Pushing the docs to dev/ for branch: main, commit a3abdbb35d0429ac7f32d6eac4fe0b7e2447c65e

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -42,7 +42,11 @@
 preprocessor = ColumnTransformer(
     [
         ("scaler", StandardScaler(), sepal_cols),
-        ("kbin", KBinsDiscretizer(encode="ordinal"), petal_cols),
+        (
+            "kbin",
+            KBinsDiscretizer(encode="ordinal", quantile_method="averaged_inverted_cdf"),
+            petal_cols,
+        ),
     ],
     verbose_feature_names_out=False,
 ).set_output(transform="pandas")

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import (\n    FunctionTransformer,\n    KBinsDiscretizer,\n    OneHotEncoder,\n    StandardScaler,\n)\n\nlog_scale_transformer = make_pipeline(\n    FunctionTransformer(np.log, validate=False), StandardScaler()\n)\n\nlinear_model_preprocessor = ColumnTransformer(\n    [\n        (\"passthrough_numeric\", \"passthrough\", [\"BonusMalus\"]),\n        (\n            \"binned_numeric\",\n            KBinsDiscretizer(n_bins=10, random_state=0),\n            [\"VehAge\", \"DrivAge\"],\n        ),\n        (\"log_scaled_numeric\", log_scale_transformer, [\"Density\"]),\n        (\n            \"onehot_categorical\",\n            OneHotEncoder(),\n            [\"VehBrand\", \"VehPower\", \"VehGas\", \"Region\", \"Area\"],\n        ),\n    ],\n    remainder=\"drop\",\n)"
+        "from sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import (\n    FunctionTransformer,\n    KBinsDiscretizer,\n    OneHotEncoder,\n    StandardScaler,\n)\n\nlog_scale_transformer = make_pipeline(\n    FunctionTransformer(np.log, validate=False), StandardScaler()\n)\n\nlinear_model_preprocessor = ColumnTransformer(\n    [\n        (\"passthrough_numeric\", \"passthrough\", [\"BonusMalus\"]),\n        (\n            \"binned_numeric\",\n            KBinsDiscretizer(\n                n_bins=10, quantile_method=\"averaged_inverted_cdf\", random_state=0\n            ),\n            [\"VehAge\", \"DrivAge\"],\n        ),\n        (\"log_scaled_numeric\", log_scale_transformer, [\"Density\"]),\n        (\n            \"onehot_categorical\",\n            OneHotEncoder(),\n            [\"VehBrand\", \"VehPower\", \"VehGas\", \"Region\", \"Area\"],\n        ),\n    ],\n    remainder=\"drop\",\n)"
       ]
     },
     {

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -76,7 +76,12 @@
     i += 1
     # transform the dataset with KBinsDiscretizer
     for strategy in strategies:
-        enc = KBinsDiscretizer(n_bins=4, encode="ordinal", strategy=strategy)
+        enc = KBinsDiscretizer(
+            n_bins=4,
+            encode="ordinal",
+            quantile_method="averaged_inverted_cdf",
+            strategy=strategy,
+        )
         enc.fit(X)
         grid_encoded = enc.transform(grid)
 

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -44,7 +44,9 @@
 X = X.reshape(-1, 1)
 
 # transform the dataset with KBinsDiscretizer
-enc = KBinsDiscretizer(n_bins=10, encode="onehot")
+enc = KBinsDiscretizer(
+    n_bins=10, encode="onehot", quantile_method="averaged_inverted_cdf"
+)
 X_binned = enc.fit_transform(X)
 
