1ST

app.py

@@ -0,0 +1,56 @@
+import streamlit as st
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.decomposition import LatentDirichletAllocation
+import matplotlib.pyplot as plt
+
+# Title and tabs
+st.title("Topic Modeling for News Articles")
+tab1, tab2 = st.tabs(["LDA Topic Modeling", "About the Dataset"])
+
+# First Tab: Topic Modeling
+with tab1:
+    st.header("Input Data")
+    
+    # Text input for articles
+    st.write("Paste your news articles (one article per line):")
+    user_input = st.text_area("Enter articles here", height=200)
+    
+    if st.button("Analyze Topics"):
+        if user_input.strip():
+            # Convert input into a list of articles
+            articles = user_input.split("\n")
+            articles = [article.strip() for article in articles if article.strip()]
+            
+            # TF-IDF Vectorization
+            vectorizer = TfidfVectorizer(stop_words='english', max_features=5000)
+            tfidf_matrix = vectorizer.fit_transform(articles)
+            
+            # LDA Topic Modeling
+            lda = LatentDirichletAllocation(n_components=5, random_state=42)
+            lda.fit(tfidf_matrix)
+            
+            # Display topics
+            st.subheader("Identified Topics")
+            feature_names = vectorizer.get_feature_names_out()
+            for idx, topic in enumerate(lda.components_):
+                st.write(f"**Topic {idx + 1}:**", ", ".join([feature_names[i] for i in topic.argsort()[-10:]]))
+            
+            # Visualize topic distribution
+            st.subheader("Topic Distribution")
+            topic_distribution = lda.transform(tfidf_matrix)
+            plt.figure(figsize=(10, 5))
+            plt.bar(range(len(topic_distribution[0])), topic_distribution[0])
+            plt.xlabel("Topics")
+            plt.ylabel("Contribution")
+            plt.title("Topic Distribution for the First Article")
+            st.pyplot(plt.gcf())
+        else:
+            st.warning("Please input some articles to analyze.")
+
+# Second Tab: About the Dataset
+with tab2:
+    st.header("About")
+    st.write("This app performs topic modeling on news articles using Latent Dirichlet Allocation (LDA).")
+    st.write("Paste articles in the text area, and the app will identify underlying topics.")
+

requirements.txt

@@ -0,0 +1,5 @@
+pandas==1.5.3
+numpy>=1.24.3
+scikit-learn>=1.3.0
+matplotlib>=3.7.1
+streamlit>=1.25.0