Pipelines

Pre-build pipelines and pipeline helpers.

Full Pipelines

GenericMobilisedPipeline(*, ...[, ...])	Pipeline structure of the Mobilise-D pipeline without any default algorithms.
MobilisedPipelineHealthy(*, ...[, ...])	Official Mobilise-D pipeline for healthy and mildly impaired gait (aka P1 pipeline).
MobilisedPipelineImpaired(*, ...[, ...])	Official Mobilise-D pipeline for impaired gait (aka P2 pipeline).
MobilisedPipelineUniversal(pipelines, ...[, ...])	Metapipeline that can use a specific pipeline depending on the cohort of the participant.

BaseClasses

base.BaseMobilisedPipeline()

Base typing interface for Mobilised Pipelines.

Docu-helper

base.mobilised_pipeline_docfiller(func)

Fill docstring from dictionary.

Evaluation

WB-Matching

categorize_intervals(*, gsd_list_detected, ...)	Evaluate a gait sequence list against a reference sequence-by-sequence with a minimum overlap threshold.
categorize_intervals_per_sample(*, ...[, ...])	Evaluate detected gait sequence intervals against a reference on a sample-wise level.
get_matching_intervals(*, metrics_detected, ...)	Extract the detected and reference gait sequences that are considered as matches sequence-by-sequence.

Per-Row-Error Funcs

ErrorTransformFuncs()

Typical row by row error functions.

get_default_error_transformations()	Get all default error metrics used in Mobilise-D.
error(df[, reference_col_name, ...])	Calculate the error between the detected and reference values.
rel_error(df[, reference_col_name, ...])	Calculate the relative error between the detected and reference values.
abs_error(df[, reference_col_name, ...])	Calculate the absolute error between the detected and reference values.
abs_rel_error(df[, reference_col_name, ...])	Calculate the absolute relative error between the detected and reference values.

Custom Error Aggregations

CustomErrorAggregations()

Custom aggregation functions that might be useful in addition to the once provided by pandas (e.g. mean/std).

get_default_error_aggregations()	Return a list containing all important error aggregations utilized in Mobilise-D.
icc(df[, reference_col_name, detected_col_name])	Calculate the intraclass correlation coefficient (ICC) for the detected and reference values.
loa(series[, agreement])	Calculate the limits of agreement of a measure.
quantiles(series[, lower, upper])	Calculate the quantiles of a measure.

Helper

Gait Sequence Iteration

GsIterator()

Iterator to split data into gait-sequences and iterate over them individually.

iter_gs(data, region_list, *[, id_col])

Iterate over the data based on the given gait-sequences.

Aggregation Functions

create_aggregate_df(result_name[, ...])

Create an aggregator for the GS iterator that aggregates dataframe results into a single dataframe.

Datatypes

FullPipelinePerGsResult(ic_list, turn_list, ...)

Default expected result type for the gait-sequence iterator.