BatchSummaryFeaturizer

BatchSummaryFeaturizer#

class lobsterpy.featurize.batch.BatchSummaryFeaturizer(path_to_lobster_calcs, path_to_jsons=None, feature_type='antibonding', charge_type='both', bonds='all', orbital_resolved=False, include_cobi_data=False, include_coop_data=False, e_range=[-5.0, 0.0], n_jobs=4, **analysis_kwargs)[source]#

Bases: object

Batch Featurizer sets that generates summary features from lobster data.

Parameters:

  • path_to_lobster_calcs (str | Path) – path to root directory consisting of all lobster calc

  • path_to_jsons (str | Path | None) – path to root directory consisting of all lobster lightweight jsons

  • feature_type (Literal['bonding', 'antibonding', 'overall']) – set the feature type for moment features. Possible options are bonding, antibonding or overall

  • charge_type (Literal['mulliken', 'loewdin', 'both']) – set charge type used for computing ionicity. Possible options are mulliken, loewdin or both.

  • bonds (Literal['all', 'cation-anion']) – all_bonds or cation_anion_bonds

  • orbital_resolved (bool) – bool indicating whether LobsterPy analysis is performed orbital wise

  • include_cobi_data (bool) – bool stating to include COBICAR.lobster features

  • include_coop_data (bool) – bool stating to include COOPCAR.lobster features

  • e_range (list[float]) – range of energy relative to fermi for which moment features needs to be computed

  • n_jobs (int) – parallel processes to run

get_df()[source]#

Generate a pandas dataframe with summary features extracted from LOBSTER files.

Uses multiprocessing to speed up the process.

Returns:

Returns a pandas dataframe

Return type:

DataFrame