Learn SPACY with Real Code Examples

Updated Nov 24, 2025

Introduction & Fundamentals Setup & Configuration Architecture & Deep Internals Performance & Security Development Workflow Learning & Career Growth Business & Strategy Examples

Code Sample Descriptions

spaCy Named Entity Recognition Example

import spacy

# Load English model
nlp = spacy.load('en_core_web_sm')

# Sample text
doc = nlp('Apple is looking at buying U.K. startup for $1 billion')

# Print named entities
for ent in doc.ents:
    print(ent.text, ent.label_)

A minimal spaCy example performing named entity recognition on a sample text.

Let’s Try →

spaCy Tokenization Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is an amazing NLP library.'
doc = nlp(text)

# Print tokens
for token in doc:
    print(token.text)

Splits text into tokens using spaCy tokenizer.

Let’s Try →

spaCy Part-of-Speech Tagging Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is fast and accurate.'
doc = nlp(text)

# Print token POS tags
for token in doc:
    print(token.text, token.pos_, token.tag_)

Tags each token with its part-of-speech (POS) label.

Let’s Try →

spaCy Dependency Parsing Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy parses text efficiently.'
doc = nlp(text)

# Print dependencies
for token in doc:
    print(token.text, token.dep_, token.head.text)

Displays syntactic dependencies between tokens.

Let’s Try →

spaCy Lemmatization Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'running runs ran'
doc = nlp(text)

# Print lemmas
for token in doc:
    print(token.text, token.lemma_)

Extracts the base form (lemma) of each token.

Let’s Try →

spaCy Sentence Segmentation Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is fast. It is easy to use.'
doc = nlp(text)

# Print sentences
for sent in doc.sents:
    print(sent.text)

Splits text into sentences.

Let’s Try →

spaCy Matcher Example

import spacy
from spacy.matcher import Matcher

nlp = spacy.load('en_core_web_sm')
doc = nlp('I love NLP and machine learning')

matcher = Matcher(nlp.vocab)
pattern = [{'LOWER':'nlp'}]
matcher.add('NLP_PATTERN', [pattern])

matches = matcher(doc)
for match_id, start, end in matches:
    print(doc[start:end].text)

Matches specific token patterns in text using spaCy Matcher.

Let’s Try →

spaCy Entity Ruler Example

import spacy
from spacy.pipeline import EntityRuler

nlp = spacy.load('en_core_web_sm')
ruler = EntityRuler(nlp)
ruler.add_patterns([{'label':'ORG','pattern':'OpenAI'}])
nlp.add_pipe(ruler, before='ner')

doc = nlp('OpenAI develops AI models.')
for ent in doc.ents:
    print(ent.text, ent.label_)

Adds custom named entities using spaCy's EntityRuler.

Let’s Try →

spaCy Text Similarity Example

import spacy

nlp = spacy.load('en_core_web_md')
text1 = nlp('I love machine learning')
text2 = nlp('I enjoy NLP')

similarity = text1.similarity(text2)
print(similarity)

Computes similarity between two texts using spaCy vectors.

Let’s Try →

spaCy Custom Component Example

import spacy

nlp = spacy.load('en_core_web_sm')

def custom_component(doc):
    print('Processing text:', doc.text)
    return doc

nlp.add_pipe(custom_component, last=True)
doc = nlp('SpaCy pipelines are powerful.')

Adds a custom pipeline component to process text.

Let’s Try →

Code Sample Descriptions

spaCy Named Entity Recognition Example

import spacy

# Load English model
nlp = spacy.load('en_core_web_sm')

# Sample text
doc = nlp('Apple is looking at buying U.K. startup for $1 billion')

# Print named entities
for ent in doc.ents:
    print(ent.text, ent.label_)

A minimal spaCy example performing named entity recognition on a sample text.

Let’s Try →

spaCy Tokenization Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is an amazing NLP library.'
doc = nlp(text)

# Print tokens
for token in doc:
    print(token.text)

Splits text into tokens using spaCy tokenizer.

Let’s Try →

spaCy Part-of-Speech Tagging Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is fast and accurate.'
doc = nlp(text)

# Print token POS tags
for token in doc:
    print(token.text, token.pos_, token.tag_)

Tags each token with its part-of-speech (POS) label.

Let’s Try →

spaCy Dependency Parsing Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy parses text efficiently.'
doc = nlp(text)

# Print dependencies
for token in doc:
    print(token.text, token.dep_, token.head.text)

Displays syntactic dependencies between tokens.

Let’s Try →

spaCy Lemmatization Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'running runs ran'
doc = nlp(text)

# Print lemmas
for token in doc:
    print(token.text, token.lemma_)

Extracts the base form (lemma) of each token.

Let’s Try →

spaCy Sentence Segmentation Example

import spacy

nlp = spacy.load('en_core_web_sm')
text = 'SpaCy is fast. It is easy to use.'
doc = nlp(text)

# Print sentences
for sent in doc.sents:
    print(sent.text)

Splits text into sentences.

Let’s Try →

spaCy Matcher Example

import spacy
from spacy.matcher import Matcher

nlp = spacy.load('en_core_web_sm')
doc = nlp('I love NLP and machine learning')

matcher = Matcher(nlp.vocab)
pattern = [{'LOWER':'nlp'}]
matcher.add('NLP_PATTERN', [pattern])

matches = matcher(doc)
for match_id, start, end in matches:
    print(doc[start:end].text)

Matches specific token patterns in text using spaCy Matcher.

Let’s Try →

spaCy Entity Ruler Example

import spacy
from spacy.pipeline import EntityRuler

nlp = spacy.load('en_core_web_sm')
ruler = EntityRuler(nlp)
ruler.add_patterns([{'label':'ORG','pattern':'OpenAI'}])
nlp.add_pipe(ruler, before='ner')

doc = nlp('OpenAI develops AI models.')
for ent in doc.ents:
    print(ent.text, ent.label_)

Adds custom named entities using spaCy's EntityRuler.

Let’s Try →

spaCy Text Similarity Example

import spacy

nlp = spacy.load('en_core_web_md')
text1 = nlp('I love machine learning')
text2 = nlp('I enjoy NLP')

similarity = text1.similarity(text2)
print(similarity)

Computes similarity between two texts using spaCy vectors.

Let’s Try →

spaCy Custom Component Example

import spacy

nlp = spacy.load('en_core_web_sm')

def custom_component(doc):
    print('Processing text:', doc.text)
    return doc

nlp.add_pipe(custom_component, last=True)
doc = nlp('SpaCy pipelines are powerful.')

Adds a custom pipeline component to process text.

Let’s Try →