spaCy

spaCy is a natural language processing library, including word segmentation, part-of-speech tagging, stemming, named entity recognition, noun phrase extraction and other functions.

Install

# Install spaCy 3 For CUDA 11.2, replace the version in [] according to the mirror CUDA version
pip install spacy[cuda112]==3.0.6

# Install spaCy 2 For CUDA 11.2, replace the version in [] according to the mirror CUDA version
pip install spacy[cuda112]==2.3.5

# Download the model through the spacy module because the wall may not be available, you can install it through the following pip installation method
python -m spacy download en_core_web_sm

# install 3.0.0 en_core_web_sm
pip install https://mirror.ghproxy.com/https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0-py3-none-any.whl - -no-cache

# install 2.3.1 en_core_web_sm
pip install https://mirror.ghproxy.com/https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz --no-cache

use

import spacy

# Load English tokenizer, tagger, parser and NER
nlp = spacy.load("en_core_web_sm")

# Process whole documents
text = ("When Sebastian Thrun started working on self-driving cars at "
        "Google in 2007, few people outside of the company took him "
        "seriously. "I can tell you very senior CEOs of major American "
        "car companies would shake my hand and turn away because I wasn't "
        "worth talking to," said Thrun, in an interview with Recode earlier "
        "this week.")
doc = nlp(text)

# Analyze syntax
print("Noun phrases:", [chunk.text for chunk in doc.noun_chunks])
print("Verbs:", [token.lemma_ for token in doc if token.pos_ == "VERB"])

# Find named entities, phrases and concepts
for entity in doc.ents:
    print(entity.text, entity.label_)