 # predict with original dataset

dev/_downloads/04b9a7769df5b331f4d94e1d065b4311/plot_voting_decision_regions.zip

@@ -72,7 +72,9 @@ def get_name(estimator):
     (
         make_pipeline(
             StandardScaler(),
-            KBinsDiscretizer(encode="onehot", random_state=0),
+            KBinsDiscretizer(
+                encode="onehot", quantile_method="averaged_inverted_cdf", random_state=0
+            ),
             LogisticRegression(random_state=0),
         ),
         {
@@ -83,7 +85,9 @@ def get_name(estimator):
     (
         make_pipeline(
             StandardScaler(),
-            KBinsDiscretizer(encode="onehot", random_state=0),
+            KBinsDiscretizer(
+                encode="onehot", quantile_method="averaged_inverted_cdf", random_state=0
+            ),
             LinearSVC(random_state=0),
         ),
         {

dev/_downloads/053b58bbfc8177072856c743b2c93424/plot_varimax_fa.zip

@@ -239,7 +239,9 @@ def score_estimator(
     [
         (
             "binned_numeric",
-            KBinsDiscretizer(n_bins=10, random_state=0),
+            KBinsDiscretizer(
+                n_bins=10, quantile_method="averaged_inverted_cdf", random_state=0
+            ),
             ["VehAge", "DrivAge"],
         ),
         (
@@ -689,8 +691,7 @@ def lorenz_curve(y_true, y_pred, exposure):
 ax.set(
     title="Lorenz Curves",
     xlabel=(
-        "Cumulative proportion of exposure\n"
-        "(ordered by model from safest to riskiest)"
+        "Cumulative proportion of exposure\n(ordered by model from safest to riskiest)"
     ),
     ylabel="Cumulative proportion of claim amounts",
 )

