Feature extractors

Default feature extractor for 1 animals and 14 body-parts

class simba.feature_extractors.feature_extractor_14bp.ExtractFeaturesFrom14bps(config_path: str)

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from two animals with 7 tracked body-parts each. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom14bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save features to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 1 animals and 16 body-parts

class simba.feature_extractors.feature_extractor_16bp.ExtractFeaturesFrom16bps(config_path: str)

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from two animals with 8 tracked body-parts each. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom16bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save feature battery to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 1 animals and 4 body-parts

class simba.feature_extractors.feature_extractor_4bp.ExtractFeaturesFrom4bps(config_path: Union[str, PathLike])

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data with one animal and 4 tracked body-parts. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial.

Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom4bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save features to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 1 animals and 7 body-parts

class simba.feature_extractors.feature_extractor_7bp.ExtractFeaturesFrom7bps(config_path: Union[str, PathLike])

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from single animals with 7 tracked body-parts. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom7bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save features to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 1 animals and 8 body-parts

class simba.feature_extractors.feature_extractor_8bp.ExtractFeaturesFrom8bps(config_path: Union[str, PathLike])

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from single animals with 8 tracked body-parts. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom8bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save features to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 2 animals and 16 body-parts

class simba.feature_extractors.feature_extractor_8bps_2_animals.ExtractFeaturesFrom8bps2Animals(config_path: str)

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from two animals with 4 tracked body-parts each. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom8bps2Animals(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save feature battery to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Default feature extractor for 1 animals and 9 body-parts

class simba.feature_extractors.feature_extractor_9bp.ExtractFeaturesFrom9bps(config_path: str)

Bases: ConfigReader, FeatureExtractionMixin

Extracts hard-coded set of features from pose-estimation data from single animals with 9 tracked body-parts. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial. Expected pose configuration

Examples

>>> feature_extractor = ExtractFeaturesFrom9bps(config_path='MyProjectConfig')
>>> feature_extractor.run()

Default feature extractor for user-defined body-parts

class simba.feature_extractors.feature_extractor_user_defined.UserDefinedFeatureExtractor(config_path: str)

Bases: ConfigReader, FeatureExtractionMixin

Generic featurizer of data within SimBA project using user-defined body-parts in the pose-estimation data. Results are stored in the project_folder/csv/features_extracted directory of the SimBA project.

Parameters

config_path (str) – path to SimBA project config file in Configparser format

Note

Feature extraction tutorial.

Examples

>>> feature_extractor = UserDefinedFeatureExtractor(config_path='MyProjectConfig')
>>> feature_extractor.run()

run()

Method to compute and save features to disk. Results are saved in the project_folder/csv/features_extracted directory of the SimBA project.

Return type

None

Feature extractor for feature subset family

class simba.feature_extractors.feature_subsets.FeatureSubsetsCalculator(config_path: Union[str, PathLike], save_dir: Optional[Union[str, PathLike]], feature_families: List[str], include_file_checks: Optional[bool] = False, append_to_features_extracted: Optional[bool] = False, append_to_targets_inserted: Optional[bool] = False)

Bases: ConfigReader, FeatureExtractionMixin, TrainModelMixin

Computes a subset of features from pose for non-ML downstream purposes. E.g., returns the size of animal convex hull in each frame.

Parameters

• config_path (str) – path to SimBA project config file in Configparser format

• save_dir (str) – directory where to store results.

• feature_family (str) – Feature subtype to calculate. E.g., “Two-point body-part distances (mm)”.

Note

Tutorial <https://github.com/sgoldenlab/simba/blob/master/docs/feature_subsets.md>_

Examples

>>> _ = FeatureSubsetsCalculator(config_path='project_folder/project_config.ini', feature_family='Frame-by-frame body-parts inside ROIs (Boolean)', save_dir='data').run()

Jitted methods for convex-hull related calculations

simba.feature_extractors.perimeter_jit.jitted_centroid(points: ndarray) → ndarray

Compute the centroid of polygons.

Parameters

• points (array) – 3d array FRAMESxBODY-PARTxCOORDINATE

• target (str) – Options [perimeter, area]

:return 1d np.array

Example

>>> points = np.random.randint(1, 50, size=(50, 5, 2)).astype(float)
>>> results = jitted_centroid(points)

simba.feature_extractors.perimeter_jit.jitted_hull(points: ndarray, target: str = 'perimeter') → ndarray

Compute attributes (e.g., perimeter or area) of a polygon.

Parameters

• points (array) – 3d array FRAMESxBODY-PARTxCOORDINATE

• target (str) – Options [perimeter, area, hull]

Returns

1d np.array representing perimeter length or area of polygon on each frame

Note

Modified from Jérôme Richard

Example

>>> points = np.random.randint(1, 50, size=(50, 5, 2)).astype(np.float32)
>>> results = jitted_hull(points, target='area')