Skip to main content

texta-crf-extractor

Project description

TEXTA CRF Extractor

Py3.8 Py3.9 Py3.10

Requirements

  • Python >= 3.8
  • SciPy installation for scikit-learn (requires BLAS & LAPACK system libraries).

Installation:

# For debian based systems (ex: debian:buster) to install binary dependencies.

apt-get update && apt-get install python3-scipy

# Install without MLP

pip install texta-crf-extractor

# Install with MLP 

pip install texta-crf-extractor[mlp]

Usage:

from texta_crf_extractor.crf_extractor import CRFExtractor
from texta_mlp.mlp import MLP

mlp = MLP(language_codes=["en"], default_language_code="en")

# prepare data
texts = ["foo", "bar"]
mlp_docs = [mlp.process(text) for text in texts]

# create extractor
extractor = CRFExtractor(mlp=mlp)

# train the CRF model
extractor.train(mlp_docs)

# tag something
extractor.tag("Tere maailm!")

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

texta-crf-extractor-2.2.0.tar.gz (20.7 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page