def test_feature_importance(self):
selector = FeatureSelector()
self.assertTrue(selector.feature_importances_ is None)
y = pd.Series(np.random.binomial(1, 0.5, 1000))
X = pd.DataFrame(index=list(range(1000)))
X["irr1"] = np.random.normal(0, 1, 1000)
X["rel1"] = y
selector.fit(X, y)
self.assertEqual(selector.feature_importances_.shape, (2,))
def test_multiclass_max_avg_p_values(self):
y0 = np.zeros(100)
y1 = np.repeat(1, 100)
y2 = np.repeat(2, 100)
y = pd.Series(np.uint8(np.concatenate([y0, y1, y2])))
X = pd.DataFrame(index=list(range(300)))
X["irr1"] = np.random.normal(0, 1, 300)
X["rel1"] = y
selector = FeatureSelector(
multiclass=True,
ml_task="classification",
n_significant=2,
multiclass_p_values="max",
)
selector.fit(X, y)
assert (selector.p_values > 0.1).all()
selector = FeatureSelector(
multiclass=True,
ml_task="classification",
n_significant=2,
multiclass_p_values="avg",
)
selector.fit(X, y)
assert (selector.p_values > 0.1).all()
def test_multiclass_importance_p_values(self):
y0 = np.zeros(100)
y1 = np.repeat(1, 100)
y2 = np.repeat(2, 100)
y = pd.Series(np.uint8(np.concatenate([y0, y1, y2])))
X = pd.DataFrame(index=list(range(300)))
X["irr1"] = np.random.normal(0, 1, 300)
X["rel1"] = y
selector = FeatureSelector(
multiclass=True,
ml_task="classification",
n_significant=2,
multiclass_p_values="all",
)
selector.fit(X, y)
self.assertEqual(selector.p_values.shape, (2, 3))
self.assertEqual(selector.feature_importances_.shape, (2, 3))
selector = FeatureSelector(
multiclass=True,
ml_task="classification",
n_significant=2,
multiclass_p_values="min",
)
selector.fit(X, y)
self.assertEqual(selector.p_values.shape, (2, ))
self.assertEqual(selector.feature_importances_.shape, (2, ))
def test_nothing_relevant(self):
selector = FeatureSelector()
y = pd.Series(np.random.binomial(1, 0.5, 1000))
X = pd.DataFrame(index=list(range(1000)))
X["irr1"] = np.random.normal(0, 1, 1000)
X["irr2"] = np.random.normal(2, 1, 1000)
selector.fit(X, y)
transformed_X = selector.transform(X.copy())
self.assertEqual(list(transformed_X.columns), [])
self.assertEqual(list(transformed_X.index), list(X.index))
def test_feature_importance(self):
selector = FeatureSelector()
self.assertIsNone(selector.p_values)
y = pd.Series(np.random.binomial(1, 0.5, 1000))
X = pd.DataFrame(index=list(range(1000)))
X["irr1"] = np.random.normal(0, 1, 1000)
X["rel1"] = y
selector.fit(X, y)
self.assertEqual(selector.p_values.shape, (2, ))
np.testing.assert_almost_equal(selector.p_values,
1.0 - selector.feature_importances_)
def test_multiclass_relevant_features_selected(self):
y0 = np.zeros(100)
y1 = np.repeat(1, 100)
y2 = np.repeat(2, 100)
y_multi = pd.Series(np.uint8(np.concatenate([y0, y1, y2])))
X_multi = pd.DataFrame()
X_multi["irrelevant"] = np.concatenate(
[np.zeros(298), np.array([0.01, -0.01])])
X_multi["relevant"] = X_multi["irrelevant"].copy()
X_multi["relevant"][y_multi == 0] = np.random.uniform(2, 3, 100)
selector = FeatureSelector(multiclass=True,
n_significant=3,
ml_task="classification")
selector.fit(X_multi, y_multi)
self.assertEqual(selector.relevant_features, ["relevant"])
def test_extract_relevant_features(self):
