atomsci

• pipeline package
  • Submodules
  • pipeline.chem_diversity module
    • calc_dist_diskdataset()
    • calc_dist_feat_array()
    • calc_dist_smiles()
    • calc_summary()
    • upload_distmatrix_to_DS()
  • pipeline.compare_models module
    • copy_best_filesystem_models()
    • del_ignored_params()
    • extract_collection_perf_metrics()
    • extract_model_and_feature_parameters()
    • get_best_models_info()
    • get_best_perf_table()
    • get_collection_datasets()
    • get_dataset_models()
    • get_filesystem_models()
    • get_filesystem_perf_results()
    • get_multitask_perf_from_files()
    • get_multitask_perf_from_files_new()
    • get_multitask_perf_from_tracker()
    • get_summary_metadata_table()
    • get_summary_perf_tables()
    • get_tarball_perf_table()
    • get_training_datasets()
    • get_training_perf_table()
    • num_trainable_parameters_from_file()
  • pipeline.dist_metrics module
    • mcs()
    • tanimoto()
    • tanimoto_single()
  • pipeline.diversity_plots module
    • diversity_plots()
    • plot_dataset_dist_distr()
    • plot_tani_dist_distr()
  • pipeline.feature_importance module
    • base_feature_importance()
    • cluster_permutation_importance()
    • display_feature_clusters()
    • permutation_feature_importance()
    • plot_feature_importances()
    • plot_nn_feature_weights_vs_epoch()
  • pipeline.hyper_perf_plots module
    • get_score_types()
    • plot_hyper_perf()
    • plot_nn_perf()
    • plot_rf_perf()
    • plot_split_perf()
    • plot_train_valid_test_scores()
    • plot_xg_perf()
  • pipeline.model_pipeline module
    • ModelPipeline
      • ModelPipeline.calc_train_dset_pair_dis()
      • ModelPipeline.create_model_metadata()
      • ModelPipeline.create_prediction_metadata()
      • ModelPipeline.create_split_metadata()
      • ModelPipeline.get_metrics()
      • ModelPipeline.load_featurize_data()
      • ModelPipeline.predict_embedding()
      • ModelPipeline.predict_full_dataset()
      • ModelPipeline.predict_on_dataframe()
      • ModelPipeline.predict_on_smiles()
      • ModelPipeline.run_predictions()
      • ModelPipeline.save_metrics()
      • ModelPipeline.save_model_metadata()
      • ModelPipeline.save_split_metadata()
      • ModelPipeline.split_dataset()
      • ModelPipeline.train_model()
    • build_dataset_name()
    • build_tarball_name()
    • calc_AD_kmean_dist()
    • calc_AD_kmean_local_density()
    • create_prediction_pipeline()
    • create_prediction_pipeline_from_file()
    • ensemble_predict()
    • get_k_nearest_index()
    • load_from_tracker()
    • main()
    • regenerate_results()
    • retrain_model()
    • run_models()
  • pipeline.model_tracker module
    • DatastoreInsertionException
    • MLMTClientInstantiationException
    • convert_metadata()
    • export_model()
    • extract_datastore_model_tarball()
    • get_full_metadata()
    • get_full_metadata_by_uuid()
    • get_metadata_by_uuid()
    • get_model_collection_by_uuid()
    • get_model_training_data_by_uuid()
    • save_model()
    • save_model_tarball()
  • pipeline.parameter_parser module
    • AutoArgumentAdder
      • AutoArgumentAdder.add_to_parser()
      • AutoArgumentAdder.all_prefixed_names()
      • AutoArgumentAdder.extract_params()
      • AutoArgumentAdder.get_list_args()
      • AutoArgumentAdder.get_list_float_args()
      • AutoArgumentAdder.get_list_int_args()
    • all_auto_arguments()
    • all_auto_float_lists()
    • all_auto_int_lists()
    • all_auto_lists()
    • dict_to_list()
    • extract_featurizer_params()
    • extract_model_params()
    • flatten_dict()
    • get_parser()
    • is_list()
    • is_list_float()
    • is_list_int()
    • is_primitive_type()
    • list_defaults()
    • main()
    • make_dataset_key_absolute()
    • parse_command_line()
    • parse_config_file()
    • parse_namespace()
    • postprocess_args()
    • primitive_type_only()
