Pushing the docs to dev/ for branch: main, commit e883b4b8c0b2ca858e6d7ddff52f6fa76981411f

Author: sklearn-ci

dev/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: b8552c1840e582d8069bb272f008b1c5
+config: a8992306144a58818a4d64d1a9e413cf
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -222,15 +222,16 @@ def score_estimator(
 
 df = load_mtpl2()
 
-# Note: filter out claims with zero amount, as the severity model
-# requires strictly positive target values.
-df.loc[(df["ClaimAmount"] == 0) & (df["ClaimNb"] >= 1), "ClaimNb"] = 0
 
 # Correct for unreasonable observations (that might be data error)
 # and a few exceptionally large claim amounts
 df["ClaimNb"] = df["ClaimNb"].clip(upper=4)
 df["Exposure"] = df["Exposure"].clip(upper=1)
 df["ClaimAmount"] = df["ClaimAmount"].clip(upper=200000)
+# If the claim amount is 0, then we do not count it as a claim. The loss function
+# used by the severity model needs strictly positive claim amounts. This way
+# frequency and severity are more consistent with each other.
+df.loc[(df["ClaimAmount"] == 0) & (df["ClaimNb"] >= 1), "ClaimNb"] = 0
 
 log_scale_transformer = make_pipeline(
     FunctionTransformer(func=np.log), StandardScaler()