Pushing the docs to dev/ for branch: main, commit fa5d7275ba4dd2627b6522e1ec4eaf0f3a2e3c05

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -655,8 +655,9 @@ def lorenz_curve(y_true, y_pred, exposure):
     ranked_pure_premium = y_true[ranking]
     cumulated_claim_amount = np.cumsum(ranked_pure_premium * ranked_exposure)
     cumulated_claim_amount /= cumulated_claim_amount[-1]
-    cumulated_samples = np.linspace(0, 1, len(cumulated_claim_amount))
-    return cumulated_samples, cumulated_claim_amount
+    cumulated_exposure = np.cumsum(ranked_exposure)
+    cumulated_exposure /= cumulated_exposure[-1]
+    return cumulated_exposure, cumulated_claim_amount
 
 
 fig, ax = plt.subplots(figsize=(8, 8))

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -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    cumulated_claim_amount = np.cumsum(ranked_pure_premium * ranked_exposure)\n    cumulated_claim_amount /= cumulated_claim_amount[-1]\n    cumulated_samples = np.linspace(0, 1, len(cumulated_claim_amount))\n    return cumulated_samples, cumulated_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    ordered_samples, cum_claims = lorenz_curve(\n        df_test[\"PurePremium\"], y_pred, df_test[\"Exposure\"]\n    )\n    gini = 1 - 2 * auc(ordered_samples, cum_claims)\n    label += \" (Gini index: {:.3f})\".format(gini)\n    ax.plot(ordered_samples, cum_claims, linestyle=\"-\", label=label)\n\n# Oracle model: y_pred == y_test\nordered_samples, cum_claims = lorenz_curve(\n    df_test[\"PurePremium\"], df_test[\"PurePremium\"], df_test[\"Exposure\"]\n)\ngini = 1 - 2 * auc(ordered_samples, cum_claims)\nlabel = \"Oracle (Gini index: {:.3f})\".format(gini)\nax.plot(ordered_samples, 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=\"Fraction of policyholders\\n(ordered by model from safest to riskiest)\",\n    ylabel=\"Fraction of total claim amount\",\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    cumulated_claim_amount = np.cumsum(ranked_pure_premium * ranked_exposure)\n    cumulated_claim_amount /= cumulated_claim_amount[-1]\n    cumulated_exposure = np.cumsum(ranked_exposure)\n    cumulated_exposure /= cumulated_exposure[-1]\n    return cumulated_exposure, cumulated_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    ordered_samples, cum_claims = lorenz_curve(\n        df_test[\"PurePremium\"], y_pred, df_test[\"Exposure\"]\n    )\n    gini = 1 - 2 * auc(ordered_samples, cum_claims)\n    label += \" (Gini index: {:.3f})\".format(gini)\n    ax.plot(ordered_samples, cum_claims, linestyle=\"-\", label=label)\n\n# Oracle model: y_pred == y_test\nordered_samples, cum_claims = lorenz_curve(\n    df_test[\"PurePremium\"], df_test[\"PurePremium\"], df_test[\"Exposure\"]\n)\ngini = 1 - 2 * auc(ordered_samples, cum_claims)\nlabel = \"Oracle (Gini index: {:.3f})\".format(gini)\nax.plot(ordered_samples, 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=\"Fraction of policyholders\\n(ordered by model from safest to riskiest)\",\n    ylabel=\"Fraction of total claim amount\",\n)\nax.legend(loc=\"upper left\")\nplt.plot()"
       ]
     }
   ],