Bits & Flames bitsandflames/fyron

Function Reference

This page is a practical function-level reference. It lists each major public function, required inputs, optional arguments, and return values. Module pages explain workflows and examples in more depth.

Use this page when you already know which module you need and want to check a call quickly. For conceptual guidance, start with the module pages; this reference is intentionally dense and optimized for lookup while coding.

For exhaustive per-function documentation generated from source signatures and docstrings, use the Complete Function Reference. It includes public functions, classes, methods, parameters, defaults, return notes, and import paths.

Reading Function Signatures

Fyron APIs are built around explicit clinical data science inputs. The same parameter names appear across modules:

Parameter patternMeaning
df, data, cohortA pandas.DataFrame, usually one row per patient, resource, feature, or result.
duration_col, time_colFollow-up duration column for survival analysis. Values should be positive.
event_colEndpoint/event indicator. Survival workflows use 1 for event and 0 for censored.
group_col, hue, strataClinical grouping variable used for summaries, plots, or model stratification.
id_col, patient_col, subject_colStable identifier used for joins, validation, or FHIR subject references.
X, yFeature matrix and target labels for machine learning.
y_true, y_pred, y_probObserved labels, hard predictions, and positive-class probabilities.
save_path, output, writeFile destination for generated artifacts.
random_stateReproducibility seed; record it in manifests for final analyses.

Where To Learn The Workflow

TopicDetailed page
FHIR REST extraction and paginationFHIR REST
DICOMweb downloads and download_idDICOMDownloader
BOA feature extractionBOA Extraction
Cohort constructionCohort Tables
Descriptive tablesDescriptive Analysis
Survival analysisSurvival Analysis
Machine learningMachine Learning
ValidationModel Validation
Publication figuresClinical Plotting
ProvenanceAudit & Provenance

CLI Commands

Global flags: --verbose, --quiet, --no-color, --json-log, and --no-progress.

CommandRequiredCommon optional argumentsOutput
fyron bannernone--no-color, --no-version, --theme bf/plain/monoterminal banner
fyron sparknone--no-color, --no-version, --theme bf/plain/monoterminal easter egg banner
fyron docs-buildnonenonestatic site in site/
fyron fhir-rest--resource, --output--base-url, --param, --params-json, --input, --column-map, --fhir-paths, --formatCSV/JSON
fyron fhir-build-bundle--input, --mapping, --resource, --subject-col, --outputIDs, imaging UIDs, bundle type, summary/validation JSON, submitFHIR JSON bundle
fyron dicom-downloadoutput target plus study/CSV IDsendpoint/auth, --output-format, --full-study, --manifest, --results-csvDICOM/NIfTI and manifests
fyron synthetic-dicom--volume, --output-dir--reference-dicom, --patient-id, --manifestDICOM slices
fyron dicom-seg--mask, --source-dicom, --segments, --output--series-description, --algorithm-name, --algorithm-type, --manufacturer, --validate, --summary-jsonDICOM SEG
fyron boa-extract--cohort-folder, --outputfeature-family flags, --num-workersCSV
fyron boa-radiomics--cohort-folder, --output--segmentation, --num-workersCSV
fyron imaging-qcat least one imaging input and --output--dicom-dir, --nifti, --mask, --formatCSV/JSON
fyron audit-manifest--write--title, --input, --output, --param, --noteprovenance JSON

Console And Banner

FunctionRequiredOptionalReturns
configure_logging(level="INFO", ...)nonecolor, JSON mode, streamconfigured fyron logger
get_logger(name=None)nonelogger namelogger under fyron
console_message(message, ...)messagelevel, color, prefix, quiet, streamrendered text
success(...), warning(...), error(...), info(...)messagecolor, prefix, quiet, streamrendered text
format_path(path)pathnonecompact display path
format_count(label, value)label and countnoneformatted count string
format_duration(seconds)secondsnonehuman duration string
supports_color(stream=None)nonestreamboolean ANSI support
get_banner(...) / print_banner(...)nonecolor, version, themecompatibility helpers for the opt-in banner easter egg
get_run_header(...) / get_run_footer(...)nonecommand, version, timestamp, status, duration, outputsrun summary text