    • prune_defaults()
    • remove_unrecognized_arguments()
    • strip_optional()
    • to_str()
    • validate_sampling_strategy_argument()
    • wrapper()
  • pipeline.perf_data module
    • ClassificationPerfData
      • ClassificationPerfData.get_prediction_results()
      • ClassificationPerfData.model_choice_score()
    • EpochManager
      • EpochManager.accumulate()
      • EpochManager.compute()
      • EpochManager.on_new_best_valid()
      • EpochManager.set_make_pred()
      • EpochManager.should_stop()
      • EpochManager.update()
      • EpochManager.update_epoch()
      • EpochManager.update_valid()
    • EpochManagerKFold
      • EpochManagerKFold.compute()
    • HybridPerfData
      • HybridPerfData.get_prediction_results()
      • HybridPerfData.model_choice_score()
    • KFoldClassificationPerfData
      • KFoldClassificationPerfData.accumulate_preds()
      • KFoldClassificationPerfData.compute_perf_metrics()
      • KFoldClassificationPerfData.get_pred_values()
      • KFoldClassificationPerfData.get_real_values()
      • KFoldClassificationPerfData.get_weights()
    • KFoldRegressionPerfData
      • KFoldRegressionPerfData.accumulate_preds()
      • KFoldRegressionPerfData.compute_perf_metrics()
      • KFoldRegressionPerfData.get_pred_values()
      • KFoldRegressionPerfData.get_real_values()
      • KFoldRegressionPerfData.get_weights()
    • PerfData
      • PerfData.accumulate_preds()
      • PerfData.compute_perf_metrics()
      • PerfData.get_pred_values()
      • PerfData.get_prediction_results()
      • PerfData.get_real_values()
      • PerfData.get_weights()
    • RegressionPerfData
      • RegressionPerfData.get_prediction_results()
      • RegressionPerfData.model_choice_score()
    • SimpleClassificationPerfData
      • SimpleClassificationPerfData.accumulate_preds()
      • SimpleClassificationPerfData.compute_perf_metrics()
      • SimpleClassificationPerfData.get_pred_values()
      • SimpleClassificationPerfData.get_real_values()
      • SimpleClassificationPerfData.get_weights()
    • SimpleHybridPerfData
      • SimpleHybridPerfData.accumulate_preds()
      • SimpleHybridPerfData.compute_perf_metrics()
      • SimpleHybridPerfData.get_pred_values()
      • SimpleHybridPerfData.get_real_values()
      • SimpleHybridPerfData.get_weights()
    • SimpleRegressionPerfData
      • SimpleRegressionPerfData.accumulate_preds()
      • SimpleRegressionPerfData.compute_perf_metrics()
      • SimpleRegressionPerfData.get_pred_values()
      • SimpleRegressionPerfData.get_real_values()
      • SimpleRegressionPerfData.get_weights()
    • create_perf_data()
    • negative_predictive_value()
    • rms_error()
  • pipeline.perf_plots module
    • get_classifier_perf_data_from_pipeline()
    • get_metrics_from_metadata()
    • get_metrics_from_model_file()
    • get_metrics_from_model_pipeline()
    • merge_response_cols_from_original()
    • old_plot_prec_recall_curve()
    • plot_ROC_curve()
    • plot_confusion_matrices()
    • plot_model_metrics()
    • plot_perf_vs_epoch()
    • plot_prec_recall_curve()
    • plot_pred_vs_actual()
    • plot_pred_vs_actual_from_df()
    • plot_pred_vs_actual_from_file()
    • plot_umap_feature_projections()
    • plot_umap_train_set_neighbors()
  • pipeline.predict_from_model module
    • predict_from_model_file()
    • predict_from_tracker_model()
  • Module contents
• utils package
  • Submodules
  • utils.compare_splits_plots module
    • SplitStats
      • SplitStats.dist_hist_plot()
      • SplitStats.dist_hist_train_v_test_plot()
      • SplitStats.dist_hist_train_v_valid_plot()
      • SplitStats.make_all_plots()
      • SplitStats.print_stats()
      • SplitStats.subset_frac_plot()
      • SplitStats.umap_plot()
    • parse_args()
    • save_figure()
    • split()
  • utils.curate_data module
    • add_classification_column()
    • aggregate_assay_data()