dev/_downloads/06c18f4675ecd124f98537d05e10abd0/plot_nca_dim_reduction.zip

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import (\n    FunctionTransformer,\n    KBinsDiscretizer,\n    OneHotEncoder,\n    StandardScaler,\n)\n\ndf = load_mtpl2()\n\n\n# Correct for unreasonable observations (that might be data error)\n# and a few exceptionally large claim amounts\ndf[\"ClaimNb\"] = df[\"ClaimNb\"].clip(upper=4)\ndf[\"Exposure\"] = df[\"Exposure\"].clip(upper=1)\ndf[\"ClaimAmount\"] = df[\"ClaimAmount\"].clip(upper=200000)\n# If the claim amount is 0, then we do not count it as a claim. The loss function\n# used by the severity model needs strictly positive claim amounts. This way\n# frequency and severity are more consistent with each other.\ndf.loc[(df[\"ClaimAmount\"] == 0) & (df[\"ClaimNb\"] >= 1), \"ClaimNb\"] = 0\n\nlog_scale_transformer = make_pipeline(\n    FunctionTransformer(func=np.log), StandardScaler()\n)\n\ncolumn_trans = ColumnTransformer(\n    [\n        (\n            \"binned_numeric\",\n            KBinsDiscretizer(n_bins=10, random_state=0),\n            [\"VehAge\", \"DrivAge\"],\n        ),\n        (\n            \"onehot_categorical\",\n            OneHotEncoder(),\n            [\"VehBrand\", \"VehPower\", \"VehGas\", \"Region\", \"Area\"],\n        ),\n        (\"passthrough_numeric\", \"passthrough\", [\"BonusMalus\"]),\n        (\"log_scaled_numeric\", log_scale_transformer, [\"Density\"]),\n    ],\n    remainder=\"drop\",\n)\nX = column_trans.fit_transform(df)\n\n# Insurances companies are interested in modeling the Pure Premium, that is\n# the expected total claim amount per unit of exposure for each policyholder\n# in their portfolio:\ndf[\"PurePremium\"] = df[\"ClaimAmount\"] / df[\"Exposure\"]\n\n# This can be indirectly approximated by a 2-step modeling: the product of the\n# Frequency times the average claim amount per claim:\ndf[\"Frequency\"] = df[\"ClaimNb\"] / df[\"Exposure\"]\ndf[\"AvgClaimAmount\"] = df[\"ClaimAmount\"] / np.fmax(df[\"ClaimNb\"], 1)\n\nwith pd.option_context(\"display.max_columns\", 15):\n    print(df[df.ClaimAmount > 0].head())"
+        "from sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import (\n    FunctionTransformer,\n    KBinsDiscretizer,\n    OneHotEncoder,\n    StandardScaler,\n)\n\ndf = load_mtpl2()\n\n\n# Correct for unreasonable observations (that might be data error)\n# and a few exceptionally large claim amounts\ndf[\"ClaimNb\"] = df[\"ClaimNb\"].clip(upper=4)\ndf[\"Exposure\"] = df[\"Exposure\"].clip(upper=1)\ndf[\"ClaimAmount\"] = df[\"ClaimAmount\"].clip(upper=200000)\n# If the claim amount is 0, then we do not count it as a claim. The loss function\n# used by the severity model needs strictly positive claim amounts. This way\n# frequency and severity are more consistent with each other.\ndf.loc[(df[\"ClaimAmount\"] == 0) & (df[\"ClaimNb\"] >= 1), \"ClaimNb\"] = 0\n\nlog_scale_transformer = make_pipeline(\n    FunctionTransformer(func=np.log), StandardScaler()\n)\n\ncolumn_trans = ColumnTransformer(\n    [\n        (\n            \"binned_numeric\",\n            KBinsDiscretizer(\n                n_bins=10, quantile_method=\"averaged_inverted_cdf\", random_state=0\n            ),\n            [\"VehAge\", \"DrivAge\"],\n        ),\n        (\n            \"onehot_categorical\",\n            OneHotEncoder(),\n            [\"VehBrand\", \"VehPower\", \"VehGas\", \"Region\", \"Area\"],\n        ),\n        (\"passthrough_numeric\", \"passthrough\", [\"BonusMalus\"]),\n        (\"log_scaled_numeric\", log_scale_transformer, [\"Density\"]),\n    ],\n    remainder=\"drop\",\n)\nX = column_trans.fit_transform(df)\n\n# Insurances companies are interested in modeling the Pure Premium, that is\n# the expected total claim amount per unit of exposure for each policyholder\n# in their portfolio:\ndf[\"PurePremium\"] = df[\"ClaimAmount\"] / df[\"Exposure\"]\n\n# This can be indirectly approximated by a 2-step modeling: the product of the\n# Frequency times the average claim amount per claim:\ndf[\"Frequency\"] = df[\"ClaimNb\"] / df[\"Exposure\"]\ndf[\"AvgClaimAmount\"] = df[\"ClaimAmount\"] / np.fmax(df[\"ClaimNb\"], 1)\n\nwith pd.option_context(\"display.max_columns\", 15):\n    print(df[df.ClaimAmount > 0].head())"
