PsychiatryNLPKit.analysis.BatchAnalyzer

class PsychiatryNLPKit.analysis.BatchAnalyzer(text_data, included_analyses='all', excluded_analyses=None, image_paths=None)

Run selected analyses on a TextData object in batch.

The analyzer is an orchestrator only — every analysis is executed through TextData.compute. Models required by the requested analyses must be attached to the TextData instance; the analyzer keeps them loaded for the whole run and unloads them afterwards.

Args:

text_data: Pre-built TextData instance with sections and any models

required by the requested analyses.

included_analyses: "all" runs every registered analysis. Pass an explicit

list of function names to run a subset.

excluded_analyses: Function names to remove from included_analyses. Every

name here must already be in the resolved inclusion list; otherwise an AssertionError is raised.

image_paths: Mapping of section name → image file path. Required if

"image_text_similarity" is in analyses; must cover every section in text_data.section_names.

Raises:

AssertionError: If a requested analysis requires a model or data argument

that was not provided.

Example:

# Run all analyses (requires all models attached to text_data)
result = BatchAnalyzer(
    text_data, image_paths={"Paragraph 1": "img1.jpg", "Paragraph 2": "img2.jpg"}
).run()

# Selective analyses with language-dependent metrics
result = BatchAnalyzer(
    text_data,
    included_analyses=["sentence_length", "adverb_ratio", "filler_words_count"],
).run()

__init__(text_data, included_analyses='all', excluded_analyses=None, image_paths=None)

Methods

__init__(text_data[, included_analyses, ...])
run()	Execute all requested analyses and return merged results.

__init__(text_data, included_analyses='all', excluded_analyses=None, image_paths=None)

run()

Execute all requested analyses and return merged results.