def gen_global_feature(self,
settings="comprehensive",
full_settings=None,
n_jobs=1):
'''
Generate per-time-series feature for each time series.
This method will be implemented by tsfresh.
Make sure that the specified column name does not contain '__'.
TODO: relationship with scale should be figured out.
:param settings: str or dict. If a string is set, then it must be one of "comprehensive"
"minimal" and "efficient". If a dict is set, then it should follow the instruction
for default_fc_parameters in tsfresh. The value is defaulted to "comprehensive".
:param full_settings: dict. It should follow the instruction for kind_to_fc_parameters in
tsfresh. The value is defaulted to None.
:param n_jobs: int. The number of processes to use for parallelization.
:return: the tsdataset instance.
'''
assert not self._has_generate_agg_feature, \
"Only one of gen_global_feature and gen_rolling_feature should be called."
if full_settings is not None:
self.df,\
addtional_feature =\
generate_global_features(input_df=self.df,
column_id=self.id_col,
column_sort=self.dt_col,
kind_to_fc_parameters=full_settings,
n_jobs=n_jobs)
self.feature_col += addtional_feature
return self
if isinstance(settings, str):
assert settings in ["comprehensive", "minimal", "efficient"], \
f"settings str should be one of \"comprehensive\", \"minimal\", \"efficient\"\
, but found {settings}."
default_fc_parameters = DEFAULT_PARAMS[settings]
else:
default_fc_parameters = settings
self.df,\
addtional_feature =\
generate_global_features(input_df=self.df,
column_id=self.id_col,
column_sort=self.dt_col,
default_fc_parameters=default_fc_parameters,
n_jobs=n_jobs)
self.feature_col += addtional_feature
self._has_generate_agg_feature = True
return self
def gen_global_feature(self, settings="comprehensive", full_settings=None):
'''
Generate per-time-series feature for each time series.
This method will be implemented by tsfresh.
:param settings: str or dict. If a string is set, then it must be one of "comprehensive"
"minimal" and "efficient". If a dict is set then it should follow the instruction
for default_fc_parameters in tsfresh. The value is defaulted to "comprehensive".
:param full_settings: dict. It should follow the instruction for kind_to_fc_parameters in
tsfresh. The value is defaulted to None.
:return: the tsdataset instance.
'''
if full_settings is not None:
self.df = generate_global_features(
input_df=self.df,
column_id=self.id_col,
column_sort=self.dt_col,
kind_to_fc_parameters=full_settings)
return self
from tsfresh.feature_extraction import ComprehensiveFCParameters,\
MinimalFCParameters, EfficientFCParameters
default_params = {
"comprehensive": ComprehensiveFCParameters(),
"minimal": MinimalFCParameters(),
"efficient": EfficientFCParameters()
}
if isinstance(settings, str):
assert settings in ["comprehensive", "minimal", "efficient"], \
f"settings str should be one of \"comprehensive\", \"minimal\", \"efficient\"\
, but found {settings}."
default_fc_parameters = default_params[settings]
else:
default_fc_parameters = settings
self.df,\
addtional_feature =\
generate_global_features(input_df=self.df,
column_id=self.id_col,
column_sort=self.dt_col,
default_fc_parameters=default_fc_parameters)
self.feature_col += addtional_feature
return self
def test_gen_global_feature_multi_id(self):
dates = pd.date_range('1/1/2019', periods=8)
data = np.random.randn(8, 3)
df = pd.DataFrame({
"datetime": dates,
"values": data[:, 0],
"A": data[:, 1],
"B": data[:, 2],
"id": ["00"] * 4 + ["01"] * 4
})
from tsfresh.feature_extraction import MinimalFCParameters
for params in [MinimalFCParameters()]:
output_df, _ = generate_global_features(
input_df=df,
column_id="id",
column_sort="datetime",
default_fc_parameters=params)
assert "datetime" in output_df.columns
assert "values" in output_df.columns
assert "A" in output_df.columns
assert "B" in output_df.columns
assert "id" in output_df.columns
for col in output_df.columns:
if col in ["datetime", "values", "A", "B", "id"]:
continue
assert len(set(output_df[output_df["id"] == "00"][col])) == 1
assert len(set(output_df[output_df["id"] == "01"][col])) == 1
assert output_df[output_df["id"] ==
"00"][col].isna().sum() == 0
assert output_df[output_df["id"] ==
"01"][col].isna().sum() == 0