Skip to main content

Batch Corpus Analyzer for MoE Classification.

File: batch_processor.py

Classes

BatchConfig

No description

CorpusProfile

No description

DocumentCluster

No description

BatchCorpusAnalyzer

Analyzes document corpus for cross-document patterns.

Functions

get_batch_analyzer(config)

No description

profile_corpus(document_paths)

Build corpus profile from document paths.

cluster_documents(document_paths)

Cluster documents by directory/naming patterns.

analyze_corpus(document_paths, classify_fn)

Full corpus analysis with optional classification.

get_consistency_check(clusters, results)

Check if classifications are consistent within clusters.