class FeatureAugmenterTestCase(DataTestCase):
def setUp(self):
self.test_df = self.create_test_data_sample()
self.settings = FeatureExtractionSettings()
self.settings.set_default_parameters("a")
calculation_settings_mapping = {
"length":
self.settings.kind_to_calculation_settings_mapping["a"]["length"]
}
self.settings.kind_to_calculation_settings_mapping = {
"a": calculation_settings_mapping.copy(),
"b": calculation_settings_mapping.copy()
}
def test_fit_and_transform(self):
augmenter = FeatureAugmenter(column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind",
settings=self.settings)
# Fit should do nothing
returned_df = augmenter.fit()
self.assertEqual(returned_df, augmenter)
self.assertRaises(RuntimeError, augmenter.transform, None)
augmenter.set_timeseries_container(self.test_df)
# Add features to all time series
X_with_index = pd.DataFrame([{"feature_1": 1}] * 2, index=[1, 5])
X_transformed = augmenter.transform(X_with_index)
# Require same shape
for i in X_transformed.index:
self.assertIn(i, X_with_index.index)
for i in X_with_index.index:
self.assertIn(i, X_transformed.index)
self.assertEqual(X_transformed.shape, (2, 3))
# Preserve old features
self.assertEqual(list(X_transformed.columns),
["feature_1", "a__length", "b__length"])
# Features are not allowed to be NaN
for index, row in X_transformed.iterrows():
print(index, row)
self.assertFalse(np.isnan(row["a__length"]))
self.assertFalse(np.isnan(row["b__length"]))
def test_add_features_to_only_a_part(self):
augmenter = FeatureAugmenter(column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind",
settings=self.settings)
augmenter.set_timeseries_container(self.test_df)
X_with_not_all_ids = pd.DataFrame([{"feature_1": 1}], index=[1])
X_transformed = augmenter.transform(X_with_not_all_ids)
for i in X_transformed.index:
self.assertIn(i, X_with_not_all_ids.index)
for i in X_with_not_all_ids.index:
self.assertIn(i, X_transformed.index)
self.assertEqual(X_transformed.shape, (1, 3))
self.assertEqual(X_transformed.index, [1])
# Features are not allowed to be NaN
for index, row in X_transformed.iterrows():
print(index, row)
self.assertFalse(np.isnan(row["a__length"]))
self.assertFalse(np.isnan(row["b__length"]))
def extract_features(timeseries_container,
feature_extraction_settings=None,
column_id=None,
column_sort=None,
column_kind=None,
column_value=None):
"""
Extract features from
* a :class:`pandas.DataFrame` containing the different time series
or
* a dictionary of :class:`pandas.DataFrame` each containing one type of time series
In both cases a :class:`pandas.DataFrame` with the calculated features will be returned.
For a list of all the calculated time series features, please see the
:class:`~tsfresh.feature_extraction.settings.FeatureExtractionSettings` class,
which is used to control which features with which parameters are calculated.
For a detailed explanation of the different parameters and data formats please see :ref:`data-formats-label`.
Examples
========
>>> from tsfresh.examples import load_robot_execution_failures
>>> from tsfresh import extract_features
>>> df, _ = load_robot_execution_failures()
>>> X = extract_features(df, column_id='id', column_sort='time')
which would give the same results as described above. In this case, the column_kind is not allowed.
Except that, the same rules for leaving out the columns apply as above.
:param timeseries_container: The pandas.DataFrame with the time series to compute the features for, or a
dictionary of pandas.DataFrames.
:type timeseries_container: pandas.DataFrame or dict
:param column_id: The name of the id column to group by.
:type column_id: str
:param column_sort: The name of the sort column.
:type column_sort: str
:param column_kind: The name of the column keeping record on the kind of the value.
:type column_kind: str
:param column_value: The name for the column keeping the value itself.
:type column_value: str
:param feature_extraction_settings: settings object that controls which features are calculated
:type feature_extraction_settings: tsfresh.feature_extraction.settings.FeatureExtractionSettings
:return: The (maybe imputed) DataFrame with the extracted features.
:rtype: pandas.DataFrame
"""
# Always use the standardized way of storing the data.
# See the function normalize_input_to_internal_representation for more information.
kind_to_df_map, column_id, column_value = \
dataframe_functions.normalize_input_to_internal_representation(timeseries_container, column_id, column_sort,
column_kind, column_value)
# Use the standard setting if the user did not supply ones himself.
if feature_extraction_settings is None:
feature_extraction_settings = FeatureExtractionSettings()
for key in kind_to_df_map:
feature_extraction_settings.set_default_parameters(key)
# If requested, do profiling (advanced feature)
if feature_extraction_settings.PROFILING:
profiler = profiling.start_profiling()
