/HBUnU7kaOHCmlp6e7tA0cOFD605/+5KaKOs+iRYuklJSUJveJoijFxMRIL774otxWX18vhYSESCtXruykCjsPAGnjxo3ydku+f1VVlaRSqaR169bJx5w4cUJSKBTSV1991Wm1d4Tzz4ckSdKsWbOkm266qdn3+PL5MBqNEgApMzNTkiT+fpx/PiSpa/9+nItX1O3MZrNh9+7dGD9+vEv7+PHjkZWV5aaqOteRI0eg0+kQFxeH22+/HUePHgUAFBUVwWAwuJwbjUaDtLS0LnFuWvL9d+/eDbvd7nKMTqfD4MGDffYcbd++HVFRUejfvz8efPBBGI1GeZ8vn4/q6moAQHh4OAD+fpx/Ps7oqr8f52JQt7OKigo4nU5ER0e7tEdHR8NgMLipqs5zxRVX4N1338XXX3+Nt956CwaDAWPGjMGpU6fk799Vz01Lvr/BYIBarUZYWFizx/iSSZMm4f3338d3332Hl156Cbt27cI111wDq9UKwHfPhyRJyMjIwO9+9zsMHjwYQNf+/WjqfABd9/fjfFyUo4OcvxqKJEmXtBKXt5g0aZL838nJyRg9ejQSEhLwzjvvyJ1Auuq5OaMt399Xz9Ftt90m//fgwYMxYsQI9OnTB1988QVuvvnmZt/n7efj0Ucfxb59+/Djjz822tcVfz+aOx9d9ffjfLyibmeRkZFQKpWN/pozGo2N/lLuCgICApCcnIwjR47Ivb+76rlpyfePiYmBzWbD6dOnmz3Gl8XGxqJPnz44cuQIAN88H4899hg2b96M77//3mWVvq76+9Hc+WhKV/j9aAqDup2p1WqkpqZi27ZtLu3btm3DmDFj3FSV+1itVuTn5yM2NhZxcXGIiYlxOTc2mw2ZmZld4ty05PunpqZCpVK5HFNeXo79+/d3iXN06tQplJaWIjY2FoBvnQ9JkvDoo49iw4YN+O677xAXF+eyv6v9flzsfDTFl38/Lsg9fdh827p16ySVSiWtWrVKOnDggPTEE09IAQEB0rFjx9xdWod78sknpe3bt0tHjx6Vfv75Z+mGG26QgoKC5O/+4osvSiEhIdKGDRuk3Nxc6Y477pBiY2Mlk8nk5srbR01NjZSTkyPl5ORIAKSXX35ZysnJkYqLiyVJatn3T09Pl3r27Cl988030p49e6RrrrlGSklJkRwOh7u+Vptd6HzU1NRITz75pJSVlSUVFRVJ33//vTR69GipR48ePnk+Zs+eLYWEhEjbt2+XysvL5ZfFYpGP6Uq/Hxc7H13t9+NCGNQd5I033pD69OkjqdVqafjw4S5DDnzZbbfdJsXGxkoqlUrS6XTSzTffLOXl5cn7RVGUFi1aJMXExEgajUa66qqrpNzcXDdW3L6+//57CUCj16xZsyRJatn3r6urkx599FEpPDxc6tatm3TDDTdIJSUlbvg2l+5C58NisUjjx4+XunfvLqlUKql3797SrFmzGn1XXzkfTZ0HANLbb78tH9OVfj8udj662u/HhXD1LCIiIg/GZ9REREQejEFNRETkwRjUREREHoxBTURE5MEY1ERERB6MQU1EROTBGNREREQejEFNRETkwRjUREREHoxBTeSj7r33XgiCAEEQoFKpEB8fj3nz5qG2ttbdpRFRK3A9aiIfNnHiRLz99tuw2+344Ycf8MADD6C2thYrVqxwOc5ut0OlUrmpyqZ5Yk1E7sAraiIfptFoEBMTg169euHOO+/EXXfdhU2bNmHx4sUYOnQoVq9ejfj4eGg0GkiShOrqajz00EOIiopCcHAwrrnmGuzdu1f+vL1792LcuHEICgpCcHAwUlNTkZ2dDQAoLi7G1KlTERYWhoCAACQlJWHLli0AgDVr1iA0NNSltk2bNkEQBHm7rTUR+TpeURN1Id26dYPdbgcAFBQU4OOPP8b69euhVCoBAFOmTEF4eDi2bNmCkJAQ/Otf/8K1116Lw4cPIzw8HHfddReGDRuGFStWQKlUQq/Xy1e9jzzyCGw2G3bs2IGAgAAcOHAAgYGBraqvLTUR+ToGNVEX8euvv+KDDz7AtddeCwCw2Wx477330L17dwDAd999h9zcXBiNRmg0GgDAsmXLsGnTJvz3v//FQw89hJKSEjz11FMYOHAgAOCyyy6TP7+kpAQzZsxAcnIyACA+Pr7VNbalJiJfx1vfRD7s888/R2BgILRaLUaPHo2rrroKr7/+OgCgT58+ciACwO7du2E2mxEREYHAwED5VVRUhMLCQgBARkYGHnjgAVx33XV48cUX5XYAmDNnDl544QVceeWVWLRoEfbt29fqettSE5Gv4xU1kQ8bN24cVqxYAZVKBZ1O59I5KyAgwOVYURQRGxuL7du3N/qcM8+XFy9ejDvvvBNffPEFvvzySyxatAjr1q3D9OnT8cADD2DChAn44osvsHXrVixduhQvvfQSHnvsMSgUCkiS5PKZZ27Bn6stNRH5OgY1kQ8LCAhAv379WnTs8OHDYTAY4Ofnh759+zZ7XP/+/dG/f3/MnTsXd9xxB95++21Mnz4dANCrVy+kp6cjPT0dCxYswFtvvYXHHnsM3bt3R01NDWpra+Uw1uv17VYTkS/jrW8iAgBcd911GD16NKZNm4avv/4ax44dQ1ZWFp555hlkZ2ejrq4Ojz76KLZv347i4mL89NNP2LVrFxITEwEATzzxBL7++msUFRVhz549+O677+R9V1xxBfz9/bFw4UIUFBTggw8+wJo1ay65JqKugEFNRAAAQRCwZcsWXHXVVfjDH/6A/v374/bbb8exY8cQHR0NpVKJU6dOYebMmejfvz9uvfVWTJo0Cc899xwAwOl04pFHHkFiYiImTpyIAQMG4M033wQAhIeHY+3atdiyZQuSk5Px4YcfYvHixZdcE1FXIEjnPzgiIiIij8EraiIiIg/GoCYiIvJgDGoiIiIPxqAmIiLyYAxqIiIiD8agJiIi8mAMaiIiIg/GoCYiIvJgDGoiIiIPxqAmIiLyYAxqIiIiD8agJiIi8mD/D2KyLsX9UYA4AAAAAElFTkSuQmCC\n",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
}
],
"source": [
- "model.fit(pressure_train3,volume_train)"
+ "sns.lmplot(x =\"Pressure\", y =\"Liq_Sat\", data = d1, order = 2, ci = None)"
]
},
{
"cell_type": "code",
- "execution_count": 46,
- "id": "96ad5df0",
+ "execution_count": 47,
+ "id": "772449da",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Weights: [[3.73717949e-05]]\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
- "print(\"Weights: \",model.coef_)"
+ "#d1.fillna(method ='ffill', inplace = True)"
]
},
{
"cell_type": "code",
- "execution_count": 47,
- "id": "e470bd03",
+ "execution_count": 49,
+ "id": "07f6efb9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Intercepts: [1.10185478]\n"
+ "0.8815664052801386\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\HBD\\AppData\\Local\\Temp\\ipykernel_17628\\1272166201.py:5: SettingWithCopyWarning: \n",
+ "A value is trying to be set on a copy of a slice from a DataFrame\n",
+ "\n",
+ "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+ " d1.dropna(inplace = True)\n"
]
}
],
"source": [
- "print(\"Intercepts: \",model.intercept_)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 48,
- "id": "4b2d4f79",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test3=list(df.loc[(df['Property']=='V')&((df['Pressure']>=1500))]['Pressure'])[-42:]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 49,
- "id": "6f7f20dc",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test3=np.array(pressure_test3)"
+ "X = np.array(d1['Pressure']).reshape(-1, 1)\n",
+ "y = np.array(d1['Liq_Sat']).reshape(-1, 1)\n",
+ " \n",
+ "\n",
+ "d1.dropna(inplace = True)\n",
+ " \n",
+ "# Dropping any rows with Nan values\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)\n",
+ " \n",
+ "# Splitting the data into training and testing data\n",
+ "regr = LinearRegression()\n",
+ " \n",
+ "regr.fit(X_train, y_train)\n",
+ "print(regr.score(X_test, y_test))"
]
},
{
"cell_type": "code",
"execution_count": 50,
- "id": "f6107115",
- "metadata": {},
- "outputs": [],
- "source": [
- "pressure_test3= pressure_test3.reshape(-1,1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 51,
- "id": "b5fa18a4",
+ "id": "ead505c5",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
- "volume_pred3=model.predict(pressure_test3)"
+ "y_pred = regr.predict(X_test)\n",
+ "plt.scatter(X_test, y_test, color ='b')\n",
+ "plt.plot(X_test, y_pred, color ='k')\n",
+ " \n",
+ "plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 52,
- "id": "945da762",
+ "id": "d309bec1",
"metadata": {},
"outputs": [
{
- "data": {
- "text/plain": [
- "-16.285576758114317"
- ]
- },
- "execution_count": 52,
- "metadata": {},
- "output_type": "execute_result"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "MAE: 0.008198233333871763\n",
+ "MSE: 9.634572930460713e-05\n",
+ "RMSE: 0.00981558603979442\n"
+ ]
}
],
"source": [
- "r2_score(volume_train,volume_pred3)"
+ "from sklearn.metrics import mean_absolute_error,mean_squared_error\n",
+ " \n",
+ "mae = mean_absolute_error(y_true=y_test,y_pred=y_pred)\n",
+ "#squared True returns MSE value, False returns RMSE value.\n",
+ "mse = mean_squared_error(y_true=y_test,y_pred=y_pred) #default=True\n",
+ "rmse = mean_squared_error(y_true=y_test,y_pred=y_pred,squared=False)\n",
+ " \n",
+ "print(\"MAE:\",mae)\n",
+ "print(\"MSE:\",mse)\n",
+ "print(\"RMSE:\",rmse)"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "c0a2c247",
+ "id": "f6ecbd3e",
"metadata": {},
"outputs": [],
"source": []
@@ -1151,7 +4021,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.1"
+ "version": "3.9.13"
}
},
"nbformat": 4,
diff --git a/assignment4.ipynb b/assignment4.ipynb
new file mode 100644
index 0000000..0c27573
--- /dev/null
+++ b/assignment4.ipynb
@@ -0,0 +1,4304 @@
+{
+ "cells": [
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Importing Libraries"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.metrics import mean_squared_error"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Relu Function"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def relu(z):\n",
+ " a = np.maximum(0,z)\n",
+ " return a"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Initialising parameters"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def initialize_params(layer_sizes):\n",
+ " params = {}\n",
+ " for i in range(1, len(layer_sizes)):\n",
+ " params['W' + str(i)] = np.random.randn(layer_sizes[i], layer_sizes[i-1])*0.01\n",
+ " params['B' + str(i)] = np.random.randn(layer_sizes[i],1)*0.01\n",
+ " return params"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Forward Propagation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def forward_propagation(X_train, params):\n",
+ " layers = len(params)//2\n",
+ " values = {}\n",
+ " for i in range(1, layers+1):\n",
+ " if i==1:\n",
+ " values['Z' + str(i)] = np.dot(params['W' + str(i)], X_train) + params['B' + str(i)]\n",
+ " values['A' + str(i)] = relu(values['Z' + str(i)])\n",
+ " else:\n",
+ " values['Z' + str(i)] = np.dot(params['W' + str(i)], values['A' + str(i-1)]) + params['B' + str(i)]\n",
+ " if i==layers:\n",
+ " values['A' + str(i)] = values['Z' + str(i)]\n",
+ " else:\n",
+ " values['A' + str(i)] = relu(values['Z' + str(i)])\n",
+ " return values"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Computing Cost"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def compute_cost(values, Y_train):\n",
+ " layers = len(values)//2\n",
+ " Y_pred = values['A' + str(layers)]\n",
+ " cost = 1/(2*len(Y_train)) * np.sum(np.square(Y_pred - Y_train))\n",
+ " return cost"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Backward propagation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def backward_propagation(params, values, X_train, Y_train):\n",
+ " layers = len(params)//2\n",
+ " m = len(Y_train)\n",
+ " grads = {}\n",
+ " for i in range(layers,0,-1):\n",
+ " if i==layers:\n",
+ " dA = 1/m * (values['A' + str(i)] - Y_train)\n",
+ " dZ = dA\n",
+ " else:\n",
+ " dA = np.dot(params['W' + str(i+1)].T, dZ)\n",
+ " dZ = np.multiply(dA, np.where(values['A' + str(i)]>=0, 1, 0))\n",
+ " if i==1:\n",
+ " grads['W' + str(i)] = 1/m * np.dot(dZ, X_train.T)\n",
+ " grads['B' + str(i)] = 1/m * np.sum(dZ, axis=1, keepdims=True)\n",
+ " else:\n",
+ " grads['W' + str(i)] = 1/m * np.dot(dZ,values['A' + str(i-1)].T)\n",
+ " grads['B' + str(i)] = 1/m * np.sum(dZ, axis=1, keepdims=True)\n",
+ " return grads"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Updating parameters"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def update_params(params, grads, learning_rate):\n",
+ " layers = len(params)//2\n",
+ " params_updated = {}\n",
+ " for i in range(1,layers+1):\n",
+ " params_updated['W' + str(i)] = params['W' + str(i)] - learning_rate * grads['W' + str(i)]\n",
+ " params_updated['B' + str(i)] = params['B' + str(i)] - learning_rate * grads['B' + str(i)]\n",
+ " return params_updated"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Training model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def model(X_train, Y_train, layer_sizes, num_iters, learning_rate):\n",
+ " params = initialize_params(layer_sizes)\n",
+ " for i in range(num_iters):\n",
+ " values = forward_propagation(X_train.T, params)\n",
+ " cost = compute_cost(values, Y_train.T)\n",
+ " grads = backward_propagation(params, values,X_train.T, Y_train.T)\n",
+ " params = update_params(params, grads, learning_rate)\n",
+ " print('Cost at iteration ' + str(i+1) + ' = ' + str(cost) + '\\n')\n",
+ " return params"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Computing accuracy"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def compute_accuracy(X_train, X_test, Y_train, Y_test, params):\n",
+ " values_train = forward_propagation(X_train.T, params)\n",
+ " values_test = forward_propagation(X_test.T, params)\n",
+ " train_acc = np.sqrt(mean_squared_error(Y_train, values_train['A' + str(len(layer_sizes)-1)].T))\n",
+ " test_acc = np.sqrt(mean_squared_error(Y_test, values_test['A' + str(len(layer_sizes)-1)].T))\n",
+ " return train_acc, test_acc"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Predict"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def predict(X, params):\n",
+ " values = forward_propagation(X.T, params)\n",
+ " predictions = values['A' + str(len(values)//2)].T\n",
+ " return predictions"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Implementation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Cost at iteration 1 = 103314.19373867307\n",
+ "\n",
+ "Cost at iteration 2 = 103185.63808277521\n",
+ "\n",
+ "Cost at iteration 3 = 102884.11672407956\n",
+ "\n",
+ "Cost at iteration 4 = 102117.04781966149\n",
+ "\n",
+ "Cost at iteration 5 = 100170.08921850033\n",
+ "\n",
+ "Cost at iteration 6 = 95326.56481725734\n",
+ "\n",
+ "Cost at iteration 7 = 83893.70851959265\n",
+ "\n",
+ "Cost at iteration 8 = 60286.12788081671\n",
+ "\n",
+ "Cost at iteration 9 = 25399.550698154675\n",
+ "\n",
+ "Cost at iteration 10 = 2376.384992313473\n",
+ "\n",
+ "Cost at iteration 11 = 139.22937635134272\n",
+ "\n",
+ "Cost at iteration 12 = 126.91174418612334\n",
+ "\n",
+ "Cost at iteration 13 = 126.29771390199156\n",
+ "\n",
+ "Cost at iteration 14 = 126.2433010240596\n",
+ "\n",
+ "Cost at iteration 15 = 126.212614355114\n",
+ "\n",
+ "Cost at iteration 16 = 126.18296861388148\n",
+ "\n",
+ "Cost at iteration 17 = 126.15337624201612\n",
+ "\n",
+ "Cost at iteration 18 = 126.12379448772876\n",
+ "\n",
+ "Cost at iteration 19 = 126.09422149106722\n",
+ "\n",
+ "Cost at iteration 20 = 126.06465716415906\n",
+ "\n",
+ "Cost at iteration 21 = 126.03510149591402\n",
+ "\n",
+ "Cost at iteration 22 = 126.00555447857731\n",
+ "\n",
+ "Cost at iteration 23 = 125.97601610454733\n",
+ "\n",
+ "Cost at iteration 24 = 125.94648636623756\n",
+ "\n",
+ "Cost at iteration 25 = 125.91696525607092\n",
+ "\n",
+ "Cost at iteration 26 = 125.88745276647927\n",
+ "\n",
+ "Cost at iteration 27 = 125.85794888990341\n",
+ "\n",
+ "Cost at iteration 28 = 125.8284536187932\n",
+ "\n",
+ "Cost at iteration 29 = 125.79896694560742\n",
+ "\n",
+ "Cost at iteration 30 = 125.76948886281373\n",
+ "\n",
+ "Cost at iteration 31 = 125.74001936288875\n",
+ "\n",
+ "Cost at iteration 32 = 125.71055843831806\n",
+ "\n",
+ "Cost at iteration 33 = 125.68110608159613\n",
+ "\n",
+ "Cost at iteration 34 = 125.65166228522631\n",
+ "\n",
+ "Cost at iteration 35 = 125.62222704172086\n",
+ "\n",
+ "Cost at iteration 36 = 125.59280034360089\n",
+ "\n",
+ "Cost at iteration 37 = 125.56338218339643\n",
+ "\n",
+ "Cost at iteration 38 = 125.53397255364625\n",
+ "\n",
+ "Cost at iteration 39 = 125.50457144689805\n",
+ "\n",
+ "Cost at iteration 40 = 125.47517885570838\n",
+ "\n",
+ "Cost at iteration 41 = 125.4457947726425\n",
+ "\n",
+ "Cost at iteration 42 = 125.41641919027458\n",
+ "\n",
+ "Cost at iteration 43 = 125.38705210118752\n",
+ "\n",
+ "Cost at iteration 44 = 125.35769349797305\n",
+ "\n",
+ "Cost at iteration 45 = 125.32834337323165\n",
+ "\n",
+ "Cost at iteration 46 = 125.29900171957253\n",
+ "\n",
+ "Cost at iteration 47 = 125.26966852961374\n",
+ "\n",
+ "Cost at iteration 48 = 125.24034379598197\n",
+ "\n",
+ "Cost at iteration 49 = 125.21102751131268\n",
+ "\n",
+ "Cost at iteration 50 = 125.18171966825004\n",
+ "\n",
+ "Cost at iteration 51 = 125.15242025944696\n",
+ "\n",
+ "Cost at iteration 52 = 125.12312927756498\n",
+ "\n",
+ "Cost at iteration 53 = 125.09384671527437\n",
+ "\n",
+ "Cost at iteration 54 = 125.06457256525407\n",
+ "\n",
+ "Cost at iteration 55 = 125.03530682019165\n",
+ "\n",
+ "Cost at iteration 56 = 125.00604947278337\n",
+ "\n",
+ "Cost at iteration 57 = 124.9768005157341\n",
+ "\n",
+ "Cost at iteration 58 = 124.94755994175735\n",
+ "\n",
+ "Cost at iteration 59 = 124.91832774357526\n",
+ "\n",
+ "Cost at iteration 60 = 124.88910391391853\n",
+ "\n",
+ "Cost at iteration 61 = 124.85988844552647\n",
+ "\n",
+ "Cost at iteration 62 = 124.83068133114705\n",
+ "\n",
+ "Cost at iteration 63 = 124.80148256353671\n",
+ "\n",
+ "Cost at iteration 64 = 124.7722921354605\n",
+ "\n",
+ "Cost at iteration 65 = 124.74311003969198\n",
+ "\n",
+ "Cost at iteration 66 = 124.71393626901337\n",
+ "\n",
+ "Cost at iteration 67 = 124.68477081621528\n",
+ "\n",
+ "Cost at iteration 68 = 124.65561367409687\n",
+ "\n",
+ "Cost at iteration 69 = 124.6264648354659\n",
+ "\n",
+ "Cost at iteration 70 = 124.59732429313853\n",
+ "\n",
+ "Cost at iteration 71 = 124.56819203993939\n",
+ "\n",
+ "Cost at iteration 72 = 124.53906806870171\n",
+ "\n",
+ "Cost at iteration 73 = 124.50995237226704\n",
+ "\n",
+ "Cost at iteration 74 = 124.48084494348547\n",
+ "\n",
+ "Cost at iteration 75 = 124.45174577521556\n",
+ "\n",
+ "Cost at iteration 76 = 124.42265486032423\n",
+ "\n",
+ "Cost at iteration 77 = 124.39357219168683\n",
+ "\n",
+ "Cost at iteration 78 = 124.36449776218714\n",
+ "\n",
+ "Cost at iteration 79 = 124.33543156471734\n",
+ "\n",
+ "Cost at iteration 80 = 124.30637359217806\n",
