Pushing the docs to dev/ for branch: main, commit 68d8c2cfcc527ca194ad8ca377acca7a38502f98

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -80,7 +80,7 @@ def load_mtpl2(n_samples=None):
     df["ClaimAmount"] = df["ClaimAmount"].fillna(0)
 
     # unquote string fields
-    for column_name in df.columns[df.dtypes.values == object]:
+    for column_name in df.columns[[t is object for t in df.dtypes.values]]:
         df[column_name] = df[column_name].str.strip("'")
     return df.iloc[:n_samples]
 

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "from functools import partial\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.metrics import (\n    mean_absolute_error,\n    mean_squared_error,\n    mean_tweedie_deviance,\n)\n\n\ndef load_mtpl2(n_samples=None):\n    \"\"\"Fetch the French Motor Third-Party Liability Claims dataset.\n\n    Parameters\n    ----------\n    n_samples: int, default=None\n      number of samples to select (for faster run time). Full dataset has\n      678013 samples.\n    \"\"\"\n    # freMTPL2freq dataset from https://www.openml.org/d/41214\n    df_freq = fetch_openml(data_id=41214, as_frame=True).data\n    df_freq[\"IDpol\"] = df_freq[\"IDpol\"].astype(int)\n    df_freq.set_index(\"IDpol\", inplace=True)\n\n    # freMTPL2sev dataset from https://www.openml.org/d/41215\n    df_sev = fetch_openml(data_id=41215, as_frame=True).data\n\n    # sum ClaimAmount over identical IDs\n    df_sev = df_sev.groupby(\"IDpol\").sum()\n\n    df = df_freq.join(df_sev, how=\"left\")\n    df[\"ClaimAmount\"] = df[\"ClaimAmount\"].fillna(0)\n\n    # unquote string fields\n    for column_name in df.columns[df.dtypes.values == object]:\n        df[column_name] = df[column_name].str.strip(\"'\")\n    return df.iloc[:n_samples]\n\n\ndef plot_obs_pred(\n    df,\n    feature,\n    weight,\n    observed,\n    predicted,\n    y_label=None,\n    title=None,\n    ax=None,\n    fill_legend=False,\n):\n    \"\"\"Plot observed and predicted - aggregated per feature level.\n\n    Parameters\n    ----------\n    df : DataFrame\n        input data\n    feature: str\n        a column name of df for the feature to be plotted\n    weight : str\n        column name of df with the values of weights or exposure\n    observed : str\n        a column name of df with the observed target\n    predicted : DataFrame\n        a dataframe, with the same index as df, with the predicted target\n    fill_legend : bool, default=False\n        whether to show fill_between legend\n    \"\"\"\n    # aggregate observed and predicted variables by feature level\n    df_ = df.loc[:, [feature, weight]].copy()\n    df_[\"observed\"] = df[observed] * df[weight]\n    df_[\"predicted\"] = predicted * df[weight]\n    df_ = (\n        df_.groupby([feature])[[weight, \"observed\", \"predicted\"]]\n        .sum()\n        .assign(observed=lambda x: x[\"observed\"] / x[weight])\n        .assign(predicted=lambda x: x[\"predicted\"] / x[weight])\n    )\n\n    ax = df_.loc[:, [\"observed\", \"predicted\"]].plot(style=\".\", ax=ax)\n    y_max = df_.loc[:, [\"observed\", \"predicted\"]].values.max() * 0.8\n    p2 = ax.fill_between(\n        df_.index,\n        0,\n        y_max * df_[weight] / df_[weight].values.max(),\n        color=\"g\",\n        alpha=0.1,\n    )\n    if fill_legend:\n        ax.legend([p2], [\"{} distribution\".format(feature)])\n    ax.set(\n        ylabel=y_label if y_label is not None else None,\n        title=title if title is not None else \"Train: Observed vs Predicted\",\n    )\n\n\ndef score_estimator(\n    estimator,\n    X_train,\n    X_test,\n    df_train,\n    df_test,\n    target,\n    weights,\n    tweedie_powers=None,\n):\n    \"\"\"Evaluate an estimator on train and test sets with different metrics\"\"\"\n\n    metrics = [\n        (\"D\u00b2 explained\", None),  # Use default scorer if it exists\n        (\"mean abs. error\", mean_absolute_error),\n        (\"mean squared error\", mean_squared_error),\n    ]\n    if tweedie_powers:\n        metrics += [\n            (\n                \"mean Tweedie dev p={:.4f}\".format(power),\n                partial(mean_tweedie_deviance, power=power),\n            )\n            for power in tweedie_powers\n        ]\n\n    res = []\n    for subset_label, X, df in [\n        (\"train\", X_train, df_train),\n        (\"test\", X_test, df_test),\n    ]:\n        y, _weights = df[target], df[weights]\n        for score_label, metric in metrics:\n            if isinstance(estimator, tuple) and len(estimator) == 2:\n                # Score the model consisting of the product of frequency and\n                # severity models.\n                est_freq, est_sev = estimator\n                y_pred = est_freq.predict(X) * est_sev.predict(X)\n            else:\n                y_pred = estimator.predict(X)\n\n            if metric is None:\n                if not hasattr(estimator, \"score\"):\n                    continue\n                score = estimator.score(X, y, sample_weight=_weights)\n            else:\n                score = metric(y, y_pred, sample_weight=_weights)\n\n            res.append({\"subset\": subset_label, \"metric\": score_label, \"score\": score})\n\n    res = (\n        pd.DataFrame(res)\n        .set_index([\"metric\", \"subset\"])\n        .score.unstack(-1)\n        .round(4)\n        .loc[:, [\"train\", \"test\"]]\n    )\n    return res"
