Pushing the docs to dev/ for branch: main, commit e82550268fce38b38c09d90483cdef8c9bde846f

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -33,32 +33,34 @@
 # We will derive a dataset from the Mauna Loa Observatory that collected air
 # samples. We are interested in estimating the concentration of CO2 and
 # extrapolate it for further year. First, we load the original dataset available
-# in OpenML.
+# in OpenML as a pandas dataframe. This will be replaced with Polars
+# once `fetch_openml` adds a native support for it.
 from sklearn.datasets import fetch_openml
 
 co2 = fetch_openml(data_id=41187, as_frame=True)
 co2.frame.head()
 
 # %%
-# First, we process the original dataframe to create a date index and select
-# only the CO2 column.
-import pandas as pd
+# First, we process the original dataframe to create a date column and select
+# it along with the CO2 column.
+import polars as pl
 
-co2_data = co2.frame
-co2_data["date"] = pd.to_datetime(co2_data[["year", "month", "day"]])
-co2_data = co2_data[["date", "co2"]].set_index("date")
+co2_data = pl.DataFrame(co2.frame[["year", "month", "day", "co2"]]).select(
+    pl.date("year", "month", "day"), "co2"
+)
 co2_data.head()
 
 # %%
-co2_data.index.min(), co2_data.index.max()
+co2_data["date"].min(), co2_data["date"].max()
 
 # %%
 # We see that we get CO2 concentration for some days from March, 1958 to
 # December, 2001. We can plot these raw information to have a better
 # understanding.
 import matplotlib.pyplot as plt
 
-co2_data.plot()
+plt.plot(co2_data["date"], co2_data["co2"])
+plt.xlabel("date")
 plt.ylabel("CO$_2$ concentration (ppm)")
 _ = plt.title("Raw air samples measurements from the Mauna Loa Observatory")
 
@@ -67,15 +69,14 @@
 # for which no measurements were collected. Such a processing will have an
 # smoothing effect on the data.
 
-try:
-    co2_data_resampled_monthly = co2_data.resample("ME")
-except ValueError:
-    # pandas < 2.2 uses M instead of ME
-    co2_data_resampled_monthly = co2_data.resample("M")
-
-
-co2_data = co2_data_resampled_monthly.mean().dropna(axis="index", how="any")
-co2_data.plot()
+co2_data = (
+    co2_data.sort(by="date")
+    .group_by_dynamic("date", every="1mo")
+    .agg(pl.col("co2").mean())
+    .drop_nulls()
+)
+plt.plot(co2_data["date"], co2_data["co2"])
+plt.xlabel("date")
 plt.ylabel("Monthly average of CO$_2$ concentration (ppm)")
 _ = plt.title(
     "Monthly average of air samples measurements\nfrom the Mauna Loa Observatory"
@@ -88,7 +89,9 @@
 #
 # As a first step, we will divide the data and the target to estimate. The data
 # being a date, we will convert it into a numeric.
-X = (co2_data.index.year + co2_data.index.month / 12).to_numpy().reshape(-1, 1)
+X = co2_data.select(
+    pl.col("date").dt.year() + pl.col("date").dt.month() / 12
+).to_numpy()
 y = co2_data["co2"].to_numpy()
 
 # %%

dev/_downloads/1b8827af01c9a70017a4739bcf2e21a8/plot_gpr_co2.py

@@ -22,7 +22,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Build the dataset\n\nWe will derive a dataset from the Mauna Loa Observatory that collected air\nsamples. We are interested in estimating the concentration of CO2 and\nextrapolate it for further year. First, we load the original dataset available\nin OpenML.\n\n"
+        "## Build the dataset\n\nWe will derive a dataset from the Mauna Loa Observatory that collected air\nsamples. We are interested in estimating the concentration of CO2 and\nextrapolate it for further year. First, we load the original dataset available\nin OpenML as a pandas dataframe. This will be replaced with Polars\nonce `fetch_openml` adds a native support for it.\n\n"
       ]
     },
     {
@@ -40,7 +40,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "First, we process the original dataframe to create a date index and select\nonly the CO2 column.\n\n"
+        "First, we process the original dataframe to create a date column and select\nit along with the CO2 column.\n\n"
       ]
     },
     {
@@ -51,7 +51,7 @@
       },
       "outputs": [],
       "source": [
-        "import pandas as pd\n\nco2_data = co2.frame\nco2_data[\"date\"] = pd.to_datetime(co2_data[[\"year\", \"month\", \"day\"]])\nco2_data = co2_data[[\"date\", \"co2\"]].set_index(\"date\")\nco2_data.head()"
+        "import polars as pl\n\nco2_data = pl.DataFrame(co2.frame[[\"year\", \"month\", \"day\", \"co2\"]]).select(\n    pl.date(\"year\", \"month\", \"day\"), \"co2\"\n)\nco2_data.head()"
       ]
     },
     {
@@ -62,7 +62,7 @@
       },
       "outputs": [],
       "source": [
-        "co2_data.index.min(), co2_data.index.max()"
+        "co2_data[\"date\"].min(), co2_data[\"date\"].max()"
       ]
     },
     {
@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nco2_data.plot()\nplt.ylabel(\"CO$_2$ concentration (ppm)\")\n_ = plt.title(\"Raw air samples measurements from the Mauna Loa Observatory\")"
+        "import matplotlib.pyplot as plt\n\nplt.plot(co2_data[\"date\"], co2_data[\"co2\"])\nplt.xlabel(\"date\")\nplt.ylabel(\"CO$_2$ concentration (ppm)\")\n_ = plt.title(\"Raw air samples measurements from the Mauna Loa Observatory\")"
       ]
     },
     {
@@ -98,7 +98,7 @@
       },
       "outputs": [],
       "source": [
-        "try:\n    co2_data_resampled_monthly = co2_data.resample(\"ME\")\nexcept ValueError:\n    # pandas < 2.2 uses M instead of ME\n    co2_data_resampled_monthly = co2_data.resample(\"M\")\n\n\nco2_data = co2_data_resampled_monthly.mean().dropna(axis=\"index\", how=\"any\")\nco2_data.plot()\nplt.ylabel(\"Monthly average of CO$_2$ concentration (ppm)\")\n_ = plt.title(\n    \"Monthly average of air samples measurements\\nfrom the Mauna Loa Observatory\"\n)"
+        "co2_data = (\n    co2_data.sort(by=\"date\")\n    .group_by_dynamic(\"date\", every=\"1mo\")\n    .agg(pl.col(\"co2\").mean())\n    .drop_nulls()\n)\nplt.plot(co2_data[\"date\"], co2_data[\"co2\"])\nplt.xlabel(\"date\")\nplt.ylabel(\"Monthly average of CO$_2$ concentration (ppm)\")\n_ = plt.title(\n    \"Monthly average of air samples measurements\\nfrom the Mauna Loa Observatory\"\n)"
       ]
     },
     {
@@ -116,7 +116,7 @@
       },
       "outputs": [],
       "source": [
-        "X = (co2_data.index.year + co2_data.index.month / 12).to_numpy().reshape(-1, 1)\ny = co2_data[\"co2\"].to_numpy()"
+        "X = co2_data.select(\n    pl.col(\"date\").dt.year() + pl.col(\"date\").dt.month() / 12\n).to_numpy()\ny = co2_data[\"co2\"].to_numpy()"
       ]
     },
     {