selector = FeatureSelector()
np.random.seed(42)
y = pd.Series(np.random.binomial(1, 0.5, 1000))
X = pd.DataFrame(index=list(range(1000)))
z = y - np.random.binomial(1, 0.1, 1000) + np.random.binomial(1, 0.1, 1000)
z[z == -1] = 0
z[z == 2] = 1
X["rel1"] = z
X["rel2"] = y * np.abs(np.random.normal(0, 1, 1000)) + np.random.normal(0, 0.1, 1000)
X["rel3"] = y + np.random.normal(0, 1, 1000)
X["rel4"] = y ** 2 + np.random.normal(0, 1, 1000)
X["rel5"] = np.sqrt(y) + np.random.binomial(2, 0.1, 1000)
X["irr_constant"] = 1.113344
X["irr1"] = np.random.normal(0, 1, 1000)
X["irr2"] = np.random.poisson(1, 1000)
X["irr3"] = np.random.binomial(1, 0.3, 1000)
X["irr4"] = np.random.normal(0, 1, 1000)
X["irr5"] = np.random.poisson(1, 1000)
X["irr6"] = np.random.binomial(1, 0.3, 1000)
X["irr7"] = np.random.normal(0, 1, 1000)
X["irr8"] = np.random.poisson(1, 1000)
X["irr9"] = np.random.binomial(1, 0.3, 1000)
returned_selector = selector.fit(X, y)
self.assertIs(returned_selector, selector)
self.assertEqual(sorted(selector.relevant_features), ["rel1", "rel2", "rel3", "rel4", "rel5"])
new_X = X.copy()
selected_X = selector.transform(new_X)
self.assertEqual(sorted(selector.relevant_features), sorted(list(selected_X.columns)))
self.assertEqual(len(selector.features), len(X.columns))
def test_with_numpy_array(self):
selector = FeatureSelector()
y = pd.Series(np.random.binomial(1, 0.5, 1000))
X = pd.DataFrame(index=list(range(1000)))
X["irr1"] = np.random.normal(0, 1, 1000)
X["rel1"] = y
y_numpy = y.values
X_numpy = X.as_matrix()
selector.fit(X, y)
selected_X = selector.transform(X)
selector.fit(X_numpy, y_numpy)
selected_X_numpy = selector.transform(X_numpy)
self.assertTrue((selected_X_numpy == selected_X.values).all())
self.assertTrue(selected_X_numpy.shape, (1, 1000))
def __init__(self,
filter_only_tsfresh_features=True,
default_fc_parameters=None,
kind_to_fc_parameters=None,
column_id=None, column_sort=None, column_kind=None, column_value=None,
timeseries_container=None,
chunksize=defaults.CHUNKSIZE,
n_jobs=defaults.N_PROCESSES,
show_warnings=defaults.SHOW_WARNINGS,
disable_progressbar=defaults.DISABLE_PROGRESSBAR,
profile=defaults.PROFILING,
profiling_filename=defaults.PROFILING_FILENAME,
profiling_sorting=defaults.PROFILING_SORTING,
test_for_binary_target_binary_feature=defaults.TEST_FOR_BINARY_TARGET_BINARY_FEATURE,
test_for_binary_target_real_feature=defaults.TEST_FOR_BINARY_TARGET_REAL_FEATURE,
test_for_real_target_binary_feature=defaults.TEST_FOR_REAL_TARGET_BINARY_FEATURE,
test_for_real_target_real_feature=defaults.TEST_FOR_REAL_TARGET_REAL_FEATURE,
fdr_level=defaults.FDR_LEVEL,
hypotheses_independent=defaults.HYPOTHESES_INDEPENDENT,
ml_task='auto'):
"""
Create a new RelevantFeatureAugmenter instance.
:param settings: The extraction settings to use. Leave empty to use the default ones.
:type settings: tsfresh.feature_extraction.settings.ExtendedFCParameters
:param filter_only_tsfresh_features: Whether to touch the manually-created features during feature selection or
not.
:type filter_only_tsfresh_features: bool
:param feature_selection_settings: The feature selection settings.
