def fit(self, X, y):
"""
Extract the information, which of the features are relevent using the given target.
For more information, please see the :func:`~tsfresh.festure_selection.festure_selector.check_fs_sig_bh`
function. All columns in the input data sample are treated as feature. The index of all
rows in X must be present in y.
:param X: data sample with the features, which will be classified as relevent or not
:type X: pandas.DataFrame or numpy.array
:param y: target vecotr to be used, to classify the features
:type y: pandas.Series or numpy.array
:return: the fitted estimator with the information, which features are relevant
:rtype: FeatureSelector
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X.copy())
if not isinstance(y, pd.Series):
y = pd.Series(y.copy())
df_bh = check_fs_sig_bh(X, y, self.settings)
self.relevant_features = df_bh[df_bh.rejected].Feature
return self
def fit(self, X, y):
"""
Extract the information, which of the features are relevent using the given target.
For more information, please see the :func:`~tsfresh.festure_selection.festure_selector.check_fs_sig_bh`
function. All columns in the input data sample are treated as feature. The index of all
rows in X must be present in y.
:param X: data sample with the features, which will be classified as relevant or not
:type X: pandas.DataFrame or numpy.array
:param y: target vecotr to be used, to classify the features
:type y: pandas.Series or numpy.array
:return: the fitted estimator with the information, which features are relevant
:rtype: FeatureSelector
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X.copy())
if not isinstance(y, pd.Series):
y = pd.Series(y.copy())
df_bh = check_fs_sig_bh(X, y, self.n_processes, self.chunksize,
self.fdr_level, self.hypotheses_independent,
self.test_for_binary_target_real_feature)
self.relevant_features = df_bh.loc[df_bh.rejected].Feature.tolist()
self.feature_importances_ = 1.0 - df_bh.p_value.values
self.p_values = df_bh.p_value.values
self.features = df_bh.Feature.tolist()
return self
def select_features(X, y, 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,
n_processes=defaults.N_PROCESSES, chunksize=defaults.CHUNKSIZE):
"""
Check the significance of all features (columns) of feature matrix X and return a possibly reduced feature matrix
only containing relevant features.
The feature matrix must be a pandas.DataFrame in the format:
+-------+-----------+-----------+-----+-----------+
| index | feature_1 | feature_2 | ... | feature_N |
+=======+===========+===========+=====+===========+
| A | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| B | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
Each column will be handled as a feature and tested for its significance to the target.
The target vector must be a pandas.Series or numpy.array in the form
+-------+--------+
| index | target |
+=======+========+
| A | ... |
+-------+--------+
| B | ... |
+-------+--------+
| . | ... |
+-------+--------+
| . | ... |
+-------+--------+
and must contain all id's that are in the feature matrix. If y is a numpy.array without index, it is assumed
that y has the same order and length than X and the rows correspond to each other.
Examples
========
>>> from tsfresh.examples import load_robot_execution_failures
>>> from tsfresh import extract_features, select_features
>>> df, y = load_robot_execution_failures()
>>> X_extracted = extract_features(df, column_id='id', column_sort='time')
>>> X_selected = select_features(X_extracted, y)
:param X: Feature matrix in the format mentioned before which will be reduced to only the relevant features.
It can contain both binary or real-valued features at the same time.
:type X: pandas.DataFrame
:param y: Target vector which is needed to test which features are relevant. Can be binary or real-valued.
:type y: pandas.Series or numpy.ndarray
: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 n_processes: Number of processes to use during the p-value calculation
:type n_processes: int
:param chunksize: Size of the chunks submitted to the worker processes
:type chunksize: int
:return: The same DataFrame as X, but possibly with reduced number of columns ( = features).
:rtype: pandas.DataFrame
:raises: ``ValueError`` when the target vector does not fit to the feature matrix.
"""
check_for_nans_in_columns(X)
if not isinstance(y, (pd.Series, np.ndarray)):
raise TypeError("The type of target vector y must be one of: pandas.Series, numpy.ndarray")
if len(X) < 2:
raise ValueError("X must contain at least two samples.")
elif isinstance(y, pd.Series) and not X.index.isin(y.index).all():
raise ValueError("Index of X must be a subset of y's index")
elif isinstance(y, np.ndarray):
if not len(y) >= len(X):
raise ValueError("Target vector y is shorter than feature matrix X")
y = pd.Series(y, index=X.index)
df_bh = check_fs_sig_bh(X, y, n_processes, chunksize, fdr_level, hypotheses_independent,
test_for_binary_target_real_feature)
return X.loc[:, df_bh[df_bh.rejected].Feature]
def select_features(X, y, feature_selection_settings=None):
"""
Check the significance of all features (columns) of feature matrix X and return a possibly reduced feature matrix
only containing relevant features.
The feature matrix must be a pandas.DataFrame in the format:
+-------+-----------+-----------+-----+-----------+
| index | feature_1 | feature_2 | ... | feature_N |
+=======+===========+===========+=====+===========+
| A | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| B | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
| ... | ... | ... | ... | ... |
+-------+-----------+-----------+-----+-----------+
Each column will be handled as a feature and tested for its significance to the target.
The target vector must be a pandas.Series or numpy.array in the form
+-------+--------+
| index | target |
+=======+========+
| A | ... |
+-------+--------+
| B | ... |
+-------+--------+
| . | ... |
+-------+--------+
| . | ... |
+-------+--------+
and must contain all id's that are in the feature matrix. If y is a numpy.array without index, it is assumed
that y has the same order and length than X and the rows correspond to each other.
Examples
========
>>> from tsfresh.examples import load_robot_execution_failures
>>> from tsfresh import extract_features, select_features
>>> df, y = load_robot_execution_failures()
>>> X_extracted = extract_features(df, column_id='id', column_sort='time')
>>> X_selected = select_features(X_extracted, y)
:param X: Feature matrix in the format mentioned before which will be reduced to only the relevant features.
It can contain both binary or real-valued features at the same time.
:type X: pandas.DataFrame
:param y: Target vector which is needed to test, which features are relevant. Can be binary or real-valued.
:type y: pandas.Series or numpy.ndarray
:param feature_selection_settings: The settings to control the feature selection algorithms. See
:class:`~tsfresh.feature_selection.settings.py` for more information. If none is passed, the defaults
will be used.
:type feature_selection_settings: FeatureSignificanceTestsSettings
:return: The same DataFrame as X, but possibly with reduced number of columns ( = features).
:rtype: pandas.DataFrame
:raises: ``ValueError`` when the target vector does not fit to the feature matrix.
"""
check_for_nans_in_columns(X)
if feature_selection_settings is None:
feature_selection_settings = FeatureSignificanceTestsSettings()
if not isinstance(y, (pd.Series, np.ndarray)):
raise TypeError(
"The type of target vector y must be one of: pandas.Series, numpy.ndarray"
)
if len(X) < 2:
raise ValueError("X must contain at least two samples.")
elif isinstance(y, pd.Series) and not X.index.isin(y.index).all():
raise ValueError("Index of X must be a subset of y's index")
elif isinstance(y, np.ndarray):
if not len(y) >= len(X):
raise ValueError(
"Target vector y is shorter than feature matrix X")
y = pd.Series(y, index=X.index)
df_bh = check_fs_sig_bh(X, y, feature_selection_settings)
return X.loc[:, df_bh[df_bh.rejected].Feature]