+        "from functools import partial\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.metrics import (\n    mean_absolute_error,\n    mean_squared_error,\n    mean_tweedie_deviance,\n)\n\n\ndef load_mtpl2(n_samples=None):\n    \"\"\"Fetch the French Motor Third-Party Liability Claims dataset.\n\n    Parameters\n    ----------\n    n_samples: int, default=None\n      number of samples to select (for faster run time). Full dataset has\n      678013 samples.\n    \"\"\"\n    # freMTPL2freq dataset from https://www.openml.org/d/41214\n    df_freq = fetch_openml(data_id=41214, as_frame=True).data\n    df_freq[\"IDpol\"] = df_freq[\"IDpol\"].astype(int)\n    df_freq.set_index(\"IDpol\", inplace=True)\n\n    # freMTPL2sev dataset from https://www.openml.org/d/41215\n    df_sev = fetch_openml(data_id=41215, as_frame=True).data\n\n    # sum ClaimAmount over identical IDs\n    df_sev = df_sev.groupby(\"IDpol\").sum()\n\n    df = df_freq.join(df_sev, how=\"left\")\n    df[\"ClaimAmount\"] = df[\"ClaimAmount\"].fillna(0)\n\n    # unquote string fields\n    for column_name in df.columns[[t is object for t in df.dtypes.values]]:\n        df[column_name] = df[column_name].str.strip(\"'\")\n    return df.iloc[:n_samples]\n\n\ndef plot_obs_pred(\n    df,\n    feature,\n    weight,\n    observed,\n    predicted,\n    y_label=None,\n    title=None,\n    ax=None,\n    fill_legend=False,\n):\n    \"\"\"Plot observed and predicted - aggregated per feature level.\n\n    Parameters\n    ----------\n    df : DataFrame\n        input data\n    feature: str\n        a column name of df for the feature to be plotted\n    weight : str\n        column name of df with the values of weights or exposure\n    observed : str\n        a column name of df with the observed target\n    predicted : DataFrame\n        a dataframe, with the same index as df, with the predicted target\n    fill_legend : bool, default=False\n        whether to show fill_between legend\n    \"\"\"\n    # aggregate observed and predicted variables by feature level\n    df_ = df.loc[:, [feature, weight]].copy()\n    df_[\"observed\"] = df[observed] * df[weight]\n    df_[\"predicted\"] = predicted * df[weight]\n    df_ = (\n        df_.groupby([feature])[[weight, \"observed\", \"predicted\"]]\n        .sum()\n        .assign(observed=lambda x: x[\"observed\"] / x[weight])\n        .assign(predicted=lambda x: x[\"predicted\"] / x[weight])\n    )\n\n    ax = df_.loc[:, [\"observed\", \"predicted\"]].plot(style=\".\", ax=ax)\n    y_max = df_.loc[:, [\"observed\", \"predicted\"]].values.max() * 0.8\n    p2 = ax.fill_between(\n        df_.index,\n        0,\n        y_max * df_[weight] / df_[weight].values.max(),\n        color=\"g\",\n        alpha=0.1,\n    )\n    if fill_legend:\n        ax.legend([p2], [\"{} distribution\".format(feature)])\n    ax.set(\n        ylabel=y_label if y_label is not None else None,\n        title=title if title is not None else \"Train: Observed vs Predicted\",\n    )\n\n\ndef score_estimator(\n    estimator,\n    X_train,\n    X_test,\n    df_train,\n    df_test,\n    target,\n    weights,\n    tweedie_powers=None,\n):\n    \"\"\"Evaluate an estimator on train and test sets with different metrics\"\"\"\n\n    metrics = [\n        (\"D\u00b2 explained\", None),  # Use default scorer if it exists\n        (\"mean abs. error\", mean_absolute_error),\n        (\"mean squared error\", mean_squared_error),\n    ]\n    if tweedie_powers:\n        metrics += [\n            (\n                \"mean Tweedie dev p={:.4f}\".format(power),\n                partial(mean_tweedie_deviance, power=power),\n            )\n            for power in tweedie_powers\n        ]\n\n    res = []\n    for subset_label, X, df in [\n        (\"train\", X_train, df_train),\n        (\"test\", X_test, df_test),\n    ]:\n        y, _weights = df[target], df[weights]\n        for score_label, metric in metrics:\n            if isinstance(estimator, tuple) and len(estimator) == 2:\n                # Score the model consisting of the product of frequency and\n                # severity models.\n                est_freq, est_sev = estimator\n                y_pred = est_freq.predict(X) * est_sev.predict(X)\n            else:\n                y_pred = estimator.predict(X)\n\n            if metric is None:\n                if not hasattr(estimator, \"score\"):\n                    continue\n                score = estimator.score(X, y, sample_weight=_weights)\n            else:\n                score = metric(y, y_pred, sample_weight=_weights)\n\n            res.append({\"subset\": subset_label, \"metric\": score_label, \"score\": score})\n\n    res = (\n        pd.DataFrame(res)\n        .set_index([\"metric\", \"subset\"])\n        .score.unstack(-1)\n        .round(4)\n        .loc[:, [\"train\", \"test\"]]\n    )\n    return res"
       ]
     },
     {