drcme.bin.run_post_r_merging¶

Script for determining how many GMM components to merge.

Gaussian mixture model (GMM) components are merged into a smaller number of clusters using an entropy criterion as described by Baudry et al. (2010). A piecewise linear fit is used to determine the point at which merging should terminate.

class drcme.bin.run_post_r_merging.PostGmmMergingParameters(extra=None, only=None, exclude=(), prefix='', strict=None, many=False, context=None, load_only=(), dump_only=(), partial=False)[source]¶

Parameter schema for merging

This schema is designed to be a schema_type for an ArgSchemaParser object

PostGmmMergingParameters¶
key	description	default	field_type	json_type
input_json	file path of input json file	NA	`InputFile`	str
output_json	file path to output json file	NA	`OutputFile`	str
log_level	set the logging level of the module	ERROR	`LogLevel`	str
tau_file	Path to file with cluster membership probabilities	NA	`InputFile`	str
labels_file	Path to file with cluster labels	NA	`InputFile`	str
merge_info_file	Path to JSON file with number of components after entropy-based merging	NA	`OutputFile`	str
entropy_piecewise_components	Number of components (2 or 3) for piecewise linear fit of entropy scores	3	`Integer`	int

Functions

main(tau_file, labels_file, merge_info_file, …)

Main runner function for script.

Classes

PostGmmMergingParameters([extra, only, …])

Parameter schema for merging