adding db.py for inserting the data into mongoDB

app.py

@@ -1,45 +1,27 @@
 import streamlit as st
 import pandas as pd
-import requests
-import io
 from pymongo import MongoClient
+from db import insert_data_if_empty, get_mongo_client  # Import functions from db.py
 
-#### **1. MongoDB Connection**
-def get_mongo_client():
-    client = MongoClient("mongodb+srv://groupA:[email protected]/?retryWrites=true&w=majority&appName=SentimentCluster")
-    db = client["sentiment_db"]
-    return db["tweets"]
+#### **1. Ensure Data is Inserted Before Display**
+insert_data_if_empty()
 
+#### **2. MongoDB Connection**
 collection = get_mongo_client()
 
-#### **2. Load Dataset from Hugging Face**
-csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"
-
-try:
-    response = requests.get(csv_url)
-    response.raise_for_status()  # Ensure the request was successful
-    df = pd.read_csv(io.StringIO(response.text), encoding="ISO-8859-1")
-    st.success("Dataset Loaded Successfully!")
-except Exception as e:
-    st.error(f"Error loading dataset: {e}")
-    st.stop()
-
-#### **3. Upload Data to MongoDB**
-collection.insert_many(df.to_dict("records"))
-st.success("Data Uploaded to MongoDB!")
-
-#### **4. Build Streamlit Dashboard**
-st.title("📊 MongoDB Data Insertion")
+#### **3. Streamlit App to Display Data**
+st.title("📊 MongoDB Data Viewer")
 
 # Show first 5 rows from MongoDB
 st.subheader("First 5 Rows from Database")
 data = list(collection.find({}, {"_id": 0}).limit(5))
-st.write(pd.DataFrame(data))
 
-# Buttons to display more data
-if st.button("Show Complete Data"):
-    st.write(df)
-
-if st.button("Show MongoDB Data"):
-    data = list(collection.find({}, {"_id": 0}))
+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))

db.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import requests
+import io
+from pymongo import MongoClient
+
+#### **1. MongoDB Connection**
+def get_mongo_client():
+    client = MongoClient("mongodb+srv://groupA:[email protected]/?retryWrites=true&w=majority&appName=SentimentCluster")
+    db = client["sentiment_db"]
+    return db["tweets"]
+
+#### **2. Insert Data If Collection is Empty**
+def insert_data_if_empty():
+    collection = get_mongo_client()
+
+    if collection.count_documents({}) == 0:
+        print("🟢 No data found. Inserting dataset...")
+
+        csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"
+
+        try:
+            response = requests.get(csv_url)
+            response.raise_for_status()  # Ensure request was successful
+            df = pd.read_csv(io.StringIO(response.text), encoding="ISO-8859-1")
+
+            # Insert into MongoDB
+            collection.insert_many(df.to_dict("records"))
+            print("✅ Data Inserted into MongoDB!")
+        except Exception as e:
+            print(f"❌ Error loading dataset: {e}")
+
+# Uncomment the below line if running `db.py` independently
+# insert_data_if_empty()