    • average_and_remove_duplicates()
    • create_new_rows_for_extra_results()
    • filter_in_by_column_values()
    • filter_in_out_by_column_values()
    • filter_out_by_column_values()
    • filter_out_comments()
    • freq_table()
    • get_rdkit_smiles_parent()
    • labeled_freq_table()
    • mle_censored_mean()
    • remove_outlier_replicates()
    • replicate_rmsd()
    • set_group_permissions()
    • summarize_data()
    • xc50topxc50_for_nm()
  • utils.data_curation_functions module
    • atom_curation()
    • atom_curation_excape()
    • compute_negative_log_responses()
    • convert_IC50_to_pIC50()
    • down_select()
    • exclude_organometallics()
    • filter_dtc_data()
    • get_smiles_4dtc_data()
    • get_smiles_dtc_data()
    • get_smiles_excape_data()
    • ic50topic50()
    • is_organometallic()
    • set_data_root()
    • standardize_relations()
    • upload_df_dtc_base_smiles_all()
    • upload_df_dtc_mleqonly()
    • upload_df_dtc_mleqonly_class()
    • upload_df_dtc_smiles()
    • upload_df_dtc_smiles_regr_all_class()
    • upload_df_excape_mleqonly()
    • upload_df_excape_mleqonly_class()
    • upload_df_excape_smiles()
    • upload_file_dtc_raw_data()
    • upload_file_dtc_smiles_regr_all()
    • upload_file_excape_raw_data()
  • utils.datastore_functions module
    • bulk_export_kv_for_files()
    • bulk_update_kv()
    • check_key_val()
    • config_client()
    • copy_datasets_to_bucket()
    • dataset_key_exists()
    • filter_datasets_interactive()
    • get_key_val()
    • get_keyval()
    • initialize_model_tracker()
    • key_exists()
    • list_key_values()
    • repeat_defined_search()
    • retrieve_bucket_names()
    • retrieve_columns_from_dataset()
    • retrieve_dataset_by_dataset_oid()
    • retrieve_dataset_by_datasetkey()
    • retrieve_keys()
    • retrieve_values_for_key()
    • search_datasets_by_key_value()
    • search_files_interactive()
    • string_to_dict()
    • string_to_list()
    • summarize_datasets()
    • update_distribution_kv()
    • update_kv()
    • upload_df_to_DS()
    • upload_file_to_DS()
    • upload_pickle_to_DS()
  • utils.generate_transformers module
    • build_and_save_feature_transformers_from_csvs()
    • filter_outlier_MW()
    • filter_outlier_features()
    • load_all_datasets()
    • prepare_csv_and_descriptor_with_dummy_response()
  • utils.hyperparam_search_wrapper module
    • GeometricSearch
      • GeometricSearch.generate_assay_list()
      • GeometricSearch.generate_combo()
      • GeometricSearch.generate_param_combos()
      • GeometricSearch.split_and_save_dataset()
    • GridSearch
      • GridSearch.generate_assay_list()
      • GridSearch.generate_combo()
      • GridSearch.generate_param_combos()
      • GridSearch.split_and_save_dataset()
    • HyperparameterSearch
      • HyperparameterSearch.already_run()
      • HyperparameterSearch.assemble_layers()
      • HyperparameterSearch.build_jobs()
      • HyperparameterSearch.filter_jobs()
      • HyperparameterSearch.generate_assay_list()
      • HyperparameterSearch.generate_combo()
      • HyperparameterSearch.generate_combos()
      • HyperparameterSearch.generate_maestro_commands()
      • HyperparameterSearch.generate_param_combos()
      • HyperparameterSearch.generate_searches()
      • HyperparameterSearch.generate_split_shortlist()
      • HyperparameterSearch.generate_split_shortlist_file()
      • HyperparameterSearch.get_dataset_metadata()
      • HyperparameterSearch.get_shortlist_df()
      • HyperparameterSearch.return_split_uuid()
      • HyperparameterSearch.return_split_uuid_file()
      • HyperparameterSearch.run_search()
      • HyperparameterSearch.split_and_save_dataset()
      • HyperparameterSearch.submit_jobs()
    • OptunaSearch
      • OptunaSearch.run_search()
    • RandomSearch
      • RandomSearch.generate_assay_list()
      • RandomSearch.generate_combo()