:type feature_selection_settings: tsfresh.feature_selection.settings.FeatureSelectionSettings
:param feature_extraction_settings: The feature extraction settings.
:type feature_selection_settings: tsfresh.feature_extraction.settings.ComprehensiveFCParameters
:param column_id: The column with the id. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_id: basestring
:param column_sort: The column with the sort data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_sort: basestring
:param column_kind: The column with the kind data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_kind: basestring
:param column_value: The column with the values. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_value: basestring
:param chunksize: The size of one chunk that is submitted to the worker
process for the parallelisation. Where one chunk is defined as a
singular time series for one id and one kind. If you set the chunksize
to 10, then it means that one task is to calculate all features for 10
time series. If it is set it to None, depending on distributor,
heuristics are used to find the optimal chunksize. If you get out of
memory exceptions, you can try it with the dask distributor and a
smaller chunksize.
:type chunksize: None or int
:param n_jobs: The number of processes to use for parallelization. If zero, no parallelization is used.
:type n_jobs: int
:param: show_warnings: Show warnings during the feature extraction (needed for debugging of calculators).
:type show_warnings: bool
:param disable_progressbar: Do not show a progressbar while doing the calculation.
:type disable_progressbar: bool
:param profile: Turn on profiling during feature extraction
:type profile: bool
:param profiling_sorting: How to sort the profiling results (see the documentation of the profiling package for
more information)
:type profiling_sorting: basestring
:param profiling_filename: Where to save the profiling results.
:type profiling_filename: basestring
:param test_for_binary_target_binary_feature: Which test to be used for binary target, binary feature (currently unused)
:type test_for_binary_target_binary_feature: str
:param test_for_binary_target_real_feature: Which test to be used for binary target, real feature
:type test_for_binary_target_real_feature: str
:param test_for_real_target_binary_feature: Which test to be used for real target, binary feature (currently unused)
:type test_for_real_target_binary_feature: str
:param test_for_real_target_real_feature: Which test to be used for real target, real feature (currently unused)
:type test_for_real_target_real_feature: str
:param fdr_level: The FDR level that should be respected, this is the theoretical expected percentage of irrelevant
features among all created features.
:type fdr_level: float
:param hypotheses_independent: Can the significance of the features be assumed to be independent?
Normally, this should be set to False as the features are never
independent (e.g. mean and median)
:type hypotheses_independent: bool
:param ml_task: The intended machine learning task. Either `'classification'`, `'regression'` or `'auto'`.
Defaults to `'auto'`, meaning the intended task is inferred from `y`.
If `y` has a boolean, integer or object dtype, the task is assumend to be classification,
else regression.
:type ml_task: str
"""
self.feature_extractor = FeatureAugmenter(column_id=column_id, column_sort=column_sort, column_kind=column_kind,
column_value=column_value,
default_fc_parameters=default_fc_parameters,
kind_to_fc_parameters=kind_to_fc_parameters,
chunksize=chunksize,
n_jobs=n_jobs, show_warnings=show_warnings,
disable_progressbar=disable_progressbar,
profile=profile,
profiling_filename=profiling_filename,
profiling_sorting=profiling_sorting
)
self.feature_selector = FeatureSelector(
test_for_binary_target_binary_feature=test_for_binary_target_binary_feature,
test_for_binary_target_real_feature=test_for_binary_target_real_feature,
test_for_real_target_binary_feature=test_for_real_target_binary_feature,
test_for_real_target_real_feature=test_for_real_target_real_feature,
fdr_level=fdr_level, hypotheses_independent=hypotheses_independent,
n_jobs=n_jobs, chunksize=chunksize, ml_task=ml_task
)
self.filter_only_tsfresh_features = filter_only_tsfresh_features
self.timeseries_container = timeseries_container
class RelevantFeatureAugmenter(BaseEstimator, TransformerMixin):
"""
Sklearn-compatible estimator to calculate relevant features out of a time series and add them to a data sample.
As many other sklearn estimators, this estimator works in two steps:
In the fit phase, all possible time series features are calculated using the time series, that is set by the
set_timeseries_container function (if the features are not manually changed by handing in a
feature_extraction_settings object). Then, their significance and relevance to the target is computed using
statistical methods and only the relevant ones are selected using the Benjamini Hochberg procedure. These features
are stored internally.
