change in app.py

app.py

@@ -3,38 +3,48 @@ import pandas as pd
 from db import insert_data_if_empty, get_mongo_client
 from chatbot import chatbot_response  # Import chatbot functionality
 
-#### **1. Ensure Data is Inserted Before Display**
+# 1. Ensure Data is Inserted Before Display
 insert_data_if_empty()
 
-#### **2. MongoDB Connection**
+# 2. MongoDB Connection
 collection = get_mongo_client()
 
-#### **3. Streamlit App UI**
-# st.title("📊 MongoDB Data Viewer with AI Sentiment Chatbot")
-
-# # Show first 5 rows from MongoDB
-# st.subheader("First 5 Rows from Database")
-# data = list(collection.find({}, {"_id": 0}).limit(5))
-
-# if data:
-#     st.write(pd.DataFrame(data))
-# else:
-#     st.warning("⚠️ No data found. Try refreshing the app.")
-
-# # Button to show full MongoDB data
-# if st.button("Show Complete Data"):
-#     all_data = list(collection.find({}, {"_id": 0}))
-#     st.write(pd.DataFrame(all_data))
+st.title("📊 MongoDB Data Viewer with AI Sentiment Chatbot")
+
+# --- Historical Data Analytics Section ---
+st.subheader("Historical Data Analytics")
+data = list(collection.find({}, {"_id": 0}))
+
+if data:
+    df = pd.DataFrame(data)
+    # The sentiment140.csv dataset typically contains a column named 'target'
+    # which holds the sentiment labels (0=Negative, 2=Neutral, 4=Positive)
+    if 'target' in df.columns:
+        # Map numeric sentiment labels to readable text
+        sentiment_map = {0: "Negative", 2: "Neutral", 4: "Positive"}
+        df['sentiment_label'] = df['target'].map(sentiment_map)
+        
+        # Compute sentiment distribution
+        sentiment_counts = df['sentiment_label'].value_counts()
+        
+        st.write("### Sentiment Distribution in Historical Data")
+        st.bar_chart(sentiment_counts)
+    else:
+        st.warning("The dataset does not contain a 'target' column for sentiment.")
+else:
+    st.warning("No historical data available.")
 
-#### **4. AI Chatbot with Sentiment & Topic Analysis**
-st.subheader("🤖 AI Chatbot with Sentiment & Topic Analysis")
+# Optionally, a button to display the complete historical data
+if st.button("Show Complete Historical Data"):
+    st.write(pd.DataFrame(data))
 
-# User input for chatbot
-user_prompt = st.text_area("Ask AI something or paste text for analysis:")
+# --- Chatbot Section with Sentiment & Topic Analysis ---
+st.subheader("💬 Chatbot with Sentiment & Topic Analysis")
+user_prompt = st.text_area("Ask me something:")
 
-if st.button("Analyze Sentiment & Get AI Response"):
+if st.button("Get AI Response"):
     ai_response, sentiment_label, sentiment_confidence, topic_label, topic_confidence = chatbot_response(user_prompt)
-
+    
     if ai_response:
         st.write("### AI Response:")
         st.write(ai_response)
@@ -42,7 +52,12 @@ if st.button("Analyze Sentiment & Get AI Response"):
         st.write("### Sentiment Analysis:")
         st.write(f"**Sentiment:** {sentiment_label} ({sentiment_confidence:.2f} confidence)")
 
-        st.write("### Topic Extraction:")
-        st.write(f"**Detected Topic:** {topic_label} ({topic_confidence:.2f} confidence)")
+        st.write("### Category Extraction:")
+        st.write(f"**Detected Category:** {topic_label} ({topic_confidence:.2f} confidence)")
+
+        # Additional: Compare with historical data
+        if data and 'target' in df.columns:
+            historical_count = df[df['sentiment_label'] == sentiment_label].shape[0]
+            st.info(f"In our historical dataset, there are {historical_count} tweets with a {sentiment_label} sentiment.")
     else:
         st.warning("⚠️ Please enter a question or text for analysis.")