Core I/O

FunctionRequiredOptionalReturns
load_env(path=None, ...)noneoverride, missing warningloaded path or None
ensure_parent_dir(path)pathnonePath
read_json(path, ...)pathJSON load kwargsPython object
write_json(payload, path, ...)payload, pathindent, parent creationoutput Path
read_table(path, ...)pathfile format, pandas kwargsDataFrame
write_table(df, path, ...)DataFrame, pathfile format, parent creation, index, pandas kwargsoutput Path
summarize_table(df, ...)DataFramenamesummary dict
describe_file(path)pathnonefile metadata dict
TeableClient.read_cohort(...)table IDID column, required columns, view, max recordsvalidated DataFrame
TeableClient.write_research_cohort(...)table ID, DataFramemode, metadata, ID column, typecastaudit dict
TeableClient.create_research_cohort_table(...)base ID, nameDataFrame, fields, metadatatable dict
TeableClient.summarize_teable_table(...)table IDview, projection, max recordssummary dict
S3Storage.read_table(...) / S3Storage.write_table(...)S3 keyformat, pandas kwargsDataFrame / S3 URI
read_s3_table(uri) / write_s3_table(df, uri)S3 URItable kwargsDataFrame / S3 URI

FHIR REST And SQL

FunctionRequiredOptionalReturns
FHIRRestClient.search_df(resource_type, ...)resource typeparams, page limit, FHIR paths, processing modeDataFrame or dict of DataFrames
FHIRRestClient.search_df_from(df, ...)input table, resource type, column mapparams, page limit, FHIR paths, metadata columnsDataFrame or dict of DataFrames
FHIRRestClient.query_df(...) / query_df_from(...)same as search aliasescompatibility namesDataFrame or dict of DataFrames
FHIRRestClient.create_resource(resource, ...)resource dictresource type overrideFHIRWriteResult
FHIRRestClient.update_resource(resource, ...)resource dictresource ID/type overrideFHIRWriteResult
FHIRRestClient.submit_bundle(bundle)transaction bundlenoneFHIRWriteResult
FHIRSQLClient.query_df(sql, ...)SQL stringparams, renameDataFrame
FHIRSQLClient.query_df_stream(sql, ...)SQL stringparams, rename, chunk sizeiterator of DataFrames
FHIRSQLClient.query_df_parallel(jobs, ...)query jobsworker count, merge optionsDataFrame
FHIRSQLClient.query_df_from(df, ...)input table, SQL template, column mapchunking and parallel optionsDataFrame

Imaging

FunctionRequiredOptionalReturns
read_dicom_header(dicom_path, ...)dicom_pathstop_before_pixels=True, force=False, as_dict=False, selected_tags=Nonepydicom.Dataset or dict
get_dicom_series_ids(dicom_dir, ...)dicom_dirinclude_metadata=False, recursive=Falselist[str] or DataFrame
read_dicom_series(study_path, series_id, ...)study_path, series_idreturn_array=FalseSimpleITK.Image or (image, array)
read_nifti(nifti_path, ...)nifti_pathreturn_array=FalseSimpleITK.Image or (image, array)
write_nifti(image, output_path, ...)image, output_pathreference_image=None, compress=Trueresolved Path
normalize_ct(image, ...)imagehu_min=-1000.0, hu_max=3000.0same type as input
normalize_mr(image, ...)imagemode="percentile", percentile=99.0, value=None, ignore_zeros=True, clip=Truesame type as input
summarize_dicom_series_geometry(dicom_dir, ...)dicom_dirrecursive=Falsegeometry DataFrame
summarize_nifti_geometry(paths)pathsnonegeometry DataFrame
check_image_mask_alignment(image, mask)image, masknonealignment dict
summarize_mask_volume(mask, ...)masklabels=None, spacing=Nonevolume DataFrame
summarize_intensity_range(image, ...)imagemask=None, percentiles=(0.5, 99.5)summary dict
dice_score(mask_true, mask_pred, ...)two maskslabelfloat
hausdorff_distance(mask_true, mask_pred, ...)two maskslabel, spacing, percentilefloat
surface_dice(mask_true, mask_pred, ...)two maskslabel, tolerance, spacingfloat
volume_difference(mask_true, mask_pred, ...)two maskslabel, spacingdict
segmentation_metric_table(mask_true, mask_pred, ...)two maskslabels, spacing, toleranceDataFrame

See Imaging for full parameter explanations.