+ "\n",
+ "Cost at iteration 81 = 124.27732383747819\n",
+ "\n",
+ "Cost at iteration 82 = 124.24828229353508\n",
+ "\n",
+ "Cost at iteration 83 = 124.2192489532744\n",
+ "\n",
+ "Cost at iteration 84 = 124.19022380963018\n",
+ "\n",
+ "Cost at iteration 85 = 124.16120685554479\n",
+ "\n",
+ "Cost at iteration 86 = 124.13219808396897\n",
+ "\n",
+ "Cost at iteration 87 = 124.10319748786164\n",
+ "\n",
+ "Cost at iteration 88 = 124.07420506019018\n",
+ "\n",
+ "Cost at iteration 89 = 124.04522079393017\n",
+ "\n",
+ "Cost at iteration 90 = 124.01624468206553\n",
+ "\n",
+ "Cost at iteration 91 = 123.98727671758843\n",
+ "\n",
+ "Cost at iteration 92 = 123.95831689349926\n",
+ "\n",
+ "Cost at iteration 93 = 123.92936520280678\n",
+ "\n",
+ "Cost at iteration 94 = 123.90042163852793\n",
+ "\n",
+ "Cost at iteration 95 = 123.8714861936878\n",
+ "\n",
+ "Cost at iteration 96 = 123.84255886131986\n",
+ "\n",
+ "Cost at iteration 97 = 123.81363963446569\n",
+ "\n",
+ "Cost at iteration 98 = 123.78472850617504\n",
+ "\n",
+ "Cost at iteration 99 = 123.75582546950605\n",
+ "\n",
+ "Cost at iteration 100 = 123.72693051752472\n",
+ "\n",
+ "Cost at iteration 101 = 123.69804364330554\n",
+ "\n",
+ "Cost at iteration 102 = 123.66916483993097\n",
+ "\n",
+ "Cost at iteration 103 = 123.6402941004917\n",
+ "\n",
+ "Cost at iteration 104 = 123.61143141808653\n",
+ "\n",
+ "Cost at iteration 105 = 123.58257678582237\n",
+ "\n",
+ "Cost at iteration 106 = 123.55373019681436\n",
+ "\n",
+ "Cost at iteration 107 = 123.52489164418556\n",
+ "\n",
+ "Cost at iteration 108 = 123.49606112106731\n",
+ "\n",
+ "Cost at iteration 109 = 123.46723862059896\n",
+ "\n",
+ "Cost at iteration 110 = 123.43842413592795\n",
+ "\n",
+ "Cost at iteration 111 = 123.40961766020979\n",
+ "\n",
+ "Cost at iteration 112 = 123.3808191866081\n",
+ "\n",
+ "Cost at iteration 113 = 123.35202870829441\n",
+ "\n",
+ "Cost at iteration 114 = 123.32324621844843\n",
+ "\n",
+ "Cost at iteration 115 = 123.29447171025788\n",
+ "\n",
+ "Cost at iteration 116 = 123.26570517691846\n",
+ "\n",
+ "Cost at iteration 117 = 123.23694661163387\n",
+ "\n",
+ "Cost at iteration 118 = 123.20819600761585\n",
+ "\n",
+ "Cost at iteration 119 = 123.17945335808413\n",
+ "\n",
+ "Cost at iteration 120 = 123.15071865626642\n",
+ "\n",
+ "Cost at iteration 121 = 123.12199189539835\n",
+ "\n",
+ "Cost at iteration 122 = 123.09327306872353\n",
+ "\n",
+ "Cost at iteration 123 = 123.06456216949361\n",
+ "\n",
+ "Cost at iteration 124 = 123.03585919096807\n",
+ "\n",
+ "Cost at iteration 125 = 123.00716412641432\n",
+ "\n",
+ "Cost at iteration 126 = 122.97847696910779\n",
+ "\n",
+ "Cost at iteration 127 = 122.94979771233179\n",
+ "\n",
+ "Cost at iteration 128 = 122.92112634937742\n",
+ "\n",
+ "Cost at iteration 129 = 122.89246287354383\n",
+ "\n",
+ "Cost at iteration 130 = 122.86380727813794\n",
+ "\n",
+ "Cost at iteration 131 = 122.83515955647461\n",
+ "\n",
+ "Cost at iteration 132 = 122.80651970187654\n",
+ "\n",
+ "Cost at iteration 133 = 122.77788770767422\n",
+ "\n",
+ "Cost at iteration 134 = 122.74926356720616\n",
+ "\n",
+ "Cost at iteration 135 = 122.72064727381847\n",
+ "\n",
+ "Cost at iteration 136 = 122.69203882086526\n",
+ "\n",
+ "Cost at iteration 137 = 122.66343820170839\n",
+ "\n",
+ "Cost at iteration 138 = 122.63484540971753\n",
+ "\n",
+ "Cost at iteration 139 = 122.60626043827014\n",
+ "\n",
+ "Cost at iteration 140 = 122.57768328075149\n",
+ "\n",
+ "Cost at iteration 141 = 122.54911393055455\n",
+ "\n",
+ "Cost at iteration 142 = 122.52055238108022\n",
+ "\n",
+ "Cost at iteration 143 = 122.49199862573695\n",
+ "\n",
+ "Cost at iteration 144 = 122.46345265794109\n",
+ "\n",
+ "Cost at iteration 145 = 122.4349144711167\n",
+ "\n",
+ "Cost at iteration 146 = 122.4063840586955\n",
+ "\n",
+ "Cost at iteration 147 = 122.377861414117\n",
+ "\n",
+ "Cost at iteration 148 = 122.34934653082838\n",
+ "\n",
+ "Cost at iteration 149 = 122.32083940228456\n",
+ "\n",
+ "Cost at iteration 150 = 122.29234002194809\n",
+ "\n",
+ "Cost at iteration 151 = 122.26384838328931\n",
+ "\n",
+ "Cost at iteration 152 = 122.23536447978609\n",
+ "\n",
+ "Cost at iteration 153 = 122.20688830492405\n",
+ "\n",
+ "Cost at iteration 154 = 122.17841985219647\n",
+ "\n",
+ "Cost at iteration 155 = 122.14995911510422\n",
+ "\n",
+ "Cost at iteration 156 = 122.12150608715585\n",
+ "\n",
+ "Cost at iteration 157 = 122.0930607618675\n",
+ "\n",
+ "Cost at iteration 158 = 122.06462313276299\n",
+ "\n",
+ "Cost at iteration 159 = 122.03619319337366\n",
+ "\n",
+ "Cost at iteration 160 = 122.00777093723849\n",
+ "\n",
+ "Cost at iteration 161 = 121.9793563579041\n",
+ "\n",
+ "Cost at iteration 162 = 121.95094944892458\n",
+ "\n",
+ "Cost at iteration 163 = 121.9225502038617\n",
+ "\n",
+ "Cost at iteration 164 = 121.89415861628464\n",
+ "\n",
+ "Cost at iteration 165 = 121.86577467977038\n",
+ "\n",
+ "Cost at iteration 166 = 121.83739838790312\n",
+ "\n",
+ "Cost at iteration 167 = 121.80902973427492\n",
+ "\n",
+ "Cost at iteration 168 = 121.78066871248507\n",
+ "\n",
+ "Cost at iteration 169 = 121.7523153161406\n",
+ "\n",
+ "Cost at iteration 170 = 121.72396953885598\n",
+ "\n",
+ "Cost at iteration 171 = 121.69563137425305\n",
+ "\n",
+ "Cost at iteration 172 = 121.66730081596133\n",
+ "\n",
+ "Cost at iteration 173 = 121.63897785761769\n",
+ "\n",
+ "Cost at iteration 174 = 121.61066249286654\n",
+ "\n",
+ "Cost at iteration 175 = 121.58235471535966\n",
+ "\n",
+ "Cost at iteration 176 = 121.55405451875639\n",
+ "\n",
+ "Cost at iteration 177 = 121.5257618967235\n",
+ "\n",
+ "Cost at iteration 178 = 121.49747684293506\n",
+ "\n",
+ "Cost at iteration 179 = 121.46919935107267\n",
+ "\n",
+ "Cost at iteration 180 = 121.44092941482543\n",
+ "\n",
+ "Cost at iteration 181 = 121.41266702788965\n",
+ "\n",
+ "Cost at iteration 182 = 121.38441218396922\n",
+ "\n",
+ "Cost at iteration 183 = 121.35616487677528\n",
+ "\n",
+ "Cost at iteration 184 = 121.3279251000264\n",
+ "\n",
+ "Cost at iteration 185 = 121.29969284744851\n",
+ "\n",
+ "Cost at iteration 186 = 121.27146811277503\n",
+ "\n",
+ "Cost at iteration 187 = 121.2432508897465\n",
+ "\n",
+ "Cost at iteration 188 = 121.215041172111\n",
+ "\n",
+ "Cost at iteration 189 = 121.18683895362383\n",
+ "\n",
+ "Cost at iteration 190 = 121.15864422804763\n",
+ "\n",
+ "Cost at iteration 191 = 121.13045698915249\n",
+ "\n",
+ "Cost at iteration 192 = 121.10227723071559\n",
+ "\n",
+ "Cost at iteration 193 = 121.07410494652154\n",
+ "\n",
+ "Cost at iteration 194 = 121.0459401303623\n",
+ "\n",
+ "Cost at iteration 195 = 121.01778277603694\n",
+ "\n",
+ "Cost at iteration 196 = 120.98963287735195\n",
+ "\n",
+ "Cost at iteration 197 = 120.96149042812107\n",
+ "\n",
+ "Cost at iteration 198 = 120.93335542216518\n",
+ "\n",
+ "Cost at iteration 199 = 120.90522785331251\n",
+ "\n",
+ "Cost at iteration 200 = 120.87710771539857\n",
+ "\n",
+ "Cost at iteration 201 = 120.84899500226595\n",
+ "\n",
+ "Cost at iteration 202 = 120.82088970776461\n",
+ "\n",
+ "Cost at iteration 203 = 120.7927918257516\n",
+ "\n",
+ "Cost at iteration 204 = 120.76470135009133\n",
+ "\n",
+ "Cost at iteration 205 = 120.73661827465521\n",
+ "\n",
+ "Cost at iteration 206 = 120.70854259332204\n",
+ "\n",
+ "Cost at iteration 207 = 120.68047429997762\n",
+ "\n",
+ "Cost at iteration 208 = 120.65241338851499\n",
+ "\n",
+ "Cost at iteration 209 = 120.62435985283444\n",
+ "\n",
+ "Cost at iteration 210 = 120.59631368684325\n",
+ "\n",
+ "Cost at iteration 211 = 120.56827488445597\n",
+ "\n",
+ "Cost at iteration 212 = 120.54024343959422\n",
+ "\n",
+ "Cost at iteration 213 = 120.51221934618678\n",
+ "\n",
+ "Cost at iteration 214 = 120.48420259816952\n",
+ "\n",
+ "Cost at iteration 215 = 120.45619318948546\n",
+ "\n",
+ "Cost at iteration 216 = 120.42819111408471\n",
+ "\n",
+ "Cost at iteration 217 = 120.40019636592444\n",
+ "\n",
+ "Cost at iteration 218 = 120.37220893896895\n",
+ "\n",
+ "Cost at iteration 219 = 120.34422882718955\n",
+ "\n",
+ "Cost at iteration 220 = 120.31625602456472\n",
+ "\n",
+ "Cost at iteration 221 = 120.2882905250799\n",
+ "\n",
+ "Cost at iteration 222 = 120.26033232272763\n",
+ "\n",
+ "Cost at iteration 223 = 120.23238141150755\n",
+ "\n",
+ "Cost at iteration 224 = 120.2044377854262\n",
+ "\n",
+ "Cost at iteration 225 = 120.17650143849724\n",
+ "\n",
+ "Cost at iteration 226 = 120.14857236474136\n",
+ "\n",
+ "Cost at iteration 227 = 120.12065055818618\n",
+ "\n",
+ "Cost at iteration 228 = 120.09273601286641\n",
+ "\n",
+ "Cost at iteration 229 = 120.06482872282368\n",
+ "\n",
+ "Cost at iteration 230 = 120.03692868210666\n",
+ "\n",
+ "Cost at iteration 231 = 120.00903588477097\n",
+ "\n",
+ "Cost at iteration 232 = 119.98115032487918\n",
+ "\n",
+ "Cost at iteration 233 = 119.95327199650087\n",
+ "\n",
+ "Cost at iteration 234 = 119.92540089371255\n",
+ "\n",
+ "Cost at iteration 235 = 119.89753701059766\n",
+ "\n",
+ "Cost at iteration 236 = 119.86968034124656\n",
+ "\n",
+ "Cost at iteration 237 = 119.84183087975663\n",
+ "\n",
+ "Cost at iteration 238 = 119.81398862023202\n",
+ "\n",
+ "Cost at iteration 239 = 119.78615355678392\n",
+ "\n",
+ "Cost at iteration 240 = 119.7583256835304\n",
+ "\n",
+ "Cost at iteration 241 = 119.73050499459634\n",
+ "\n",
+ "Cost at iteration 242 = 119.70269148411363\n",
+ "\n",
+ "Cost at iteration 243 = 119.67488514622094\n",
+ "\n",
+ "Cost at iteration 244 = 119.64708597506387\n",
+ "\n",
+ "Cost at iteration 245 = 119.61929396479485\n",
+ "\n",
+ "Cost at iteration 246 = 119.59150910957321\n",
+ "\n",
+ "Cost at iteration 247 = 119.56373140356501\n",
+ "\n",
+ "Cost at iteration 248 = 119.53596084094333\n",
+ "\n",
+ "Cost at iteration 249 = 119.5081974158879\n",
+ "\n",
+ "Cost at iteration 250 = 119.48044112258542\n",
+ "\n",
+ "Cost at iteration 251 = 119.45269195522931\n",
+ "\n",
+ "Cost at iteration 252 = 119.42494990801983\n",
+ "\n",
+ "Cost at iteration 253 = 119.39721497516405\n",
+ "\n",
+ "Cost at iteration 254 = 119.36948715087581\n",
+ "\n",
+ "Cost at iteration 255 = 119.34176642937571\n",
+ "\n",
+ "Cost at iteration 256 = 119.3140528048912\n",
+ "\n",
+ "Cost at iteration 257 = 119.28634627165641\n",
+ "\n",
+ "Cost at iteration 258 = 119.2586468239123\n",
+ "\n",
+ "Cost at iteration 259 = 119.23095445590657\n",
+ "\n",
+ "Cost at iteration 260 = 119.20326916189359\n",
+ "\n",
+ "Cost at iteration 261 = 119.17559093613457\n",
+ "\n",
+ "Cost at iteration 262 = 119.14791977289737\n",
+ "\n",
+ "Cost at iteration 263 = 119.12025566645661\n",
+ "\n",
+ "Cost at iteration 264 = 119.09259861109362\n",
+ "\n",
+ "Cost at iteration 265 = 119.06494860109643\n",
+ "\n",
+ "Cost at iteration 266 = 119.03730563075973\n",
+ "\n",
+ "Cost at iteration 267 = 119.00966969438495\n",
+ "\n",
+ "Cost at iteration 268 = 118.9820407862802\n",
+ "\n",
+ "Cost at iteration 269 = 118.95441890076022\n",
+ "\n",
+ "Cost at iteration 270 = 118.92680403214646\n",
+ "\n",
+ "Cost at iteration 271 = 118.89919617476698\n",
+ "\n",
+ "Cost at iteration 272 = 118.87159532295657\n",
+ "\n",
+ "Cost at iteration 273 = 118.84400147105652\n",
+ "\n",
+ "Cost at iteration 274 = 118.81641461341496\n",
+ "\n",
+ "Cost at iteration 275 = 118.78883474438645\n",
+ "\n",
+ "Cost at iteration 276 = 118.7612618583323\n",
+ "\n",
+ "Cost at iteration 277 = 118.73369594962034\n",
+ "\n",
+ "Cost at iteration 278 = 118.7061370126251\n",
+ "\n",
+ "Cost at iteration 279 = 118.6785850417276\n",
+ "\n",
+ "Cost at iteration 280 = 118.65104003131555\n",
+ "\n",
+ "Cost at iteration 281 = 118.62350197578319\n",
+ "\n",
+ "Cost at iteration 282 = 118.59597086953129\n",
+ "\n",
+ "Cost at iteration 283 = 118.56844670696728\n",
+ "\n",
+ "Cost at iteration 284 = 118.5409294825051\n",
+ "\n",
+ "Cost at iteration 285 = 118.51341919056522\n",
+ "\n",
+ "Cost at iteration 286 = 118.48591582557471\n",
+ "\n",
+ "Cost at iteration 287 = 118.45841938196715\n",
+ "\n",
+ "Cost at iteration 288 = 118.43092985418258\n",
+ "\n",
+ "Cost at iteration 289 = 118.40344723666767\n",
+ "\n",
+ "Cost at iteration 290 = 118.37597152387558\n",
+ "\n",
+ "Cost at iteration 291 = 118.34850271026592\n",
+ "\n",
+ "Cost at iteration 292 = 118.32104079030482\n",
+ "\n",
+ "Cost at iteration 293 = 118.2935857584649\n",
+ "\n",
+ "Cost at iteration 294 = 118.26613760922532\n",
+ "\n",
+ "Cost at iteration 295 = 118.23869633707166\n",
+ "\n",
+ "Cost at iteration 296 = 118.21126193649597\n",
+ "\n",
+ "Cost at iteration 297 = 118.18383440199678\n",
+ "\n",
+ "Cost at iteration 298 = 118.15641372807906\n",
+ "\n",
+ "Cost at iteration 299 = 118.12899990925425\n",
+ "\n",
+ "Cost at iteration 300 = 118.10159294004013\n",
+ "\n",
+ "Cost at iteration 301 = 118.07419281496112\n",
+ "\n",
+ "Cost at iteration 302 = 118.04679952854782\n",
+ "\n",
+ "Cost at iteration 303 = 118.01941307533745\n",
+ "\n",
+ "Cost at iteration 304 = 117.99203344987353\n",
+ "\n",
+ "Cost at iteration 305 = 117.96466064670601\n",
+ "\n",
+ "Cost at iteration 306 = 117.9372946603912\n",
+ "\n",
+ "Cost at iteration 307 = 117.90993548549187\n",
+ "\n",
+ "Cost at iteration 308 = 117.88258311657708\n",
+ "\n",
+ "Cost at iteration 309 = 117.85523754822242\n",
+ "\n",
+ "Cost at iteration 310 = 117.82789877500963\n",
+ "\n",
+ "Cost at iteration 311 = 117.80056679152696\n",
+ "\n",
+ "Cost at iteration 312 = 117.77324159236896\n",
+ "\n",
+ "Cost at iteration 313 = 117.74592317213656\n",
+ "\n",
+ "Cost at iteration 314 = 117.71861152543698\n",
+ "\n",
+ "Cost at iteration 315 = 117.69130664688379\n",
+ "\n",
+ "Cost at iteration 316 = 117.66400853109693\n",
+ "\n",
+ "Cost at iteration 317 = 117.63671717270257\n",
+ "\n",
+ "Cost at iteration 318 = 117.60943256633325\n",
+ "\n",
+ "Cost at iteration 319 = 117.58215470662779\n",
+ "\n",
+ "Cost at iteration 320 = 117.55488358823125\n",
+ "\n",
+ "Cost at iteration 321 = 117.5276192057951\n",
+ "\n",
+ "Cost at iteration 322 = 117.50036155397706\n",
+ "\n",
+ "Cost at iteration 323 = 117.473110627441\n",
+ "\n",
+ "Cost at iteration 324 = 117.44586642085717\n",
+ "\n",
+ "Cost at iteration 325 = 117.41862892890204\n",
+ "\n",
+ "Cost at iteration 326 = 117.3913981462584\n",
+ "\n",
+ "Cost at iteration 327 = 117.36417406761514\n",
+ "\n",
+ "Cost at iteration 328 = 117.33695668766757\n",
+ "\n",
+ "Cost at iteration 329 = 117.30974600111703\n",
+ "\n",
+ "Cost at iteration 330 = 117.28254200267125\n",
+ "\n",
+ "Cost at iteration 331 = 117.25534468704414\n",
+ "\n",
+ "Cost at iteration 332 = 117.22815404895573\n",
+ "\n",
+ "Cost at iteration 333 = 117.2009700831324\n",
+ "\n",
+ "Cost at iteration 334 = 117.17379278430657\n",
+ "\n",
+ "Cost at iteration 335 = 117.14662214721695\n",
+ "\n",
+ "Cost at iteration 336 = 117.1194581666084\n",
+ "\n",
+ "Cost at iteration 337 = 117.09230083723195\n",
+ "\n",
+ "Cost at iteration 338 = 117.06515015384485\n",
+ "\n",
+ "Cost at iteration 339 = 117.0380061112104\n",
+ "\n",
+ "Cost at iteration 340 = 117.01086870409817\n",
+ "\n",
+ "Cost at iteration 341 = 116.98373792728381\n",
+ "\n",
+ "Cost at iteration 342 = 116.95661377554913\n",
+ "\n",
+ "Cost at iteration 343 = 116.92949624368207\n",
+ "\n",
+ "Cost at iteration 344 = 116.9023853264767\n",
+ "\n",
+ "Cost at iteration 345 = 116.87528101873323\n",
+ "\n",
+ "Cost at iteration 346 = 116.8481833152579\n",
+ "\n",
+ "Cost at iteration 347 = 116.82109221086318\n",
+ "\n",
+ "Cost at iteration 348 = 116.79400770036756\n",
+ "\n",
+ "Cost at iteration 349 = 116.76692977859562\n",
+ "\n",
+ "Cost at iteration 350 = 116.73985844037806\n",
+ "\n",
+ "Cost at iteration 351 = 116.71279368055166\n",
+ "\n",
+ "Cost at iteration 352 = 116.6857354939592\n",
+ "\n",
+ "Cost at iteration 353 = 116.65868387544961\n",
+ "\n",
+ "Cost at iteration 354 = 116.63163881987782\n",
+ "\n",
+ "Cost at iteration 355 = 116.60460032210491\n",
+ "\n",
+ "Cost at iteration 356 = 116.57756837699787\n",
+ "\n",
+ "Cost at iteration 357 = 116.55054297942984\n",
+ "\n",