In the transform step, the information on which features are relevant from the fit step is used and those features
are extracted from the time series. These extracted features are then added to the input data sample.
This estimator is a wrapper around most of the functionality in the tsfresh package. For more information on the
subtasks, please refer to the single modules and functions, which are:
* Settings for the feature extraction: :class:`~tsfresh.feature_extraction.settings.ComprehensiveFCParameters`
* Feature extraction method: :func:`~tsfresh.feature_extraction.extraction.extract_features`
* Extracted features: :mod:`~tsfresh.feature_extraction.feature_calculators`
* Feature selection: :func:`~tsfresh.feature_selection.feature_selector.check_fs_sig_bh`
This estimator works analogue to the :class:`~tsfresh.transformers.feature_augmenter.FeatureAugmenter` with
the difference that this estimator does only output and calculate the relevant features,
whereas the other outputs all features.
Also for this estimator, two datasets play a crucial role:
1. the time series container with the timeseries data. This container (for the format see
:mod:`~tsfresh.feature_extraction.extraction`) contains the data which is used for calculating the
features. It must be groupable by ids which are used to identify which feature should be attached to which row
in the second dataframe:
2. the input data, where the features will be added to.
Imagine the following situation: You want to classify 10 different financial shares and you have their development
in the last year as a time series. You would then start by creating features from the metainformation of the
shares, e.g. how long they were on the market etc. and filling up a table - the features of one stock in one row.
>>> # Fill in the information of the stocks and the target
>>> X_train, X_test, y_train = pd.DataFrame(), pd.DataFrame(), pd.Series()
You can then extract all the relevant features from the time development of the shares, by using this estimator:
>>> train_time_series, test_time_series = read_in_timeseries() # get the development of the shares
>>> from tsfresh.transformers import RelevantFeatureAugmenter
>>> augmenter = RelevantFeatureAugmenter()
>>> augmenter.set_timeseries_container(train_time_series)
>>> augmenter.fit(X_train, y_train)
>>> augmenter.set_timeseries_container(test_time_series)
>>> X_test_with_features = augmenter.transform(X_test)
X_test_with_features will then contain the same information as X_test (with all the meta information you have
probably added) plus some relevant time series features calculated on the time series you handed in.
Please keep in mind that the time series you hand in before fit or transform must contain data for the rows that are
present in X.
If your set filter_only_tsfresh_features to True, your manually-created features that were present in X_train (or
X_test) before using this estimator are not touched. Otherwise, also those features are evaluated and may be
rejected from the data sample, because they are irrelevant.
For a description what the parameters column_id, column_sort, column_kind and column_value mean, please see
:mod:`~tsfresh.feature_extraction.extraction`.
You can control the feature extraction in the fit step (the feature extraction in the transform step is done
automatically) as well as the feature selection in the fit step by handing in settings.
However, the default settings which are used if you pass no flags are often quite sensible.
"""
def __init__(self,
filter_only_tsfresh_features=True,
default_fc_parameters=None,
kind_to_fc_parameters=None,
column_id=None, column_sort=None, column_kind=None, column_value=None,
timeseries_container=None,
chunksize=defaults.CHUNKSIZE,
n_jobs=defaults.N_PROCESSES,
show_warnings=defaults.SHOW_WARNINGS,
disable_progressbar=defaults.DISABLE_PROGRESSBAR,
profile=defaults.PROFILING,
profiling_filename=defaults.PROFILING_FILENAME,
profiling_sorting=defaults.PROFILING_SORTING,
test_for_binary_target_binary_feature=defaults.TEST_FOR_BINARY_TARGET_BINARY_FEATURE,
test_for_binary_target_real_feature=defaults.TEST_FOR_BINARY_TARGET_REAL_FEATURE,
test_for_real_target_binary_feature=defaults.TEST_FOR_REAL_TARGET_BINARY_FEATURE,
test_for_real_target_real_feature=defaults.TEST_FOR_REAL_TARGET_REAL_FEATURE,
fdr_level=defaults.FDR_LEVEL,
hypotheses_independent=defaults.HYPOTHESES_INDEPENDENT,
ml_task='auto'):
"""
Create a new RelevantFeatureAugmenter instance.
