Libraries Used in the Notebook
1. spacy
SpaCy is a library for Natural Language Processing (NLP). It allows you to analyze and
understand text with Python.
In this notebook, spaCy is used to:
• Split a sentence into individual words or punctuation marks (called tokens).
• Figure out what grammatical role each word plays (called part-of-speech or POS
tagging), such as noun, verb, or adjective.
The line used to load the English model:
nlp = [Link]('en_core_web_sm')
loads a small English model that comes with vocabulary, grammar rules, and statistical
patterns.
Note: If you haven’t downloaded this model before, you'll need to run this in your terminal:
python -m spacy download en_core_web_sm
2. pandas
A popular Python library for working with structured data.
In this notebook, it’s used to organize and display the POS tagging results in a readable format
called a DataFrame, which looks like a table with rows and columns.
Example of creating an empty DataFrame:
pos_df = [Link](columns=['token', 'pos_tag'])
What the Code Does
Step 1: Load the NLP Model
nlp = [Link]('en_core_web_sm')
This line prepares spaCy to process English text.
The model understands grammar and can label each word with its role in the sentence.
Step 2: Add a Text Sample
emma_ja = "emma woodhouse handsome clever and rich..."
This is a paragraph from Jane Austen’s Emma.
The text is already cleaned: it’s all lowercase and doesn’t contain punctuation.
This makes it simpler to analyze.
Step 3: Process the Text
spacy_doc = nlp(emma_ja)
The text is passed through the NLP model.
The result is a Doc object, which contains all the individual words and information about them
(like POS tags).
Step 4: Set Up a Data Table
pos_df = [Link](columns=['token', 'pos_tag'])
This creates a table structure where each word and its part-of-speech tag will be added.