+ "Cost at iteration 358 = 116.52352412427987\n",
+ "\n",
+ "Cost at iteration 359 = 116.4965118064332\n",
+ "\n",
+ "Cost at iteration 360 = 116.46950602078094\n",
+ "\n",
+ "Cost at iteration 361 = 116.44250676222029\n",
+ "\n",
+ "Cost at iteration 362 = 116.41551402565437\n",
+ "\n",
+ "Cost at iteration 363 = 116.38852780599245\n",
+ "\n",
+ "Cost at iteration 364 = 116.36154809814971\n",
+ "\n",
+ "Cost at iteration 365 = 116.3345748970472\n",
+ "\n",
+ "Cost at iteration 366 = 116.30760819761217\n",
+ "\n",
+ "Cost at iteration 367 = 116.28064799477764\n",
+ "\n",
+ "Cost at iteration 368 = 116.25369428348273\n",
+ "\n",
+ "Cost at iteration 369 = 116.22674705867247\n",
+ "\n",
+ "Cost at iteration 370 = 116.19980631529782\n",
+ "\n",
+ "Cost at iteration 371 = 116.17287204831574\n",
+ "\n",
+ "Cost at iteration 372 = 116.14594425268908\n",
+ "\n",
+ "Cost at iteration 373 = 116.1190229233866\n",
+ "\n",
+ "Cost at iteration 374 = 116.09210805538312\n",
+ "\n",
+ "Cost at iteration 375 = 116.06519964365917\n",
+ "\n",
+ "Cost at iteration 376 = 116.03829768320136\n",
+ "\n",
+ "Cost at iteration 377 = 116.0114021690022\n",
+ "\n",
+ "Cost at iteration 378 = 115.98451309605996\n",
+ "\n",
+ "Cost at iteration 379 = 115.95763045937892\n",
+ "\n",
+ "Cost at iteration 380 = 115.93075425396928\n",
+ "\n",
+ "Cost at iteration 381 = 115.90388447484696\n",
+ "\n",
+ "Cost at iteration 382 = 115.87702111703395\n",
+ "\n",
+ "Cost at iteration 383 = 115.85016417555795\n",
+ "\n",
+ "Cost at iteration 384 = 115.82331364545263\n",
+ "\n",
+ "Cost at iteration 385 = 115.7964695217574\n",
+ "\n",
+ "Cost at iteration 386 = 115.76963179951763\n",
+ "\n",
+ "Cost at iteration 387 = 115.7428004737845\n",
+ "\n",
+ "Cost at iteration 388 = 115.71597553961499\n",
+ "\n",
+ "Cost at iteration 389 = 115.6891569920719\n",
+ "\n",
+ "Cost at iteration 390 = 115.66234482622392\n",
+ "\n",
+ "Cost at iteration 391 = 115.63553903714552\n",
+ "\n",
+ "Cost at iteration 392 = 115.60873961991695\n",
+ "\n",
+ "Cost at iteration 393 = 115.5819465696243\n",
+ "\n",
+ "Cost at iteration 394 = 115.55515988135944\n",
+ "\n",
+ "Cost at iteration 395 = 115.52837955022008\n",
+ "\n",
+ "Cost at iteration 396 = 115.5016055713096\n",
+ "\n",
+ "Cost at iteration 397 = 115.47483793973727\n",
+ "\n",
+ "Cost at iteration 398 = 115.44807665061809\n",
+ "\n",
+ "Cost at iteration 399 = 115.42132169907286\n",
+ "\n",
+ "Cost at iteration 400 = 115.39457308022801\n",
+ "\n",
+ "Cost at iteration 401 = 115.36783078921594\n",
+ "\n",
+ "Cost at iteration 402 = 115.34109482117462\n",
+ "\n",
+ "Cost at iteration 403 = 115.31436517124776\n",
+ "\n",
+ "Cost at iteration 404 = 115.28764183458495\n",
+ "\n",
+ "Cost at iteration 405 = 115.26092480634134\n",
+ "\n",
+ "Cost at iteration 406 = 115.23421408167793\n",
+ "\n",
+ "Cost at iteration 407 = 115.20750965576137\n",
+ "\n",
+ "Cost at iteration 408 = 115.18081152376404\n",
+ "\n",
+ "Cost at iteration 409 = 115.15411968086399\n",
+ "\n",
+ "Cost at iteration 410 = 115.127434122245\n",
+ "\n",
+ "Cost at iteration 411 = 115.10075484309657\n",
+ "\n",
+ "Cost at iteration 412 = 115.0740818386138\n",
+ "\n",
+ "Cost at iteration 413 = 115.04741510399755\n",
+ "\n",
+ "Cost at iteration 414 = 115.02075463445433\n",
+ "\n",
+ "Cost at iteration 415 = 114.99410042519622\n",
+ "\n",
+ "Cost at iteration 416 = 114.96745247144115\n",
+ "\n",
+ "Cost at iteration 417 = 114.94081076841255\n",
+ "\n",
+ "Cost at iteration 418 = 114.91417531133953\n",
+ "\n",
+ "Cost at iteration 419 = 114.8875460954569\n",
+ "\n",
+ "Cost at iteration 420 = 114.86092311600504\n",
+ "\n",
+ "Cost at iteration 421 = 114.83430636822995\n",
+ "\n",
+ "Cost at iteration 422 = 114.80769584738337\n",
+ "\n",
+ "Cost at iteration 423 = 114.78109154872247\n",
+ "\n",
+ "Cost at iteration 424 = 114.75449346751023\n",
+ "\n",
+ "Cost at iteration 425 = 114.72790159901506\n",
+ "\n",
+ "Cost at iteration 426 = 114.70131593851112\n",
+ "\n",
+ "Cost at iteration 427 = 114.67473648127805\n",
+ "\n",
+ "Cost at iteration 428 = 114.64816322260113\n",
+ "\n",
+ "Cost at iteration 429 = 114.62159615777118\n",
+ "\n",
+ "Cost at iteration 430 = 114.59503528208471\n",
+ "\n",
+ "Cost at iteration 431 = 114.56848059084362\n",
+ "\n",
+ "Cost at iteration 432 = 114.54193207935555\n",
+ "\n",
+ "Cost at iteration 433 = 114.51538974293356\n",
+ "\n",
+ "Cost at iteration 434 = 114.48885357689633\n",
+ "\n",
+ "Cost at iteration 435 = 114.46232357656808\n",
+ "\n",
+ "Cost at iteration 436 = 114.4357997372786\n",
+ "\n",
+ "Cost at iteration 437 = 114.40928205436308\n",
+ "\n",
+ "Cost at iteration 438 = 114.38277052316243\n",
+ "\n",
+ "Cost at iteration 439 = 114.35626513902294\n",
+ "\n",
+ "Cost at iteration 440 = 114.32976589729645\n",
+ "\n",
+ "Cost at iteration 441 = 114.30327279334034\n",
+ "\n",
+ "Cost at iteration 442 = 114.27678582251752\n",
+ "\n",
+ "Cost at iteration 443 = 114.25030498019628\n",
+ "\n",
+ "Cost at iteration 444 = 114.22383026175054\n",
+ "\n",
+ "Cost at iteration 445 = 114.19736166255954\n",
+ "\n",
+ "Cost at iteration 446 = 114.17089917800824\n",
+ "\n",
+ "Cost at iteration 447 = 114.14444280348685\n",
+ "\n",
+ "Cost at iteration 448 = 114.11799253439116\n",
+ "\n",
+ "Cost at iteration 449 = 114.09154836612244\n",
+ "\n",
+ "Cost at iteration 450 = 114.06511029408732\n",
+ "\n",
+ "Cost at iteration 451 = 114.03867831369793\n",
+ "\n",
+ "Cost at iteration 452 = 114.01225242037194\n",
+ "\n",
+ "Cost at iteration 453 = 113.98583260953231\n",
+ "\n",
+ "Cost at iteration 454 = 113.9594188766075\n",
+ "\n",
+ "Cost at iteration 455 = 113.9330112170314\n",
+ "\n",
+ "Cost at iteration 456 = 113.90660962624335\n",
+ "\n",
+ "Cost at iteration 457 = 113.8802140996881\n",
+ "\n",
+ "Cost at iteration 458 = 113.85382463281573\n",
+ "\n",
+ "Cost at iteration 459 = 113.82744122108186\n",
+ "\n",
+ "Cost at iteration 460 = 113.80106385994732\n",
+ "\n",
+ "Cost at iteration 461 = 113.77469254487855\n",
+ "\n",
+ "Cost at iteration 462 = 113.74832727134726\n",
+ "\n",
+ "Cost at iteration 463 = 113.72196803483052\n",
+ "\n",
+ "Cost at iteration 464 = 113.69561483081088\n",
+ "\n",
+ "Cost at iteration 465 = 113.66926765477619\n",
+ "\n",
+ "Cost at iteration 466 = 113.64292650221962\n",
+ "\n",
+ "Cost at iteration 467 = 113.61659136863982\n",
+ "\n",
+ "Cost at iteration 468 = 113.5902622495407\n",
+ "\n",
+ "Cost at iteration 469 = 113.56393914043156\n",
+ "\n",
+ "Cost at iteration 470 = 113.53762203682702\n",
+ "\n",
+ "Cost at iteration 471 = 113.51131093424708\n",
+ "\n",
+ "Cost at iteration 472 = 113.48500582821701\n",
+ "\n",
+ "Cost at iteration 473 = 113.45870671426748\n",
+ "\n",
+ "Cost at iteration 474 = 113.43241358793439\n",
+ "\n",
+ "Cost at iteration 475 = 113.40612644475904\n",
+ "\n",
+ "Cost at iteration 476 = 113.37984528028801\n",
+ "\n",
+ "Cost at iteration 477 = 113.35357009007318\n",
+ "\n",
+ "Cost at iteration 478 = 113.3273008696717\n",
+ "\n",
+ "Cost at iteration 479 = 113.30103761464609\n",
+ "\n",
+ "Cost at iteration 480 = 113.27478032056408\n",
+ "\n",
+ "Cost at iteration 481 = 113.24852898299868\n",
+ "\n",
+ "Cost at iteration 482 = 113.22228359752827\n",
+ "\n",
+ "Cost at iteration 483 = 113.1960441597364\n",
+ "\n",
+ "Cost at iteration 484 = 113.16981066521194\n",
+ "\n",
+ "Cost at iteration 485 = 113.14358310954901\n",
+ "\n",
+ "Cost at iteration 486 = 113.117361488347\n",
+ "\n",
+ "Cost at iteration 487 = 113.09114579721046\n",
+ "\n",
+ "Cost at iteration 488 = 113.0649360317493\n",
+ "\n",
+ "Cost at iteration 489 = 113.03873218757857\n",
+ "\n",
+ "Cost at iteration 490 = 113.01253426031873\n",
+ "\n",
+ "Cost at iteration 491 = 112.98634224559524\n",
+ "\n",
+ "Cost at iteration 492 = 112.96015613903886\n",
+ "\n",
+ "Cost at iteration 493 = 112.93397593628565\n",
+ "\n",
+ "Cost at iteration 494 = 112.9078016329768\n",
+ "\n",
+ "Cost at iteration 495 = 112.88163322475872\n",
+ "\n",
+ "Cost at iteration 496 = 112.85547070728302\n",
+ "\n",
+ "Cost at iteration 497 = 112.82931407620653\n",
+ "\n",
+ "Cost at iteration 498 = 112.80316332719124\n",
+ "\n",
+ "Cost at iteration 499 = 112.77701845590433\n",
+ "\n",
+ "Cost at iteration 500 = 112.75087945801813\n",
+ "\n",
+ "Cost at iteration 501 = 112.72474632921025\n",
+ "\n",
+ "Cost at iteration 502 = 112.69861906516336\n",
+ "\n",
+ "Cost at iteration 503 = 112.6724976615653\n",
+ "\n",
+ "Cost at iteration 504 = 112.64638211410913\n",
+ "\n",
+ "Cost at iteration 505 = 112.620272418493\n",
+ "\n",
+ "Cost at iteration 506 = 112.59416857042024\n",
+ "\n",
+ "Cost at iteration 507 = 112.56807056559931\n",
+ "\n",
+ "Cost at iteration 508 = 112.54197839974385\n",
+ "\n",
+ "Cost at iteration 509 = 112.51589206857248\n",
+ "\n",
+ "Cost at iteration 510 = 112.48981156780921\n",
+ "\n",
+ "Cost at iteration 511 = 112.4637368931829\n",
+ "\n",
+ "Cost at iteration 512 = 112.43766804042765\n",
+ "\n",
+ "Cost at iteration 513 = 112.41160500528274\n",
+ "\n",
+ "Cost at iteration 514 = 112.3855477834924\n",
+ "\n",
+ "Cost at iteration 515 = 112.35949637080607\n",
+ "\n",
+ "Cost at iteration 516 = 112.33345076297822\n",
+ "\n",
+ "Cost at iteration 517 = 112.30741095576846\n",
+ "\n",
+ "Cost at iteration 518 = 112.28137694494143\n",
+ "\n",
+ "Cost at iteration 519 = 112.25534872626693\n",
+ "\n",
+ "Cost at iteration 520 = 112.22932629551973\n",
+ "\n",
+ "Cost at iteration 521 = 112.20330964847979\n",
+ "\n",
+ "Cost at iteration 522 = 112.17729878093196\n",
+ "\n",
+ "Cost at iteration 523 = 112.15129368866634\n",
+ "\n",
+ "Cost at iteration 524 = 112.12529436747793\n",
+ "\n",
+ "Cost at iteration 525 = 112.09930081316688\n",
+ "\n",
+ "Cost at iteration 526 = 112.07331302153833\n",
+ "\n",
+ "Cost at iteration 527 = 112.04733098840246\n",
+ "\n",
+ "Cost at iteration 528 = 112.02135470957451\n",
+ "\n",
+ "Cost at iteration 529 = 111.99538418087468\n",
+ "\n",
+ "Cost at iteration 530 = 111.96941939812831\n",
+ "\n",
+ "Cost at iteration 531 = 111.94346035716563\n",
+ "\n",
+ "Cost at iteration 532 = 111.91750705382194\n",
+ "\n",
+ "Cost at iteration 533 = 111.89155948393756\n",
+ "\n",
+ "Cost at iteration 534 = 111.86561764335778\n",
+ "\n",
+ "Cost at iteration 535 = 111.83968152793291\n",
+ "\n",
+ "Cost at iteration 536 = 111.81375113351822\n",
+ "\n",
+ "Cost at iteration 537 = 111.78782645597403\n",
+ "\n",
+ "Cost at iteration 538 = 111.76190749116553\n",
+ "\n",
+ "Cost at iteration 539 = 111.73599423496302\n",
+ "\n",
+ "Cost at iteration 540 = 111.71008668324168\n",
+ "\n",
+ "Cost at iteration 541 = 111.68418483188165\n",
+ "\n",
+ "Cost at iteration 542 = 111.65828867676807\n",
+ "\n",
+ "Cost at iteration 543 = 111.63239821379106\n",
+ "\n",
+ "Cost at iteration 544 = 111.60651343884564\n",
+ "\n",
+ "Cost at iteration 545 = 111.58063434783175\n",
+ "\n",
+ "Cost at iteration 546 = 111.55476093665436\n",
+ "\n",
+ "Cost at iteration 547 = 111.52889320122334\n",
+ "\n",
+ "Cost at iteration 548 = 111.50303113745342\n",
+ "\n",
+ "Cost at iteration 549 = 111.47717474126435\n",
+ "\n",
+ "Cost at iteration 550 = 111.45132400858078\n",
+ "\n",
+ "Cost at iteration 551 = 111.4254789353322\n",
+ "\n",
+ "Cost at iteration 552 = 111.39963951745312\n",
+ "\n",
+ "Cost at iteration 553 = 111.37380575088292\n",
+ "\n",
+ "Cost at iteration 554 = 111.34797763156584\n",
+ "\n",
+ "Cost at iteration 555 = 111.32215515545103\n",
+ "\n",
+ "Cost at iteration 556 = 111.29633831849259\n",
+ "\n",
+ "Cost at iteration 557 = 111.27052711664942\n",
+ "\n",
+ "Cost at iteration 558 = 111.24472154588534\n",
+ "\n",
+ "Cost at iteration 559 = 111.21892160216908\n",
+ "\n",
+ "Cost at iteration 560 = 111.19312728147419\n",
+ "\n",
+ "Cost at iteration 561 = 111.1673385797791\n",
+ "\n",
+ "Cost at iteration 562 = 111.14155549306714\n",
+ "\n",
+ "Cost at iteration 563 = 111.11577801732643\n",
+ "\n",
+ "Cost at iteration 564 = 111.09000614854999\n",
+ "\n",
+ "Cost at iteration 565 = 111.06423988273566\n",
+ "\n",
+ "Cost at iteration 566 = 111.03847921588617\n",
+ "\n",
+ "Cost at iteration 567 = 111.01272414400903\n",
+ "\n",
+ "Cost at iteration 568 = 110.98697466311658\n",
+ "\n",
+ "Cost at iteration 569 = 110.96123076922608\n",
+ "\n",
+ "Cost at iteration 570 = 110.9354924583595\n",
+ "\n",
+ "Cost at iteration 571 = 110.90975972654368\n",
+ "\n",
+ "Cost at iteration 572 = 110.88403256981029\n",
+ "\n",
+ "Cost at iteration 573 = 110.85831098419575\n",
+ "\n",
+ "Cost at iteration 574 = 110.83259496574134\n",
+ "\n",
+ "Cost at iteration 575 = 110.80688451049313\n",
+ "\n",
+ "Cost at iteration 576 = 110.78117961450195\n",
+ "\n",
+ "Cost at iteration 577 = 110.75548027382347\n",
+ "\n",
+ "Cost at iteration 578 = 110.72978648451812\n",
+ "\n",
+ "Cost at iteration 579 = 110.70409824265104\n",
+ "\n",
+ "Cost at iteration 580 = 110.6784155442923\n",
+ "\n",
+ "Cost at iteration 581 = 110.6527383855166\n",
+ "\n",
+ "Cost at iteration 582 = 110.62706676240347\n",
+ "\n",
+ "Cost at iteration 583 = 110.60140067103718\n",
+ "\n",
+ "Cost at iteration 584 = 110.57574010750683\n",
+ "\n",
+ "Cost at iteration 585 = 110.55008506790612\n",
+ "\n",
+ "Cost at iteration 586 = 110.52443554833363\n",
+ "\n",
+ "Cost at iteration 587 = 110.49879154489263\n",
+ "\n",
+ "Cost at iteration 588 = 110.47315305369114\n",
+ "\n",
+ "Cost at iteration 589 = 110.44752007084186\n",
+ "\n",
+ "Cost at iteration 590 = 110.42189259246236\n",
+ "\n",
+ "Cost at iteration 591 = 110.39627061467473\n",
+ "\n",
+ "Cost at iteration 592 = 110.37065413360598\n",
+ "\n",
+ "Cost at iteration 593 = 110.34504314538765\n",
+ "\n",
+ "Cost at iteration 594 = 110.31943764615613\n",
+ "\n",
+ "Cost at iteration 595 = 110.2938376320525\n",
+ "\n",
+ "Cost at iteration 596 = 110.26824309922249\n",
+ "\n",
+ "Cost at iteration 597 = 110.24265404381646\n",
+ "\n",
+ "Cost at iteration 598 = 110.21707046198964\n",
+ "\n",
+ "Cost at iteration 599 = 110.19149234990181\n",
+ "\n",
+ "Cost at iteration 600 = 110.16591970371745\n",
+ "\n",
+ "Cost at iteration 601 = 110.1403525196058\n",
+ "\n",
+ "Cost at iteration 602 = 110.11479079374064\n",
+ "\n",
+ "Cost at iteration 603 = 110.0892345223005\n",
+ "\n",
+ "Cost at iteration 604 = 110.06368370146859\n",
+ "\n",
+ "Cost at iteration 605 = 110.03813832743273\n",
+ "\n",
+ "Cost at iteration 606 = 110.01259839638546\n",
+ "\n",
+ "Cost at iteration 607 = 109.98706390452386\n",
+ "\n",
+ "Cost at iteration 608 = 109.96153484804972\n",
+ "\n",
+ "Cost at iteration 609 = 109.93601122316954\n",
+ "\n",
+ "Cost at iteration 610 = 109.91049302609431\n",
+ "\n",
+ "Cost at iteration 611 = 109.88498025303979\n",
+ "\n",
+ "Cost at iteration 612 = 109.85947290022627\n",
+ "\n",
+ "Cost at iteration 613 = 109.83397096387866\n",
+ "\n",
+ "Cost at iteration 614 = 109.8084744402266\n",
+ "\n",
+ "Cost at iteration 615 = 109.78298332550425\n",
+ "\n",
+ "Cost at iteration 616 = 109.75749761595036\n",
+ "\n",
+ "Cost at iteration 617 = 109.73201730780833\n",
+ "\n",
+ "Cost at iteration 618 = 109.70654239732619\n",
+ "\n",
+ "Cost at iteration 619 = 109.6810728807565\n",
+ "\n",
+ "Cost at iteration 620 = 109.65560875435648\n",
+ "\n",
+ "Cost at iteration 621 = 109.63015001438784\n",
+ "\n",
+ "Cost at iteration 622 = 109.6046966571169\n",
+ "\n",
+ "Cost at iteration 623 = 109.5792486788147\n",
+ "\n",
+ "Cost at iteration 624 = 109.55380607575667\n",
+ "\n",
+ "Cost at iteration 625 = 109.52836884422284\n",
+ "\n",
+ "Cost at iteration 626 = 109.50293698049792\n",
+ "\n",
+ "Cost at iteration 627 = 109.47751048087106\n",
+ "\n",
+ "Cost at iteration 628 = 109.45208934163601\n",
+ "\n",
+ "Cost at iteration 629 = 109.4266735590911\n",
+ "\n",
+ "Cost at iteration 630 = 109.40126312953915\n",
+ "\n",
+ "Cost at iteration 631 = 109.37585804928754\n",
+ "\n",
+ "Cost at iteration 632 = 109.35045831464818\n",
+ "\n",
+ "Cost at iteration 633 = 109.32506392193761\n",
+ "\n",
+ "Cost at iteration 634 = 109.29967486747675\n",
