Fixed UnicodeDecodeError

app.py

@@ -1,11 +1,11 @@
-from pymongo import MongoClient
+import streamlit as st
 import pandas as pd
+from pymongo import MongoClient
 from transformers import pipeline
-import streamlit as st
 
 #### **1. MongoDB Connection**
 def get_mongo_client():
-    client = MongoClient("mongodb+srv://groupA:pythongroupA@sentimentcluster.4usfj.mongodb.net/?retryWrites=true&w=majority&appName=SentimentCluster")
+    client = MongoClient("mongodb+srv://GMP-21-03:groupa2025@cluster1.u1zed.mongodb.net/?retryWrites=true&w=majority&appName=Cluster1")
     db = client["sentiment_db"]
     return db["tweets"]
 
@@ -13,9 +13,18 @@ collection = get_mongo_client()
 
 #### **2. Load Dataset from Hugging Face**
 csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"
-df = pd.read_csv(csv_url)
+
+try:
+    df = pd.read_csv(csv_url, encoding="ISO-8859-1", errors="replace")  # Fix encoding issue
+except Exception as e:
+    st.error(f"Error loading dataset: {e}")
+    st.stop()
+
+st.success("Dataset Loaded Successfully!")
 
 #### **3. Sentiment Analysis using BERT-ROBERTA**
+st.info("Running Sentiment Analysis...")
+
 sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
 
 # Function to analyze sentiment
@@ -25,18 +34,19 @@ def analyze_sentiment(text):
 df["sentiment"] = df["text"].apply(analyze_sentiment)
 
 #### **4. Upload Data to MongoDB**
-# Convert DataFrame to dictionary and upload to MongoDB
 collection.delete_many({})  # Optional: Clear existing data before inserting
 collection.insert_many(df.to_dict("records"))
+st.success("Data Uploaded to MongoDB!")
 
 #### **5. Build Streamlit Dashboard**
-st.title("Sentiment Analysis Dashboard")
+st.title("📊 Sentiment Analysis Dashboard")
 
 # 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)