def transform(self, X: dt.Frame):
# Keep date only
X = X[:, self.time_column].to_pandas()
# Transform to pandas date time
X[self.time_column] = pd.to_datetime(X[self.time_column])
# Create Year and day of year so that we can merge with stored holidays
X['year'] = X[self.time_column].dt.year
X['doy'] = X[self.time_column].dt.dayofyear
# General first
holi_df = self.memos['country']
holi_df['is_DE_holiday_country'] = 1
X["is_DE_holiday_country"] = X.merge(
self.memos['country'], on=['year', 'doy'], how='left'
).fillna(0)['is_DE_holiday_country']
# Then Landers
for prov in ['BW', 'BY', 'BE', 'BB', 'HB', 'HH', 'HE', 'MV', 'NI', 'NW', 'RP', 'SL', 'SN', 'ST', 'SH', 'TH']:
holi_df = self.memos[prov]
holi_df[f'is_DE_holiday_{prov}'] = 1
X[f'is_DE_holiday_{prov}'] = X.merge(
holi_df, on=['year', 'doy'], how='left'
).fillna(0)[f'is_DE_holiday_{prov}']
X.drop([self.time_column, 'year', 'doy'], axis=1, inplace=True)
features = [
f'is_DE_holiday_{prov}'
for prov in ['country', 'BW', 'BY', 'BE', 'BB', 'HB', 'HH', 'HE',
'MV', 'NI', 'NW', 'RP', 'SL', 'SN', 'ST', 'SH', 'TH']
]
self._output_feature_names = list(features)
self._feature_desc = list(features)
return X
def transform(self, X: dt.Frame):
X = X[:, self.time_column]
X = X.to_pandas()
ge_holidays = holidays.DE()
X["is_ge_holiday"] = X[self.time_column].apply(
lambda x: x in ge_holidays)
for prov in [
"BW", 'BY', 'BE', 'BB', 'HB', 'HH', 'HE', 'MV', 'NI', 'NW',
'RP', 'SL', 'SN', 'ST', 'SH', 'TH'
]:
ge_prov_holidays = holidays.DE(state=prov)
X["is_ge_holiday_%s" % prov] = X[self.time_column].apply(
lambda x: x in ge_prov_holidays)
X.drop(self.time_column, axis=1, inplace=True)
return X
def transform(self, X: dt.Frame):
X = X[:, self.time_column]
if X[:, self.time_column].ltypes[0] != dt.ltype.str:
assert self.datetime_formats[self.time_column] in ["%Y%m%d", "%Y%m%d%H%M"]
X[:, self.time_column] = dt.stype.str32(dt.stype.int64(dt.f[0]))
X.replace(['', 'None'], None)
X = X.to_pandas()
X.loc[:, self.time_column] = pd.to_datetime(X[self.time_column],
format=self.datetime_formats[self.time_column])
X['year'] = X[self.time_column].dt.year
X['doy'] = X[self.time_column].dt.dayofyear
X.drop(self.time_column, axis=1, inplace=True)
feat = 'is_holiday'
self.memo[feat] = 1
X = X.merge(self.memo, how='left', on=['year', 'doy']).fillna(0)
self.memo.drop(feat, axis=1, inplace=True)
X = X[[feat]].astype(int)
return X
def create_data(X: dt.Frame = None) -> pd.DataFrame:
if X is None:
return []
from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS
X = X.to_pandas()
y = X[TARGET_COLUMN].values
X.drop(TARGET_COLUMN, axis=1, inplace=True)
efs = EFS(ESTIMATOR,
min_features=MIN_FEATURES,
max_features=MAX_FEATURES,
scoring=SCORING,
cv=CV,
n_jobs=-1)
efs.fit(X, y)
X_fs = X.iloc[:, list(efs.best_idx_)]
return X_fs
def create_data(X: dt.Frame = None) -> pd.DataFrame:
if X is None:
return []
from mlxtend.feature_selection import SequentialFeatureSelector as SFS
X = X.to_pandas()
y = X[TARGET_COLUMN].values
X.drop(TARGET_COLUMN, axis=1, inplace=True)
sfs = SFS(ESTIMATOR,
k_features=K_FEATURES,
forward=False,
floating=False,
scoring=SCORING,
cv=CV,
n_jobs=-1)
sfs.fit(X, y)
X_fs = X.iloc[:, list(sfs.k_feature_idx_)]
return X_fs
def transform(self, X: dt.Frame):
X = X[:, self.time_column]
if X[:, self.time_column].ltypes[0] != dt.ltype.str:
if self.datetime_formats[self.time_column] not in [
"%Y%m%d", "%Y%m%d%H%M", "%Y", "%Y%m"
]:
# raise IgnoreEntirelyError("Unsupported format %s" % self.datetime_formats[self.time_column])
# just return bad data, so feature is not pruned and breaks backend tuning
return np.zeros((X.shape[0], 1))
X[:, self.time_column] = dt.stype.str32(dt.stype.int64(dt.f[0]))
X.replace(['', 'None'], None)
X = X.to_pandas()
X.loc[:, self.time_column] = pd.to_datetime(
X[self.time_column],
format=self.datetime_formats[self.time_column])
X['year'] = X[self.time_column].dt.year
X['doy'] = X[self.time_column].dt.dayofyear
X.drop(self.time_column, axis=1, inplace=True)
feat = 'is_ramadan'
self.memo[feat] = 1
X = X.merge(self.memo, how='left', on=['year', 'doy']).fillna(0)
self.memo.drop(feat, axis=1, inplace=True)
X = X[[feat]].astype(int)
return X