+ "\n",
+ "Cost at iteration 635 = 109.27429114759116\n",
+ "\n",
+ "Cost at iteration 636 = 109.24891275861084\n",
+ "\n",
+ "Cost at iteration 637 = 109.22353969687033\n",
+ "\n",
+ "Cost at iteration 638 = 109.19817195870873\n",
+ "\n",
+ "Cost at iteration 639 = 109.17280954046961\n",
+ "\n",
+ "Cost at iteration 640 = 109.14745243850105\n",
+ "\n",
+ "Cost at iteration 641 = 109.1221006491556\n",
+ "\n",
+ "Cost at iteration 642 = 109.0967541687903\n",
+ "\n",
+ "Cost at iteration 643 = 109.07141299376676\n",
+ "\n",
+ "Cost at iteration 644 = 109.04607712045103\n",
+ "\n",
+ "Cost at iteration 645 = 109.02074654521361\n",
+ "\n",
+ "Cost at iteration 646 = 108.99542126442948\n",
+ "\n",
+ "Cost at iteration 647 = 108.97010127447817\n",
+ "\n",
+ "Cost at iteration 648 = 108.94478657174362\n",
+ "\n",
+ "Cost at iteration 649 = 108.91947715261416\n",
+ "\n",
+ "Cost at iteration 650 = 108.89417301348276\n",
+ "\n",
+ "Cost at iteration 651 = 108.86887415074668\n",
+ "\n",
+ "Cost at iteration 652 = 108.84358056080777\n",
+ "\n",
+ "Cost at iteration 653 = 108.81829224007215\n",
+ "\n",
+ "Cost at iteration 654 = 108.79300918495059\n",
+ "\n",
+ "Cost at iteration 655 = 108.76773139185815\n",
+ "\n",
+ "Cost at iteration 656 = 108.74245885721436\n",
+ "\n",
+ "Cost at iteration 657 = 108.71719157744322\n",
+ "\n",
+ "Cost at iteration 658 = 108.69192954897312\n",
+ "\n",
+ "Cost at iteration 659 = 108.66667276823686\n",
+ "\n",
+ "Cost at iteration 660 = 108.64142123167174\n",
+ "\n",
+ "Cost at iteration 661 = 108.61617493571934\n",
+ "\n",
+ "Cost at iteration 662 = 108.59093387682577\n",
+ "\n",
+ "Cost at iteration 663 = 108.56569805144149\n",
+ "\n",
+ "Cost at iteration 664 = 108.54046745602132\n",
+ "\n",
+ "Cost at iteration 665 = 108.51524208702459\n",
+ "\n",
+ "Cost at iteration 666 = 108.49002194091496\n",
+ "\n",
+ "Cost at iteration 667 = 108.46480701416041\n",
+ "\n",
+ "Cost at iteration 668 = 108.43959730323344\n",
+ "\n",
+ "Cost at iteration 669 = 108.41439280461083\n",
+ "\n",
+ "Cost at iteration 670 = 108.38919351477378\n",
+ "\n",
+ "Cost at iteration 671 = 108.36399943020783\n",
+ "\n",
+ "Cost at iteration 672 = 108.33881054740293\n",
+ "\n",
+ "Cost at iteration 673 = 108.31362686285337\n",
+ "\n",
+ "Cost at iteration 674 = 108.2884483730578\n",
+ "\n",
+ "Cost at iteration 675 = 108.26327507451921\n",
+ "\n",
+ "Cost at iteration 676 = 108.23810696374497\n",
+ "\n",
+ "Cost at iteration 677 = 108.21294403724681\n",
+ "\n",
+ "Cost at iteration 678 = 108.18778629154077\n",
+ "\n",
+ "Cost at iteration 679 = 108.16263372314718\n",
+ "\n",
+ "Cost at iteration 680 = 108.13748632859085\n",
+ "\n",
+ "Cost at iteration 681 = 108.11234410440079\n",
+ "\n",
+ "Cost at iteration 682 = 108.08720704711035\n",
+ "\n",
+ "Cost at iteration 683 = 108.06207515325731\n",
+ "\n",
+ "Cost at iteration 684 = 108.03694841938362\n",
+ "\n",
+ "Cost at iteration 685 = 108.01182684203569\n",
+ "\n",
+ "Cost at iteration 686 = 107.98671041776413\n",
+ "\n",
+ "Cost at iteration 687 = 107.96159914312386\n",
+ "\n",
+ "Cost at iteration 688 = 107.9364930146742\n",
+ "\n",
+ "Cost at iteration 689 = 107.91139202897867\n",
+ "\n",
+ "Cost at iteration 690 = 107.88629618260514\n",
+ "\n",
+ "Cost at iteration 691 = 107.86120547212573\n",
+ "\n",
+ "Cost at iteration 692 = 107.8361198941169\n",
+ "\n",
+ "Cost at iteration 693 = 107.81103944515934\n",
+ "\n",
+ "Cost at iteration 694 = 107.78596412183802\n",
+ "\n",
+ "Cost at iteration 695 = 107.76089392074226\n",
+ "\n",
+ "Cost at iteration 696 = 107.73582883846557\n",
+ "\n",
+ "Cost at iteration 697 = 107.7107688716057\n",
+ "\n",
+ "Cost at iteration 698 = 107.68571401676478\n",
+ "\n",
+ "Cost at iteration 699 = 107.66066427054909\n",
+ "\n",
+ "Cost at iteration 700 = 107.63561962956925\n",
+ "\n",
+ "Cost at iteration 701 = 107.61058009044007\n",
+ "\n",
+ "Cost at iteration 702 = 107.58554564978061\n",
+ "\n",
+ "Cost at iteration 703 = 107.56051630421418\n",
+ "\n",
+ "Cost at iteration 704 = 107.53549205036836\n",
+ "\n",
+ "Cost at iteration 705 = 107.51047288487496\n",
+ "\n",
+ "Cost at iteration 706 = 107.48545880436997\n",
+ "\n",
+ "Cost at iteration 707 = 107.46044980549361\n",
+ "\n",
+ "Cost at iteration 708 = 107.43544588489043\n",
+ "\n",
+ "Cost at iteration 709 = 107.41044703920906\n",
+ "\n",
+ "Cost at iteration 710 = 107.38545326510244\n",
+ "\n",
+ "Cost at iteration 711 = 107.36046455922767\n",
+ "\n",
+ "Cost at iteration 712 = 107.3354809182461\n",
+ "\n",
+ "Cost at iteration 713 = 107.31050233882323\n",
+ "\n",
+ "Cost at iteration 714 = 107.28552881762883\n",
+ "\n",
+ "Cost at iteration 715 = 107.26056035133678\n",
+ "\n",
+ "Cost at iteration 716 = 107.23559693662523\n",
+ "\n",
+ "Cost at iteration 717 = 107.21063857017644\n",
+ "\n",
+ "Cost at iteration 718 = 107.18568524867695\n",
+ "\n",
+ "Cost at iteration 719 = 107.16073696881743\n",
+ "\n",
+ "Cost at iteration 720 = 107.1357937272927\n",
+ "\n",
+ "Cost at iteration 721 = 107.11085552080179\n",
+ "\n",
+ "Cost at iteration 722 = 107.08592234604791\n",
+ "\n",
+ "Cost at iteration 723 = 107.06099419973839\n",
+ "\n",
+ "Cost at iteration 724 = 107.03607107858473\n",
+ "\n",
+ "Cost at iteration 725 = 107.01115297930265\n",
+ "\n",
+ "Cost at iteration 726 = 106.98623989861196\n",
+ "\n",
+ "Cost at iteration 727 = 106.9613318332366\n",
+ "\n",
+ "Cost at iteration 728 = 106.93642877990474\n",
+ "\n",
+ "Cost at iteration 729 = 106.91153073534863\n",
+ "\n",
+ "Cost at iteration 730 = 106.88663769630467\n",
+ "\n",
+ "Cost at iteration 731 = 106.86174965951339\n",
+ "\n",
+ "Cost at iteration 732 = 106.83686662171947\n",
+ "\n",
+ "Cost at iteration 733 = 106.81198857967172\n",
+ "\n",
+ "Cost at iteration 734 = 106.78711553012302\n",
+ "\n",
+ "Cost at iteration 735 = 106.76224746983043\n",
+ "\n",
+ "Cost at iteration 736 = 106.7373843955551\n",
+ "\n",
+ "Cost at iteration 737 = 106.71252630406232\n",
+ "\n",
+ "Cost at iteration 738 = 106.68767319212144\n",
+ "\n",
+ "Cost at iteration 739 = 106.66282505650595\n",
+ "\n",
+ "Cost at iteration 740 = 106.63798189399341\n",
+ "\n",
+ "Cost at iteration 741 = 106.61314370136552\n",
+ "\n",
+ "Cost at iteration 742 = 106.58831047540802\n",
+ "\n",
+ "Cost at iteration 743 = 106.56348221291083\n",
+ "\n",
+ "Cost at iteration 744 = 106.53865891066786\n",
+ "\n",
+ "Cost at iteration 745 = 106.51384056547711\n",
+ "\n",
+ "Cost at iteration 746 = 106.48902717414073\n",
+ "\n",
+ "Cost at iteration 747 = 106.4642187334649\n",
+ "\n",
+ "Cost at iteration 748 = 106.43941524025986\n",
+ "\n",
+ "Cost at iteration 749 = 106.4146166913399\n",
+ "\n",
+ "Cost at iteration 750 = 106.38982308352345\n",
+ "\n",
+ "Cost at iteration 751 = 106.36503441363294\n",
+ "\n",
+ "Cost at iteration 752 = 106.34025067849485\n",
+ "\n",
+ "Cost at iteration 753 = 106.31547187493979\n",
+ "\n",
+ "Cost at iteration 754 = 106.29069799980229\n",
+ "\n",
+ "Cost at iteration 755 = 106.26592904992101\n",
+ "\n",
+ "Cost at iteration 756 = 106.2411650221387\n",
+ "\n",
+ "Cost at iteration 757 = 106.21640591330204\n",
+ "\n",
+ "Cost at iteration 758 = 106.19165172026177\n",
+ "\n",
+ "Cost at iteration 759 = 106.16690243987274\n",
+ "\n",
+ "Cost at iteration 760 = 106.14215806899372\n",
+ "\n",
+ "Cost at iteration 761 = 106.11741860448757\n",
+ "\n",
+ "Cost at iteration 762 = 106.09268404322118\n",
+ "\n",
+ "Cost at iteration 763 = 106.06795438206535\n",
+ "\n",
+ "Cost at iteration 764 = 106.04322961789508\n",
+ "\n",
+ "Cost at iteration 765 = 106.01850974758919\n",
+ "\n",
+ "Cost at iteration 766 = 105.99379476803061\n",
+ "\n",
+ "Cost at iteration 767 = 105.96908467610625\n",
+ "\n",
+ "Cost at iteration 768 = 105.94437946870704\n",
+ "\n",
+ "Cost at iteration 769 = 105.91967914272784\n",
+ "\n",
+ "Cost at iteration 770 = 105.89498369506758\n",
+ "\n",
+ "Cost at iteration 771 = 105.87029312262909\n",
+ "\n",
+ "Cost at iteration 772 = 105.8456074223193\n",
+ "\n",
+ "Cost at iteration 773 = 105.82092659104899\n",
+ "\n",
+ "Cost at iteration 774 = 105.79625062573307\n",
+ "\n",
+ "Cost at iteration 775 = 105.7715795232902\n",
+ "\n",
+ "Cost at iteration 776 = 105.74691328064324\n",
+ "\n",
+ "Cost at iteration 777 = 105.72225189471891\n",
+ "\n",
+ "Cost at iteration 778 = 105.6975953624479\n",
+ "\n",
+ "Cost at iteration 779 = 105.67294368076486\n",
+ "\n",
+ "Cost at iteration 780 = 105.64829684660836\n",
+ "\n",
+ "Cost at iteration 781 = 105.62365485692102\n",
+ "\n",
+ "Cost at iteration 782 = 105.59901770864931\n",
+ "\n",
+ "Cost at iteration 783 = 105.5743853987437\n",
+ "\n",
+ "Cost at iteration 784 = 105.54975792415858\n",
+ "\n",
+ "Cost at iteration 785 = 105.5251352818523\n",
+ "\n",
+ "Cost at iteration 786 = 105.50051746878708\n",
+ "\n",
+ "Cost at iteration 787 = 105.47590448192915\n",
+ "\n",
+ "Cost at iteration 788 = 105.45129631824865\n",
+ "\n",
+ "Cost at iteration 789 = 105.42669297471961\n",
+ "\n",
+ "Cost at iteration 790 = 105.40209444832001\n",
+ "\n",
+ "Cost at iteration 791 = 105.37750073603172\n",
+ "\n",
+ "Cost at iteration 792 = 105.35291183484057\n",
+ "\n",
+ "Cost at iteration 793 = 105.32832774173626\n",
+ "\n",
+ "Cost at iteration 794 = 105.30374845371242\n",
+ "\n",
+ "Cost at iteration 795 = 105.27917396776652\n",
+ "\n",
+ "Cost at iteration 796 = 105.25460428090008\n",
+ "\n",
+ "Cost at iteration 797 = 105.23003939011832\n",
+ "\n",
+ "Cost at iteration 798 = 105.20547929243048\n",
+ "\n",
+ "Cost at iteration 799 = 105.18092398484968\n",
+ "\n",
+ "Cost at iteration 800 = 105.15637346439289\n",
+ "\n",
+ "Cost at iteration 801 = 105.13182772808102\n",
+ "\n",
+ "Cost at iteration 802 = 105.10728677293874\n",
+ "\n",
+ "Cost at iteration 803 = 105.08275059599474\n",
+ "\n",
+ "Cost at iteration 804 = 105.05821919428148\n",
+ "\n",
+ "Cost at iteration 805 = 105.03369256483535\n",
+ "\n",
+ "Cost at iteration 806 = 105.00917070469657\n",
+ "\n",
+ "Cost at iteration 807 = 104.98465361090922\n",
+ "\n",
+ "Cost at iteration 808 = 104.96014128052128\n",
+ "\n",
+ "Cost at iteration 809 = 104.93563371058451\n",
+ "\n",
+ "Cost at iteration 810 = 104.91113089815465\n",
+ "\n",
+ "Cost at iteration 811 = 104.88663284029116\n",
+ "\n",
+ "Cost at iteration 812 = 104.86213953405736\n",
+ "\n",
+ "Cost at iteration 813 = 104.83765097652051\n",
+ "\n",
+ "Cost at iteration 814 = 104.8131671647516\n",
+ "\n",
+ "Cost at iteration 815 = 104.78868809582552\n",
+ "\n",
+ "Cost at iteration 816 = 104.76421376682096\n",
+ "\n",
+ "Cost at iteration 817 = 104.73974417482046\n",
+ "\n",
+ "Cost at iteration 818 = 104.71527931691037\n",
+ "\n",
+ "Cost at iteration 819 = 104.69081919018086\n",
+ "\n",
+ "Cost at iteration 820 = 104.66636379172593\n",
+ "\n",
+ "Cost at iteration 821 = 104.64191311864339\n",
+ "\n",
+ "Cost at iteration 822 = 104.61746716803489\n",
+ "\n",
+ "Cost at iteration 823 = 104.59302593700578\n",
+ "\n",
+ "Cost at iteration 824 = 104.5685894226654\n",
+ "\n",
+ "Cost at iteration 825 = 104.54415762212668\n",
+ "\n",
+ "Cost at iteration 826 = 104.51973053250656\n",
+ "\n",
+ "Cost at iteration 827 = 104.49530815092561\n",
+ "\n",
+ "Cost at iteration 828 = 104.47089047450827\n",
+ "\n",
+ "Cost at iteration 829 = 104.44647750038276\n",
+ "\n",
+ "Cost at iteration 830 = 104.42206922568106\n",
+ "\n",
+ "Cost at iteration 831 = 104.39766564753893\n",
+ "\n",
+ "Cost at iteration 832 = 104.37326676309597\n",
+ "\n",
+ "Cost at iteration 833 = 104.34887256949551\n",
+ "\n",
+ "Cost at iteration 834 = 104.32448306388463\n",
+ "\n",
+ "Cost at iteration 835 = 104.30009824341425\n",
+ "\n",
+ "Cost at iteration 836 = 104.27571810523895\n",
+ "\n",
+ "Cost at iteration 837 = 104.25134264651717\n",
+ "\n",
+ "Cost at iteration 838 = 104.22697186441106\n",
+ "\n",
+ "Cost at iteration 839 = 104.20260575608658\n",
+ "\n",
+ "Cost at iteration 840 = 104.17824431871334\n",
+ "\n",
+ "Cost at iteration 841 = 104.1538875494648\n",
+ "\n",
+ "Cost at iteration 842 = 104.12953544551812\n",
+ "\n",
+ "Cost at iteration 843 = 104.10518800405418\n",
+ "\n",
+ "Cost at iteration 844 = 104.08084522225766\n",
+ "\n",
+ "Cost at iteration 845 = 104.05650709731698\n",
+ "\n",
+ "Cost at iteration 846 = 104.03217362642421\n",
+ "\n",
+ "Cost at iteration 847 = 104.00784480677522\n",
+ "\n",
+ "Cost at iteration 848 = 103.98352063556955\n",
+ "\n",
+ "Cost at iteration 849 = 103.95920111001055\n",
+ "\n",
+ "Cost at iteration 850 = 103.93488622730524\n",
+ "\n",
+ "Cost at iteration 851 = 103.91057598466436\n",
+ "\n",
+ "Cost at iteration 852 = 103.8862703793023\n",
+ "\n",
+ "Cost at iteration 853 = 103.86196940843732\n",
+ "\n",
+ "Cost at iteration 854 = 103.83767306929121\n",
+ "\n",
+ "Cost at iteration 855 = 103.81338135908962\n",
+ "\n",
+ "Cost at iteration 856 = 103.78909427506176\n",
+ "\n",
+ "Cost at iteration 857 = 103.76481181444066\n",
+ "\n",
+ "Cost at iteration 858 = 103.74053397446295\n",
+ "\n",
+ "Cost at iteration 859 = 103.71626075236902\n",
+ "\n",
+ "Cost at iteration 860 = 103.69199214540293\n",
+ "\n",
+ "Cost at iteration 861 = 103.6677281508124\n",
+ "\n",
+ "Cost at iteration 862 = 103.64346876584888\n",
+ "\n",
+ "Cost at iteration 863 = 103.61921398776744\n",
+ "\n",
+ "Cost at iteration 864 = 103.59496381382682\n",
+ "\n",
+ "Cost at iteration 865 = 103.57071824128955\n",
+ "\n",
+ "Cost at iteration 866 = 103.54647726742174\n",
+ "\n",
+ "Cost at iteration 867 = 103.52224088949312\n",
+ "\n",
+ "Cost at iteration 868 = 103.4980091047772\n",
+ "\n",
+ "Cost at iteration 869 = 103.47378191055105\n",
+ "\n",
+ "Cost at iteration 870 = 103.44955930409546\n",
+ "\n",
+ "Cost at iteration 871 = 103.42534128269486\n",
+ "\n",
+ "Cost at iteration 872 = 103.40112784363731\n",
+ "\n",
+ "Cost at iteration 873 = 103.37691898421456\n",
+ "\n",
+ "Cost at iteration 874 = 103.35271470172192\n",
+ "\n",
+ "Cost at iteration 875 = 103.32851499345843\n",
+ "\n",
+ "Cost at iteration 876 = 103.30431985672678\n",
+ "\n",
+ "Cost at iteration 877 = 103.28012928883322\n",
+ "\n",
+ "Cost at iteration 878 = 103.25594328708769\n",
+ "\n",
+ "Cost at iteration 879 = 103.23176184880369\n",
+ "\n",
+ "Cost at iteration 880 = 103.20758497129842\n",
+ "\n",
+ "Cost at iteration 881 = 103.18341265189268\n",
+ "\n",
+ "Cost at iteration 882 = 103.1592448879109\n",
+ "\n",
+ "Cost at iteration 883 = 103.13508167668112\n",
+ "\n",
+ "Cost at iteration 884 = 103.11092301553496\n",
+ "\n",
+ "Cost at iteration 885 = 103.08676890180774\n",
+ "\n",
+ "Cost at iteration 886 = 103.06261933283828\n",
+ "\n",
+ "Cost at iteration 887 = 103.03847430596906\n",
+ "\n",
+ "Cost at iteration 888 = 103.01433381854616\n",
+ "\n",
+ "Cost at iteration 889 = 102.99019786791929\n",
+ "\n",
+ "Cost at iteration 890 = 102.96606645144168\n",
+ "\n",
+ "Cost at iteration 891 = 102.94193956647025\n",
+ "\n",
+ "Cost at iteration 892 = 102.91781721036543\n",
+ "\n",
+ "Cost at iteration 893 = 102.89369938049123\n",
+ "\n",
+ "Cost at iteration 894 = 102.8695860742153\n",
+ "\n",
+ "Cost at iteration 895 = 102.8454772889089\n",
+ "\n",
+ "Cost at iteration 896 = 102.82137302194677\n",
+ "\n",
+ "Cost at iteration 897 = 102.7972732707073\n",
+ "\n",
+ "Cost at iteration 898 = 102.77317803257236\n",
+ "\n",
+ "Cost at iteration 899 = 102.74908730492754\n",
+ "\n",
+ "Cost at iteration 900 = 102.72500108516188\n",
+ "\n",
+ "Cost at iteration 901 = 102.70091937066802\n",
+ "\n",
+ "Cost at iteration 902 = 102.6768421588421\n",
+ "\n",
+ "Cost at iteration 903 = 102.65276944708397\n",
+ "\n",
+ "Cost at iteration 904 = 102.62870123279686\n",
+ "\n",
+ "Cost at iteration 905 = 102.60463751338766\n",
+ "\n",
+ "Cost at iteration 906 = 102.58057828626677\n",
+ "\n",
+ "Cost at iteration 907 = 102.55652354884815\n",
+ "\n",
+ "Cost at iteration 908 = 102.53247329854926\n",
+ "\n",
+ "Cost at iteration 909 = 102.5084275327912\n",
+ "\n",
+ "Cost at iteration 910 = 102.48438624899846\n",
+ "\n",
+ "Cost at iteration 911 = 102.46034944459922\n",