:param settings: The extraction settings to use. Leave empty to use the default ones.
:type settings: tsfresh.feature_extraction.settings.ExtendedFCParameters
:param filter_only_tsfresh_features: Whether to touch the manually-created features during feature selection or
not.
:type filter_only_tsfresh_features: bool
:param feature_selection_settings: The feature selection settings.
:type feature_selection_settings: tsfresh.feature_selection.settings.FeatureSelectionSettings
:param feature_extraction_settings: The feature extraction settings.
:type feature_selection_settings: tsfresh.feature_extraction.settings.ComprehensiveFCParameters
:param column_id: The column with the id. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_id: basestring
:param column_sort: The column with the sort data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_sort: basestring
:param column_kind: The column with the kind data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_kind: basestring
:param column_value: The column with the values. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_value: basestring
:param chunksize: The size of one chunk that is submitted to the worker
process for the parallelisation. Where one chunk is defined as a
singular time series for one id and one kind. If you set the chunksize
to 10, then it means that one task is to calculate all features for 10
time series. If it is set it to None, depending on distributor,
heuristics are used to find the optimal chunksize. If you get out of
memory exceptions, you can try it with the dask distributor and a
smaller chunksize.
:type chunksize: None or int
:param n_jobs: The number of processes to use for parallelization. If zero, no parallelization is used.
:type n_jobs: int
:param: show_warnings: Show warnings during the feature extraction (needed for debugging of calculators).
:type show_warnings: bool
:param disable_progressbar: Do not show a progressbar while doing the calculation.
:type disable_progressbar: bool
:param profile: Turn on profiling during feature extraction
:type profile: bool
:param profiling_sorting: How to sort the profiling results (see the documentation of the profiling package for
more information)
:type profiling_sorting: basestring
:param profiling_filename: Where to save the profiling results.
:type profiling_filename: basestring
:param test_for_binary_target_binary_feature: Which test to be used for binary target, binary feature (currently unused)
:type test_for_binary_target_binary_feature: str
:param test_for_binary_target_real_feature: Which test to be used for binary target, real feature
:type test_for_binary_target_real_feature: str
:param test_for_real_target_binary_feature: Which test to be used for real target, binary feature (currently unused)
:type test_for_real_target_binary_feature: str
:param test_for_real_target_real_feature: Which test to be used for real target, real feature (currently unused)
:type test_for_real_target_real_feature: str
:param fdr_level: The FDR level that should be respected, this is the theoretical expected percentage of irrelevant
features among all created features.
:type fdr_level: float
:param hypotheses_independent: Can the significance of the features be assumed to be independent?
Normally, this should be set to False as the features are never
independent (e.g. mean and median)
:type hypotheses_independent: bool
:param ml_task: The intended machine learning task. Either `'classification'`, `'regression'` or `'auto'`.
Defaults to `'auto'`, meaning the intended task is inferred from `y`.
If `y` has a boolean, integer or object dtype, the task is assumend to be classification,
else regression.
:type ml_task: str
"""
self.feature_extractor = FeatureAugmenter(column_id=column_id, column_sort=column_sort, column_kind=column_kind,
column_value=column_value,
default_fc_parameters=default_fc_parameters,
kind_to_fc_parameters=kind_to_fc_parameters,
chunksize=chunksize,
n_jobs=n_jobs, show_warnings=show_warnings,
disable_progressbar=disable_progressbar,
profile=profile,
profiling_filename=profiling_filename,
profiling_sorting=profiling_sorting
)
self.feature_selector = FeatureSelector(
test_for_binary_target_binary_feature=test_for_binary_target_binary_feature,
test_for_binary_target_real_feature=test_for_binary_target_real_feature,
test_for_real_target_binary_feature=test_for_real_target_binary_feature,
test_for_real_target_real_feature=test_for_real_target_real_feature,
fdr_level=fdr_level, hypotheses_independent=hypotheses_independent,
n_jobs=n_jobs, chunksize=chunksize, ml_task=ml_task
)
self.filter_only_tsfresh_features = filter_only_tsfresh_features
self.timeseries_container = timeseries_container
def set_timeseries_container(self, timeseries_container):
"""
Set the timeseries, with which the features will be calculated. For a format of the time series container,
please refer to :mod:`~tsfresh.feature_extraction.extraction`. The timeseries must contain the same indices
as the later DataFrame, to which the features will be added (the one you will pass to :func:`~transform` or
:func:`~fit`). You can call this function as often as you like, to change the timeseries later
(e.g. if you want to extract for different ids).