       ]
     },
     {
@@ -242,7 +242,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.metrics import auc\n\n\ndef lorenz_curve(y_true, y_pred, exposure):\n    y_true, y_pred = np.asarray(y_true), np.asarray(y_pred)\n    exposure = np.asarray(exposure)\n\n    # order samples by increasing predicted risk:\n    ranking = np.argsort(y_pred)\n    ranked_exposure = exposure[ranking]\n    ranked_pure_premium = y_true[ranking]\n    cumulative_claim_amount = np.cumsum(ranked_pure_premium * ranked_exposure)\n    cumulative_claim_amount /= cumulative_claim_amount[-1]\n    cumulative_exposure = np.cumsum(ranked_exposure)\n    cumulative_exposure /= cumulative_exposure[-1]\n    return cumulative_exposure, cumulative_claim_amount\n\n\nfig, ax = plt.subplots(figsize=(8, 8))\n\ny_pred_product = glm_freq.predict(X_test) * glm_sev.predict(X_test)\ny_pred_total = glm_pure_premium.predict(X_test)\n\nfor label, y_pred in [\n    (\"Frequency * Severity model\", y_pred_product),\n    (\"Compound Poisson Gamma\", y_pred_total),\n]:\n    cum_exposure, cum_claims = lorenz_curve(\n        df_test[\"PurePremium\"], y_pred, df_test[\"Exposure\"]\n    )\n    gini = 1 - 2 * auc(cum_exposure, cum_claims)\n    label += \" (Gini index: {:.3f})\".format(gini)\n    ax.plot(cum_exposure, cum_claims, linestyle=\"-\", label=label)\n\n# Oracle model: y_pred == y_test\ncum_exposure, cum_claims = lorenz_curve(\n    df_test[\"PurePremium\"], df_test[\"PurePremium\"], df_test[\"Exposure\"]\n)\ngini = 1 - 2 * auc(cum_exposure, cum_claims)\nlabel = \"Oracle (Gini index: {:.3f})\".format(gini)\nax.plot(cum_exposure, cum_claims, linestyle=\"-.\", color=\"gray\", label=label)\n\n# Random baseline\nax.plot([0, 1], [0, 1], linestyle=\"--\", color=\"black\", label=\"Random baseline\")\nax.set(\n    title=\"Lorenz Curves\",\n    xlabel=(\n        \"Cumulative proportion of exposure\\n\"\n        \"(ordered by model from safest to riskiest)\"\n    ),\n    ylabel=\"Cumulative proportion of claim amounts\",\n)\nax.legend(loc=\"upper left\")\nplt.plot()"
+        "from sklearn.metrics import auc\n\n\ndef lorenz_curve(y_true, y_pred, exposure):\n    y_true, y_pred = np.asarray(y_true), np.asarray(y_pred)\n    exposure = np.asarray(exposure)\n\n    # order samples by increasing predicted risk:\n    ranking = np.argsort(y_pred)\n    ranked_exposure = exposure[ranking]\n    ranked_pure_premium = y_true[ranking]\n    cumulative_claim_amount = np.cumsum(ranked_pure_premium * ranked_exposure)\n    cumulative_claim_amount /= cumulative_claim_amount[-1]\n    cumulative_exposure = np.cumsum(ranked_exposure)\n    cumulative_exposure /= cumulative_exposure[-1]\n    return cumulative_exposure, cumulative_claim_amount\n\n\nfig, ax = plt.subplots(figsize=(8, 8))\n\ny_pred_product = glm_freq.predict(X_test) * glm_sev.predict(X_test)\ny_pred_total = glm_pure_premium.predict(X_test)\n\nfor label, y_pred in [\n    (\"Frequency * Severity model\", y_pred_product),\n    (\"Compound Poisson Gamma\", y_pred_total),\n]:\n    cum_exposure, cum_claims = lorenz_curve(\n        df_test[\"PurePremium\"], y_pred, df_test[\"Exposure\"]\n    )\n    gini = 1 - 2 * auc(cum_exposure, cum_claims)\n    label += \" (Gini index: {:.3f})\".format(gini)\n    ax.plot(cum_exposure, cum_claims, linestyle=\"-\", label=label)\n\n# Oracle model: y_pred == y_test\ncum_exposure, cum_claims = lorenz_curve(\n    df_test[\"PurePremium\"], df_test[\"PurePremium\"], df_test[\"Exposure\"]\n)\ngini = 1 - 2 * auc(cum_exposure, cum_claims)\nlabel = \"Oracle (Gini index: {:.3f})\".format(gini)\nax.plot(cum_exposure, cum_claims, linestyle=\"-.\", color=\"gray\", label=label)\n\n# Random baseline\nax.plot([0, 1], [0, 1], linestyle=\"--\", color=\"black\", label=\"Random baseline\")\nax.set(\n    title=\"Lorenz Curves\",\n    xlabel=(\n        \"Cumulative proportion of exposure\\n(ordered by model from safest to riskiest)\"\n    ),\n    ylabel=\"Cumulative proportion of claim amounts\",\n)\nax.legend(loc=\"upper left\")\nplt.plot()"
       ]
     }
   ],