FHIR Builder

FunctionRequiredOptionalReturns
build_observation(...)subject, codevalue, components, data_absent_reason, performer, encounter, derived_from, method, body_site, versionObservation dict
build_observation_component(...)codevalue, unit, value_type, data_absent_reason, interpretationObservation component dict
build_encounter(...), build_procedure(...)patient subject and code/contextids, period/performed, profile metadataEncounter/Procedure dict
build_medication_statement(...), build_service_request(...), build_specimen(...)patient subject and resource-specific code/typeids, status, profile metadataresource dict
build_condition(...)subject, codeclinical/verification status, onset, evidence, versionCondition dict
build_document_reference(...)subject plus URL/data attachment valuestitle, content type, date, description, versionDocumentReference dict
build_diagnostic_report(...)subject, coderesults, imaging study refs, conclusion, presented formDiagnosticReport dict
build_imaging_study_reference(...)subject, study_instance_uidseries UID/description, modality, started, versionImagingStudy dict
build_model_device(...) / build_endpoint(...)model/endpoint identityversion, model endpoint, manufacturerDevice/Endpoint dict
build_provenance(...)targetsagent, entity, recorded, activity, prompt versionProvenance dict
build_llm_extraction_bundle(...)subject, source report, model name, bundle typeobservations, conditions, summary, endpoint, versions, id_prefixBundle dict
build_imaging_measurement_bundle(...)subject, study UID, measurements, bundle typeseries UID, model info, id_prefix, versionBundle dict
build_bundle(resources, bundle_type=...)resources, explicit bundle typebundle id, transaction method, conditional create, versionBundle dict
loinc(...), snomed(...), icd10(...), dicom_code(...)codedisplayCoding dict
ucum_quantity(...)value, unitcodeQuantity dict
write_fhir_json(payload, path)payload, pathnoneresolved path
read_fhir_json(path)pathnonepayload dict
summarize_fhir_resource(...) / summarize_fhir_bundle(...)resource/bundlenonesummary dict
validate_fhir_resource(...) / validate_fhir_bundle(...)resource/bundleversionvalidated dict or raises
validate_fhir_references(...)bundlenonereference report dict
build_observations_from_dataframe(...)DataFrame, mapping, subject columnid, bundle type, transaction methodmapping result dict
build_conditions_from_dataframe(...)DataFrame, mapping, subject columnid/evidence/status mappingsmapping result dict
build_document_references_from_dataframe(...)DataFrame, mapping, subject columnURL/title/content mappingsmapping result dict
build_imaging_measurements_from_dataframe(...)DataFrame, mapping, subject and study UID columnsseries UID, id, model metadatamapping result dict
build_bundle_from_dataframe(...)DataFrame, resource type, mapping, subject columndispatch and transaction optionsmapping result dict
validate_fhir_mapping(...), validate_fhir_payload(...)mapping or FHIR payloadDataFrame, strict modevalidation report dict

See FHIR Builder for LLM extraction and imaging measurement examples.