+ "\n",
+ "Cost at iteration 912 = 102.43631711702506\n",
+ "\n",
+ "Cost at iteration 913 = 102.41228926371116\n",
+ "\n",
+ "Cost at iteration 914 = 102.38826588209623\n",
+ "\n",
+ "Cost at iteration 915 = 102.36424696962244\n",
+ "\n",
+ "Cost at iteration 916 = 102.34023252373557\n",
+ "\n",
+ "Cost at iteration 917 = 102.31622254188478\n",
+ "\n",
+ "Cost at iteration 918 = 102.29221702152292\n",
+ "\n",
+ "Cost at iteration 919 = 102.26821596010622\n",
+ "\n",
+ "Cost at iteration 920 = 102.24421935509444\n",
+ "\n",
+ "Cost at iteration 921 = 102.22022720395088\n",
+ "\n",
+ "Cost at iteration 922 = 102.19623950414231\n",
+ "\n",
+ "Cost at iteration 923 = 102.17225625313904\n",
+ "\n",
+ "Cost at iteration 924 = 102.1482774484148\n",
+ "\n",
+ "Cost at iteration 925 = 102.12430308744688\n",
+ "\n",
+ "Cost at iteration 926 = 102.10033316771604\n",
+ "\n",
+ "Cost at iteration 927 = 102.07636768670656\n",
+ "\n",
+ "Cost at iteration 928 = 102.05240664190612\n",
+ "\n",
+ "Cost at iteration 929 = 102.02845003080593\n",
+ "\n",
+ "Cost at iteration 930 = 102.00449785090072\n",
+ "\n",
+ "Cost at iteration 931 = 101.98055009968866\n",
+ "\n",
+ "Cost at iteration 932 = 101.95660677467131\n",
+ "\n",
+ "Cost at iteration 933 = 101.93266787335385\n",
+ "\n",
+ "Cost at iteration 934 = 101.90873339324484\n",
+ "\n",
+ "Cost at iteration 935 = 101.88480333185635\n",
+ "\n",
+ "Cost at iteration 936 = 101.8608776867038\n",
+ "\n",
+ "Cost at iteration 937 = 101.83695645530622\n",
+ "\n",
+ "Cost at iteration 938 = 101.81303963518604\n",
+ "\n",
+ "Cost at iteration 939 = 101.78912722386907\n",
+ "\n",
+ "Cost at iteration 940 = 101.76521921888467\n",
+ "\n",
+ "Cost at iteration 941 = 101.74131561776555\n",
+ "\n",
+ "Cost at iteration 942 = 101.71741641804803\n",
+ "\n",
+ "Cost at iteration 943 = 101.69352161727166\n",
+ "\n",
+ "Cost at iteration 944 = 101.66963121297957\n",
+ "\n",
+ "Cost at iteration 945 = 101.64574520271829\n",
+ "\n",
+ "Cost at iteration 946 = 101.62186358403774\n",
+ "\n",
+ "Cost at iteration 947 = 101.59798635449137\n",
+ "\n",
+ "Cost at iteration 948 = 101.57411351163596\n",
+ "\n",
+ "Cost at iteration 949 = 101.55024505303177\n",
+ "\n",
+ "Cost at iteration 950 = 101.52638097624248\n",
+ "\n",
+ "Cost at iteration 951 = 101.50252127883513\n",
+ "\n",
+ "Cost at iteration 952 = 101.47866595838025\n",
+ "\n",
+ "Cost at iteration 953 = 101.45481501245176\n",
+ "\n",
+ "Cost at iteration 954 = 101.43096843862695\n",
+ "\n",
+ "Cost at iteration 955 = 101.40712623448658\n",
+ "\n",
+ "Cost at iteration 956 = 101.38328839761482\n",
+ "\n",
+ "Cost at iteration 957 = 101.35945492559912\n",
+ "\n",
+ "Cost at iteration 958 = 101.33562581603054\n",
+ "\n",
+ "Cost at iteration 959 = 101.31180106650329\n",
+ "\n",
+ "Cost at iteration 960 = 101.28798067461523\n",
+ "\n",
+ "Cost at iteration 961 = 101.2641646379674\n",
+ "\n",
+ "Cost at iteration 962 = 101.24035295416434\n",
+ "\n",
+ "Cost at iteration 963 = 101.21654562081393\n",
+ "\n",
+ "Cost at iteration 964 = 101.19274263552748\n",
+ "\n",
+ "Cost at iteration 965 = 101.16894399591962\n",
+ "\n",
+ "Cost at iteration 966 = 101.14514969960841\n",
+ "\n",
+ "Cost at iteration 967 = 101.12135974421525\n",
+ "\n",
+ "Cost at iteration 968 = 101.09757412736495\n",
+ "\n",
+ "Cost at iteration 969 = 101.07379284668569\n",
+ "\n",
+ "Cost at iteration 970 = 101.05001589980894\n",
+ "\n",
+ "Cost at iteration 971 = 101.02624328436961\n",
+ "\n",
+ "Cost at iteration 972 = 101.00247499800595\n",
+ "\n",
+ "Cost at iteration 973 = 100.97871103835956\n",
+ "\n",
+ "Cost at iteration 974 = 100.95495140307546\n",
+ "\n",
+ "Cost at iteration 975 = 100.9311960898019\n",
+ "\n",
+ "Cost at iteration 976 = 100.90744509619054\n",
+ "\n",
+ "Cost at iteration 977 = 100.88369841989648\n",
+ "\n",
+ "Cost at iteration 978 = 100.85995605857799\n",
+ "\n",
+ "Cost at iteration 979 = 100.83621800989683\n",
+ "\n",
+ "Cost at iteration 980 = 100.81248427151804\n",
+ "\n",
+ "Cost at iteration 981 = 100.78875484110996\n",
+ "\n",
+ "Cost at iteration 982 = 100.76502971634439\n",
+ "\n",
+ "Cost at iteration 983 = 100.7413088948963\n",
+ "\n",
+ "Cost at iteration 984 = 100.7175923744441\n",
+ "\n",
+ "Cost at iteration 985 = 100.6938801526695\n",
+ "\n",
+ "Cost at iteration 986 = 100.67017222725748\n",
+ "\n",
+ "Cost at iteration 987 = 100.64646859589648\n",
+ "\n",
+ "Cost at iteration 988 = 100.6227692562781\n",
+ "\n",
+ "Cost at iteration 989 = 100.59907420609733\n",
+ "\n",
+ "Cost at iteration 990 = 100.57538344305247\n",
+ "\n",
+ "Cost at iteration 991 = 100.55169696484515\n",
+ "\n",
+ "Cost at iteration 992 = 100.5280147691803\n",
+ "\n",
+ "Cost at iteration 993 = 100.50433685376606\n",
+ "\n",
+ "Cost at iteration 994 = 100.48066321631406\n",
+ "\n",
+ "Cost at iteration 995 = 100.45699385453904\n",
+ "\n",
+ "Cost at iteration 996 = 100.43332876615914\n",
+ "\n",
+ "Cost at iteration 997 = 100.4096679488958\n",
+ "\n",
+ "Cost at iteration 998 = 100.38601140047373\n",
+ "\n",
+ "Cost at iteration 999 = 100.36235911862092\n",
+ "\n",
+ "Cost at iteration 1000 = 100.33871110106863\n",
+ "\n",
+ "Cost at iteration 1001 = 100.31506734555144\n",
+ "\n",
+ "Cost at iteration 1002 = 100.29142784980725\n",
+ "\n",
+ "Cost at iteration 1003 = 100.26779261157714\n",
+ "\n",
+ "Cost at iteration 1004 = 100.24416162860551\n",
+ "\n",
+ "Cost at iteration 1005 = 100.22053489864007\n",
+ "\n",
+ "Cost at iteration 1006 = 100.19691241943174\n",
+ "\n",
+ "Cost at iteration 1007 = 100.17329418873479\n",
+ "\n",
+ "Cost at iteration 1008 = 100.1496802043067\n",
+ "\n",
+ "Cost at iteration 1009 = 100.12607046390816\n",
+ "\n",
+ "Cost at iteration 1010 = 100.1024649653032\n",
+ "\n",
+ "Cost at iteration 1011 = 100.07886370625916\n",
+ "\n",
+ "Cost at iteration 1012 = 100.05526668454651\n",
+ "\n",
+ "Cost at iteration 1013 = 100.03167389793904\n",
+ "\n",
+ "Cost at iteration 1014 = 100.00808534421375\n",
+ "\n",
+ "Cost at iteration 1015 = 99.98450102115096\n",
+ "\n",
+ "Cost at iteration 1016 = 99.96092092653419\n",
+ "\n",
+ "Cost at iteration 1017 = 99.93734505815019\n",
+ "\n",
+ "Cost at iteration 1018 = 99.91377341378895\n",
+ "\n",
+ "Cost at iteration 1019 = 99.89020599124376\n",
+ "\n",
+ "Cost at iteration 1020 = 99.86664278831105\n",
+ "\n",
+ "Cost at iteration 1021 = 99.84308380279059\n",
+ "\n",
+ "Cost at iteration 1022 = 99.81952903248526\n",
+ "\n",
+ "Cost at iteration 1023 = 99.79597847520128\n",
+ "\n",
+ "Cost at iteration 1024 = 99.77243212874802\n",
+ "\n",
+ "Cost at iteration 1025 = 99.74888999093811\n",
+ "\n",
+ "Cost at iteration 1026 = 99.72535205958741\n",
+ "\n",
+ "Cost at iteration 1027 = 99.70181833251493\n",
+ "\n",
+ "Cost at iteration 1028 = 99.67828880754298\n",
+ "\n",
+ "Cost at iteration 1029 = 99.65476348249703\n",
+ "\n",
+ "Cost at iteration 1030 = 99.63124235520576\n",
+ "\n",
+ "Cost at iteration 1031 = 99.6077254235011\n",
+ "\n",
+ "Cost at iteration 1032 = 99.58421268521812\n",
+ "\n",
+ "Cost at iteration 1033 = 99.56070413819516\n",
+ "\n",
+ "Cost at iteration 1034 = 99.53719978027371\n",
+ "\n",
+ "Cost at iteration 1035 = 99.5136996092985\n",
+ "\n",
+ "Cost at iteration 1036 = 99.49020362311742\n",
+ "\n",
+ "Cost at iteration 1037 = 99.46671181958155\n",
+ "\n",
+ "Cost at iteration 1038 = 99.44322419654519\n",
+ "\n",
+ "Cost at iteration 1039 = 99.4197407518658\n",
+ "\n",
+ "Cost at iteration 1040 = 99.39626148340405\n",
+ "\n",
+ "Cost at iteration 1041 = 99.37278638902379\n",
+ "\n",
+ "Cost at iteration 1042 = 99.34931546659199\n",
+ "\n",
+ "Cost at iteration 1043 = 99.32584871397889\n",
+ "\n",
+ "Cost at iteration 1044 = 99.30238612905784\n",
+ "\n",
+ "Cost at iteration 1045 = 99.27892770970539\n",
+ "\n",
+ "Cost at iteration 1046 = 99.25547345380127\n",
+ "\n",
+ "Cost at iteration 1047 = 99.23202335922834\n",
+ "\n",
+ "Cost at iteration 1048 = 99.20857742387265\n",
+ "\n",
+ "Cost at iteration 1049 = 99.18513564562345\n",
+ "\n",
+ "Cost at iteration 1050 = 99.16169802237303\n",
+ "\n",
+ "Cost at iteration 1051 = 99.138264552017\n",
+ "\n",
+ "Cost at iteration 1052 = 99.11483523245397\n",
+ "\n",
+ "Cost at iteration 1053 = 99.09141006158582\n",
+ "\n",
+ "Cost at iteration 1054 = 99.06798903731756\n",
+ "\n",
+ "Cost at iteration 1055 = 99.04457215755728\n",
+ "\n",
+ "Cost at iteration 1056 = 99.02115942021629\n",
+ "\n",
+ "Cost at iteration 1057 = 98.99775082320897\n",
+ "\n",
+ "Cost at iteration 1058 = 98.97434636445297\n",
+ "\n",
+ "Cost at iteration 1059 = 98.95094604186887\n",
+ "\n",
+ "Cost at iteration 1060 = 98.92754985338064\n",
+ "\n",
+ "Cost at iteration 1061 = 98.90415779691516\n",
+ "\n",
+ "Cost at iteration 1062 = 98.88076987040255\n",
+ "\n",
+ "Cost at iteration 1063 = 98.85738607177608\n",
+ "\n",
+ "Cost at iteration 1064 = 98.83400639897205\n",
+ "\n",
+ "Cost at iteration 1065 = 98.81063084992998\n",
+ "\n",
+ "Cost at iteration 1066 = 98.7872594225925\n",
+ "\n",
+ "Cost at iteration 1067 = 98.76389211490525\n",
+ "\n",
+ "Cost at iteration 1068 = 98.74052892481718\n",
+ "\n",
+ "Cost at iteration 1069 = 98.71716985028013\n",
+ "\n",
+ "Cost at iteration 1070 = 98.69381488924923\n",
+ "\n",
+ "Cost at iteration 1071 = 98.67046403968266\n",
+ "\n",
+ "Cost at iteration 1072 = 98.64711729954166\n",
+ "\n",
+ "Cost at iteration 1073 = 98.62377466679064\n",
+ "\n",
+ "Cost at iteration 1074 = 98.60043613939709\n",
+ "\n",
+ "Cost at iteration 1075 = 98.5771017153316\n",
+ "\n",
+ "Cost at iteration 1076 = 98.55377139256787\n",
+ "\n",
+ "Cost at iteration 1077 = 98.53044516908261\n",
+ "\n",
+ "Cost at iteration 1078 = 98.50712304285578\n",
+ "\n",
+ "Cost at iteration 1079 = 98.4838050118703\n",
+ "\n",
+ "Cost at iteration 1080 = 98.46049107411224\n",
+ "\n",
+ "Cost at iteration 1081 = 98.43718122757069\n",
+ "\n",
+ "Cost at iteration 1082 = 98.41387547023791\n",
+ "\n",
+ "Cost at iteration 1083 = 98.39057380010922\n",
+ "\n",
+ "Cost at iteration 1084 = 98.36727621518295\n",
+ "\n",
+ "Cost at iteration 1085 = 98.34398271346065\n",
+ "\n",
+ "Cost at iteration 1086 = 98.32069329294673\n",
+ "\n",
+ "Cost at iteration 1087 = 98.29740795164888\n",
+ "\n",
+ "Cost at iteration 1088 = 98.27412668757769\n",
+ "\n",
+ "Cost at iteration 1089 = 98.25084949874697\n",
+ "\n",
+ "Cost at iteration 1090 = 98.22757638317348\n",
+ "\n",
+ "Cost at iteration 1091 = 98.20430733887711\n",
+ "\n",
+ "Cost at iteration 1092 = 98.18104236388079\n",
+ "\n",
+ "Cost at iteration 1093 = 98.15778145621046\n",
+ "\n",
+ "Cost at iteration 1094 = 98.1345246138952\n",
+ "\n",
+ "Cost at iteration 1095 = 98.11127183496707\n",
+ "\n",
+ "Cost at iteration 1096 = 98.0880231174612\n",
+ "\n",
+ "Cost at iteration 1097 = 98.06477845941582\n",
+ "\n",
+ "Cost at iteration 1098 = 98.04153785887208\n",
+ "\n",
+ "Cost at iteration 1099 = 98.01830131387437\n",
+ "\n",
+ "Cost at iteration 1100 = 97.99506882246993\n",
+ "\n",
+ "Cost at iteration 1101 = 97.97184038270916\n",
+ "\n",
+ "Cost at iteration 1102 = 97.94861599264544\n",
+ "\n",
+ "Cost at iteration 1103 = 97.92539565033516\n",
+ "\n",
+ "Cost at iteration 1104 = 97.90217935383784\n",
+ "\n",
+ "Cost at iteration 1105 = 97.87896710121592\n",
+ "\n",
+ "Cost at iteration 1106 = 97.85575889053494\n",
+ "\n",
+ "Cost at iteration 1107 = 97.83255471986348\n",
+ "\n",
+ "Cost at iteration 1108 = 97.809354587273\n",
+ "\n",
+ "Cost at iteration 1109 = 97.7861584908382\n",
+ "\n",
+ "Cost at iteration 1110 = 97.76296642863662\n",
+ "\n",
+ "Cost at iteration 1111 = 97.73977839874887\n",
+ "\n",
+ "Cost at iteration 1112 = 97.71659439925864\n",
+ "\n",
+ "Cost at iteration 1113 = 97.69341442825252\n",
+ "\n",
+ "Cost at iteration 1114 = 97.67023848382019\n",
+ "\n",
+ "Cost at iteration 1115 = 97.64706656405428\n",
+ "\n",
+ "Cost at iteration 1116 = 97.62389866705053\n",
+ "\n",
+ "Cost at iteration 1117 = 97.60073479090752\n",
+ "\n",
+ "Cost at iteration 1118 = 97.57757493372696\n",
+ "\n",
+ "Cost at iteration 1119 = 97.5544190936135\n",
+ "\n",
+ "Cost at iteration 1120 = 97.53126726867482\n",
+ "\n",
+ "Cost at iteration 1121 = 97.50811945702158\n",
+ "\n",
+ "Cost at iteration 1122 = 97.48497565676738\n",
+ "\n",
+ "Cost at iteration 1123 = 97.46183586602886\n",
+ "\n",
+ "Cost at iteration 1124 = 97.4387000829257\n",
+ "\n",
+ "Cost at iteration 1125 = 97.41556830558046\n",
+ "\n",
+ "Cost at iteration 1126 = 97.39244053211874\n",
+ "\n",
+ "Cost at iteration 1127 = 97.36931676066908\n",
+ "\n",
+ "Cost at iteration 1128 = 97.34619698936307\n",
+ "\n",
+ "Cost at iteration 1129 = 97.32308121633517\n",
+ "\n",
+ "Cost at iteration 1130 = 97.29996943972289\n",
+ "\n",
+ "Cost at iteration 1131 = 97.27686165766673\n",
+ "\n",
+ "Cost at iteration 1132 = 97.25375786831007\n",
+ "\n",
+ "Cost at iteration 1133 = 97.23065806979938\n",
+ "\n",
+ "Cost at iteration 1134 = 97.20756226028394\n",
+ "\n",
+ "Cost at iteration 1135 = 97.18447043791612\n",
+ "\n",
+ "Cost at iteration 1136 = 97.1613826008512\n",
+ "\n",
+ "Cost at iteration 1137 = 97.1382987472474\n",
+ "\n",
+ "Cost at iteration 1138 = 97.11521887526594\n",
+ "\n",
+ "Cost at iteration 1139 = 97.09214298307097\n",
+ "\n",
+ "Cost at iteration 1140 = 97.06907106882953\n",
+ "\n",
+ "Cost at iteration 1141 = 97.04600313071177\n",
+ "\n",
+ "Cost at iteration 1142 = 97.02293916689064\n",
+ "\n",
+ "Cost at iteration 1143 = 96.99987917554203\n",
+ "\n",
+ "Cost at iteration 1144 = 96.9768231548449\n",
+ "\n",
+ "Cost at iteration 1145 = 96.95377110298105\n",
+ "\n",
+ "Cost at iteration 1146 = 96.93072301813518\n",
+ "\n",
+ "Cost at iteration 1147 = 96.90767889849509\n",
+ "\n",
+ "Cost at iteration 1148 = 96.88463874225131\n",
+ "\n",
+ "Cost at iteration 1149 = 96.86160254759744\n",
+ "\n",
+ "Cost at iteration 1150 = 96.83857031272998\n",
+ "\n",
+ "Cost at iteration 1151 = 96.81554203584835\n",
+ "\n",
+ "Cost at iteration 1152 = 96.79251771515482\n",
+ "\n",
+ "Cost at iteration 1153 = 96.76949734885476\n",
+ "\n",
+ "Cost at iteration 1154 = 96.74648093515626\n",
+ "\n",
+ "Cost at iteration 1155 = 96.72346847227047\n",
+ "\n",
+ "Cost at iteration 1156 = 96.70045995841137\n",
+ "\n",
+ "Cost at iteration 1157 = 96.6774553917959\n",
+ "\n",
+ "Cost at iteration 1158 = 96.65445477064398\n",
+ "\n",
+ "Cost at iteration 1159 = 96.63145809317824\n",
+ "\n",
+ "Cost at iteration 1160 = 96.60846535762441\n",
+ "\n",
+ "Cost at iteration 1161 = 96.58547656221103\n",
+ "\n",
+ "Cost at iteration 1162 = 96.56249170516958\n",
+ "\n",
+ "Cost at iteration 1163 = 96.5395107847344\n",
+ "\n",
+ "Cost at iteration 1164 = 96.51653379914276\n",
+ "\n",
+ "Cost at iteration 1165 = 96.49356074663484\n",
+ "\n",
+ "Cost at iteration 1166 = 96.47059162545371\n",
+ "\n",
+ "Cost at iteration 1167 = 96.4476264338453\n",
+ "\n",
+ "Cost at iteration 1168 = 96.42466517005842\n",
+ "\n",
+ "Cost at iteration 1169 = 96.40170783234484\n",
+ "\n",
+ "Cost at iteration 1170 = 96.37875441895916\n",
+ "\n",
+ "Cost at iteration 1171 = 96.35580492815886\n",
+ "\n",
+ "Cost at iteration 1172 = 96.33285935820432\n",
+ "\n",
+ "Cost at iteration 1173 = 96.3099177073588\n",
+ "\n",
+ "Cost at iteration 1174 = 96.28697997388846\n",
+ "\n",
+ "Cost at iteration 1175 = 96.26404615606228\n",
+ "\n",
+ "Cost at iteration 1176 = 96.24111625215218\n",
+ "\n",
+ "Cost at iteration 1177 = 96.2181902604328\n",
+ "\n",
+ "Cost at iteration 1178 = 96.19526817918194\n",
+ "\n",
+ "Cost at iteration 1179 = 96.17235000667995\n",
+ "\n",
+ "Cost at iteration 1180 = 96.14943574121021\n",
+ "\n",
+ "Cost at iteration 1181 = 96.12652538105895\n",
+ "\n",
+ "Cost at iteration 1182 = 96.10361892451526\n",
+ "\n",
+ "Cost at iteration 1183 = 96.08071636987106\n",
+ "\n",
+ "Cost at iteration 1184 = 96.05781771542114\n",
+ "\n",
+ "Cost at iteration 1185 = 96.03492295946315\n",
+ "\n",
+ "Cost at iteration 1186 = 96.01203210029757\n",
+ "\n",
+ "Cost at iteration 1187 = 95.98914513622776\n",
+ "\n",
