def test_internal_target_encoder_fit_and_transform():
X = np.array([[2, 2], [2, 4], [2, 6], [8, 7], [8, 8], [8, 9], [8, 10]])
y = np.array([1, 1, 0, 1, 1, 1, 0])
fold = KFold(n_splits=2, shuffle=False)
trn_idx, tst_idx = next(fold.split(X))
assert np.array_equal(tst_idx, np.array([0, 1, 2, 3]))
encoder = _TargetEncoder(fold=fold)
# Test `fit()` and `fit_transform()`.
encoder.fit(X[:, 0], y)
y_trn = encoder.transform(X[:, 0])
assert np.allclose(
y_trn,
np.array([
0.33333334,
0.33333334,
0.33333334,
0.83333334,
0.83333334,
0.83333334,
0.83333334,
]))
X_tst = np.array([8, 0, 2])
y_tst = encoder.transform(X_tst)
assert np.allclose(
y_tst,
np.array([0.83333334, 0., 0.33333334]),
)
def test_internal_target_encoder_with_cudf():
if not cudf_is_available() or cudf is not None or cupy is not None:
# Skip test.
return
X = cudf.Series(
np.array([[2, 2], [2, 4], [2, 6], [8, 7], [8, 8], [8, 9], [8, 10]]))
y = cudf.Series(np.array([1, 1, 0, 1, 1, 1, 0]))
fold = KFold(n_splits=2, shuffle=False)
trn_idx, tst_idx = next(fold.split(X))
assert np.array_equal(tst_idx, np.array([0, 1, 2, 3]))
encoder = _TargetEncoder(fold=fold)
# Test `fit_transform()`.
y_trn = encoder.fit_transform(X[:, 0], y)
assert np.allclose(y_trn.values,
np.array([
0.0,
0.0,
0.0,
0.66666667,
1.0,
1.0,
1.0,
]))
X_tst = np.array([8, 0, 2])
y_tst = encoder.transform(X_tst)
assert np.allclose(
y_tst.values,
np.array([0.83333334, 0., 0.33333334]),
)
def fit(self, input_df: XDataFrame, y: XSeries = None) -> None:
input_cols = self._input_cols
if not input_cols:
input_cols = input_df.columns.tolist()
self._input_cols = input_cols
# Remove `target_col` from `self._input_cols`.
if self._target_col in self._input_cols:
self._input_cols.remove(self._target_col)
for col in self._input_cols:
target_encoder = _TargetEncoder(self.fold)
self._target_encoders[col] = target_encoder
if y is None:
y = input_df[self._target_col]
target_encoder.fit(input_df[col], y)
def fit_transform(self, input_df: XDataFrame, y: XSeries = None) -> XDataFrame:
out_df = input_df.copy()
input_cols = self._input_cols
if not input_cols:
input_cols = input_df.columns.tolist()
self._input_cols = input_cols
# Remove `target_col` from `self._input_cols`.
if self._target_col in self._input_cols:
self._input_cols.remove(self._target_col)
for col in self._input_cols:
out_col = self._output_prefix + col + self._output_suffix
target_encoder = _TargetEncoder(self.fold)
self._target_encoders[col] = target_encoder
if isinstance(input_df[col], pd.Series):
X = column_or_1d(input_df[col], warn=True)
if y is None:
y = column_or_1d(input_df[self._target_col], warn=True)
else:
y = column_or_1d(y, warn=True)
elif cudf and isinstance(input_df[col], cudf.Series):
X = input_df[col]
if y is None:
y = input_df[self._target_col]
else:
raise TypeError
out_df[out_col] = target_encoder.fit_transform(X, y).copy()
if self.noise_level > 0:
np.random.seed(self.random_state)
out_df += np.random.normal(0, self.noise_level, out_df.shape)
return out_df