Changes to the csv file and app.py

app.py

@@ -3,7 +3,6 @@ import pandas as pd
 import requests
 import io
 from pymongo import MongoClient
-from transformers import pipeline
 
 #### **1. MongoDB Connection**
 def get_mongo_client():
@@ -25,24 +24,13 @@ except Exception as e:
     st.error(f"Error loading dataset: {e}")
     st.stop()
 
-#### **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
-def analyze_sentiment(text):
-    return sentiment_pipeline(text)[0]['label']
-
-df["sentiment"] = df["text"].apply(analyze_sentiment)
-
-#### **4. Upload Data to MongoDB**
+#### **3. Upload Data 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")
+#### **4. Build Streamlit Dashboard**
+st.title("📊 MongoDB Data Insertion")
 
 # Show first 5 rows from MongoDB
 st.subheader("First 5 Rows from Database")

backup.py

@@ -1,21 +1,33 @@
+import streamlit as st
+import pandas as pd
+import requests
+import io
 from pymongo import MongoClient
+from transformers import pipeline
 
+#### **1. MongoDB Connection**
 def get_mongo_client():
-    client = MongoClient("mongodb+srv://GMP-21-03:groupa2025@cluster1.u1zed.mongodb.net/?retryWrites=true&w=majority&appName=Cluster1")
+    client = MongoClient("mongodb+srv://groupA:pythongroupA@sentimentcluster.4usfj.mongodb.net/?retryWrites=true&w=majority&appName=SentimentCluster")
     db = client["sentiment_db"]
     return db["tweets"]
 
-#### *3. Load and Process Dataset*
-import pandas as pd
+collection = get_mongo_client()
 
-# Load dataset
-df = pd.read_csv("https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv")
+#### **2. Load Dataset from Hugging Face**
+csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"
 
-#### *4. Sentiment Analysis using BERT-ROBERTA*
+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()
 
-from transformers import pipeline
+#### **3. Sentiment Analysis using BERT-ROBERTA**
+st.info("Running Sentiment Analysis...")
 
-# Load Hugging Face model
 sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
 
 # Function to analyze sentiment
@@ -24,16 +36,21 @@ def analyze_sentiment(text):
 
 df["sentiment"] = df["text"].apply(analyze_sentiment)
 
-# Save results to MongoDB
-collection = get_mongo_client()
+#### **4. Upload Data 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*
-import streamlit as st
+#### **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))
 
-if st.button("Show Data"):
+# Buttons to display more data
+if st.button("Show Complete Data"):
     st.write(df)
 
 if st.button("Show MongoDB Data"):

sentiment140.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08cba6317a49528fcd074f9043aafcd5ad6c6be45ede159c4e36cec33af24afe
-size 238803811
+oid sha256:865c9a16106df762ab3cff2cdb713bc0d9bc103436365ba7bca3e136d653912a
+size 145627981