:param timeseries_container: The timeseries as a pandas.DataFrame or a dict. See
:mod:`~tsfresh.feature_extraction.extraction` for the format.
:type timeseries_container: pandas.DataFrame or dict
:return: None
:rtype: None
"""
self.timeseries_container = timeseries_container
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 transform(self, X):
"""
After the fit step, it is known which features are relevant, Only extract those from the time series handed in
with the function :func:`~set_timeseries_container`.
If filter_only_tsfresh_features is False, also delete the irrelevant, already present features in the data frame.
:param X: the data sample to add the relevant (and delete the irrelevant) features to.
:type X: pandas.DataFrame or numpy.array
:return: a data sample with the same information as X, but with added relevant time series features and
deleted irrelevant information (only if filter_only_tsfresh_features is False).
:rtype: pandas.DataFrame
"""
if self.feature_selector.relevant_features is None:
raise RuntimeError("You have to call fit before.")
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)
relevant_time_series_features = set(self.feature_selector.relevant_features) - set(pd.DataFrame(X).columns)
relevant_extraction_settings = from_columns(relevant_time_series_features)
# Set imputing strategy
impute_function = partial(impute_dataframe_range, col_to_max=self.col_to_max,
col_to_min=self.col_to_min, col_to_median=self.col_to_median)
relevant_feature_extractor = FeatureAugmenter(kind_to_fc_parameters=relevant_extraction_settings,
default_fc_parameters={},
column_id=self.feature_extractor.column_id,
column_sort=self.feature_extractor.column_sort,
column_kind=self.feature_extractor.column_kind,
column_value=self.feature_extractor.column_value,
chunksize=self.feature_extractor.chunksize,
n_jobs=self.feature_extractor.n_jobs,
show_warnings=self.feature_extractor.show_warnings,
disable_progressbar=self.feature_extractor.disable_progressbar,
impute_function=impute_function,
profile=self.feature_extractor.profile,
profiling_filename=self.feature_extractor.profiling_filename,
profiling_sorting=self.feature_extractor.profiling_sorting)
relevant_feature_extractor.set_timeseries_container(self.feature_extractor.timeseries_container)
X_augmented = relevant_feature_extractor.transform(X)
if self.filter_only_tsfresh_features:
return X_augmented.copy().loc[:, self.feature_selector.relevant_features + X.columns.tolist()]
else:
return X_augmented.copy().loc[:, self.feature_selector.relevant_features]
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
def __init__(self,
filter_only_tsfresh_features=True,
default_fc_parameters=None,
kind_to_fc_parameters=None,
column_id=None,
column_sort=None,
column_kind=None,
column_value=None,
timeseries_container=None,
chunksize=defaults.CHUNKSIZE,
impute_function=defaults.IMPUTE_FUNCTION,
n_jobs=defaults.N_PROCESSES,
show_warnings=defaults.SHOW_WARNINGS,
disable_progressbar=defaults.DISABLE_PROGRESSBAR,
profile=defaults.PROFILING,
profiling_filename=defaults.PROFILING_FILENAME,
profiling_sorting=defaults.PROFILING_SORTING,
test_for_binary_target_binary_feature=defaults.
TEST_FOR_BINARY_TARGET_BINARY_FEATURE,
test_for_binary_target_real_feature=defaults.
