jbesomi/texthero

Health v2 · maintenance only

Adoption not part of the score

2907 stars · 236 forks observed · 2026-08-28

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

Texthero is a Python toolkit for text preprocessing, representation, and visualization, designed to work on top of Pandas Series and DataFrames. It provides pipelines for cleaning text, mapping it into vector spaces (TF-IDF, term frequency), clustering, dimensionality reduction, and visualizing text datasets in a few lines of code.

Use cases

• clean and preprocess text data in pandas
• compute tf-idf vectors for a text corpus
• cluster documents with k-means
• visualize text vector spaces with pca and tsne
• extract named entities from text
• find top words and keywords in a dataset
• remove stopwords, punctuation, and html tags from text

When to choose

• you work with text datasets in Pandas and want quick cleaning and vectorization
• you need fast exploratory insights into text-only data
• you want a simple scikit-learn-like API for text preprocessing and clustering

When to avoid

• you need state-of-the-art NLP models or transformer-based pipelines
• you need actively developed features or timely bug fixes
• you need production-grade, highly customizable NLP pipelines

Facets

library · maturity maintenance

nlp data-science data-visualization machine-learning parser data-science machine-learning python text-preprocessing pandas tf-idf word-embeddings text-clustering topic-modeling named-entity-recognition scikit-learn natural-language-processing text-mining

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jbesomi/texthero")