DICOM Export

FunctionRequiredOptionalReturns
write_synthetic_nifti(volume, output_path, ...)volume, output_pathreference_image, spacing, origin, direction, dtype, compress, metadataresolved Path
write_synthetic_dicom_series(volume, output_dir, ...)volume, output_dirreference_dicom_dir, reference_datasets, patient_id, UIDs, modality, description, intensity mode, rescale tags, patient-copy flagmanifest DataFrame
write_dicom_seg(mask, source_images, output_path, segment_descriptions, ...)mask, source_images, output_path, segment_descriptionsseries_description, manufacturer, algorithm metadataresolved Path
label_map_to_segments(label_map, labels)label_map, labelsnonebinary stack (segment, z, y, x)
validate_dicom_seg(path, ...)pathsource_images=Nonemetadata dict
summarize_dicom_seg(path, ...)pathsource_images=Nonemetadata dict
load_source_dicom_series(source_dicom_dir, ...)source_dicom_dirsort_by="geometry"sorted source DICOM datasets
read_segment_descriptions(path)pathnonevalidated segment description list
validate_segment_descriptions(segment_descriptions)segment listnonenormalized segment description list

See Synthetic Export and DICOM SEG for scientific context and examples.

Datasets

FunctionRequiredOptionalReturns
make_clinical_cohort(n=40, ...)nonen, random_state=42clinical DataFrame
make_survival_cohort(n=40, ...)nonen, random_state=42survival DataFrame
make_classification_cohort(n=80, ...)nonen, random_state=42(X, y)
make_nifti_pair(output_dir, ...)output_dirshape=(4, 8, 8)dict of image/mask paths
make_dicom_series(output_dir, ...)output_dirshape, patient_idlist of DICOM paths
make_boa_like_folder(output_dir)output_dirnoneBOA-like root path
prepare_nnunetv2_dataset(manifest, output_dir, ...)manifest, output dir, dataset ID/namecolumns, labels, copy mode, validationwritten-file manifest
prepare_yolo_classification_dataset(manifest, output_dir, ...)manifest, output dirclass/split columns, slice behavior, copy modewritten-image manifest
prepare_yolo_detection_dataset(manifest, output_dir, ...)manifest, output dirclass/box columns, slice behavior, copy modeimage/label manifest
validate_nnunetv2_dataset(dataset_dir)dataset dirnoneQC DataFrame
validate_yolo_dataset(dataset_dir, ...)dataset dirtask="detect" or "classify"QC DataFrame

Cohort

FunctionRequiredOptionalReturns
join_cohort_tables(features, outcomes, ...)features, outcomeson="patient_id", how="inner", suffix optionsmerged DataFrame
validate_cohort_table(df, ...)dfrequired_columns=None, id_column=Nonevalidated DataFrame / raises on problems
build_survival_columns(df, start_col, end_col, event_col, ...)df, start_col, end_col, event_coltime_col="time", date parsing/output optionsDataFrame with time and event

Phenotyping

FunctionRequiredOptionalReturns
define_code_phenotype(df, code_col, codes, ...)table, code column, codespatient/date/code-system columnsphenotype table
define_lab_threshold_phenotype(df, value_col, threshold, ...)table, value column, thresholddirection, patient/date columnsphenotype table
define_medication_exposure(df, medication_col, medications, ...)table, medication column, medication listpatient/start/end columnsexposure table
combine_phenotypes(tables, ...)phenotype tablespatient column, strategy, namecombined phenotype table
phenotype_summary(df, phenotype_col, ...)table and phenotype columnpatient/group columnsprevalence table

Survival

FunctionRequiredOptionalReturns
ml.plot_kaplan_meier(df, duration_col, event_col, ...)df, duration_col, event_colgroup_col, split_column, CI/risk count/style/save/RMST optionsKaplanMeierPlotResult
create_survival_groups(df, column, method, out_col, ...)df, column, method, out_colbins, labels, method-specific optionsDataFrame copy
calculate_rmst(df, duration_col, event_col, ...)df, duration_col, event_colgroup_col=None, tau=NoneRMST DataFrame
compare_rmst(df, duration_col, event_col, group_col, ...)df, duration_col, event_col, group_colreference=None, tau=Nonepairwise comparison DataFrame
fit_univariate_cox(df, duration_col, event_col, covariates, ...)df, duration_col, event_col, covariatesstrata=None, robust=Falseresult table and fitters
fit_multivariate_cox(df, duration_col, event_col, ...)df, duration_col, event_col, one of covariates/formulastrata=None, robust=Falseresult table and fitter
check_ph_assumptions(df, fitter, ...)df, fitted Cox modelshow_plots=False, diagnostic optionssummary and violations
fit_weibull_aft(df, duration_col, event_col, ...)df, duration_col, event_col, one of covariates/formularobust=Falseresult table and fitter
plot_aft_survival_curves(fitter, covariates, profiles, ...)fitter, covariates, profilesplot_baseline=True, figsize, ax, plot_kwargsfigure/axes/fitter dict
train_gradient_survival_boosting(X_train, duration_train, event_train, ...)X_train, duration_train, event_traintest data, random_state=42, model paramsmodel, risk scores, concordance