      • RandomSearch.generate_param_combos()
      • RandomSearch.split_and_save_dataset()
    • UserSpecifiedSearch
      • UserSpecifiedSearch.generate_assay_list()
      • UserSpecifiedSearch.generate_combo()
      • UserSpecifiedSearch.generate_param_combos()
      • UserSpecifiedSearch.split_and_save_dataset()
    • build_optuna_suggest()
    • build_search()
    • gen_maestro_command()
    • get_num_params()
    • main()
    • parse_params()
    • permutate_NNlayer_combo_params()
    • reformat_filter_dict()
    • run_cmd()
    • run_command()
  • utils.many_to_one module
    • ManyToOneException
    • NANCompoundIDException
    • NANSMILESException
    • has_nans()
    • many_to_one()
    • many_to_one_df()
    • no_nan_ids_or_smiles()
  • utils.model_file_reader module
    • ModelFileReader
      • ModelFileReader.get_dataset_key()
      • ModelFileReader.get_descriptor_type()
      • ModelFileReader.get_embedding_and_features()
      • ModelFileReader.get_embedding_model_path()
      • ModelFileReader.get_embedding_model_uuid()
      • ModelFileReader.get_embedding_specific_parameters()
      • ModelFileReader.get_featurizer()
      • ModelFileReader.get_id_col()
      • ModelFileReader.get_imputer_strategy()
      • ModelFileReader.get_model_info()
      • ModelFileReader.get_model_parameters()
      • ModelFileReader.get_model_type()
      • ModelFileReader.get_model_uuid()
      • ModelFileReader.get_powertransformer_method()
      • ModelFileReader.get_powertransformer_standardize()
      • ModelFileReader.get_random_seed()
      • ModelFileReader.get_response_cols()
      • ModelFileReader.get_robustscaler_quartile_range()
      • ModelFileReader.get_robustscaler_unit_variance()
      • ModelFileReader.get_robustscaler_with_centering()
      • ModelFileReader.get_robustscaler_with_scaling()
      • ModelFileReader.get_smiles_col()
      • ModelFileReader.get_split_csv()
      • ModelFileReader.get_split_strategy()
      • ModelFileReader.get_split_uuid()
      • ModelFileReader.get_splitter()
      • ModelFileReader.get_splitting_parameters()
      • ModelFileReader.get_training_dataset()
      • ModelFileReader.get_transformer_dataset_key_configs()
      • ModelFileReader.get_transformer_specific_parameters()
      • ModelFileReader.get_version()
    • get_multiple_models_metadata()
    • main()
  • utils.model_retrain module
    • main()
    • train_model()
    • train_model_from_tar()
    • train_model_from_tracker()
    • train_models_from_dataset_keys()
  • utils.model_version_utils module
    • check_version_compatible()
    • get_ampl_version()
    • get_ampl_version_from_dir()
    • get_ampl_version_from_json()
    • get_ampl_version_from_model()
    • get_major_version()
    • main()
    • validate_version()
  • utils.pubchem_utils module
    • download_SID_from_bioactivity_assay()
    • download_activitytype()
    • download_bioactivity_assay()
    • download_dose_response_from_bioactivity()
    • download_smiles()
  • utils.rdkit_easy module
    • add_mol_column()
    • calculate_descriptors()
    • cluster_dataframe()
    • cluster_fingerprints()
    • compute_drug_likeness()
    • matching_atoms_and_bonds()
    • mol_to_html()
    • mol_to_pil()
    • mol_to_svg()
    • save_png()
    • save_svg()
    • setup_notebook()
    • show_df()
    • show_html()
  • utils.split_response_dist_plots module
    • compute_split_subset_wasserstein_distances()
    • get_split_labeled_dataset()
    • plot_split_subset_response_distrs()
  • utils.struct_utils module
    • base_mol_from_inchi()
    • base_mol_from_smiles()
    • base_smiles_from_inchi()
    • base_smiles_from_smiles()
    • canonical_tautomers_from_smiles()
    • draw_structure()
    • fix_moe_smiles()
    • get_rdkit_smiles()
    • kekulize_smiles()
    • mol_wt_from_smiles()
    • mols_from_smiles()
    • rdkit_smiles_from_smiles()
    • smiles_to_inchi_key()
  • Module contents