spacy_nlp_program

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Filename: spacy_nlp_program.py
# Author: Jeoi Reqi

"""
Welcome to the SpaCy NLP Tool!

This interactive script provides a Natural Language Processing (NLP) tool powered by the SpaCy library.
It offers various text analysis functionalities through a user-friendly menu.

Requirements:
- Python 3
- SpaCy library
- SpacyTextBlob library for sentiment analysis

Usage:
1. Run the script.
2. Follow the menu prompts to select the desired analysis.
3. Enter the text for analysis.

Menu Options:
1. Tokenization: Breaks text into words and sentences.
2. Named Entity Recognition: Identifies entities such as persons, organizations, and locations.
3. Part-of-Speech Tagging: Identifies grammatical parts of speech for each word.
4. Sentiment Analysis: Determines sentiment polarity (negative, neutral, positive).

Examples:

1. Tokenization
Enter the text: Hello, World!
Tokenized Words: ['Hello', ',', 'World', '!']
Tokenized Sentences: ['Hello, World!']

2. Part-of-Speech Tagging
Enter the text: Hello, World!
Part-of-Speech Tags: [('Hello', 'NNP'), (',', ','), ('World', 'NNP'), ('!', '.')]

3. Named Entity Recognition
Enter the text: Hello, World!
Named Entity Recognition: (S (GPE Hello/NNP) ,/, (PERSON World/NNP) !/.)

4. Sentiment Analysis
Enter the text: Hello, World!
Sentiment Analysis: {'neg': 0.0, 'neu': 1.0, 'pos': 0.0, 'compound': 0.0}

Enjoy exploring the world of Natural Language Processing with SpaCy!
"""

# Imports
import spacy
from spacytextblob.spacytextblob import SpacyTextBlob
from spacy.tokens import Doc
from textblob import TextBlob

# Tokenization Function
def tokenization_spacy(text):
    """
    Tokenizes the input text into words and sentences using SpaCy.

    Parameters:
    - text (str): Input text for tokenization.

    Returns:
    Tuple[List[str], List[str]]: Tokenized words and sentences.
    """
    nlp = spacy.load("en_core_web_sm")
    doc = nlp(text)
    tokens = [token.text for token in doc]
    sentences = [sent.text for sent in doc.sents]
    print("Tokenized Words:", tokens)
    print("Tokenized Sentences:", sentences)

# Named Entity Recognition Function
def named_entity_recognition_spacy(text):
    """
    Identifies named entities in the input text using SpaCy.

    Parameters:
    - text (str): Input text for named entity recognition.

    Returns:
    List[Tuple[str, str]]: Named entities and their labels.
    """
    nlp = spacy.load("en_core_web_sm")
    doc = nlp(text)
    entities = [(ent.text, ent.label_) for ent in doc.ents]
    print("Named Entities:", entities)

# Part-of-Speech Tagging Function
def part_of_speech_tagging_spacy(text):
    """
    Performs part-of-speech tagging on the input text using SpaCy.

    Parameters:
    - text (str): Input text for part-of-speech tagging.

    Returns:
    List[Tuple[str, str]]: Part-of-speech tags for each word.
    """
    nlp = spacy.load("en_core_web_sm")
    doc = nlp(text)
    pos_tags = [(token.text, token.pos_) for token in doc]
    print("Part-of-Speech Tags:", pos_tags)

# Sentiment Analysis Function
def sentiment_analysis_spacy(text):
    """
    Analyzes the sentiment of the input text using SpaCyTextBlob.

    Parameters:
    - text (str): Input text for sentiment analysis.

    Returns:
    float: Sentiment polarity score.
    """
    nlp = spacy.load("en_core_web_sm")
    nlp.add_pipe('spacytextblob')
    doc = nlp(text)

    # Access sentiment polarity from the 'doc' object
    sentiment_score = doc._.sentiment.polarity
    print("Sentiment Score:", sentiment_score)

# Menu & Options Function
def main_spacy():
    """
    Main function for the SpaCy NLP tool, providing a user-friendly menu for text analysis.
    """
    print("Welcome to the SpaCy NLP Tool!\n")

    while True:
        print_menu()
        choice = input("Enter your choice (0-4): ")

        if choice == '0':
            print("Exiting the program. Goodbye!")
            break
        elif choice == '1':
            text = input("Enter the text: ")
            tokenization_spacy(text)
        elif choice == '2':
            text = input("Enter the text: ")
            named_entity_recognition_spacy(text)
        elif choice == '3':
            text = input("Enter the text: ")
            part_of_speech_tagging_spacy(text)
        elif choice == '4':
            text = input("Enter the text: ")
            sentiment_analysis_spacy(text)
        else:
            print("Invalid choice. Please enter a number between 0 and 4.")

# Menu Printing Function
def print_menu():
    """
    Prints the menu options for the user.
    """
    print("\nMenu:")
    print("1. Tokenization")
    print("2. Named Entity Recognition")
    print("3. Part-of-Speech Tagging")
    print("4. Sentiment Analysis")
    print("0. Exit")

if __name__ == "__main__":
    main_spacy()