def test_no_finite_values_yields_0(self):
df = pd.DataFrame([np.NaN, np.PINF, np.NINF], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 0})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 0})
def test_ignores_non_finite_values(self):
df = pd.DataFrame([0, 1, 2, 3, np.NaN, np.PINF, np.NINF], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 3})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 1.5})
def test_range_values_correct_with_uneven_length(self):
df = pd.DataFrame([0, 1, 2], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 2})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 1})
def test_range_values_correct_with_uneven_length(self):
df = pd.DataFrame([0, 1, 2], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 2})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 1})
def test_no_finite_values_yields_0(self):
df = pd.DataFrame([np.NaN, np.PINF, np.NINF], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 0})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 0})
def test_ignores_non_finite_values(self):
df = pd.DataFrame([0, 1, 2, 3, np.NaN, np.PINF, np.NINF], columns=["value"])
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(col_to_max, {"value": 3})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 1.5})
def test_no_finite_values_yields_0(self):
df = pd.DataFrame([np.NaN, np.PINF, np.NINF], columns=["value"])
with warnings.catch_warnings(record=True) as w:
col_to_max, col_to_min, col_to_median = dataframe_functions.get_range_values_per_column(df)
self.assertEqual(len(w), 1)
self.assertEqual(str(w[0].message),
"The columns ['value'] did not have any finite values. Filling with zeros.")
self.assertEqual(col_to_max, {"value": 0})
self.assertEqual(col_to_min, {"value": 0})
self.assertEqual(col_to_median, {"value": 0})
def fit(self, X, y):
"""
Use the given timeseries from :func:`~set_timeseries_container` and calculate features from it and add them
to the data sample X (which can contain other manually-designed features).
Then determine which of the features of X are relevant for the given target y.
Store those relevant features internally to only extract them in the transform step.
If evaluate_only_added_features is True, only reject newly, automatically added features. If it is False,
also look at the features that are already present in the DataFrame.
:param X: The data frame without the time series features. The index rows should be present in the timeseries
and in the target vector.
:type X: pandas.DataFrame or numpy.array
:param y: The target vector to define, which features are relevant.
:type y: pandas.Series or numpy.array
:return: the fitted estimator with the information, which features are relevant.
:rtype: RelevantFeatureAugmenter
"""
if self.timeseries_container is None:
raise RuntimeError(
"You have to provide a time series using the set_timeseries_container function before."
)
self.feature_extractor.set_timeseries_container(
self.timeseries_container)
if self.evaluate_only_added_features:
# Do not merge the time series features to the old features
X_augmented = self.feature_extractor.transform(
pd.DataFrame(index=X.index))
else:
X_augmented = self.feature_extractor.transform(X)
if self.feature_extractor.settings.IMPUTE is impute:
col_to_max, col_to_min, col_to_median = get_range_values_per_column(
X_augmented)
self.feature_extractor.settings.IMPUTE = partial(
impute_dataframe_range,
col_to_max=col_to_max,
col_to_min=col_to_min,
col_to_median=col_to_median)
self.feature_selector.fit(X_augmented, y)
return self
def fit(self, X, y=None):
"""
Compute the min, max and median for all columns in the DataFrame. For more information,
please see the :func:`~tsfresh.utilities.dataframe_functions.get_range_values_per_column` function.
:param X: DataFrame to calculate min, max and median values on
:type X: pandas.DataFrame
:param y: Unneeded.
:type y: Any
:return: the estimator with the computed min, max and median values
:rtype: Imputer
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
col_to_max, col_to_min, col_to_median = get_range_values_per_column(X)
if self.col_to_NINF_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_NINF_repl_preset.keys()):
raise ValueError(
"Preset dictionary 'col_to_NINF_repl_preset' contain more keys "
"than the column names in X")
col_to_min.update(self.col_to_NINF_repl_preset)
self._col_to_NINF_repl = col_to_min
if self.col_to_PINF_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_PINF_repl_preset.keys()):
raise ValueError(
"Preset dictionary 'col_to_PINF_repl_preset' contain more keys "
"than the column names in X")
col_to_max.update(self.col_to_PINF_repl_preset)
self._col_to_PINF_repl = col_to_max
if self.col_to_NAN_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_NAN_repl_preset.keys()):
raise ValueError(
"Preset dictionary 'col_to_NAN_repl_preset' contain more keys "
"than the column names in X")
col_to_median.update(self.col_to_NAN_repl_preset)
self._col_to_NAN_repl = col_to_median
return self
def fit(self, X, y):
"""
Use the given timeseries from :func:`~set_timeseries_container` and calculate features from it and add them
to the data sample X (which can contain other manually-designed features).
