Upload app.py

app.py

@@ -0,0 +1,117 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import torch
+import ast
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import random
+import asyncio
+import os
+os.environ["STREAMLIT_WATCHDOG"] = "0"
+
+try:
+    asyncio.get_running_loop()
+except RuntimeError:
+    asyncio.set_event_loop(asyncio.new_event_loop())
+
+
+# Load pre-trained model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def get_embedding(text):
+    return model.encode(text, convert_to_numpy=True)
+
+# Load datasets
+tweets_df = pd.read_csv("dataset_with_embeddings.csv")  # Contains 'tweet_id' and 'sentence_embedding'
+original_tweets_df = pd.read_csv("dataset_with_actual_text.csv")  # Contains 'tweet_id' and 'original_text'
+
+# Convert embeddings from string to list
+
+def parse_embedding(embedding_str):
+    try:
+        return ast.literal_eval(embedding_str)
+    except (ValueError, SyntaxError):
+        return None  # Handle errors gracefully
+
+
+tweets_df['sentence_embedding'] = tweets_df['sentence_embedding'].astype(str).apply(parse_embedding)
+
+# Simulated user database
+users = {"testuser": "password123"}  # Dictionary to store usernames and passwords
+
+# Session state for login
+if "logged_in" not in st.session_state:
+    st.session_state["logged_in"] = False
+    st.session_state["username"] = ""
+    st.session_state["liked_tweets"] = []
+    st.session_state["posted_tweets"] = []
+
+# Login Page
+if not st.session_state["logged_in"]:
+    st.title("Tweet Recommendation System")
+    username = st.text_input("Username")
+    password = st.text_input("Password", type="password")
+    if st.button("Login"):
+        if username in users and users[username] == password:
+            st.session_state["logged_in"] = True
+            st.session_state["username"] = username
+            st.success("Login successful!")
+            st.experimental_rerun()
+        else:
+            st.error("Invalid credentials")
+else:
+    st.title(f"Welcome, {st.session_state['username']}!")
+    
+    # Randomly select 10 tweets for the Explore Page
+    random_tweets = original_tweets_df.sample(10)
+    
+    st.subheader("Explore Tweets")
+    for _, row in random_tweets.iterrows():
+        tweet_id = row['tweet_id']
+        text = row['original_text']
+        
+        with st.container():
+            st.write(f"*Tweet:* {text}")
+            if st.button(f"Like ❤ {tweet_id}", key=f"like_{tweet_id}"):
+                if tweet_id not in st.session_state["liked_tweets"]:
+                    st.session_state["liked_tweets"].append(tweet_id)
+                st.success("Tweet Liked!")
+    
+    # Posting new tweets
+    st.subheader("Post a Tweet")
+    new_tweet = st.text_area("Write your tweet here:")
+    if st.button("Post Tweet"):
+        if new_tweet:
+            new_tweet_embedding = get_embedding(new_tweet)
+            st.session_state["posted_tweets"].append(new_tweet_embedding)
+            st.success("Tweet posted successfully!")
+    
+    # Recommendation Logic
+    if st.session_state["liked_tweets"] or st.session_state["posted_tweets"]:
+        st.subheader("Recommended Tweets for You")
+        
+        # Get embeddings of liked tweets
+        liked_embeddings = [tweets_df[tweets_df['tweet_id'] == tid]['sentence_embedding'].values[0] 
+                            for tid in st.session_state["liked_tweets"]]
+        
+        # Get embeddings of posted tweets
+        posted_embeddings = st.session_state["posted_tweets"]
+        
+        # Combine all embeddings
+        user_profile_embedding = np.mean(liked_embeddings + posted_embeddings, axis=0)
+        
+        # Compute cosine similarity
+        all_embeddings = np.vstack(tweets_df['sentence_embedding'].values)
+        similarities = cosine_similarity([user_profile_embedding], all_embeddings)[0]
+        
+        # Get top 10 similar tweets
+        top_indices = np.argsort(similarities)[-10:][::-1]
+        recommended_tweets = tweets_df.iloc[top_indices]
+        
+        # Display recommended tweets
+        for _, row in recommended_tweets.iterrows():
+            tweet_id = row['tweet_id']
+            text = original_tweets_df[original_tweets_df['tweet_id'] == tweet_id]['original_text'].values[0]
+            with st.container():
+                st.write(f"*Recommended Tweet:* {text}")