def test_arrays_transformer_pandas():
pd = pytest.importorskip("pandas")
X = np.array([[0, 0], [1, 1]])
y = np.array([0, 1])
X_df = pd.DataFrame(X, columns=["a", "b"])
X_df = X_df.astype(int)
y_df = pd.DataFrame(y, columns=["target", ])
y_df = y_df.astype(int)
y_s = pd.Series(y, name="target", dtype=int)
# DataFrame and DataFrame case
arrays_transformer = ArraysTransformer(X_df, y_df)
X_res, y_res = arrays_transformer.transform(X, y)
assert isinstance(X_res, pd.DataFrame)
assert_array_equal(X_res.columns, X_df.columns)
assert_array_equal(X_res.dtypes, X_df.dtypes)
assert isinstance(y_res, pd.DataFrame)
assert_array_equal(y_res.columns, y_df.columns)
assert_array_equal(y_res.dtypes, y_df.dtypes)
# DataFrames and Series case
arrays_transformer = ArraysTransformer(X_df, y_s)
_, y_res = arrays_transformer.transform(X, y)
assert isinstance(y_res, pd.Series)
assert_array_equal(y_res.name, y_s.name)
assert_array_equal(y_res.dtype, y_s.dtype)
def fit_resample(self, X, y, **fit_params):
"""Resample the dataset.
Parameters
----------
X : {array-like, dataframe, sparse matrix} of shape \
(n_samples, n_features)
Matrix containing the data which have to be sampled.
y : array-like of shape (n_samples,)
Corresponding label for each sample in X.
Returns
-------
X_resampled : {array-like, dataframe, sparse matrix} of shape \
(n_samples_new, n_features)
The array containing the resampled data.
y_resampled : array-like of shape (n_samples_new,)
The corresponding label of `X_resampled`.
"""
check_classification_targets(y)
arrays_transformer = ArraysTransformer(X, y)
X, y, binarize_y = self._check_X_y(X, y)
self._check(X, y)._fit(X, y, **fit_params)
output = self._fit_resample(X, y)
y_ = (
label_binarize(y=output[1], classes=np.unique(y))
if binarize_y
else output[1]
)
X_, y_ = arrays_transformer.transform(output[0], y_)
return (X_, y_) if len(output) == 2 else (X_, y_, output[2])
def test_arrays_transformer_numpy():
X = np.array([[0, 0], [1, 1]])
y = np.array([[0, 0], [1, 1]])
arrays_transformer = ArraysTransformer(X, y)
X_res, y_res = arrays_transformer.transform(X, y)
assert isinstance(X_res, np.ndarray)
assert isinstance(y_res, np.ndarray)
def test_arrays_transformer_plain_list():
X = np.array([[0, 0], [1, 1]])
y = np.array([[0, 0], [1, 1]])
arrays_transformer = ArraysTransformer(X.tolist(), y.tolist())
X_res, y_res = arrays_transformer.transform(X, y)
assert isinstance(X_res, list)
assert isinstance(y_res, list)