Statistics

FunctionRequiredOptionalReturns
normality_test(values, ...)valuesmethod="shapiro"StatisticalTestResult
compare_two_groups(group_a, group_b, ...)group_a, group_bpaired, method, alternative, equal_varStatisticalTestResult
compare_multiple_groups(groups, ...)groupsmethod="auto"StatisticalTestResult
categorical_test(table, ...)contingency tablemethod="auto"StatisticalTestResult
correlation_test(x, y, ...)x, ymethod="spearman", alternativeStatisticalTestResult
bootstrap_summary(values, ...)valuesstatistic, n_rounds, alpha, random_stateBootstrapResult
bootstrap_metric(*arrays, metric_func=...)aligned arrays, metric_funcmetric_name, n_rounds, alpha, random_stateBootstrapResult
bootstrap_binary_classification_metrics(y_true, y_pred, ...)y_true, y_predy_prob, metric list, pos_label, n_rounds, alphaDataFrame
cohens_d(group_a, group_b)two groupsnonefloat
cliffs_delta(group_a, group_b)two groupsnonefloat
cramers_v(table)contingency tablenonefloat
odds_ratio_ci(table)2x2 tablealpha, correctiondict
risk_ratio_ci(table)2x2 tablealpha, correctiondict
standardized_mean_difference(group_a, group_b, ...)two groupscategorical flagfloat

Machine Learning

FunctionRequiredOptionalReturns
train_test_split_data(X, y, ...)X, ytest_size=0.2, stratify=True, random_state=42X_train, X_test, y_train, y_test
compute_class_weights(y, ...)yclass-weight optionsclass-to-weight dict
compute_scale_pos_weight(y, ...)ypositive label optionsfloat ratio for XGBoost
sample_weights_for_sklearn(y, ...)yclass-weight optionssample-weight array
train_random_forest(X_train, y_train, ...)X_train, y_traintest data, class_weight, random_state, plot, RF paramsmodel/predictions/metrics/figures dict
train_xgboost(X_train, y_train, ...)X_train, y_traintest data, scale_pos_weight, random_state, plot, XGB paramsmodel/predictions/metrics/figures dict
calculate_classification_metrics(y_true, y_pred, ...)y_true, y_predy_prob=None, pos_label=Nonemetrics dict
cross_validate_model(estimator, X, y, ...)estimator, X, ycv=5, return_models, return_oof_predictions, pos_labelCV result dict
nested_cross_validate_model(estimator, param_grid, X, y, ...)estimator, grid, X, youter/inner CV, scoringnested CV result dict
evaluate_external_validation(estimator, X_external, y_external, ...)fitted estimator and external datalocked threshold, pos labelvalidation dict
evaluate_locked_threshold(y_true, y_prob, ...)labels, probabilities, thresholdlabelsmetrics dict
fit_probability_calibrator(estimator, X_calibration, y_calibration, ...)fitted estimator and calibration datamethodcalibrator
apply_probability_calibrator(calibrator, X)calibrator and featurespositive class indexprobabilities
model_card_summary(estimator, ...)estimatorX, y, metrics, intended usedict
grid_search_model(estimator, param_grid, X_train, y_train, ...)estimator, param_grid, X_train, y_trainvalidation data, scoring/CV/jobs/refit/random statesearch result dict
get_default_param_grid(model_name)model_namenoneparameter grid dict
get_feature_importance(model, ...)modelfeature_names=Noneimportance DataFrame
plot_feature_importance(model_or_df, ...)model or importance tablefeature_names, top_n, save_path(fig, ax)
run_boruta_feature_selection(X, y, ...)X, yBoruta/model paramsselected features, ranking, transform
run_classification_pipeline(X, y, ...)X, ymodel/split/imbalance/Boruta/search/plot/model paramsfull pipeline result dict
save_estimator(model, path)model, pathnonewrites joblib file
load_estimator(path)pathnoneloaded estimator

