add progress bar

main.py

@@ -9,6 +9,13 @@ matplotlib.use('Agg')  # Prevents GUI issues for Matplotlib
 import matplotlib.pyplot as plt
 import base64
 from io import BytesIO
+from flask import send_file
+
+
+# Ensure the file exists in the current directory
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+FILE_PATH = os.path.join(BASE_DIR, "Student_Feedback_Dataset__20_Rows_.csv")
+
 
 # Fix Permission Issues: Set Writable Directories for Hugging Face & Matplotlib
 os.environ["HF_HOME"] = "/tmp"
@@ -29,79 +36,82 @@ model = BertForSequenceClassification.from_pretrained(MODEL_NAME)
 
 model.eval()
 
-
 # Function to Predict Sentiment
 def predict_sentiment(text):
-    # Split the text into chunks of 512 tokens
-    tokenized_text = tokenizer.encode(text, add_special_tokens=True)
-    chunks = [tokenized_text[i:i + 512] for i in range(0, len(tokenized_text), 512)]
-
-    # Predict sentiment for each chunk
-    sentiments = []
-    for chunk in chunks:
-        # inputs = tokenizer.decode(chunk, skip_special_tokens=True)
-        inputs = tokenizer.decode(chunk, skip_special_tokens=True, clean_up_tokenization_spaces=True)  # Explicitly set clean_up_tokenization_spaces
-        inputs = tokenizer(inputs, return_tensors="pt", truncation=True, padding=True, max_length=512)
-        with torch.no_grad():
-            outputs = model(**inputs)
-        sentiments.append(outputs.logits.argmax(dim=1).item())
-
-    # Aggregate the predictions (majority voting)
-    sentiment_counts = Counter(sentiments)
-    majority_sentiment = sentiment_counts.most_common(1)[0][0]
-    return 'Positive' if majority_sentiment == 1 else 'Negative'
+    if not text.strip():
+        return "Neutral"  # Avoid processing empty text
+
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    sentiment = outputs.logits.argmax(dim=1).item()
+    return "Positive" if sentiment == 1 else "Negative"
 
 @app.route('/')
 def upload_file():
     return render_template('upload.html')
 
+@app.route('/download-sample')
+def download_sample():
+    if os.path.exists(FILE_PATH):
+        return send_file(FILE_PATH, as_attachment=True)
+    else:
+        return "Error: File not found!", 404
 
 @app.route('/analyze_text', methods=['POST'])
 def analyze_text():
-    if request.method == 'POST':
-        text = request.form['text']
-        sentiment = predict_sentiment(text)
-        return render_template('upload.html', sentiment=sentiment)
+    text = request.form.get('text', '').strip()
+    
+    if not text:
+        return render_template('upload.html', sentiment="Error: No text provided!")
 
+    sentiment = predict_sentiment(text)
+    return render_template('upload.html', sentiment=sentiment)
 
-@app.route('/uploader', methods=['GET', 'POST'])
+@app.route('/uploader', methods=['POST'])
 def upload_file_post():
-    if request.method == 'POST':
-        f = request.files['file']
+    if 'file' not in request.files:
+        return "Error: No file uploaded!", 400
+
+    f = request.files['file']
+    if f.filename == '':
+        return "Error: No file selected!", 400
+
+    try:
         data = pd.read_csv(f)
 
+        # Ensure 'review' column exists
+        if 'review' not in data.columns:
+            return "Error: CSV file must contain a 'review' column!", 400
+
         # Predict sentiment for each review
-        data['sentiment'] = data['review'].apply(predict_sentiment)
+        data['sentiment'] = data['review'].astype(str).apply(predict_sentiment)
 
-        # Sentiment Analysis Summary
+        # Generate summary
         sentiment_counts = data['sentiment'].value_counts().to_dict()
         summary = f"Total Reviews: {len(data)}<br>" \
                   f"Positive: {sentiment_counts.get('Positive', 0)}<br>" \
                   f"Negative: {sentiment_counts.get('Negative', 0)}<br>"
 
-        # Generate plot
+        # Generate sentiment plot
         fig, ax = plt.subplots()
         ax.bar(sentiment_counts.keys(), sentiment_counts.values(), color=['red', 'blue'])
         ax.set_ylabel('Counts')
         ax.set_title('Sentiment Analysis Summary')
-        
-        # Save the plot to a BytesIO object
+
+        # Save plot as an image
         img = BytesIO()
         plt.savefig(img, format='png', bbox_inches='tight')
         img.seek(0)
-
-        # Encode the image in base64 and decode it to UTF-8
         plot_url = base64.b64encode(img.getvalue()).decode('utf8')
-
-        # Close the plot to free memory
         plt.close(fig)
 
         return render_template('result.html', tables=[data.to_html(classes='data')], titles=data.columns.values, summary=summary, plot_url=plot_url)
 
-
+    except Exception as e:
+        return f"Error processing file: {str(e)}", 500
 
 if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=7860, debug=True)
-
-
-
+    app.run(host='0.0.0.0', port=7860, debug=True)