def test_TargetEncoderRegressor(cv, noise_level):
df = get_sample_df(100)
df["cat_col"] = df["text_col"].apply(lambda s: s[0:3])
np.random.seed(123)
y = np.random.randn(100)
encoder = TargetEncoderRegressor(noise_level=noise_level, cv=cv)
encoder.fit(df, y)
res = encoder.transform(df)
assert encoder.get_feature_names() == ["float_col", "int_col", "text_col", "cat_col__target_mean"]
assert list(res.columns) == ["float_col", "int_col", "text_col", "cat_col__target_mean"]
assert res["cat_col__target_mean"].isnull().sum() == 0
assert (res.index == df.index).all()
assert encoder._columns_informations["input_columns"] == ["cat_col"]
temp = pd.DataFrame({"cat_col": df["cat_col"], "cat_col__target_mean": res["cat_col__target_mean"]})
assert temp.groupby("cat_col")["cat_col__target_mean"].std().max() == 0
encoder = TargetEncoderRegressor(noise_level=noise_level, cv=cv)
res = encoder.fit_transform(df, y)
assert encoder.get_feature_names() == ["float_col", "int_col", "text_col", "cat_col__target_mean"]
assert list(res.columns) == ["float_col", "int_col", "text_col", "cat_col__target_mean"]
assert res["cat_col__target_mean"].isnull().sum() == 0
assert (res.index == df.index).all()
assert encoder._columns_informations["input_columns"] == ["cat_col"]
def test_TargetEncoderRegressor_is_picklable():
df = get_sample_df(100)
df["cat_col"] = df["text_col"].apply(lambda s: s[0:3])
np.random.seed(123)
y = np.random.randn(100)
encoder = TargetEncoderRegressor(cv=2)
encoder.fit(df, y)
pickled_encoder = pickle.dumps(encoder)
unpickled_encoder = pickle.loads(pickled_encoder)
assert type(unpickled_encoder) == type(encoder)
X1 = encoder.transform(df)
X2 = unpickled_encoder.transform(df)
assert X1.shape == X2.shape
assert (X1 == X2).all().all()
def test_TargetEncoderRegressor_columns_to_encode_object():
np.random.seed(123)
Xnum = np.random.randn(1000, 10)
dfX = pd.DataFrame(Xnum, columns=["col_%d" % i for i in range(10)])
dfX["object_column"] = ["string_%2.4f" % x for x in dfX["col_0"]]
y = np.random.randn(1000)
# with --object--
encoder = TargetEncoderRegressor(columns_to_encode="--object--")
dfX_enc = encoder.fit_transform(dfX, y)
assert not (dfX_enc.dtypes == "object").any()
# with default behavior
encoder = TargetEncoderRegressor()
dfX_enc = encoder.fit_transform(dfX, y)
assert "object_column" in dfX_enc
assert (dfX_enc["object_column"] == dfX["object_column"]).all()