TEST_FOR_BINARY_TARGET_REAL_FEATURE,
test_for_real_target_binary_feature=defaults.
TEST_FOR_REAL_TARGET_BINARY_FEATURE,
test_for_real_target_real_feature=defaults.
TEST_FOR_REAL_TARGET_REAL_FEATURE,
fdr_level=defaults.FDR_LEVEL,
hypotheses_independent=defaults.HYPOTHESES_INDEPENDENT):
"""
Create a new RelevantFeatureAugmenter instance.
:param settings: The extraction settings to use. Leave empty to use the default ones.
:type settings: tsfresh.feature_extraction.settings.ExtendedFCParameters
:param filter_only_tsfresh_features: Whether to touch the manually-created features during feature selection or
not.
:type filter_only_tsfresh_features: bool
:param feature_selection_settings: The feature selection settings.
:type feature_selection_settings: tsfresh.feature_selection.settings.FeatureSelectionSettings
:param feature_extraction_settings: The feature extraction settings.
:type feature_selection_settings: tsfresh.feature_extraction.settings.ComprehensiveFCParameters
:param column_id: The column with the id. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_id: basestring
:param column_sort: The column with the sort data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_sort: basestring
:param column_kind: The column with the kind data. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_kind: basestring
:param column_value: The column with the values. See :mod:`~tsfresh.feature_extraction.extraction`.
:type column_value: basestring
:param chunksize: The size of one chunk for the parallelisation
:type chunksize: None or int
:param n_jobs: The number of processes to use for parallelization. If zero, no parallelization is used.
:type n_jobs: int
:param: show_warnings: Show warnings during the feature extraction (needed for debugging of calculators).
:type show_warnings: bool
:param disable_progressbar: Do not show a progressbar while doing the calculation.
:type disable_progressbar: bool
:param profile: Turn on profiling during feature extraction
:type profile: bool
:param profiling_sorting: How to sort the profiling results (see the documentation of the profiling package for
more information)
:type profiling_sorting: basestring
:param profiling_filename: Where to save the profiling results.
:type profiling_filename: basestring
:param test_for_binary_target_binary_feature: Which test to be used for binary target, binary feature (currently unused)
:type test_for_binary_target_binary_feature: str
:param test_for_binary_target_real_feature: Which test to be used for binary target, real feature
:type test_for_binary_target_real_feature: str
:param test_for_real_target_binary_feature: Which test to be used for real target, binary feature (currently unused)
:type test_for_real_target_binary_feature: str
:param test_for_real_target_real_feature: Which test to be used for real target, real feature (currently unused)
:type test_for_real_target_real_feature: str
:param fdr_level: The FDR level that should be respected, this is the theoretical expected percentage of irrelevant
features among all created features.
:type fdr_level: float
:param hypotheses_independent: Can the significance of the features be assumed to be independent?
Normally, this should be set to False as the features are never
independent (e.g. mean and median)
:type hypotheses_independent: bool
"""
self.feature_extractor = FeatureAugmenter(
column_id=column_id,
column_sort=column_sort,
column_kind=column_kind,
column_value=column_value,
default_fc_parameters=default_fc_parameters,
kind_to_fc_parameters=kind_to_fc_parameters,
chunksize=chunksize,
n_jobs=n_jobs,
show_warnings=show_warnings,
disable_progressbar=disable_progressbar,
impute_function=impute_function,
profile=profile,
profiling_filename=profiling_filename,
profiling_sorting=profiling_sorting)
self.feature_selector = FeatureSelector(
test_for_binary_target_binary_feature=
test_for_binary_target_binary_feature,
test_for_binary_target_real_feature=
test_for_binary_target_real_feature,
test_for_real_target_binary_feature=
test_for_real_target_binary_feature,
test_for_real_target_real_feature=test_for_real_target_real_feature,
fdr_level=fdr_level,
hypotheses_independent=hypotheses_independent,
n_jobs=n_jobs,
chunksize=chunksize)
self.filter_only_tsfresh_features = filter_only_tsfresh_features
self.timeseries_container = timeseries_container
