API Reference

You can customise the behaviour of the pipeline to your own specification. The following pages provide a developer reference to the modules and functions used in the pipeline to allow for customisation.

• nccidxclean package
  • Module contents
  • nccidxclean.nccidxclean module
    • main()
    • xclean_nccid()
  • nccidxclean.analysis module
    • main()
    • make_figures_and_numeric_analysis()
    • print_df_as_latex()
  • nccidxclean.eda module
  • Subpackages
    • nccidxclean.clean subpackage
      • Submodules
      • nccidxclean.clean.binary_and_cat module
        • binarise_lung_csv()
        • parse_binary_and_cat()
      • nccidxclean.clean.dicts_and_maps module
      • nccidxclean.clean.enrich_with_dcm module
        • add_dicom_update()
        • extract_dcm_metadata()
        • save_dcm_updates()
      • nccidxclean.clean.ethnicity_and_sex module
        • remap_ethnicity()
        • remap_sex()
      • nccidxclean.clean.fix_headers_and_order module
        • fix_headers()
        • order_columns()
        • select_output_cols()
      • nccidxclean.clean.geh_col_shift module
        • column_shift()
      • nccidxclean.clean.inferences module
        • inferences()
      • nccidxclean.clean.numeric module
        • clean_numeric()
        • clip_numeric()
        • rescale_fio2()
      • nccidxclean.clean.parse_dates module
        • parse_date_columns()
      • nccidxclean.clean.remap_hospitals module
        • check_new_centres()
        • remap_hospitals()
      • nccidxclean.clean.sense_check module
        • sense_check()
        • sense_check_dicom_dates()
      • nccidxclean.clean.utils module
        • create_error_report()
        • create_xclean_id()
        • extract_old_data()
        • merge_checks_with_cleaned_df()
        • read_in_clinical_data()
        • update_with_prev_changes()
    • nccidxclean.figures subpackage
      • Submodules
      • nccidxclean.figures.categorical
        • CategoricalField
          • CategoricalField.__init__()
          • CategoricalField.cvs_map_values()
          • CategoricalField.map_values()
          • CategoricalField.methods_hist_by_hosp()
          • CategoricalField.remap_column_names()
          • CategoricalField.rename_field()
          • CategoricalField.results_hist_by_dataset()
        • make_figure_2()
        • make_figure_6()
      • nccidxclean.figures.dates
        • extract_day_and_month()
        • get_gov_data()
        • get_min_gap()
        • make_figure_3()
        • make_figure_7()
        • merge_pcr_and_study_dates()
        • prepare_dataframe_dates()
        • remap_melted_date_names()
      • nccidxclean.figures.numeric
        • clean_raw_data()
        • create_numeric_results_fig()
        • is_float()
        • make_figure_4()
        • make_figure_5()
        • make_figure_8()
      • nccidxclean.figures.overall_numbers
        • get_total_missing()
        • make_figure_1()
      • nccidxclean.figures.prepare_dataframes
        • allocate_hospital_codes()
        • prepare_dataframes_for_comparison()
      • nccidxclean.figures.sns_settings
    • nccidxclean.num_analysis subpackage
      • Submodules
      • nccidxclean.num_analysis.categorical
        • analyse_age()
        • analyse_pmh_cvs()
        • analyse_pmh_htn()
        • analyse_sex()
        • categorical_fields_analysis()
      • nccidxclean.num_analysis.dates
        • count_dates()
        • date_field_analysis()
        • dates_summary()
        • excel_dates()
        • incorrect_date_format()
        • pcr_imaging_gaps()
      • nccidxclean.num_analysis.num_analysis
        • count_missing()
        • numeric_analysis()