Clinical Plots

FunctionRequiredOptionalReturns
plot_kaplan_meier(df, duration_col, event_col, ...)df, duration_col, event_colgroup_col, split_column, CI/risk count/style/save/RMST optionsKaplanMeierPlotResult
plot_roc_curve(y_true, y_prob, ...)y_true, y_probtitle, ax, save_path, fmt, pos_label(fig, ax)
plot_precision_recall_curve(y_true, y_prob, ...)y_true, y_probtitle, ax, save_path, fmt, pos_label(fig, ax)
plot_calibration_curve(y_true, y_prob, ...)y_true, y_probn_bins=10, strategy, title, ax, save_path, fmt, pos_label(fig, ax)
plot_confusion_matrix(y_true, y_pred, ...)y_true, y_predtitle, ax, save_path, fmt, pos_label(fig, ax)
plot_grouped_boxplot(data, x, y, ...)data, x, yhue, order, hue_order, labels, palette, jitter/save options(fig, ax)
plot_grouped_bar_with_significance(data, x, y, ...)data, x, yhue, estimator/error/test/comparison settings, notation thresholds, save(fig, ax, table)
plot_density(data, x, ...)data, xhue, hue_order, labels, palette, fill, bandwidth, gridsize, save(fig, ax)
plot_missingness_bar(data, ...)missingness summary tablecolumn/group/value names, save options(fig, ax)
plot_feature_selection_summary(data, ...)feature-selection summary tablefeature/selected/score columns, top N, save(fig, ax)
plot_stability_selection(data, ...)stability-selection tablefeature/frequency columns, threshold, top N, save(fig, ax)
plot_bland_altman(method_a, method_b, ...)two aligned measurementstitle/save options(fig, ax)
plot_waterfall(values, ...)ordered numeric valueslabels, threshold, title/save options(fig, ax)
plot_table_one_summary(data, ...)Table 1 long table with p-valuesvariable/p-value columns, save(fig, ax)
plot_survival_calibration(data, ...)calibration tableobserved/predicted columns, save(fig, ax)
plot_decision_curve(data, ...)decision-curve tablethreshold/net-benefit columns, save(fig, ax)
plot_time_dependent_auc(data, ...)time/AUC tablecolumn names, save(fig, ax)
plot_cohort_flow(data, ...)flow tablestep/count columns, save(fig, ax)
plot_segmentation_overlay_grid(image, mask, ...)image and mask arraysslice indices, label, alpha, save(fig, axes)
plot_dice_by_label(data, ...)segmentation metric tablelabel/Dice columns, save(fig, ax)
plot_external_validation_metrics(data, ...)metric dict/tablemetric/value columns, save(fig, ax)
plot_correlation_heatmap(data, ...)datacolumns, method, title, annotate, mask_upper, cmap, range, ax, save_path(fig, ax, corr_df)
plot_patterned_bar(data, x, y, ...)data, x, ygroup, error, labels, orientation, palette, hatches, annotate, save(fig, ax)
plot_metric_bars(metrics, ...)metricsmetrics_to_plot, model_col, title, ax, save_path(fig, ax)
plot_risk_score_distribution(data, ...)data with risk score columnrisk_col, event_col, labels, jitter/violin, palette, save(fig, ax)
plot_signed_feature_weights(data, ...)data with feature and weight columnsfeature_col, weight_col, top_n, labels, save(fig, ax)
plot_significance_bars(data, ...)data with label and p-value columnslabel_col, p_col, threshold, annotate, save(fig, ax, table)
plot_volcano(data, ...)feature, effect, and p-value columnsgroup column, thresholds, labels, palette, save(fig, ax)
plot_swimmer(data, ...)patient, start, and end columnsgroup and event columns, palette, save(fig, ax)
plot_raincloud(data, ...)group and numeric value columnsorder, palette, random state, save(fig, ax)
plot_alluvial_flow(data, ...)path, stage, category, and value columnsstage order, palette, save(fig, ax)
plot_binned_marker_heatmap(data, ...)row, column, and bin columnsrow/column order, colormap, missing color, save(fig, ax)
plot_directional_ratio_rows(data, ...)data with feature and ratio columnsoptional CI, p-value, group, n columns, OR/HR table headers, reference, log scale, save(fig, ax)
plot_forest_estimates(data, ...)data with estimate and CI columnslabel/estimate/CI column names, p_col, n_col, reference, log_scale, save(fig, ax)

