spaCy
spaCy is an open-source Python library for natural language processing, providing tools and pretrained pipelines for tasks such as tokenization and linguistic analysis.
Natural Language Processing in Action, Second Edition
spaCy is an open-source software library for advanced natural-language processing, including tokenization and syntactic analysis.
- How it is used
- Deploys tokenization, grammatical analysis, dependency parsing, visualization, and entity extraction in practical NLP pipelines.
- How deep it goes
- Explains runnable model loading, token attributes, visualization, pipeline timing, and NER architecture without teaching neural-network construction.
- Examples
- Uses thinker quotations, an AsciiDoc chapter, medical-record workloads, dependency diagrams, and text about Timnit Gebru.
- What you can do after
- Apply it via spaCy to tokenize text, inspect grammatical structure, render dependencies, extract entities, and tune pipeline speed.
Read how Natural Language Processing in Action, Second Edition explains spaCy →
Starting Data Analytics with Generative AI and Python
spaCy is an open-source Python library for industrial-strength natural language processing.
- How it is used
- Supports customer-review keyword search by lemmatizing text before matching.
- How deep it goes
- Demonstrates a concrete preprocessing function but stops short of explaining spaCy internals or comparing model quality.
- Examples
- Uses Portuguese customer reviews, the pt_core_news_sm model, and cleaned_review_text as concrete artifacts.
- What you can do after
- Apply spaCy to lemmatize review text and prepare it for keyword matching.
Read how Starting Data Analytics with Generative AI and Python explains spaCy →
Generative AI in Action
spaCy is an open-source Python library for efficient natural-language processing, including linguistic annotation and text segmentation.
- How it is used
- Supports retrieval-augmented generation by producing context-aware chunks for downstream retrieval and generation.
- How deep it goes
- Implements model loading, sentence extraction, token counting, and overlap, without detailing linguistic-model internals.
- Examples
- Demonstrates sentence chunking with en_core_web_sm, configurable overlap, and a performance comparison against NLTK and simpler methods.
- What you can do after
- Apply spaCy via Python to create token-bounded, sentence-aware text chunks.
Outlier Detection in Python
spaCy is an open-source Python library for efficient natural language processing and linguistic feature extraction.
- How it is used
- Extracts interpretable linguistic features for text analysis and obvious outlier detection.
- How deep it goes
- Explains document processing and feature counts, but stops short of detailed parsing internals or advanced language-model methods.
- Examples
- Uses the 20 Newsgroups messages to count words, unique words, non-stop words, sentences, and characters.
- What you can do after
- Build text-derived features with spaCy and use them as interpretable inputs for anomaly analysis.
AI-Powered Search
spaCy is an open-source Python library for natural language processing that provides pretrained models and linguistic analysis pipelines.
- How it is used
- Supports relationship extraction, knowledge-graph construction, concept discovery, autocomplete, and semantic-search preparation.
- How deep it goes
- Explains pipeline outputs and implementation patterns, but stops short of detailing model architectures or training procedures.
- Examples
- Uses school-attendance and employment sentences, relationship triples, Matcher patterns, corpus frequencies, and batched document processing.
- What you can do after
- Builds Python pipelines that extract linguistic concepts, relationships, graph facts, and filtered vocabulary from text.
Related concepts
- part of speechuses · A part of speech is a grammatical category assigned to a word according to its syntactic role and related properties.
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- tokenizeruses · A tokenizer is a text-processing component or algorithm that segments text into discrete tokens and may map them to identifiers for computational processing.
- librarykind of · A software library is a reusable collection of code or components that other programs can incorporate or invoke to provide functionality.
- text chunkuses · A text chunk is a bounded segment of a larger text treated as a unit for processing, storage, or retrieval.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.