# Extract the time series features for every type of time series and concatenate them together.
all_possible_unique_id_values = set(id_value
for kind, df in kind_to_df_map.items()
for id_value in df[column_id])
df_with_ids = pd.DataFrame(index=all_possible_unique_id_values)
pool = Pool(feature_extraction_settings.n_processes)
partial_extract_features_for_one_time_series = partial(
_extract_features_for_one_time_series,
column_id=column_id,
column_value=column_value,
settings=feature_extraction_settings)
extracted_features = pool.map(partial_extract_features_for_one_time_series,
kind_to_df_map.items())
# Add time series features to result
result = pd.concat([df_with_ids] + extracted_features, axis=1, join='outer', join_axes=[df_with_ids.index])\
.astype(np.float64)
# Impute the result if requested
if feature_extraction_settings.IMPUTE is not None:
feature_extraction_settings.IMPUTE(result)
# Turn off profiling if it was turned on
if feature_extraction_settings.PROFILING:
profiling.end_profiling(
profiler,
filename=feature_extraction_settings.PROFILING_FILENAME,
sorting=feature_extraction_settings.PROFILING_SORTING)
return result
def extract_features(timeseries_container, feature_extraction_settings=None,
column_id=None, column_sort=None, column_kind=None, column_value=None,
parallelization=None):
"""
Extract features from
* a :class:`pandas.DataFrame` containing the different time series
or
* a dictionary of :class:`pandas.DataFrame` each containing one type of time series
In both cases a :class:`pandas.DataFrame` with the calculated features will be returned.
For a list of all the calculated time series features, please see the
:class:`~tsfresh.feature_extraction.settings.FeatureExtractionSettings` class,
which is used to control which features with which parameters are calculated.
For a detailed explanation of the different parameters and data formats please see :ref:`data-formats-label`.
Examples
========
>>> from tsfresh.examples import load_robot_execution_failures
>>> from tsfresh import extract_features
>>> df, _ = load_robot_execution_failures()
>>> X = extract_features(df, column_id='id', column_sort='time')
which would give the same results as described above. In this case, the column_kind is not allowed.
Except that, the same rules for leaving out the columns apply as above.
:param timeseries_container: The pandas.DataFrame with the time series to compute the features for, or a
dictionary of pandas.DataFrames.
:type timeseries_container: pandas.DataFrame or dict
:param feature_extraction_settings: settings object that controls which features are calculated
:type feature_extraction_settings: tsfresh.feature_extraction.settings.FeatureExtractionSettings
:param column_id: The name of the id column to group by.
:type column_id: str
:param column_sort: The name of the sort column.
:type column_sort: str
:param column_kind: The name of the column keeping record on the kind of the value.
:type column_kind: str
:param column_value: The name for the column keeping the value itself.
:type column_value: str
:param parallelization: Either ``'per_sample'`` or ``'per_kind'`` , see
:func:`~tsfresh.feature_extraction.extraction._extract_features_parallel_per_sample`,
:func:`~tsfresh.feature_extraction.extraction._extract_features_parallel_per_kind` and
:ref:`parallelization-label` for details.
:type parallelization: str
:return: The (maybe imputed) DataFrame containing extracted features.
:rtype: pandas.DataFrame
"""
import logging
logging.basicConfig()
# Always use the standardized way of storing the data.
# See the function normalize_input_to_internal_representation for more information.
kind_to_df_map, column_id, column_value = \
dataframe_functions.normalize_input_to_internal_representation(df_or_dict=timeseries_container,
column_id=column_id,
column_sort=column_sort,
column_kind=column_kind,
column_value=column_value)
# Use the standard setting if the user did not supply ones himself.
if feature_extraction_settings is None:
feature_extraction_settings = FeatureExtractionSettings()
for key in kind_to_df_map:
feature_extraction_settings.set_default_parameters(key)
# Choose the parallelization according to a rule-of-thumb
if parallelization is None:
parallelization = 'per_sample' if (feature_extraction_settings.n_processes / 2) > len(kind_to_df_map) \
else 'per_kind'
_logger.info('Parallelizing feature calculation {}'.format(parallelization))
# If requested, do profiling (advanced feature)
if feature_extraction_settings.PROFILING:
profiler = profiling.start_profiling()
# Calculate the result
if parallelization == 'per_kind':
result = _extract_features_per_kind(kind_to_df_map, feature_extraction_settings,
column_id, column_value)
elif parallelization == 'per_sample':
result = _extract_features_parallel_per_sample(kind_to_df_map, feature_extraction_settings,
column_id, column_value)
elif parallelization == 'no_parallelization':
result = _extract_features_per_kind(kind_to_df_map, feature_extraction_settings,
column_id, column_value, serial=True)
else:
raise ValueError("Argument parallelization must be one of: 'per_kind', 'per_sample'")
# Turn off profiling if it was turned on
if feature_extraction_settings.PROFILING:
profiling.end_profiling(profiler, filename=feature_extraction_settings.PROFILING_FILENAME,
sorting=feature_extraction_settings.PROFILING_SORTING)
return result