+ "Cost at iteration 1188 = 95.96626206555992\n",
+ "\n",
+ "Cost at iteration 1189 = 95.94338288660306\n",
+ "\n",
+ "Cost at iteration 1190 = 95.9205075976691\n",
+ "\n",
+ "Cost at iteration 1191 = 95.89763619707277\n",
+ "\n",
+ "Cost at iteration 1192 = 95.87476868313155\n",
+ "\n",
+ "Cost at iteration 1193 = 95.85190505416594\n",
+ "\n",
+ "Cost at iteration 1194 = 95.82904530849913\n",
+ "\n",
+ "Cost at iteration 1195 = 95.8061894444572\n",
+ "\n",
+ "Cost at iteration 1196 = 95.78333746036904\n",
+ "\n",
+ "Cost at iteration 1197 = 95.76048935456642\n",
+ "\n",
+ "Cost at iteration 1198 = 95.73764512538385\n",
+ "\n",
+ "Cost at iteration 1199 = 95.7148047711587\n",
+ "\n",
+ "Cost at iteration 1200 = 95.69196829023123\n",
+ "\n",
+ "Cost at iteration 1201 = 95.66913568094442\n",
+ "\n",
+ "Cost at iteration 1202 = 95.64630694164414\n",
+ "\n",
+ "Cost at iteration 1203 = 95.62348207067903\n",
+ "\n",
+ "Cost at iteration 1204 = 95.60066106640059\n",
+ "\n",
+ "Cost at iteration 1205 = 95.57784392716309\n",
+ "\n",
+ "Cost at iteration 1206 = 95.55503065132363\n",
+ "\n",
+ "Cost at iteration 1207 = 95.53222123724211\n",
+ "\n",
+ "Cost at iteration 1208 = 95.50941568328123\n",
+ "\n",
+ "Cost at iteration 1209 = 95.48661398780656\n",
+ "\n",
+ "Cost at iteration 1210 = 95.46381614918637\n",
+ "\n",
+ "Cost at iteration 1211 = 95.4410221657918\n",
+ "\n",
+ "Cost at iteration 1212 = 95.41823203599677\n",
+ "\n",
+ "Cost at iteration 1213 = 95.39544575817797\n",
+ "\n",
+ "Cost at iteration 1214 = 95.37266333071491\n",
+ "\n",
+ "Cost at iteration 1215 = 95.34988475198995\n",
+ "\n",
+ "Cost at iteration 1216 = 95.32711002038809\n",
+ "\n",
+ "Cost at iteration 1217 = 95.30433913429727\n",
+ "\n",
+ "Cost at iteration 1218 = 95.28157209210814\n",
+ "\n",
+ "Cost at iteration 1219 = 95.25880889221412\n",
+ "\n",
+ "Cost at iteration 1220 = 95.23604953301151\n",
+ "\n",
+ "Cost at iteration 1221 = 95.21329401289924\n",
+ "\n",
+ "Cost at iteration 1222 = 95.19054233027914\n",
+ "\n",
+ "Cost at iteration 1223 = 95.16779448355578\n",
+ "\n",
+ "Cost at iteration 1224 = 95.14505047113644\n",
+ "\n",
+ "Cost at iteration 1225 = 95.12231029143133\n",
+ "\n",
+ "Cost at iteration 1226 = 95.09957394285324\n",
+ "\n",
+ "Cost at iteration 1227 = 95.07684142381783\n",
+ "\n",
+ "Cost at iteration 1228 = 95.05411273274355\n",
+ "\n",
+ "Cost at iteration 1229 = 95.03138786805155\n",
+ "\n",
+ "Cost at iteration 1230 = 95.00866682816579\n",
+ "\n",
+ "Cost at iteration 1231 = 94.98594961151294\n",
+ "\n",
+ "Cost at iteration 1232 = 94.96323621652247\n",
+ "\n",
+ "Cost at iteration 1233 = 94.9405266416266\n",
+ "\n",
+ "Cost at iteration 1234 = 94.9178208852603\n",
+ "\n",
+ "Cost at iteration 1235 = 94.89511894586127\n",
+ "\n",
+ "Cost at iteration 1236 = 94.87242082186995\n",
+ "\n",
+ "Cost at iteration 1237 = 94.84972651172961\n",
+ "\n",
+ "Cost at iteration 1238 = 94.8270360138862\n",
+ "\n",
+ "Cost at iteration 1239 = 94.80434932678841\n",
+ "\n",
+ "Cost at iteration 1240 = 94.78166644888768\n",
+ "\n",
+ "Cost at iteration 1241 = 94.75898737863821\n",
+ "\n",
+ "Cost at iteration 1242 = 94.73631211449693\n",
+ "\n",
+ "Cost at iteration 1243 = 94.71364065492351\n",
+ "\n",
+ "Cost at iteration 1244 = 94.69097299838027\n",
+ "\n",
+ "Cost at iteration 1245 = 94.66830914333245\n",
+ "\n",
+ "Cost at iteration 1246 = 94.64564908824784\n",
+ "\n",
+ "Cost at iteration 1247 = 94.62299283159705\n",
+ "\n",
+ "Cost at iteration 1248 = 94.60034037185335\n",
+ "\n",
+ "Cost at iteration 1249 = 94.57769170749283\n",
+ "\n",
+ "Cost at iteration 1250 = 94.55504683699418\n",
+ "\n",
+ "Cost at iteration 1251 = 94.53240575883896\n",
+ "\n",
+ "Cost at iteration 1252 = 94.5097684715113\n",
+ "\n",
+ "Cost at iteration 1253 = 94.48713497349816\n",
+ "\n",
+ "Cost at iteration 1254 = 94.46450526328913\n",
+ "\n",
+ "Cost at iteration 1255 = 94.44187933937654\n",
+ "\n",
+ "Cost at iteration 1256 = 94.41925720025549\n",
+ "\n",
+ "Cost at iteration 1257 = 94.39663884442369\n",
+ "\n",
+ "Cost at iteration 1258 = 94.37402427038167\n",
+ "\n",
+ "Cost at iteration 1259 = 94.35141347663249\n",
+ "\n",
+ "Cost at iteration 1260 = 94.32880646168212\n",
+ "\n",
+ "Cost at iteration 1261 = 94.30620322403911\n",
+ "\n",
+ "Cost at iteration 1262 = 94.28360376221471\n",
+ "\n",
+ "Cost at iteration 1263 = 94.26100807472288\n",
+ "\n",
+ "Cost at iteration 1264 = 94.2384161600803\n",
+ "\n",
+ "Cost at iteration 1265 = 94.21582801680636\n",
+ "\n",
+ "Cost at iteration 1266 = 94.19324364342305\n",
+ "\n",
+ "Cost at iteration 1267 = 94.17066303845513\n",
+ "\n",
+ "Cost at iteration 1268 = 94.14808620043003\n",
+ "\n",
+ "Cost at iteration 1269 = 94.12551312787785\n",
+ "\n",
+ "Cost at iteration 1270 = 94.10294381933139\n",
+ "\n",
+ "Cost at iteration 1271 = 94.08037827332613\n",
+ "\n",
+ "Cost at iteration 1272 = 94.05781648840018\n",
+ "\n",
+ "Cost at iteration 1273 = 94.03525846309442\n",
+ "\n",
+ "Cost at iteration 1274 = 94.01270419595234\n",
+ "\n",
+ "Cost at iteration 1275 = 93.99015368552011\n",
+ "\n",
+ "Cost at iteration 1276 = 93.96760693034662\n",
+ "\n",
+ "Cost at iteration 1277 = 93.94506392898334\n",
+ "\n",
+ "Cost at iteration 1278 = 93.92252467998448\n",
+ "\n",
+ "Cost at iteration 1279 = 93.89998918190689\n",
+ "\n",
+ "Cost at iteration 1280 = 93.87745743331016\n",
+ "\n",
+ "Cost at iteration 1281 = 93.85492943275634\n",
+ "\n",
+ "Cost at iteration 1282 = 93.83240517881039\n",
+ "\n",
+ "Cost at iteration 1283 = 93.80988467003974\n",
+ "\n",
+ "Cost at iteration 1284 = 93.78736790501458\n",
+ "\n",
+ "Cost at iteration 1285 = 93.76485488230773\n",
+ "\n",
+ "Cost at iteration 1286 = 93.74234560049463\n",
+ "\n",
+ "Cost at iteration 1287 = 93.71984005815342\n",
+ "\n",
+ "Cost at iteration 1288 = 93.69733825386483\n",
+ "\n",
+ "Cost at iteration 1289 = 93.67484018621234\n",
+ "\n",
+ "Cost at iteration 1290 = 93.65234585378192\n",
+ "\n",
+ "Cost at iteration 1291 = 93.62985525516235\n",
+ "\n",
+ "Cost at iteration 1292 = 93.60736838894495\n",
+ "\n",
+ "Cost at iteration 1293 = 93.58488525372368\n",
+ "\n",
+ "Cost at iteration 1294 = 93.56240584809517\n",
+ "\n",
+ "Cost at iteration 1295 = 93.53993017065868\n",
+ "\n",
+ "Cost at iteration 1296 = 93.51745822001611\n",
+ "\n",
+ "Cost at iteration 1297 = 93.49498999477196\n",
+ "\n",
+ "Cost at iteration 1298 = 93.4725254935334\n",
+ "\n",
+ "Cost at iteration 1299 = 93.45006471491021\n",
+ "\n",
+ "Cost at iteration 1300 = 93.42760765751478\n",
+ "\n",
+ "Cost at iteration 1301 = 93.40515431996216\n",
+ "\n",
+ "Cost at iteration 1302 = 93.38270470087002\n",
+ "\n",
+ "Cost at iteration 1303 = 93.3602587988586\n",
+ "\n",
+ "Cost at iteration 1304 = 93.33781661255078\n",
+ "\n",
+ "Cost at iteration 1305 = 93.31537814057216\n",
+ "\n",
+ "Cost at iteration 1306 = 93.29294338155078\n",
+ "\n",
+ "Cost at iteration 1307 = 93.27051233411741\n",
+ "\n",
+ "Cost at iteration 1308 = 93.2480849969054\n",
+ "\n",
+ "Cost at iteration 1309 = 93.2256613685507\n",
+ "\n",
+ "Cost at iteration 1310 = 93.20324144769187\n",
+ "\n",
+ "Cost at iteration 1311 = 93.18082523297015\n",
+ "\n",
+ "Cost at iteration 1312 = 93.15841272302927\n",
+ "\n",
+ "Cost at iteration 1313 = 93.13600391651559\n",
+ "\n",
+ "Cost at iteration 1314 = 93.11359881207815\n",
+ "\n",
+ "Cost at iteration 1315 = 93.0911974083685\n",
+ "\n",
+ "Cost at iteration 1316 = 93.06879970404081\n",
+ "\n",
+ "Cost at iteration 1317 = 93.04640569775188\n",
+ "\n",
+ "Cost at iteration 1318 = 93.02401538816103\n",
+ "\n",
+ "Cost at iteration 1319 = 93.00162877393029\n",
+ "\n",
+ "Cost at iteration 1320 = 92.97924585372414\n",
+ "\n",
+ "Cost at iteration 1321 = 92.95686662620975\n",
+ "\n",
+ "Cost at iteration 1322 = 92.93449109005681\n",
+ "\n",
+ "Cost at iteration 1323 = 92.91211924393764\n",
+ "\n",
+ "Cost at iteration 1324 = 92.88975108652714\n",
+ "\n",
+ "Cost at iteration 1325 = 92.86738661650277\n",
+ "\n",
+ "Cost at iteration 1326 = 92.84502583254458\n",
+ "\n",
+ "Cost at iteration 1327 = 92.82266873333518\n",
+ "\n",
+ "Cost at iteration 1328 = 92.80031531755975\n",
+ "\n",
+ "Cost at iteration 1329 = 92.77796558390607\n",
+ "\n",
+ "Cost at iteration 1330 = 92.75561953106453\n",
+ "\n",
+ "Cost at iteration 1331 = 92.73327715772798\n",
+ "\n",
+ "Cost at iteration 1332 = 92.71093846259191\n",
+ "\n",
+ "Cost at iteration 1333 = 92.68860344435438\n",
+ "\n",
+ "Cost at iteration 1334 = 92.66627210171598\n",
+ "\n",
+ "Cost at iteration 1335 = 92.6439444333799\n",
+ "\n",
+ "Cost at iteration 1336 = 92.62162043805185\n",
+ "\n",
+ "Cost at iteration 1337 = 92.59930011444014\n",
+ "\n",
+ "Cost at iteration 1338 = 92.57698346125558\n",
+ "\n",
+ "Cost at iteration 1339 = 92.55467047721156\n",
+ "\n",
+ "Cost at iteration 1340 = 92.53236116102413\n",
+ "\n",
+ "Cost at iteration 1341 = 92.51005551141165\n",
+ "\n",
+ "Cost at iteration 1342 = 92.4877535270953\n",
+ "\n",
+ "Cost at iteration 1343 = 92.46545520679861\n",
+ "\n",
+ "Cost at iteration 1344 = 92.44316054924775\n",
+ "\n",
+ "Cost at iteration 1345 = 92.4208695531714\n",
+ "\n",
+ "Cost at iteration 1346 = 92.39858221730083\n",
+ "\n",
+ "Cost at iteration 1347 = 92.37629854036977\n",
+ "\n",
+ "Cost at iteration 1348 = 92.35401852111455\n",
+ "\n",
+ "Cost at iteration 1349 = 92.33174215827401\n",
+ "\n",
+ "Cost at iteration 1350 = 92.30946945058952\n",
+ "\n",
+ "Cost at iteration 1351 = 92.28720039680505\n",
+ "\n",
+ "Cost at iteration 1352 = 92.264934995667\n",
+ "\n",
+ "Cost at iteration 1353 = 92.2426732459244\n",
+ "\n",
+ "Cost at iteration 1354 = 92.22041514632869\n",
+ "\n",
+ "Cost at iteration 1355 = 92.19816069563394\n",
+ "\n",
+ "Cost at iteration 1356 = 92.17590989259672\n",
+ "\n",
+ "Cost at iteration 1357 = 92.15366273597611\n",
+ "\n",
+ "Cost at iteration 1358 = 92.13141922453364\n",
+ "\n",
+ "Cost at iteration 1359 = 92.10917935703354\n",
+ "\n",
+ "Cost at iteration 1360 = 92.08694313224238\n",
+ "\n",
+ "Cost at iteration 1361 = 92.06471054892933\n",
+ "\n",
+ "Cost at iteration 1362 = 92.04248160586604\n",
+ "\n",
+ "Cost at iteration 1363 = 92.02025630182669\n",
+ "\n",
+ "Cost at iteration 1364 = 91.99803463558803\n",
+ "\n",
+ "Cost at iteration 1365 = 91.97581660592917\n",
+ "\n",
+ "Cost at iteration 1366 = 91.95360221163187\n",
+ "\n",
+ "Cost at iteration 1367 = 91.93139145148032\n",
+ "\n",
+ "Cost at iteration 1368 = 91.90918432426123\n",
+ "\n",
+ "Cost at iteration 1369 = 91.88698082876383\n",
+ "\n",
+ "Cost at iteration 1370 = 91.86478096377981\n",
+ "\n",
+ "Cost at iteration 1371 = 91.8425847281034\n",
+ "\n",
+ "Cost at iteration 1372 = 91.8203921205313\n",
+ "\n",
+ "Cost at iteration 1373 = 91.79820313986275\n",
+ "\n",
+ "Cost at iteration 1374 = 91.77601778489937\n",
+ "\n",
+ "Cost at iteration 1375 = 91.75383605444539\n",
+ "\n",
+ "Cost at iteration 1376 = 91.73165794730748\n",
+ "\n",
+ "Cost at iteration 1377 = 91.70948346229481\n",
+ "\n",
+ "Cost at iteration 1378 = 91.68731259821898\n",
+ "\n",
+ "Cost at iteration 1379 = 91.6651453538942\n",
+ "\n",
+ "Cost at iteration 1380 = 91.64298172813702\n",
+ "\n",
+ "Cost at iteration 1381 = 91.62082171976657\n",
+ "\n",
+ "Cost at iteration 1382 = 91.59866532760441\n",
+ "\n",
+ "Cost at iteration 1383 = 91.57651255047459\n",
+ "\n",
+ "Cost at iteration 1384 = 91.55436338720362\n",
+ "\n",
+ "Cost at iteration 1385 = 91.5322178366205\n",
+ "\n",
+ "Cost at iteration 1386 = 91.51007589755676\n",
+ "\n",
+ "Cost at iteration 1387 = 91.48793756884625\n",
+ "\n",
+ "Cost at iteration 1388 = 91.46580284932544\n",
+ "\n",
+ "Cost at iteration 1389 = 91.4436717378332\n",
+ "\n",
+ "Cost at iteration 1390 = 91.42154423321085\n",
+ "\n",
+ "Cost at iteration 1391 = 91.39942033430216\n",
+ "\n",
+ "Cost at iteration 1392 = 91.37730003995347\n",
+ "\n",
+ "Cost at iteration 1393 = 91.35518334901346\n",
+ "\n",
+ "Cost at iteration 1394 = 91.3330702603333\n",
+ "\n",
+ "Cost at iteration 1395 = 91.31096077276666\n",
+ "\n",
+ "Cost at iteration 1396 = 91.28885488516961\n",
+ "\n",
+ "Cost at iteration 1397 = 91.2667525964007\n",
+ "\n",
+ "Cost at iteration 1398 = 91.24465390532092\n",
+ "\n",
+ "Cost at iteration 1399 = 91.22255881079374\n",
+ "\n",
+ "Cost at iteration 1400 = 91.20046731168502\n",
+ "\n",
+ "Cost at iteration 1401 = 91.17837940686313\n",
+ "\n",
+ "Cost at iteration 1402 = 91.15629509519881\n",
+ "\n",
+ "Cost at iteration 1403 = 91.13421437556534\n",
+ "\n",
+ "Cost at iteration 1404 = 91.11213724683834\n",
+ "\n",
+ "Cost at iteration 1405 = 91.09006370789591\n",
+ "\n",
+ "Cost at iteration 1406 = 91.06799375761865\n",
+ "\n",
+ "Cost at iteration 1407 = 91.04592739488947\n",
+ "\n",
+ "Cost at iteration 1408 = 91.0238646185938\n",
+ "\n",
+ "Cost at iteration 1409 = 91.00180542761953\n",
+ "\n",
+ "Cost at iteration 1410 = 90.9797498208569\n",
+ "\n",
+ "Cost at iteration 1411 = 90.95769779719859\n",
+ "\n",
+ "Cost at iteration 1412 = 90.93564935553974\n",
+ "\n",
+ "Cost at iteration 1413 = 90.91360449477796\n",
+ "\n",
+ "Cost at iteration 1414 = 90.89156321381313\n",
+ "\n",
+ "Cost at iteration 1415 = 90.86952551154775\n",
+ "\n",
+ "Cost at iteration 1416 = 90.84749138688657\n",
+ "\n",
+ "Cost at iteration 1417 = 90.82546083873687\n",
+ "\n",
+ "Cost at iteration 1418 = 90.8034338660083\n",
+ "\n",
+ "Cost at iteration 1419 = 90.7814104676129\n",
+ "\n",
+ "Cost at iteration 1420 = 90.75939064246518\n",
+ "\n",
+ "Cost at iteration 1421 = 90.73737438948207\n",
+ "\n",
+ "Cost at iteration 1422 = 90.7153617075828\n",
+ "\n",
+ "Cost at iteration 1423 = 90.69335259568915\n",
+ "\n",
+ "Cost at iteration 1424 = 90.67134705272524\n",
+ "\n",
+ "Cost at iteration 1425 = 90.64934507761757\n",
+ "\n",
+ "Cost at iteration 1426 = 90.62734666929505\n",
+ "\n",
+ "Cost at iteration 1427 = 90.60535182668907\n",
+ "\n",
+ "Cost at iteration 1428 = 90.58336054873332\n",
+ "\n",
+ "Cost at iteration 1429 = 90.56137283436395\n",
+ "\n",
+ "Cost at iteration 1430 = 90.5393886825195\n",
+ "\n",
+ "Cost at iteration 1431 = 90.51740809214085\n",
+ "\n",
+ "Cost at iteration 1432 = 90.49543106217133\n",
+ "\n",
+ "Cost at iteration 1433 = 90.47345759155665\n",
+ "\n",
+ "Cost at iteration 1434 = 90.45148767924495\n",
+ "\n",
+ "Cost at iteration 1435 = 90.42952132418665\n",
+ "\n",
+ "Cost at iteration 1436 = 90.40755852533468\n",
+ "\n",
+ "Cost at iteration 1437 = 90.38559928164423\n",
+ "\n",
+ "Cost at iteration 1438 = 90.36364359207299\n",
+ "\n",
+ "Cost at iteration 1439 = 90.34169145558099\n",
+ "\n",
+ "Cost at iteration 1440 = 90.31974287113059\n",
+ "\n",
+ "Cost at iteration 1441 = 90.29779783768659\n",
+ "\n",
+ "Cost at iteration 1442 = 90.27585635421616\n",
+ "\n",
+ "Cost at iteration 1443 = 90.25391841968882\n",
+ "\n",
+ "Cost at iteration 1444 = 90.23198403307644\n",
+ "\n",
+ "Cost at iteration 1445 = 90.21005319335336\n",
+ "\n",
+ "Cost at iteration 1446 = 90.1881258994962\n",
+ "\n",
+ "Cost at iteration 1447 = 90.16620215048397\n",
+ "\n",
+ "Cost at iteration 1448 = 90.14428194529805\n",
+ "\n",
+ "Cost at iteration 1449 = 90.12236528292219\n",
+ "\n",
+ "Cost at iteration 1450 = 90.10045216234249\n",
+ "\n",
+ "Cost at iteration 1451 = 90.07854258254743\n",
+ "\n",
+ "Cost at iteration 1452 = 90.05663654252783\n",
+ "\n",
+ "Cost at iteration 1453 = 90.03473404127692\n",
+ "\n",
+ "Cost at iteration 1454 = 90.01283507779019\n",
+ "\n",
+ "Cost at iteration 1455 = 89.99093965106557\n",
+ "\n",
+ "Cost at iteration 1456 = 89.96904776010332\n",
+ "\n",
+ "Cost at iteration 1457 = 89.94715940390601\n",
+ "\n",
+ "Cost at iteration 1458 = 89.92527458147867\n",
+ "\n",
+ "Cost at iteration 1459 = 89.90339329182854\n",
+ "\n",
+ "Cost at iteration 1460 = 89.88151553396528\n",
+ "\n",
+ "Cost at iteration 1461 = 89.85964130690093\n",
+ "\n",
+ "Cost at iteration 1462 = 89.83777060964977\n",
+ "\n",
+ "Cost at iteration 1463 = 89.81590344122853\n",
+ "\n",
+ "Cost at iteration 1464 = 89.79403980065622\n",
+ "\n",
