fix: changes

app.py

@@ -1,76 +1,67 @@
 import streamlit as st
 import pandas as pd
-from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
-import time
+from transformers import pipeline
 import matplotlib.pyplot as plt
-import os
+import time
+
+# Load the sentiment analysis model
+sentiment_model = pipeline("sentiment-analysis", model="tabularisai/multilingual-sentiment-analysis")
+
+# Function to perform sentiment analysis
+def perform_sentiment_analysis(texts):
+    sentiments = sentiment_model(texts)
+    return sentiments
+
+# Function to plot the sentiment analysis results
+def plot_sentiment_analysis(sentiments):
+    labels = [item['label'] for item in sentiments]
+    label_counts = pd.Series(labels).value_counts()
+
+    fig, ax = plt.subplots()
+    ax.pie(label_counts, labels=label_counts.index, autopct='%1.1f%%', startangle=90)
+    ax.axis('equal')  # Equal aspect ratio ensures that pie is drawn as a circle.
 
+    st.pyplot(fig)
+
+# Streamlit UI
 st.title("Sentiment Analysis App")
-st.write("Upload a CSV or Excel file containing text data for sentiment analysis.")
 
-# File uploader
+# File upload
 uploaded_file = st.file_uploader("Upload a CSV or Excel file", type=["csv", "xlsx"])
 
-# Load sentiment analysis model
-try:
-    sentiment_pipeline = pipeline(
-        "sentiment-analysis", 
-        model="distilbert-base-uncased-finetuned-sst-2-english"
-    )
-    st.success("Sentiment analysis model loaded successfully!")
-except Exception as e:
-    st.error(f"Error loading model: {e}")
-    st.stop()
-
-if uploaded_file:
-    # Check file type
-    if uploaded_file.name.endswith('.csv'):
+if uploaded_file is not None:
+    # Read the file
+    if uploaded_file.name.endswith(".csv"):
         df = pd.read_csv(uploaded_file)
-    elif uploaded_file.name.endswith('.xlsx'):
-        df = pd.read_excel(uploaded_file)
     else:
-        st.error("Unsupported file format.")
-        st.stop()
-
-    st.write("Data Preview:", df.head())
+        df = pd.read_excel(uploaded_file, engine='openpyxl')
 
-    # Check for 'text' column
+    # Check if 'text' column exists
     if 'text' not in df.columns:
-        text_column = st.text_input("Enter the name of the column containing text values:")
-        if text_column not in df.columns:
-            st.error(f"Column '{text_column}' not found in the file.")
-            st.stop()
-        else:
-            df.rename(columns={text_column: 'text'}, inplace=True)
+        st.warning("Column 'text' not found. Please enter the column name containing the text values.")
+        text_column = st.text_input("Enter the column name containing the text values")
     else:
         text_column = 'text'
 
-    if st.button("Run Sentiment Analysis"):
-        # Progress bar
-        progress_bar = st.progress(0)
+    if text_column in df.columns:
+        # Display the first few rows of the dataframe
+        st.write("First few rows of the uploaded file:")
+        st.write(df.head())
 
-        sentiments = []
-        for i, text in enumerate(df[text_column]):
-            try:
-                result = sentiment_pipeline(text)[0]
-                sentiments.append(result['label'])
-            except Exception as e:
-                sentiments.append("Error")
-                st.error(f"Error processing text at row {i + 1}: {e}")
+        # Perform sentiment analysis
+        if st.button("Run Sentiment Analysis"):
+            texts = df[text_column].tolist()
+            progress_bar = st.progress(0)
 
-            progress_bar.progress((i + 1) / len(df))
-            time.sleep(0.1)  # Simulating processing time
+            # Simulate progress
+            for i in range(100):
+                time.sleep(0.05)
+                progress_bar.progress(i + 1)
 
-        df['Sentiment'] = sentiments
-        st.write("Sentiment Analysis Output:", df[['text', 'Sentiment']])
-
-        # Pie chart
-        sentiment_counts = df['Sentiment'].value_counts()
-        fig, ax = plt.subplots()
-        ax.pie(sentiment_counts, labels=sentiment_counts.index, autopct='%1.1f%%', startangle=90)
-        ax.axis('equal')
-        st.pyplot(fig)
-
-        # Clear progress bar
-        progress_bar.empty()
+            sentiments = perform_sentiment_analysis(texts)
+            st.success("Sentiment analysis completed!")
 
+            # Plot the sentiment analysis results
+            plot_sentiment_analysis(sentiments)
+    else:
+        st.error("The specified column does not exist in the uploaded file.")