Then determine which of the features of X are relevant for the given target y.
Store those relevant features internally to only extract them in the transform step.
If filter_only_tsfresh_features is True, only reject newly, automatically added features. If it is False,
also look at the features that are already present in the DataFrame.
:param X: The data frame without the time series features. The index rows should be present in the timeseries
and in the target vector.
:type X: pandas.DataFrame or numpy.array
:param y: The target vector to define, which features are relevant.
:type y: pandas.Series or numpy.array
:return: the fitted estimator with the information, which features are relevant.
:rtype: RelevantFeatureAugmenter
"""
if self.timeseries_container is None:
raise RuntimeError("You have to provide a time series using the set_timeseries_container function before.")
self.feature_extractor.set_timeseries_container(self.timeseries_container)
if self.filter_only_tsfresh_features:
# Do not merge the time series features to the old features
X_tmp = pd.DataFrame(index=X.index)
else:
X_tmp = X
X_augmented = self.feature_extractor.transform(X_tmp)
self.col_to_max, self.col_to_min, self.col_to_median = get_range_values_per_column(X_augmented)
X_augmented = impute_dataframe_range(X_augmented, col_to_max=self.col_to_max, col_to_median=self.col_to_median,
col_to_min=self.col_to_min)
self.feature_selector.fit(X_augmented, y)
return self
def fit(self, X, y=None):
"""
Compute the min, max and median for all columns in the DataFrame. For more information,
please see the :func:`~tsfresh.utilities.dataframe_functions.get_range_values_per_column` function.
:param X: DataFrame to calculate min, max and median values on
:type X: pandas.DataFrame
:param y: Unneeded.
:type y: Any
:return: the estimator with the computed min, max and median values
:rtype: Imputer
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
col_to_max, col_to_min, col_to_median = get_range_values_per_column(X)
if self.col_to_NINF_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_NINF_repl_preset.keys()):
raise ValueError("Preset dictionary 'col_to_NINF_repl_preset' contain more keys "
"than the column names in X")
col_to_min.update(self.col_to_NINF_repl_preset)
self._col_to_NINF_repl = col_to_min
if self.col_to_PINF_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_PINF_repl_preset.keys()):
raise ValueError("Preset dictionary 'col_to_PINF_repl_preset' contain more keys "
"than the column names in X")
col_to_max.update(self.col_to_PINF_repl_preset)
self._col_to_PINF_repl = col_to_max
if self.col_to_NAN_repl_preset is not None:
if not set(X.columns) >= set(self.col_to_NAN_repl_preset.keys()):
raise ValueError("Preset dictionary 'col_to_NAN_repl_preset' contain more keys "
"than the column names in X")
col_to_median.update(self.col_to_NAN_repl_preset)
self._col_to_NAN_repl = col_to_median
return self
def fit(self, X, y):
"""
Use the given timeseries from :func:`~set_timeseries_container` and calculate features from it and add them
to the data sample X (which can contain other manually-designed features).
Then determine which of the features of X are relevant for the given target y.
Store those relevant features internally to only extract them in the transform step.
If filter_only_tsfresh_features is True, only reject newly, automatically added features. If it is False,
also look at the features that are already present in the DataFrame.
:param X: The data frame without the time series features. The index rows should be present in the timeseries
and in the target vector.
:type X: pandas.DataFrame or numpy.array
:param y: The target vector to define, which features are relevant.
:type y: pandas.Series or numpy.array
:return: the fitted estimator with the information, which features are relevant.
:rtype: RelevantFeatureAugmenter
"""
if self.timeseries_container is None:
raise RuntimeError(
"You have to provide a time series using the set_timeseries_container function before."
