-# Investigating interhemispheric precipitation changes over the past millennium¶
+# Investigating interhemispheric precipitation changes over the past millennium
[](https://github.com/ProjectPythia/paleoPCA-Cookbook/actions/workflows/nightly-build.yaml)
[](https://binder.projectpythia.org/v2/gh/ProjectPythia/paleoPCA-Cookbook/main?labpath=notebooks)
diff --git a/notebooks/.virtual_documents/notebook-template.ipynb b/notebooks/.virtual_documents/notebook-template.ipynb
index 7723c17..0cc8d09 100644
--- a/notebooks/.virtual_documents/notebook-template.ipynb
+++ b/notebooks/.virtual_documents/notebook-template.ipynb
@@ -230,17 +230,26 @@ SELECT distinct?varID ?dataSetName ?lat ?lon ?varname ?interpLabel ?val ?varunit
response = requests.post(url, data = {'query': query})
data = io.StringIO(response.text)
-df = pd.read_csv(data, sep=",")
+df_res = pd.read_csv(data, sep=",")
-df['val']=df['val'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)
-df['timeval']=df['timeval'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)
+df_res['val']=df_res['val'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)
+df_res['timeval']=df_res['timeval'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)
-df.head()
+df_res.head()
+len(df_res)
+
+
+
+
+
+df = df_res[~df_res['varID'].duplicated()]
+
+
len(df)
@@ -298,7 +307,6 @@ def array_range_exceeds(array, threshold=1500):
return np.max(array) - np.min(array) > threshold
filt_df = filtered_df[filtered_df['timeval'].apply(array_range_exceeds)]
-filt_df.head()
@@ -358,7 +366,8 @@ mgs.map()
-mgs.sel(time=slice(0,2000)).stackplot(v_shift_factor=2.5)
+fig, ax = mgs.sel(time=slice(0,2000)).stackplot(v_shift_factor=1.2)
+plt.show(fig)
@@ -404,3 +413,6 @@ pca.modeplot(index=2)
+
+
+
diff --git a/notebooks/paleoPCA.ipynb b/notebooks/paleoPCA.ipynb
index 2deb6c7..c8d26c2 100644
--- a/notebooks/paleoPCA.ipynb
+++ b/notebooks/paleoPCA.ipynb
@@ -977,7 +977,7 @@
"\n",
"The database uses the SPARQL language for queries. We are filtering the database for the following criteria:\n",
"* Datasets bounded by 27°S-27°N and 70°W-150°W\n",
- "* Datasets from the [Pages2k](https://lipdverse.org/project/pages2k/), [Iso2k](https://lipdverse.org/project/iso2k/), CoralHydro2k and SISAL working groups. These working groups identified archived datasets that were sensitive to temperature and the isotopic composition of precipication (precipitation $\\delta{18}$O) and curated them for use in a standardized database.\n",
+ "* Datasets from the [Pages2k](https://lipdverse.org/project/pages2k/), [Iso2k](https://lipdverse.org/project/iso2k/), [CoralHydro2k](https://essd.copernicus.org/articles/15/2081/2023/essd-15-2081-2023-discussion.html) and [SISAL](https://essd.copernicus.org/articles/12/2579/2020/) working groups. These working groups identified archived datasets that were sensitive to temperature and the isotopic composition of precipication (precipitation $\\delta{18}$O) and curated them for use in a standardized database.\n",
"* Timeseries within these datasets representing precipitation.\n",
"\n",
"We asked for the following information back:\n",
@@ -993,7 +993,7 @@
},
{
"cell_type": "code",
- "execution_count": 73,
+ "execution_count": 224,
"metadata": {},
"outputs": [],
"source": [
@@ -1051,7 +1051,7 @@
},
{
"cell_type": "code",
- "execution_count": 179,
+ "execution_count": 225,
"metadata": {},
"outputs": [
{
@@ -1192,7 +1192,7 @@
"4 [-1905513, -1903265, -1900455, -1897645, -1894... yr AD Speleothem "
]
},
- "execution_count": 179,
+ "execution_count": 225,
"metadata": {},
"output_type": "execute_result"
}
@@ -1201,12 +1201,12 @@
"response = requests.post(url, data = {'query': query})\n",
"\n",
"data = io.StringIO(response.text)\n",
- "df = pd.read_csv(data, sep=\",\")\n",
+ "df_res = pd.read_csv(data, sep=\",\")\n",
"\n",
- "df['val']=df['val'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)\n",
- "df['timeval']=df['timeval'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)\n",
+ "df_res['val']=df_res['val'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)\n",