+ "Cost at iteration 1465 = 89.77217968695417\n",
+ "\n",
+ "Cost at iteration 1466 = 89.75032309914613\n",
+ "\n",
+ "Cost at iteration 1467 = 89.7284700362581\n",
+ "\n",
+ "Cost at iteration 1468 = 89.70662049731844\n",
+ "\n",
+ "Cost at iteration 1469 = 89.68477448135789\n",
+ "\n",
+ "Cost at iteration 1470 = 89.66293198740945\n",
+ "\n",
+ "Cost at iteration 1471 = 89.64109301450847\n",
+ "\n",
+ "Cost at iteration 1472 = 89.61925756169266\n",
+ "\n",
+ "Cost at iteration 1473 = 89.59742562800204\n",
+ "\n",
+ "Cost at iteration 1474 = 89.57559721247893\n",
+ "\n",
+ "Cost at iteration 1475 = 89.55377231416794\n",
+ "\n",
+ "Cost at iteration 1476 = 89.53195093211616\n",
+ "\n",
+ "Cost at iteration 1477 = 89.51013306537276\n",
+ "\n",
+ "Cost at iteration 1478 = 89.48831871298945\n",
+ "\n",
+ "Cost at iteration 1479 = 89.46650787402014\n",
+ "\n",
+ "Cost at iteration 1480 = 89.44470054752102\n",
+ "\n",
+ "Cost at iteration 1481 = 89.42289673255074\n",
+ "\n",
+ "Cost at iteration 1482 = 89.40109642817008\n",
+ "\n",
+ "Cost at iteration 1483 = 89.37929963344227\n",
+ "\n",
+ "Cost at iteration 1484 = 89.35750634743279\n",
+ "\n",
+ "Cost at iteration 1485 = 89.33571656920942\n",
+ "\n",
+ "Cost at iteration 1486 = 89.31393029784225\n",
+ "\n",
+ "Cost at iteration 1487 = 89.2921475324037\n",
+ "\n",
+ "Cost at iteration 1488 = 89.27036827196848\n",
+ "\n",
+ "Cost at iteration 1489 = 89.24859251561351\n",
+ "\n",
+ "Cost at iteration 1490 = 89.2268202624182\n",
+ "\n",
+ "Cost at iteration 1491 = 89.20505151146405\n",
+ "\n",
+ "Cost at iteration 1492 = 89.18328626183502\n",
+ "\n",
+ "Cost at iteration 1493 = 89.16152451261725\n",
+ "\n",
+ "Cost at iteration 1494 = 89.13976626289923\n",
+ "\n",
+ "Cost at iteration 1495 = 89.1180115117717\n",
+ "\n",
+ "Cost at iteration 1496 = 89.09626025832777\n",
+ "\n",
+ "Cost at iteration 1497 = 89.07451250166271\n",
+ "\n",
+ "Cost at iteration 1498 = 89.05276824087419\n",
+ "\n",
+ "Cost at iteration 1499 = 89.03102747506207\n",
+ "\n",
+ "Cost at iteration 1500 = 89.0092902033286\n",
+ "\n",
+ "Cost at iteration 1501 = 88.98755642477823\n",
+ "\n",
+ "Cost at iteration 1502 = 88.96582613851767\n",
+ "\n",
+ "Cost at iteration 1503 = 88.94409934365598\n",
+ "\n",
+ "Cost at iteration 1504 = 88.92237603930447\n",
+ "\n",
+ "Cost at iteration 1505 = 88.90065622457671\n",
+ "\n",
+ "Cost at iteration 1506 = 88.87893989858851\n",
+ "\n",
+ "Cost at iteration 1507 = 88.85722706045802\n",
+ "\n",
+ "Cost at iteration 1508 = 88.83551770930562\n",
+ "\n",
+ "Cost at iteration 1509 = 88.813811844254\n",
+ "\n",
+ "Cost at iteration 1510 = 88.792109464428\n",
+ "\n",
+ "Cost at iteration 1511 = 88.7704105689549\n",
+ "\n",
+ "Cost at iteration 1512 = 88.74871515696408\n",
+ "\n",
+ "Cost at iteration 1513 = 88.7270232275873\n",
+ "\n",
+ "Cost at iteration 1514 = 88.70533477995848\n",
+ "\n",
+ "Cost at iteration 1515 = 88.68364981321385\n",
+ "\n",
+ "Cost at iteration 1516 = 88.66196832649193\n",
+ "\n",
+ "Cost at iteration 1517 = 88.64029031893345\n",
+ "\n",
+ "Cost at iteration 1518 = 88.61861578968139\n",
+ "\n",
+ "Cost at iteration 1519 = 88.59694473788099\n",
+ "\n",
+ "Cost at iteration 1520 = 88.57527716267973\n",
+ "\n",
+ "Cost at iteration 1521 = 88.55361306322739\n",
+ "\n",
+ "Cost at iteration 1522 = 88.53195243867593\n",
+ "\n",
+ "Cost at iteration 1523 = 88.5102952881796\n",
+ "\n",
+ "Cost at iteration 1524 = 88.48864161089485\n",
+ "\n",
+ "Cost at iteration 1525 = 88.46699140598044\n",
+ "\n",
+ "Cost at iteration 1526 = 88.44534467259729\n",
+ "\n",
+ "Cost at iteration 1527 = 88.42370140990862\n",
+ "\n",
+ "Cost at iteration 1528 = 88.4020616170799\n",
+ "\n",
+ "Cost at iteration 1529 = 88.38042529327873\n",
+ "\n",
+ "Cost at iteration 1530 = 88.35879243767509\n",
+ "\n",
+ "Cost at iteration 1531 = 88.33716304944109\n",
+ "\n",
+ "Cost at iteration 1532 = 88.31553712775107\n",
+ "\n",
+ "Cost at iteration 1533 = 88.29391467178165\n",
+ "\n",
+ "Cost at iteration 1534 = 88.27229568071171\n",
+ "\n",
+ "Cost at iteration 1535 = 88.25068015372223\n",
+ "\n",
+ "Cost at iteration 1536 = 88.22906808999656\n",
+ "\n",
+ "Cost at iteration 1537 = 88.2074594887201\n",
+ "\n",
+ "Cost at iteration 1538 = 88.18585434908071\n",
+ "\n",
+ "Cost at iteration 1539 = 88.16425267026824\n",
+ "\n",
+ "Cost at iteration 1540 = 88.14265445147488\n",
+ "\n",
+ "Cost at iteration 1541 = 88.12105969189501\n",
+ "\n",
+ "Cost at iteration 1542 = 88.09946839072522\n",
+ "\n",
+ "Cost at iteration 1543 = 88.07788054716437\n",
+ "\n",
+ "Cost at iteration 1544 = 88.05629616041337\n",
+ "\n",
+ "Cost at iteration 1545 = 88.03471522967558\n",
+ "\n",
+ "Cost at iteration 1546 = 88.01313775415638\n",
+ "\n",
+ "Cost at iteration 1547 = 87.99156373306343\n",
+ "\n",
+ "Cost at iteration 1548 = 87.96999316560655\n",
+ "\n",
+ "Cost at iteration 1549 = 87.94842605099787\n",
+ "\n",
+ "Cost at iteration 1550 = 87.92686238845161\n",
+ "\n",
+ "Cost at iteration 1551 = 87.90530217718421\n",
+ "\n",
+ "Cost at iteration 1552 = 87.88374541641443\n",
+ "\n",
+ "Cost at iteration 1553 = 87.86219210536302\n",
+ "\n",
+ "Cost at iteration 1554 = 87.84064224325311\n",
+ "\n",
+ "Cost at iteration 1555 = 87.81909582930996\n",
+ "\n",
+ "Cost at iteration 1556 = 87.79755286276098\n",
+ "\n",
+ "Cost at iteration 1557 = 87.77601334283585\n",
+ "\n",
+ "Cost at iteration 1558 = 87.75447726876635\n",
+ "\n",
+ "Cost at iteration 1559 = 87.73294463978657\n",
+ "\n",
+ "Cost at iteration 1560 = 87.71141545513267\n",
+ "\n",
+ "Cost at iteration 1561 = 87.68988971404302\n",
+ "\n",
+ "Cost at iteration 1562 = 87.66836741575827\n",
+ "\n",
+ "Cost at iteration 1563 = 87.64684855952113\n",
+ "\n",
+ "Cost at iteration 1564 = 87.62533314457656\n",
+ "\n",
+ "Cost at iteration 1565 = 87.60382117017168\n",
+ "\n",
+ "Cost at iteration 1566 = 87.5823126355558\n",
+ "\n",
+ "Cost at iteration 1567 = 87.56080753998037\n",
+ "\n",
+ "Cost at iteration 1568 = 87.53930588269908\n",
+ "\n",
+ "Cost at iteration 1569 = 87.51780766296773\n",
+ "\n",
+ "Cost at iteration 1570 = 87.49631288004433\n",
+ "\n",
+ "Cost at iteration 1571 = 87.47482153318903\n",
+ "\n",
+ "Cost at iteration 1572 = 87.45333362166419\n",
+ "\n",
+ "Cost at iteration 1573 = 87.4318491447343\n",
+ "\n",
+ "Cost at iteration 1574 = 87.41036810166602\n",
+ "\n",
+ "Cost at iteration 1575 = 87.38889049172822\n",
+ "\n",
+ "Cost at iteration 1576 = 87.36741631419187\n",
+ "\n",
+ "Cost at iteration 1577 = 87.34594556833012\n",
+ "\n",
+ "Cost at iteration 1578 = 87.32447825341832\n",
+ "\n",
+ "Cost at iteration 1579 = 87.30301436873394\n",
+ "\n",
+ "Cost at iteration 1580 = 87.28155391355658\n",
+ "\n",
+ "Cost at iteration 1581 = 87.26009688716806\n",
+ "\n",
+ "Cost at iteration 1582 = 87.23864328885232\n",
+ "\n",
+ "Cost at iteration 1583 = 87.21719311789542\n",
+ "\n",
+ "Cost at iteration 1584 = 87.19574637358565\n",
+ "\n",
+ "Cost at iteration 1585 = 87.17430305521337\n",
+ "\n",
+ "Cost at iteration 1586 = 87.15286316207116\n",
+ "\n",
+ "Cost at iteration 1587 = 87.13142669345368\n",
+ "\n",
+ "Cost at iteration 1588 = 87.10999364865773\n",
+ "\n",
+ "Cost at iteration 1589 = 87.08856402698234\n",
+ "\n",
+ "Cost at iteration 1590 = 87.0671378277286\n",
+ "\n",
+ "Cost at iteration 1591 = 87.04571505019976\n",
+ "\n",
+ "Cost at iteration 1592 = 87.02429569370122\n",
+ "\n",
+ "Cost at iteration 1593 = 87.0028797575405\n",
+ "\n",
+ "Cost at iteration 1594 = 86.98146724102727\n",
+ "\n",
+ "Cost at iteration 1595 = 86.96005814347335\n",
+ "\n",
+ "Cost at iteration 1596 = 86.93865246419263\n",
+ "\n",
+ "Cost at iteration 1597 = 86.9172502025012\n",
+ "\n",
+ "Cost at iteration 1598 = 86.8958513577172\n",
+ "\n",
+ "Cost at iteration 1599 = 86.87445592916107\n",
+ "\n",
+ "Cost at iteration 1600 = 86.85306391615512\n",
+ "\n",
+ "Cost at iteration 1601 = 86.831675318024\n",
+ "\n",
+ "Cost at iteration 1602 = 86.81029013409436\n",
+ "\n",
+ "Cost at iteration 1603 = 86.78890836369504\n",
+ "\n",
+ "Cost at iteration 1604 = 86.76753000615696\n",
+ "\n",
+ "Cost at iteration 1605 = 86.74615506081314\n",
+ "\n",
+ "Cost at iteration 1606 = 86.7247835269988\n",
+ "\n",
+ "Cost at iteration 1607 = 86.70341540405123\n",
+ "\n",
+ "Cost at iteration 1608 = 86.68205069130977\n",
+ "\n",
+ "Cost at iteration 1609 = 86.66068938811598\n",
+ "\n",
+ "Cost at iteration 1610 = 86.63933149381347\n",
+ "\n",
+ "Cost at iteration 1611 = 86.61797700774792\n",
+ "\n",
+ "Cost at iteration 1612 = 86.59662592926725\n",
+ "\n",
+ "Cost at iteration 1613 = 86.57527825772135\n",
+ "\n",
+ "Cost at iteration 1614 = 86.5539339924623\n",
+ "\n",
+ "Cost at iteration 1615 = 86.5325931328442\n",
+ "\n",
+ "Cost at iteration 1616 = 86.5112556782234\n",
+ "\n",
+ "Cost at iteration 1617 = 86.48992162795814\n",
+ "\n",
+ "Cost at iteration 1618 = 86.46859098140897\n",
+ "\n",
+ "Cost at iteration 1619 = 86.44726373793839\n",
+ "\n",
+ "Cost at iteration 1620 = 86.42593989691103\n",
+ "\n",
+ "Cost at iteration 1621 = 86.4046194576937\n",
+ "\n",
+ "Cost at iteration 1622 = 86.3833024196552\n",
+ "\n",
+ "Cost at iteration 1623 = 86.36198878216642\n",
+ "\n",
+ "Cost at iteration 1624 = 86.3406785446004\n",
+ "\n",
+ "Cost at iteration 1625 = 86.31937170633225\n",
+ "\n",
+ "Cost at iteration 1626 = 86.29806826673915\n",
+ "\n",
+ "Cost at iteration 1627 = 86.2767682252004\n",
+ "\n",
+ "Cost at iteration 1628 = 86.25547158109732\n",
+ "\n",
+ "Cost at iteration 1629 = 86.23417833381336\n",
+ "\n",
+ "Cost at iteration 1630 = 86.21288848273406\n",
+ "\n",
+ "Cost at iteration 1631 = 86.19160202724699\n",
+ "\n",
+ "Cost at iteration 1632 = 86.17031896674187\n",
+ "\n",
+ "Cost at iteration 1633 = 86.14903930061044\n",
+ "\n",
+ "Cost at iteration 1634 = 86.12776302824649\n",
+ "\n",
+ "Cost at iteration 1635 = 86.10649014904594\n",
+ "\n",
+ "Cost at iteration 1636 = 86.08522066240683\n",
+ "\n",
+ "Cost at iteration 1637 = 86.06395456772911\n",
+ "\n",
+ "Cost at iteration 1638 = 86.04269186441493\n",
+ "\n",
+ "Cost at iteration 1639 = 86.0214325518685\n",
+ "\n",
+ "Cost at iteration 1640 = 86.00017662949602\n",
+ "\n",
+ "Cost at iteration 1641 = 85.97892409670585\n",
+ "\n",
+ "Cost at iteration 1642 = 85.9576749529083\n",
+ "\n",
+ "Cost at iteration 1643 = 85.93642919751585\n",
+ "\n",
+ "Cost at iteration 1644 = 85.915186829943\n",
+ "\n",
+ "Cost at iteration 1645 = 85.89394784960628\n",
+ "\n",
+ "Cost at iteration 1646 = 85.87271225592424\n",
+ "\n",
+ "Cost at iteration 1647 = 85.85148004831764\n",
+ "\n",
+ "Cost at iteration 1648 = 85.83025122620917\n",
+ "\n",
+ "Cost at iteration 1649 = 85.80902578902361\n",
+ "\n",
+ "Cost at iteration 1650 = 85.7878037361877\n",
+ "\n",
+ "Cost at iteration 1651 = 85.76658506713044\n",
+ "\n",
+ "Cost at iteration 1652 = 85.74536978128265\n",
+ "\n",
+ "Cost at iteration 1653 = 85.72415787807732\n",
+ "\n",
+ "Cost at iteration 1654 = 85.70294935694947\n",
+ "\n",
+ "Cost at iteration 1655 = 85.68174421733615\n",
+ "\n",
+ "Cost at iteration 1656 = 85.66054245867642\n",
+ "\n",
+ "Cost at iteration 1657 = 85.63934408041148\n",
+ "\n",
+ "Cost at iteration 1658 = 85.61814908198444\n",
+ "\n",
+ "Cost at iteration 1659 = 85.59695746284054\n",
+ "\n",
+ "Cost at iteration 1660 = 85.57576922242698\n",
+ "\n",
+ "Cost at iteration 1661 = 85.55458436019316\n",
+ "\n",
+ "Cost at iteration 1662 = 85.53340287559026\n",
+ "\n",
+ "Cost at iteration 1663 = 85.5122247680717\n",
+ "\n",
+ "Cost at iteration 1664 = 85.49105003709283\n",
+ "\n",
+ "Cost at iteration 1665 = 85.46987868211107\n",
+ "\n",
+ "Cost at iteration 1666 = 85.44871070258581\n",
+ "\n",
+ "Cost at iteration 1667 = 85.42754609797856\n",
+ "\n",
+ "Cost at iteration 1668 = 85.40638486775279\n",
+ "\n",
+ "Cost at iteration 1669 = 85.38522701137394\n",
+ "\n",
+ "Cost at iteration 1670 = 85.3640725283096\n",
+ "\n",
+ "Cost at iteration 1671 = 85.3429214180293\n",
+ "\n",
+ "Cost at iteration 1672 = 85.3217736800046\n",
+ "\n",
+ "Cost at iteration 1673 = 85.30062931370905\n",
+ "\n",
+ "Cost at iteration 1674 = 85.27948831861828\n",
+ "\n",
+ "Cost at iteration 1675 = 85.25835069420987\n",
+ "\n",
+ "Cost at iteration 1676 = 85.23721643996345\n",
+ "\n",
+ "Cost at iteration 1677 = 85.21608555536064\n",
+ "\n",
+ "Cost at iteration 1678 = 85.19495803988508\n",
+ "\n",
+ "Cost at iteration 1679 = 85.17383389302243\n",
+ "\n",
+ "Cost at iteration 1680 = 85.15271311426032\n",
+ "\n",
+ "Cost at iteration 1681 = 85.13159570308841\n",
+ "\n",
+ "Cost at iteration 1682 = 85.1104816589984\n",
+ "\n",
+ "Cost at iteration 1683 = 85.0893709814839\n",
+ "\n",
+ "Cost at iteration 1684 = 85.0682636700406\n",
+ "\n",
+ "Cost at iteration 1685 = 85.04715972416614\n",
+ "\n",
+ "Cost at iteration 1686 = 85.0260591433602\n",
+ "\n",
+ "Cost at iteration 1687 = 85.0049619271244\n",
+ "\n",
+ "Cost at iteration 1688 = 84.98386807496243\n",
+ "\n",
+ "Cost at iteration 1689 = 84.96277758637993\n",
+ "\n",
+ "Cost at iteration 1690 = 84.94169046088454\n",
+ "\n",
+ "Cost at iteration 1691 = 84.92060669798579\n",
+ "\n",
+ "Cost at iteration 1692 = 84.89952629719544\n",
+ "\n",
+ "Cost at iteration 1693 = 84.87844925802696\n",
+ "\n",
+ "Cost at iteration 1694 = 84.85737557999599\n",
+ "\n",
+ "Cost at iteration 1695 = 84.83630526262012\n",
+ "\n",
+ "Cost at iteration 1696 = 84.81523830541884\n",
+ "\n",
+ "Cost at iteration 1697 = 84.79417470791375\n",
+ "\n",
+ "Cost at iteration 1698 = 84.77311446962831\n",
+ "\n",
+ "Cost at iteration 1699 = 84.75205759008803\n",
+ "\n",
+ "Cost at iteration 1700 = 84.73100406882037\n",
+ "\n",
+ "Cost at iteration 1701 = 84.70995390535478\n",
+ "\n",
+ "Cost at iteration 1702 = 84.68890709922269\n",
+ "\n",
+ "Cost at iteration 1703 = 84.66786364995745\n",
+ "\n",
+ "Cost at iteration 1704 = 84.64682355709445\n",
+ "\n",
+ "Cost at iteration 1705 = 84.625786820171\n",
+ "\n",
+ "Cost at iteration 1706 = 84.6047534387264\n",
+ "\n",
+ "Cost at iteration 1707 = 84.58372341230194\n",
+ "\n",
+ "Cost at iteration 1708 = 84.56269674044083\n",
+ "\n",
+ "Cost at iteration 1709 = 84.54167342268822\n",
+ "\n",
+ "Cost at iteration 1710 = 84.52065345859133\n",
+ "\n",
+ "Cost at iteration 1711 = 84.49963684769922\n",
+ "\n",
+ "Cost at iteration 1712 = 84.47862358956301\n",
+ "\n",
+ "Cost at iteration 1713 = 84.45761368373572\n",
+ "\n",
+ "Cost at iteration 1714 = 84.4366071297723\n",
+ "\n",
+ "Cost at iteration 1715 = 84.41560392722972\n",
+ "\n",
+ "Cost at iteration 1716 = 84.39460407566689\n",
+ "\n",
+ "Cost at iteration 1717 = 84.37360757464462\n",
+ "\n",
+ "Cost at iteration 1718 = 84.35261442372573\n",
+ "\n",
+ "Cost at iteration 1719 = 84.33162462247498\n",
+ "\n",
+ "Cost at iteration 1720 = 84.31063817045906\n",
+ "\n",
+ "Cost at iteration 1721 = 84.28965506724656\n",
+ "\n",
+ "Cost at iteration 1722 = 84.2686753124081\n",
+ "\n",
+ "Cost at iteration 1723 = 84.24769890551623\n",
+ "\n",
+ "Cost at iteration 1724 = 84.22672584614543\n",
+ "\n",
+ "Cost at iteration 1725 = 84.205756133872\n",
+ "\n",
+ "Cost at iteration 1726 = 84.18478976827441\n",
+ "\n",
+ "Cost at iteration 1727 = 84.16382674893289\n",
+ "\n",
+ "Cost at iteration 1728 = 84.14286707542966\n",
+ "\n",
+ "Cost at iteration 1729 = 84.12191074734892\n",
+ "\n",
+ "Cost at iteration 1730 = 84.1009577642767\n",
+ "\n",
+ "Cost at iteration 1731 = 84.08000812580104\n",
+ "\n",
+ "Cost at iteration 1732 = 84.05906183151188\n",
+ "\n",
+ "Cost at iteration 1733 = 84.03811888100113\n",
+ "\n",
+ "Cost at iteration 1734 = 84.01717927386254\n",
+ "\n",
+ "Cost at iteration 1735 = 83.99624300969192\n",
+ "\n",
+ "Cost at iteration 1736 = 83.97531008808686\n",
+ "\n",
+ "Cost at iteration 1737 = 83.95438050864693\n",
+ "\n",
+ "Cost at iteration 1738 = 83.93345427097366\n",
+ "\n",
+ "Cost at iteration 1739 = 83.91253137467046\n",
+ "\n",
+ "Cost at iteration 1740 = 83.89161181934267\n",
+ "\n",
+ "Cost at iteration 1741 = 83.87069560459753\n",
+ "\n",