      • nccidxclean.eda.numeric
        • creatinine_analysis()
        • ddimer_analysis()
        • fio2_analysis()
        • numeric_fields_analysis()
        • pao2_analysis()
        • round_sig()
        • troponin_analysis()
        • value_counts_with_percentage()
      • nccidxclean.eda.tables
        • info_by_center()
        • summary_table()
    • nccidxclean.eda subpackage
      • Submodules
      • nccidxclean.eda.produce_reports
• nccidxclean.clean subpackage
  • Submodules
  • nccidxclean.clean.binary_and_cat module
    • binarise_lung_csv()
    • parse_binary_and_cat()
  • nccidxclean.clean.dicts_and_maps module
  • nccidxclean.clean.enrich_with_dcm module
    • add_dicom_update()
    • extract_dcm_metadata()
    • save_dcm_updates()
  • nccidxclean.clean.ethnicity_and_sex module
    • remap_ethnicity()
    • remap_sex()
  • nccidxclean.clean.fix_headers_and_order module
    • fix_headers()
    • order_columns()
    • select_output_cols()
  • nccidxclean.clean.geh_col_shift module
    • column_shift()
  • nccidxclean.clean.inferences module
    • inferences()
  • nccidxclean.clean.numeric module
    • clean_numeric()
    • clip_numeric()
    • rescale_fio2()
  • nccidxclean.clean.parse_dates module
    • parse_date_columns()
  • nccidxclean.clean.remap_hospitals module
    • check_new_centres()
    • remap_hospitals()
  • nccidxclean.clean.sense_check module
    • sense_check()
    • sense_check_dicom_dates()
  • nccidxclean.clean.utils module
    • create_error_report()
    • create_xclean_id()
    • extract_old_data()
    • merge_checks_with_cleaned_df()
    • read_in_clinical_data()
    • update_with_prev_changes()
• nccidxclean.figures subpackage
  • Submodules
  • nccidxclean.figures.categorical
    • CategoricalField
      • CategoricalField.__init__()
      • CategoricalField.cvs_map_values()
      • CategoricalField.map_values()
      • CategoricalField.methods_hist_by_hosp()
      • CategoricalField.remap_column_names()
      • CategoricalField.rename_field()
      • CategoricalField.results_hist_by_dataset()
    • make_figure_2()
    • make_figure_6()
  • nccidxclean.figures.dates
    • extract_day_and_month()
    • get_gov_data()
    • get_min_gap()
    • make_figure_3()
    • make_figure_7()
    • merge_pcr_and_study_dates()
    • prepare_dataframe_dates()
    • remap_melted_date_names()
  • nccidxclean.figures.numeric
    • clean_raw_data()
    • create_numeric_results_fig()
    • is_float()
    • make_figure_4()
    • make_figure_5()
    • make_figure_8()
  • nccidxclean.figures.overall_numbers
    • get_total_missing()
    • make_figure_1()
  • nccidxclean.figures.prepare_dataframes
    • allocate_hospital_codes()
    • prepare_dataframes_for_comparison()
  • nccidxclean.figures.sns_settings
• nccidxclean.num_analysis subpackage
  • Submodules
  • nccidxclean.num_analysis.categorical
    • analyse_age()
    • analyse_pmh_cvs()
    • analyse_pmh_htn()
    • analyse_sex()
    • categorical_fields_analysis()
  • nccidxclean.num_analysis.dates
    • count_dates()
    • date_field_analysis()
    • dates_summary()
    • excel_dates()
    • incorrect_date_format()
    • pcr_imaging_gaps()
  • nccidxclean.num_analysis.num_analysis
    • count_missing()
    • numeric_analysis()
  • nccidxclean.eda.numeric
    • creatinine_analysis()
    • ddimer_analysis()
    • fio2_analysis()
    • numeric_fields_analysis()
    • pao2_analysis()
    • round_sig()
    • troponin_analysis()
    • value_counts_with_percentage()
  • nccidxclean.eda.tables
    • info_by_center()
    • summary_table()
• nccidxclean.eda subpackage
  • Submodules
  • nccidxclean.eda.produce_reports