Create stock_selection.ipynb

AI4Finance-Foundation · Oct 23, 2022 · 1a6a261 · 1a6a261
1 parent 2884984
commit 1a6a261
Showing 1 changed file with 200 additions and 0 deletions.
diff --git a/stock_selection.ipynb b/stock_selection.ipynb
@@ -0,0 +1,200 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import time\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sectors = range(10, 65, 5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#gvkey is unique identifier\n",
+    "df_dict = {'gvkey':[], 'predicted_return':[], 'trade_date':[]}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "start=time.time()\n",
+    "for sector in sectors:\n",
+    "    os.system(f\"python3 fundamental_run_model.py -sector_name sector{sector} -tic_column gvkey -fundamental final_ratios.csv -sector sector{sector}.xlsx \")\n",
+    "    df = pd.read_csv(f\"results/sector{sector}/df_predict_best.csv\", index_col=0)\n",
+    "    for idx in df.index:\n",
+    "        predicted_return = df.loc[idx]\n",
+    "        top_q = predicted_return.quantile(0.75)\n",
+    "        predicted_return = predicted_return[predicted_return >= top_q]\n",
+    "        for gvkey in predicted_return.index:\n",
+    "            df_dict[\"gvkey\"].append(gvkey)\n",
+    "            df_dict[\"predicted_return\"].append(predicted_return[gvkey])\n",
+    "            df_dict[\"trade_date\"].append(idx)\n",
+    "end=time.time()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "it took  0.40141645272572835  minutes\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"it took \", (end-start)/60, ' minutes')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_result = pd.DataFrame(df_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_result.to_csv(\"stock_selected.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>gvkey</th>\n",
+       "      <th>predicted_return</th>\n",
+       "      <th>trade_date</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2991</td>\n",
+       "      <td>-0.000871</td>\n",
+       "      <td>2001-03-01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4430</td>\n",
+       "      <td>0.001057</td>\n",
+       "      <td>2001-03-01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7017</td>\n",
+       "      <td>-0.001656</td>\n",
+       "      <td>2001-03-01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7912</td>\n",
+       "      <td>0.002009</td>\n",
+       "      <td>2001-03-01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8068</td>\n",
+       "      <td>-0.000118</td>\n",
+       "      <td>2001-03-01</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  gvkey  predicted_return  trade_date\n",
+       "0  2991         -0.000871  2001-03-01\n",
+       "1  4430          0.001057  2001-03-01\n",
+       "2  7017         -0.001656  2001-03-01\n",
+       "3  7912          0.002009  2001-03-01\n",
+       "4  8068         -0.000118  2001-03-01"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_result.head()"
+   ]
+  }
+ ],
+ "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": "3.7.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}