def test_multi_columns_time_shift_feature(self):
shift = Shift(shift=-2)
df_multi = pd.DataFrame({"x0": [0, 1, 2, 3, 4, 5], "x1": [7, 8, 9, 10, 11, 12]})
expected_df = pd.DataFrame.from_dict(
{
f"x0__{shift_class_name}": [2, 3, 4, 5, np.nan, np.nan],
f"x1__{shift_class_name}": [9, 10, 11, 12, np.nan, np.nan],
}
)
testing.assert_frame_equal(shift.fit_transform(df_multi), expected_df)
def horizon_shift(time_series: pd.DataFrame,
horizon: Union[int, List[int]] = 5) -> pd.DataFrame:
"""Perform a shift of the original ``time_series`` for each time step between 1 and
``horizon``.
Parameters
----------
time_series : pd.DataFrame, shape (n_samples, n_features), required
The list of ``TimeSeriesFeature`` from which to compute the feature_extraction.
horizon : int, optional, default: ``5``
It represents how much into the future is necessary to predict. This corresponds
to the number of shifts that are going to be performed on y.
Returns
-------
y : pd.DataFrame, shape (n_samples, horizon)
The shifted time series.
Examples
--------
>>> import pandas as pd
>>> from gtime.model_selection import horizon_shift
>>> X = pd.DataFrame(range(0, 5), index=pd.date_range("2020-01-01", "2020-01-05"))
>>> horizon_shift(X, horizon=2)
y_1 y_2
2020-01-01 1.0 2.0
2020-01-02 2.0 3.0
2020-01-03 3.0 4.0
2020-01-04 4.0 NaN
2020-01-05 NaN NaN
>>> horizon_shift(X, horizon=[2])
y_2
2020-01-01 2.0
2020-01-02 3.0
2020-01-03 4.0
2020-01-04 NaN
2020-01-05 NaN
"""
horizon = range(1, horizon + 1) if isinstance(horizon,
(int, float)) else horizon
y = pd.DataFrame(index=time_series.index)
for k in sorted(horizon):
shift_feature = Shift(-k)
y[f"y_{k}"] = shift_feature.fit_transform(time_series)
return y
def test_random_ts_and_shifts(self, df: pd.DataFrame, shift: int):
shift_feature = Shift(shift=shift)
df_shifted = shift_feature.fit_transform(df)
correct_df_shifted = self._correct_shift(df, shift)
def test_shift_transform(self, shift, expected):
shift = Shift(shift=shift)
testing.assert_frame_equal(shift.fit_transform(df), expected)