def test_grouped_returns_numpy(pipeline, groupby, is_estimator, input_df):
gp = GroupedPipeline(groupby=groupby, pipeline=pipeline)
if is_estimator:
out = gp.fit_predict(input_df)
else:
out = gp.fit_transform(input_df)
assert type(out) is np.ndarray
def test_grouped_order(pipeline, groupby, is_estimator, input_df):
gp = GroupedPipeline(groupby=groupby, pipeline=pipeline)
if is_estimator:
out = gp.fit_predict(input_df).values
expected = input_df[ini.Columns.target].values
else:
out = gp.fit_transform(input_df).values
expected = input_df[[ini.Columns.target]].values
np.testing.assert_array_equal(out, expected)
def test_grouped_values(mocker, pipeline, groupby, is_estimator, input_df):
gp = GroupedPipeline(groupby=groupby, pipeline=pipeline)
if is_estimator:
out = gp.fit_predict(input_df)
else:
out = gp.fit_transform(input_df)
input_df['out'] = out
for _, df in input_df.groupby(groupby):
expected = df[ini.Columns.target].shift(1)
np.testing.assert_array_equal(expected.values, df['out'].values)
def test_grouped_returns_pandas(pipeline, groupby, input_df):
gp = GroupedPipeline(groupby=groupby, pipeline=pipeline)
out = gp.fit_transform(input_df)
assert type(out) is pd.DataFrame