Preprocessing, Reporting, Validation, Explainability, Audit

FunctionRequiredOptionalReturns
summarize_missingness(df, ...)dfcolumns, group_colmissingness DataFrame
find_duplicate_ids(df, ...)dfid_colduplicate rows
compare_train_test_balance(train, test, ...)train/test DataFramescolumnsbalance DataFrame
detect_potential_leakage(columns, ...)DataFrame or column listkeyword listsleakage flag table
fit_imputer(df, ...)DataFramenumeric/categorical strategiesimputer dict
apply_imputer(df, imputer)DataFrame and imputernoneimputed DataFrame
fit_categorical_encoder(df, ...)DataFramerare handling, drop-firstencoder dict
apply_categorical_encoder(df, encoder)DataFrame and encodernoneencoded DataFrame
describe_numeric(df, ...)DataFramecolumns, group column, digitsnumeric summary DataFrame
describe_categorical(df, ...)DataFramecolumns, group column, missing handlingcategorical summary DataFrame
compare_descriptive_groups(df, group_col, ...)DataFrame and group columnnumeric/categorical columnsp-value summary table
create_table_one(df, ...)DataFramegroup, numeric/categorical columnslong Table 1 table
summarize_endpoint(df, event_col, ...)DataFrame and event columntime/group columnsendpoint summary table
univariate_feature_screening(X, y, ...)features, targettask, alpha, correctionselection result dict
variance_filter(X, ...)featuresthresholdselection result dict
correlation_filter(X, ...)featuresthreshold, methodselection result dict
model_importance_selection(estimator, X, y, ...)estimator, features, targetthreshold/top Nselection result dict
permutation_importance_selection(estimator, X, y, ...)estimator, features, targetrepeats, scoring, threshold/top Nselection result dict
stability_selection(estimator, X, y, ...)estimator, features, targetrounds, fraction, thresholdselection result dict
combine_feature_selection_results(results, ...)selection resultsstrategy, minimum methodsconsensus result dict
summarize_baseline_table(df, ...)dfgroup, continuous/categorical columns, digitsbaseline table
cohort_flow_table(steps)step dictionariesnoneflow table
metrics_table(metrics, ...)metrics mapping/DataFramemodel column, digitsreport metric table
p_value_correction_table(df, ...)DataFrame with p-valuesmethod, alphaadjusted p-value table
fit_logistic_regression_table(df, ...)DataFrame, outcome, covariatesintercept, alpha, p adjustmentOR table
fit_linear_regression_table(df, ...)DataFrame, outcome, covariatesintercept, alpha, p adjustmentbeta table
vif_table(df, covariates)DataFrame and covariatesnonemulticollinearity table
mcnemar_test(y_true, pred_a, pred_b, ...)paired labels/predictionsexact modeMcNemar table
bootstrap_auc_difference(y_true, prob_a, prob_b, ...)labels and two probability vectorsrounds, alpha, seedAUC difference table
FlowTracker(title).add_step(label, df, ...)step label and DataFramereason, metadataDataFrame unchanged and recorded flow step
track_filter(flow, label=...)FlowTracker, labelreason, metadatadecorated DataFrame filter
find_best_threshold(y_true, y_prob, ...)labels, probabilitiesmetric, thresholds, positive labelthreshold dict/table
calibration_summary(y_true, y_prob, ...)labels, probabilitiesbins, positive labelsummary dict and bin table
subgroup_metric_table(df, ...)DataFrame and group/label/pred columnsprobability column, positive labelsubgroup metric table
decision_curve_table(y_true, y_prob, ...)labels, probabilitiesthresholds, positive labelnet-benefit table
bootstrap_concordance_index(df, ...)survival table and duration/event/risk columnsrounds, random stateC-index summary dict
survival_calibration_at_time(df, ...)survival table and prediction columntime horizon, binssummary dict and bin table
brier_score_at_time(df, ...)survival table and prediction columntime horizonBrier score dict
external_survival_validation(...)external table and risk columnprediction column, horizonvalidation dict
permutation_importance_table(estimator, X, y, ...)fitted estimator, features, labelsnames, repeats, scoring, random stateimportance DataFrame
partial_dependence_table(estimator, X, ...)fitted estimator and featuresselected features, names, grid resolutionPDP DataFrame
shap_summary_table(estimator, X, ...)fitted estimator and feature tablefeature names, custom explainer, background data, max rowsSHAP summary DataFrame
shap_values_table(estimator, X, ...)fitted estimator and feature tablefeature names, custom explainer, background data, max rowslong SHAP DataFrame
explain_model_summary(...)importance, SHAP, or feature QC tablemetrics, notes, feature columnmerged explanation summary
explain_patient_prediction(contributions, ...)long contribution tablerow/patient selector, top Ntop signed drivers
create_provenance_manifest(...)nonetitle, inputs, outputs, parameters, notesmanifest dict
write_manifest(manifest, path)manifest and output pathnonewritten path

