def map_transform(self, data: DataEntry, is_train: bool) -> DataEntry:
start = data[self.start_field]
length = target_transformation_length(data[self.target_field],
self.pred_length,
is_train=is_train)
self._update_cache(start, length)
i0 = self._date_index[start]
date_idx = self._date_index.iloc[i0:i0 + length].index
# When is_train is false, date_idx has len of target_len + prediction_len
# which is useful in time feature generation, but we only need target length
date_idx = date_idx[:len(data[self.target_field])]
feature = pd.Series(np.ones(len(date_idx)) * np.nan, index=date_idx)
mask = data[self.target_field] > 0
feature.loc[mask] = feature.loc[mask].index
# filling in nan in first row with the corresponding date
# Assumption: If the frame starts with a zero demand, earliest date in frame is taken as a start
if len(feature) > 0:
if pd.isnull(feature[0]):
feature[0] = feature.index[0]
feature = feature.ffill().to_frame()
feature["diff"] = feature.index.to_period(
feature.index.freqstr).astype(int) - pd.DatetimeIndex(
feature.iloc[:, 0]).to_period(
feature.index.freqstr).astype(int)
feature["diff"] = feature["diff"].shift(1).round() + 1
feature["diff"] = feature["diff"].fillna(method="bfill")
feature = feature["diff"].values
if self.output_field in data.keys():
data[self.output_field] = np.vstack(
[data[self.output_field], feature])
else:
data[self.output_field] = feature
return data
def transform(self, data: DataEntry) -> DataEntry:
if self.output_field not in data.keys():
data[self.output_field] = self.value
return data
def transform(self, data: DataEntry) -> DataEntry:
for k in self.field_names:
if k in data.keys():
del data[k]
return data