)
self.feature_extractor = FeatureAugmenter(
default_fc_parameters=self.default_fc_parameters,
kind_to_fc_parameters=self.kind_to_fc_parameters,
column_id=self.column_id,
column_sort=self.column_sort,
column_kind=self.column_kind,
column_value=self.column_value,
timeseries_container=self.timeseries_container,
chunksize=self.chunksize,
n_jobs=self.n_jobs,
show_warnings=self.show_warnings,
disable_progressbar=self.disable_progressbar,
profile=self.profile,
profiling_filename=self.profiling_filename,
profiling_sorting=self.profiling_sorting)
self.feature_selector = FeatureSelector(
test_for_binary_target_binary_feature=self.
test_for_binary_target_binary_feature,
test_for_binary_target_real_feature=self.
test_for_binary_target_real_feature,
test_for_real_target_binary_feature=self.
test_for_real_target_binary_feature,
test_for_real_target_real_feature=self.
test_for_real_target_real_feature,
fdr_level=self.fdr_level,
hypotheses_independent=self.hypotheses_independent,
n_jobs=self.n_jobs,
chunksize=self.chunksize,
ml_task=self.ml_task)
if self.filter_only_tsfresh_features:
# Do not merge the time series features to the old features
X_tmp = pd.DataFrame(index=X.index)
else:
X_tmp = X
X_augmented = self.feature_extractor.transform(X_tmp)
self.col_to_max, self.col_to_min, self.col_to_median = get_range_values_per_column(
X_augmented)
X_augmented = impute_dataframe_range(X_augmented,
col_to_max=self.col_to_max,
col_to_median=self.col_to_median,
col_to_min=self.col_to_min)
self.feature_selector.fit(X_augmented, y)
return self
def _fit_and_augment(self, X, y):
"""
Helper for the :func:`~fit` and :func:`~fit_transform` functions, which does most of the work described in
:func:`~fit`.
:param X: The data frame without the time series features. The index rows should be present in the timeseries
and in the target vector.
:type X: pandas.DataFrame or numpy.array
:param y: The target vector to define, which features are relevant.
:type y: pandas.Series or numpy.array
:return: a data sample with the extraced time series features. If filter_only_tsfresh_features is False
the data sample will also include the information in X.
:rtype: pandas.DataFrame
"""
if self.timeseries_container is None:
raise RuntimeError(
"You have to provide a time series using the set_timeseries_container function before."
)
self.feature_extractor = FeatureAugmenter(
default_fc_parameters=self.default_fc_parameters,
kind_to_fc_parameters=self.kind_to_fc_parameters,
column_id=self.column_id,
column_sort=self.column_sort,
column_kind=self.column_kind,
column_value=self.column_value,
timeseries_container=self.timeseries_container,
chunksize=self.chunksize,
n_jobs=self.n_jobs,
show_warnings=self.show_warnings,
disable_progressbar=self.disable_progressbar,
profile=self.profile,
profiling_filename=self.profiling_filename,
profiling_sorting=self.profiling_sorting)
self.feature_selector = FeatureSelector(
test_for_binary_target_binary_feature=self.
test_for_binary_target_binary_feature,
test_for_binary_target_real_feature=self.
test_for_binary_target_real_feature,
test_for_real_target_binary_feature=self.
test_for_real_target_binary_feature,
test_for_real_target_real_feature=self.
test_for_real_target_real_feature,
fdr_level=self.fdr_level,
hypotheses_independent=self.hypotheses_independent,
n_jobs=self.n_jobs,
chunksize=self.chunksize,
ml_task=self.ml_task,
multiclass=self.multiclass,
n_significant=self.n_significant,
multiclass_p_values=self.multiclass_p_values,
)
if self.filter_only_tsfresh_features:
# Do not merge the time series features to the old features
X_tmp = pd.DataFrame(index=X.index)
else:
X_tmp = X
X_augmented = self.feature_extractor.transform(X_tmp)
self.col_to_max, self.col_to_min, self.col_to_median = get_range_values_per_column(
X_augmented)
X_augmented = impute_dataframe_range(X_augmented,
col_to_max=self.col_to_max,
col_to_median=self.col_to_median,
col_to_min=self.col_to_min)
self.feature_selector.fit(X_augmented, y)
return X_augmented