+ "Cost at iteration 1742 = 83.84978273004421\n",
+ "\n",
+ "Cost at iteration 1743 = 83.82887319529384\n",
+ "\n",
+ "Cost at iteration 1744 = 83.80796699995932\n",
+ "\n",
+ "Cost at iteration 1745 = 83.78706414365563\n",
+ "\n",
+ "Cost at iteration 1746 = 83.76616462599955\n",
+ "\n",
+ "Cost at iteration 1747 = 83.74526844660984\n",
+ "\n",
+ "Cost at iteration 1748 = 83.72437560510708\n",
+ "\n",
+ "Cost at iteration 1749 = 83.70348610111384\n",
+ "\n",
+ "Cost at iteration 1750 = 83.68259993425454\n",
+ "\n",
+ "Cost at iteration 1751 = 83.66171710415553\n",
+ "\n",
+ "Cost at iteration 1752 = 83.64083761044508\n",
+ "\n",
+ "Cost at iteration 1753 = 83.61996145275324\n",
+ "\n",
+ "Cost at iteration 1754 = 83.59908863071216\n",
+ "\n",
+ "Cost at iteration 1755 = 83.57821914395569\n",
+ "\n",
+ "Cost at iteration 1756 = 83.55735299211973\n",
+ "\n",
+ "Cost at iteration 1757 = 83.53649017484194\n",
+ "\n",
+ "Cost at iteration 1758 = 83.51563069176197\n",
+ "\n",
+ "Cost at iteration 1759 = 83.49477454252133\n",
+ "\n",
+ "Cost at iteration 1760 = 83.4739217267634\n",
+ "\n",
+ "Cost at iteration 1761 = 83.45307224413345\n",
+ "\n",
+ "Cost at iteration 1762 = 83.43222609427872\n",
+ "\n",
+ "Cost at iteration 1763 = 83.41138327684818\n",
+ "\n",
+ "Cost at iteration 1764 = 83.39054379149279\n",
+ "\n",
+ "Cost at iteration 1765 = 83.36970763786539\n",
+ "\n",
+ "Cost at iteration 1766 = 83.34887481562068\n",
+ "\n",
+ "Cost at iteration 1767 = 83.32804532441521\n",
+ "\n",
+ "Cost at iteration 1768 = 83.30721916390748\n",
+ "\n",
+ "Cost at iteration 1769 = 83.28639633375779\n",
+ "\n",
+ "Cost at iteration 1770 = 83.26557683362837\n",
+ "\n",
+ "Cost at iteration 1771 = 83.2447606631833\n",
+ "\n",
+ "Cost at iteration 1772 = 83.2239478220885\n",
+ "\n",
+ "Cost at iteration 1773 = 83.2031383100118\n",
+ "\n",
+ "Cost at iteration 1774 = 83.18233212662294\n",
+ "\n",
+ "Cost at iteration 1775 = 83.16152927159344\n",
+ "\n",
+ "Cost at iteration 1776 = 83.1407297445967\n",
+ "\n",
+ "Cost at iteration 1777 = 83.1199335453081\n",
+ "\n",
+ "Cost at iteration 1778 = 83.09914067340472\n",
+ "\n",
+ "Cost at iteration 1779 = 83.07835112856556\n",
+ "\n",
+ "Cost at iteration 1780 = 83.05756491047153\n",
+ "\n",
+ "Cost at iteration 1781 = 83.03678201880535\n",
+ "\n",
+ "Cost at iteration 1782 = 83.01600245325169\n",
+ "\n",
+ "Cost at iteration 1783 = 82.99522621349688\n",
+ "\n",
+ "Cost at iteration 1784 = 82.97445329922924\n",
+ "\n",
+ "Cost at iteration 1785 = 82.95368371013902\n",
+ "\n",
+ "Cost at iteration 1786 = 82.93291744591814\n",
+ "\n",
+ "Cost at iteration 1787 = 82.91215450626042\n",
+ "\n",
+ "Cost at iteration 1788 = 82.89139489086168\n",
+ "\n",
+ "Cost at iteration 1789 = 82.87063859941941\n",
+ "\n",
+ "Cost at iteration 1790 = 82.84988563163297\n",
+ "\n",
+ "Cost at iteration 1791 = 82.82913598720368\n",
+ "\n",
+ "Cost at iteration 1792 = 82.80838966583455\n",
+ "\n",
+ "Cost at iteration 1793 = 82.7876466672306\n",
+ "\n",
+ "Cost at iteration 1794 = 82.76690699109847\n",
+ "\n",
+ "Cost at iteration 1795 = 82.74617063714689\n",
+ "\n",
+ "Cost at iteration 1796 = 82.72543760508628\n",
+ "\n",
+ "Cost at iteration 1797 = 82.7047078946288\n",
+ "\n",
+ "Cost at iteration 1798 = 82.68398150548869\n",
+ "\n",
+ "Cost at iteration 1799 = 82.66325843738187\n",
+ "\n",
+ "Cost at iteration 1800 = 82.64253869002607\n",
+ "\n",
+ "Cost at iteration 1801 = 82.62182226314094\n",
+ "\n",
+ "Cost at iteration 1802 = 82.60110915644788\n",
+ "\n",
+ "Cost at iteration 1803 = 82.58039936967015\n",
+ "\n",
+ "Cost at iteration 1804 = 82.55969290253292\n",
+ "\n",
+ "Cost at iteration 1805 = 82.538989754763\n",
+ "\n",
+ "Cost at iteration 1806 = 82.51828992608914\n",
+ "\n",
+ "Cost at iteration 1807 = 82.49759341624193\n",
+ "\n",
+ "Cost at iteration 1808 = 82.47690022495372\n",
+ "\n",
+ "Cost at iteration 1809 = 82.45621035195876\n",
+ "\n",
+ "Cost at iteration 1810 = 82.43552379699301\n",
+ "\n",
+ "Cost at iteration 1811 = 82.4148405597942\n",
+ "\n",
+ "Cost at iteration 1812 = 82.39416064010217\n",
+ "\n",
+ "Cost at iteration 1813 = 82.37348403765823\n",
+ "\n",
+ "Cost at iteration 1814 = 82.35281075220568\n",
+ "\n",
+ "Cost at iteration 1815 = 82.33214078348959\n",
+ "\n",
+ "Cost at iteration 1816 = 82.31147413125684\n",
+ "\n",
+ "Cost at iteration 1817 = 82.29081079525615\n",
+ "\n",
+ "Cost at iteration 1818 = 82.27015077523802\n",
+ "\n",
+ "Cost at iteration 1819 = 82.24949407095468\n",
+ "\n",
+ "Cost at iteration 1820 = 82.22884068216025\n",
+ "\n",
+ "Cost at iteration 1821 = 82.20819060861068\n",
+ "\n",
+ "Cost at iteration 1822 = 82.18754385006359\n",
+ "\n",
+ "Cost at iteration 1823 = 82.16690040627857\n",
+ "\n",
+ "Cost at iteration 1824 = 82.14626027701681\n",
+ "\n",
+ "Cost at iteration 1825 = 82.12562346204152\n",
+ "\n",
+ "Cost at iteration 1826 = 82.10498996111757\n",
+ "\n",
+ "Cost at iteration 1827 = 82.08435977401147\n",
+ "\n",
+ "Cost at iteration 1828 = 82.06373290049184\n",
+ "\n",
+ "Cost at iteration 1829 = 82.04310934032901\n",
+ "\n",
+ "Cost at iteration 1830 = 82.02248909329487\n",
+ "\n",
+ "Cost at iteration 1831 = 82.00187215916318\n",
+ "\n",
+ "Cost at iteration 1832 = 81.98125853770983\n",
+ "\n",
+ "Cost at iteration 1833 = 81.96064822871203\n",
+ "\n",
+ "Cost at iteration 1834 = 81.94004123194904\n",
+ "\n",
+ "Cost at iteration 1835 = 81.9194375472017\n",
+ "\n",
+ "Cost at iteration 1836 = 81.89883717425286\n",
+ "\n",
+ "Cost at iteration 1837 = 81.87824011288707\n",
+ "\n",
+ "Cost at iteration 1838 = 81.85764636289065\n",
+ "\n",
+ "Cost at iteration 1839 = 81.83705592405151\n",
+ "\n",
+ "Cost at iteration 1840 = 81.81646879615964\n",
+ "\n",
+ "Cost at iteration 1841 = 81.79588497900654\n",
+ "\n",
+ "Cost at iteration 1842 = 81.77530447238577\n",
+ "\n",
+ "Cost at iteration 1843 = 81.75472727609237\n",
+ "\n",
+ "Cost at iteration 1844 = 81.73415338992322\n",
+ "\n",
+ "Cost at iteration 1845 = 81.71358281367718\n",
+ "\n",
+ "Cost at iteration 1846 = 81.6930155471546\n",
+ "\n",
+ "Cost at iteration 1847 = 81.67245159015769\n",
+ "\n",
+ "Cost at iteration 1848 = 81.65189094249047\n",
+ "\n",
+ "Cost at iteration 1849 = 81.63133360395868\n",
+ "\n",
+ "Cost at iteration 1850 = 81.61077957436987\n",
+ "\n",
+ "Cost at iteration 1851 = 81.59022885353323\n",
+ "\n",
+ "Cost at iteration 1852 = 81.5696814412598\n",
+ "\n",
+ "Cost at iteration 1853 = 81.54913733736242\n",
+ "\n",
+ "Cost at iteration 1854 = 81.52859654165542\n",
+ "\n",
+ "Cost at iteration 1855 = 81.50805905395534\n",
+ "\n",
+ "Cost at iteration 1856 = 81.48752487408005\n",
+ "\n",
+ "Cost at iteration 1857 = 81.46699400184949\n",
+ "\n",
+ "Cost at iteration 1858 = 81.44646643708496\n",
+ "\n",
+ "Cost at iteration 1859 = 81.42594217960976\n",
+ "\n",
+ "Cost at iteration 1860 = 81.40542122924916\n",
+ "\n",
+ "Cost at iteration 1861 = 81.38490358582973\n",
+ "\n",
+ "Cost at iteration 1862 = 81.36438924918\n",
+ "\n",
+ "Cost at iteration 1863 = 81.34387821913006\n",
+ "\n",
+ "Cost at iteration 1864 = 81.32337049551224\n",
+ "\n",
+ "Cost at iteration 1865 = 81.30286607816006\n",
+ "\n",
+ "Cost at iteration 1866 = 81.28236496690896\n",
+ "\n",
+ "Cost at iteration 1867 = 81.26186716159607\n",
+ "\n",
+ "Cost at iteration 1868 = 81.24137266206056\n",
+ "\n",
+ "Cost at iteration 1869 = 81.2208814681429\n",
+ "\n",
+ "Cost at iteration 1870 = 81.20039357968548\n",
+ "\n",
+ "Cost at iteration 1871 = 81.17990899653263\n",
+ "\n",
+ "Cost at iteration 1872 = 81.15942771852984\n",
+ "\n",
+ "Cost at iteration 1873 = 81.13894974552495\n",
+ "\n",
+ "Cost at iteration 1874 = 81.1184750773672\n",
+ "\n",
+ "Cost at iteration 1875 = 81.09800371390759\n",
+ "\n",
+ "Cost at iteration 1876 = 81.07753565499891\n",
+ "\n",
+ "Cost at iteration 1877 = 81.05707090049548\n",
+ "\n",
+ "Cost at iteration 1878 = 81.03660945025362\n",
+ "\n",
+ "Cost at iteration 1879 = 81.01615130413116\n",
+ "\n",
+ "Cost at iteration 1880 = 80.99569646198786\n",
+ "\n",
+ "Cost at iteration 1881 = 80.97524492368494\n",
+ "\n",
+ "Cost at iteration 1882 = 80.95479668908536\n",
+ "\n",
+ "Cost at iteration 1883 = 80.93435175805399\n",
+ "\n",
+ "Cost at iteration 1884 = 80.91391013045721\n",
+ "\n",
+ "Cost at iteration 1885 = 80.89347180616345\n",
+ "\n",
+ "Cost at iteration 1886 = 80.87303678504222\n",
+ "\n",
+ "Cost at iteration 1887 = 80.8526050669653\n",
+ "\n",
+ "Cost at iteration 1888 = 80.83217665180617\n",
+ "\n",
+ "Cost at iteration 1889 = 80.81175153943941\n",
+ "\n",
+ "Cost at iteration 1890 = 80.7913297297421\n",
+ "\n",
+ "Cost at iteration 1891 = 80.77091122259226\n",
+ "\n",
+ "Cost at iteration 1892 = 80.75049601787046\n",
+ "\n",
+ "Cost at iteration 1893 = 80.73008411545817\n",
+ "\n",
+ "Cost at iteration 1894 = 80.70967551523887\n",
+ "\n",
+ "Cost at iteration 1895 = 80.68927021709798\n",
+ "\n",
+ "Cost at iteration 1896 = 80.66886822092223\n",
+ "\n",
+ "Cost at iteration 1897 = 80.64846952660001\n",
+ "\n",
+ "Cost at iteration 1898 = 80.62807413402193\n",
+ "\n",
+ "Cost at iteration 1899 = 80.60768204307978\n",
+ "\n",
+ "Cost at iteration 1900 = 80.58729325366734\n",
+ "\n",
+ "Cost at iteration 1901 = 80.56690776567959\n",
+ "\n",
+ "Cost at iteration 1902 = 80.54652557901375\n",
+ "\n",
+ "Cost at iteration 1903 = 80.52614669356872\n",
+ "\n",
+ "Cost at iteration 1904 = 80.50577110924448\n",
+ "\n",
+ "Cost at iteration 1905 = 80.48539882594332\n",
+ "\n",
+ "Cost at iteration 1906 = 80.46502984356886\n",
+ "\n",
+ "Cost at iteration 1907 = 80.44466416202671\n",
+ "\n",
+ "Cost at iteration 1908 = 80.42430178122383\n",
+ "\n",
+ "Cost at iteration 1909 = 80.40394270106884\n",
+ "\n",
+ "Cost at iteration 1910 = 80.38358692147239\n",
+ "\n",
+ "Cost at iteration 1911 = 80.3632344423464\n",
+ "\n",
+ "Cost at iteration 1912 = 80.34288526360493\n",
+ "\n",
+ "Cost at iteration 1913 = 80.32253938516314\n",
+ "\n",
+ "Cost at iteration 1914 = 80.30219680693827\n",
+ "\n",
+ "Cost at iteration 1915 = 80.28185752884909\n",
+ "\n",
+ "Cost at iteration 1916 = 80.26152155081594\n",
+ "\n",
+ "Cost at iteration 1917 = 80.24118887276127\n",
+ "\n",
+ "Cost at iteration 1918 = 80.22085949460833\n",
+ "\n",
+ "Cost at iteration 1919 = 80.20053341628291\n",
+ "\n",
+ "Cost at iteration 1920 = 80.18021063771207\n",
+ "\n",
+ "Cost at iteration 1921 = 80.15989115882432\n",
+ "\n",
+ "Cost at iteration 1922 = 80.13957497955022\n",
+ "\n",
+ "Cost at iteration 1923 = 80.119262099822\n",
+ "\n",
+ "Cost at iteration 1924 = 80.098952519573\n",
+ "\n",
+ "Cost at iteration 1925 = 80.07864623873897\n",
+ "\n",
+ "Cost at iteration 1926 = 80.05834325725651\n",
+ "\n",
+ "Cost at iteration 1927 = 80.03804357506478\n",
+ "\n",
+ "Cost at iteration 1928 = 80.01774719210341\n",
+ "\n",
+ "Cost at iteration 1929 = 79.99745410831493\n",
+ "\n",
+ "Cost at iteration 1930 = 79.97716432364271\n",
+ "\n",
+ "Cost at iteration 1931 = 79.956877838032\n",
+ "\n",
+ "Cost at iteration 1932 = 79.93659465142971\n",
+ "\n",
+ "Cost at iteration 1933 = 79.91631476378433\n",
+ "\n",
+ "Cost at iteration 1934 = 79.89603817504613\n",
+ "\n",
+ "Cost at iteration 1935 = 79.87576488516679\n",
+ "\n",
+ "Cost at iteration 1936 = 79.85549489409955\n",
+ "\n",
+ "Cost at iteration 1937 = 79.83522820179977\n",
+ "\n",
+ "Cost at iteration 1938 = 79.81496480822396\n",
+ "\n",
+ "Cost at iteration 1939 = 79.79470471333082\n",
+ "\n",
+ "Cost at iteration 1940 = 79.77444791707971\n",
+ "\n",
+ "Cost at iteration 1941 = 79.75419441943264\n",
+ "\n",
+ "Cost at iteration 1942 = 79.7339442203527\n",
+ "\n",
+ "Cost at iteration 1943 = 79.71369731980468\n",
+ "\n",
+ "Cost at iteration 1944 = 79.69345371775526\n",
+ "\n",
+ "Cost at iteration 1945 = 79.6732134141723\n",
+ "\n",
+ "Cost at iteration 1946 = 79.65297640902571\n",
+ "\n",
+ "Cost at iteration 1947 = 79.63274270228644\n",
+ "\n",
+ "Cost at iteration 1948 = 79.61251229392778\n",
+ "\n",
+ "Cost at iteration 1949 = 79.5922851839241\n",
+ "\n",
+ "Cost at iteration 1950 = 79.57206137225197\n",
+ "\n",
+ "Cost at iteration 1951 = 79.5518408588887\n",
+ "\n",
+ "Cost at iteration 1952 = 79.53162364381375\n",
+ "\n",
+ "Cost at iteration 1953 = 79.51140972700826\n",
+ "\n",
+ "Cost at iteration 1954 = 79.49119910845509\n",
+ "\n",
+ "Cost at iteration 1955 = 79.47099178813811\n",
+ "\n",
+ "Cost at iteration 1956 = 79.45078776604339\n",
+ "\n",
+ "Cost at iteration 1957 = 79.430587042158\n",
+ "\n",
+ "Cost at iteration 1958 = 79.41038961647145\n",
+ "\n",
+ "Cost at iteration 1959 = 79.39019548897446\n",
+ "\n",
+ "Cost at iteration 1960 = 79.37000465965865\n",
+ "\n",
+ "Cost at iteration 1961 = 79.34981712851831\n",
+ "\n",
+ "Cost at iteration 1962 = 79.32963289554911\n",
+ "\n",
+ "Cost at iteration 1963 = 79.30945196074754\n",
+ "\n",
+ "Cost at iteration 1964 = 79.28927432411265\n",
+ "\n",
+ "Cost at iteration 1965 = 79.26909998564453\n",
+ "\n",
+ "Cost at iteration 1966 = 79.24892894534494\n",
+ "\n",
+ "Cost at iteration 1967 = 79.22876120321752\n",
+ "\n",
+ "Cost at iteration 1968 = 79.20859675926722\n",
+ "\n",
+ "Cost at iteration 1969 = 79.18843561350037\n",
+ "\n",
+ "Cost at iteration 1970 = 79.1682777659256\n",
+ "\n",
+ "Cost at iteration 1971 = 79.14812321655229\n",
+ "\n",
+ "Cost at iteration 1972 = 79.12797196539209\n",
+ "\n",
+ "Cost at iteration 1973 = 79.10782401245756\n",
+ "\n",
+ "Cost at iteration 1974 = 79.08767935776356\n",
+ "\n",
+ "Cost at iteration 1975 = 79.06753800132617\n",
+ "\n",
+ "Cost at iteration 1976 = 79.04739994316287\n",
+ "\n",
+ "Cost at iteration 1977 = 79.02726518329278\n",
+ "\n",
+ "Cost at iteration 1978 = 79.00713372173729\n",
+ "\n",
+ "Cost at iteration 1979 = 78.98700555851843\n",
+ "\n",
+ "Cost at iteration 1980 = 78.96688069366002\n",
+ "\n",
+ "Cost at iteration 1981 = 78.9467591271879\n",
+ "\n",
+ "Cost at iteration 1982 = 78.92664085912917\n",
+ "\n",
+ "Cost at iteration 1983 = 78.90652588951217\n",
+ "\n",
+ "Cost at iteration 1984 = 78.8864142183676\n",
+ "\n",
+ "Cost at iteration 1985 = 78.86630584572698\n",
+ "\n",
+ "Cost at iteration 1986 = 78.84620077162363\n",
+ "\n",
+ "Cost at iteration 1987 = 78.82609899609272\n",
+ "\n",
+ "Cost at iteration 1988 = 78.80600051917065\n",
+ "\n",
+ "Cost at iteration 1989 = 78.78590534089545\n",
+ "\n",
+ "Cost at iteration 1990 = 78.76581346130666\n",
+ "\n",
+ "Cost at iteration 1991 = 78.74572488044589\n",
+ "\n",
+ "Cost at iteration 1992 = 78.72563959835517\n",
+ "\n",
+ "Cost at iteration 1993 = 78.70555761507924\n",
+ "\n",
+ "Cost at iteration 1994 = 78.6854789306638\n",
+ "\n",
+ "Cost at iteration 1995 = 78.6654035451564\n",
+ "\n",
+ "Cost at iteration 1996 = 78.64533145860555\n",
+ "\n",
+ "Cost at iteration 1997 = 78.62526267106213\n",
+ "\n",
+ "Cost at iteration 1998 = 78.60519718257801\n",
+ "\n",
+ "Cost at iteration 1999 = 78.58513499320681\n",
+ "\n",
+ "Cost at iteration 2000 = 78.56507610300345\n",
+ "\n",
+ "Root Mean Squared Error on Training Data = 12.533556599148145\n",
+ "Root Mean Squared Error on Test Data = 12.441166736948473\n"
+ ]
+ }
+ ],
+ "source": [
+ "df = pd.concat(pd.read_excel(\"data.xlsx\", sheet_name=None), ignore_index=True)\n",
+ "X = df[['AT','V', 'AP', 'RH']].values\n",
+ "Y=df['PE'].values\n",
+ "X_train,X_test,Y_train,Y_test = train_test_split(X, Y, test_size = 0.2) \n",
+ "layer_sizes = [4, 2, 1] \n",
+ "num_iters = 2000 \n",
+ "learning_rate = 0.05 \n",
+ "params = model(X_train, Y_train, layer_sizes, num_iters, learning_rate) \n",
+ "train_acc, test_acc = compute_accuracy(X_train, X_test, Y_train, Y_test, params) \n",
+ "print('Root Mean Squared Error on Training Data = ' + str(train_acc))\n",
+ "print('Root Mean Squared Error on Test Data = ' + str(test_acc))\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.5"
+ },
+ "orig_nbformat": 4,
+ "vscode": {
+ "interpreter": {
+ "hash": "027efd7095115064582efab50921964d678032cf36f1ec215c675cf4ffc5e6b9"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}