Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import TfidfVectorizer

st.title('Topic Similarity Analysis')

# Sample Wikipedia articles (You may replace these with actual articles if available)
articles = {
    'Python (programming language)': 'Python is an interpreted, high-level, general-purpose programming language.',
    'Java (programming language)': 'Java is a high-level, class-based, object-oriented programming language that is designed to have as few implementation dependencies as possible.',
    'JavaScript': 'JavaScript is a programming language that conforms to the ECMAScript specification.',
    'Data Science': 'Data science is a multi-disciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from structured and unstructured data.',
    'Machine Learning': 'Machine learning is the study of computer algorithms that improve automatically through experience and by the use of data.'
}

# Create a DataFrame from articles
article_df = pd.DataFrame(articles.items(), columns=['Topic', 'Content'])

# User input for the primary topic
primary_topic = st.selectbox('Select a primary topic:', article_df['Topic'])

# Prepare the vectorizer and transform the articles into TF-IDF matrix
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(article_df['Content'])

# Calculate cosine similarity
cosine_sim = cosine_similarity(X)

# Find the index of the selected primary topic
primary_index = article_df[article_df['Topic'] == primary_topic].index[0]

# Get similarity scores for the primary topic
similarity_scores = cosine_sim[primary_index]

# Create a DataFrame for results
similarity_df = pd.DataFrame({'Topic': article_df['Topic'], 'Similarity Score': similarity_scores})

# Sort the DataFrame by similarity scores
similarity_df = similarity_df.sort_values(by='Similarity Score', ascending=False)

# Display the similarity results
st.write('Similarity Scores for topics related to **' + primary_topic + '**')
st.table(similarity_df)