BOA Extraction, Radiomics And Visualization

FunctionRequiredOptionalReturns
discover_boa_cases(cohort_folder, ...)cohort_foldermeasurement_filenamelist of case folders
extract_body_region_features(case_folder_or_measurements, ...)patient folder or measurement JSONbody regions, tissues, SMA labels, derived markers, height, missing valuefeature dict or None
extract_total_segmentation_features(case_folder, ...)case_folderlabels, ratios, measurement filename, rounding, missing valuefeature dict or None
extract_experimental_aortic_calcification_features(case_folder_or_masks_dir, ...)patient or mask folderCT path, mask folder, HU threshold, aorta/total/body-region/iliac mask settingsfeature dict or None
extract_experimental_cohort_aortic_calcification_features(cohort_folder_or_cases, ...)cohort root or case foldersworkers, progress, single-case extraction optionsaortic calcification DataFrame
discover_boa_radiomics_cases(cohort_folder, ...)cohort_foldersegmentation_filenamelist of case folders
extract_case_radiomics_features(case_folder, ...)case_folderimage/segmentation filenames, labels, extractor settings, paths, on_errorfeature dict or None
extract_boa_radiomics_features(cohort_folder_or_cases, ...)cohort root or case folderssegmentation kind, labels, extractor settings, workersradiomics DataFrame
SegmentationLayer(kind, ...)kinddisplay_mode, title, filename, opacitylayer configuration
create_boa_segmentation_collage(boa_folders, output_path, ...)boa_folders, output_pathorientation, layers, labels, slices, CT window, opacity, panel width, body-region crop optionsmetadata dict and output image
plot_volume_difference_heatmap(volume_a, volume_b, ...)two aligned CT/MR volumesdata type, orientation, slices, labels, CT/MR scaling, difference colormap, save path(fig, axes, table)

Documents, DICOM, FHIR, LLM

Client classes have broader method surfaces; see their module pages for workflow detail: