chartbeat-labs/textacy

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2239 stars · 247 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

textacy is a Python NLP library built on spaCy that handles tasks before and after spaCy's core pipeline, such as text cleaning, information extraction, and topic modeling. It also provides prepared text datasets and readability/lexical diversity statistics.

Use cases

• extract keyterms and n-grams from documents
• train and visualize topic models on a corpus
• clean and normalize raw text before spaCy processing
• compute Flesch-Kincaid readability scores
• extract entities, acronyms, and SVO triples from text
• load prepared NLP datasets like Congressional speeches
• compare strings with similarity metrics

When to choose

• you already use spaCy and need higher-level text analysis utilities
• you need keyterm extraction, topic modeling, or readability statistics in Python
• you want convenient access to prepared text datasets with metadata

When to avoid

• you need core tokenization, tagging, or parsing - use spaCy directly
• you need a framework-agnostic NLP toolkit independent of spaCy
• you need actively developed features - releases have slowed since 2023

Facets

library · maturity maintenance

nlp parser machine-learning data-science text-editors data-science python spacy topic-modeling text-processing keyterm-extraction readability-statistics linguistics natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="chartbeat-labs/textacy")