+ "df_res['timeval']=df_res['timeval'].apply(lambda row : json.loads(row) if isinstance(row, str) else row)\n",
"\n",
- "df.head()"
+ "df_res.head()"
]
},
{
@@ -1218,7 +1218,7 @@
},
{
"cell_type": "code",
- "execution_count": 118,
+ "execution_count": 226,
"metadata": {},
"outputs": [
{
@@ -1227,7 +1227,43 @@
"106"
]
},
- "execution_count": 118,
+ "execution_count": 226,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(df_res)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Make sure we have unique timeseries (some may be found across compilations): "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 228,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = df_res[~df_res['varID'].duplicated()]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 229,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "44"
+ ]
+ },
+ "execution_count": 229,
"metadata": {},
"output_type": "execute_result"
}
@@ -1245,7 +1281,7 @@
},
{
"cell_type": "code",
- "execution_count": 103,
+ "execution_count": 230,
"metadata": {},
"outputs": [
{
@@ -1254,7 +1290,7 @@
"array(['year', 'age'], dtype=object)"
]
},
- "execution_count": 103,
+ "execution_count": 230,
"metadata": {},
"output_type": "execute_result"
}
@@ -1272,7 +1308,7 @@
},
{
"cell_type": "code",
- "execution_count": 104,
+ "execution_count": 231,
"metadata": {},
"outputs": [
{
@@ -1281,7 +1317,7 @@
"array(['yr AD', 'yr BP'], dtype=object)"
]
},
- "execution_count": 104,
+ "execution_count": 231,
"metadata": {},
"output_type": "execute_result"
}
@@ -1299,7 +1335,7 @@
},
{
"cell_type": "code",
- "execution_count": 180,
+ "execution_count": 232,
"metadata": {},
"outputs": [],
"source": [
@@ -1324,7 +1360,7 @@
},
{
"cell_type": "code",
- "execution_count": 181,
+ "execution_count": 233,
"metadata": {},
"outputs": [],
"source": [
@@ -1348,16 +1384,16 @@
},
{
"cell_type": "code",
- "execution_count": 182,
+ "execution_count": 234,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "44"
+ "17"
]
},
- "execution_count": 182,
+ "execution_count": 234,
"metadata": {},
"output_type": "execute_result"
}
@@ -1375,165 +1411,14 @@
},
{
"cell_type": "code",
- "execution_count": 183,
+ "execution_count": 235,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "| \n", - " | varID | \n", - "dataSetName | \n", - "lat | \n", - "lon | \n", - "varname | \n", - "interpLabel | \n", - "val | \n", - "varunits | \n", - "timevarname | \n", - "timeval | \n", - "timeunits | \n", - "archiveType | \n", - "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 12 | \n", - "IC95THHU02D | \n", - "IC95THHU | \n", - "-9.0000 | \n", - "-77.5000 | \n", - "d18O | \n", - "precipitationIsotope | \n", - "[-17.38, -17.24, -18.3, -19.1, -19.34, -19.2, ... | \n", - "permil | \n", - "year | \n", - "[1950, 1850, 1750, 1650, 1550, 1450, 1350, 125... | \n", - "yr AD | \n", - "Glacier ice | \n", - "
| 13 | \n", - "SP13CHPE01A | \n", - "SP13CHPE | \n", - "-5.9300 | \n", - "-77.3000 | \n", - "d18O | \n", - "precipitationIsotope | \n", - "[-7.17, -7.24, nan, -6.99, -7.15, -7.41, -7.31... | \n", - "permil | \n", - "year | \n", - "[1660, 1650, 1650, 1640, 1630, 1630, 1620, 161... | \n", - "yr AD | \n", - "Speleothem | \n", - "
| 14 | \n", - "SP13CHPE01A | \n", - "SP13CHPE | \n", - "-5.9300 | \n", - "-77.3000 | \n", - "d18O | \n", - "Precipitation_amount, SAM | \n", - "[-7.17, -7.24, nan, -6.99, -7.15, -7.41, -7.31... | \n", - "permil | \n", - "year | \n", - "[1660, 1650, 1650, 1640, 1630, 1630, 1620, 161... | \n", - "yr AD | \n", - "Speleothem | \n", - "
| 17 | \n", - "SAm_035 | \n", - "IC13THQU | \n", - "-13.9333 | \n", - "-70.8333 | \n", - "d18O | \n", - "precipitationIsotope | \n", - "[-18.5905, -16.3244, -16.2324, -17.0112, -18.6... | \n", - "permil | \n", - "year | \n", - "[2009, 2008, 2007, 2006, 2005, 2004, 2003, 200... | \n", - "yr AD | \n", - "Glacier ice | \n", - "
| 20 | \n", - "SP08VBPE03A | \n", - "SP08VBPE | \n", - "-5.9400 | \n", - "-77.3100 | \n", - "d18O | \n", - "precipitationIsotope | \n", - "[-6.09, -6.74, -6.37, -6.91, -6.57, nan, -5.64... | \n", - "permil | \n", - "year | \n", - "[1915, 513, 81, -911, -1405, -2192, -3477, -42... | \n", - "yr AD | \n", - "Speleothem | \n", - "