Update main.py

main.py

@@ -1,69 +1,62 @@
-import os
 from flask import Flask, request, render_template
 import pandas as pd
 import torch
 from transformers import BertTokenizer, BertForSequenceClassification
 from collections import Counter
 import matplotlib
-matplotlib.use('Agg')  # Prevents GUI issues for Matplotlib
+matplotlib.use('Agg')  # Set the backend before importing pyplot
 import matplotlib.pyplot as plt
+
 import base64
 from io import BytesIO
 
-# Set writable cache directories within /tmp
-os.environ["HF_HOME"] = "/tmp/huggingface_cache"  # Replaces TRANSFORMERS_CACHE
-os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
-
-# Create directories if they don't exist
-os.makedirs(os.environ["HF_HOME"], exist_ok=True)
-os.makedirs(os.environ["MPLCONFIGDIR"], exist_ok=True)
 
 app = Flask(__name__)
 
-# Load Model from Local Directory
-MODEL_PATH = "bert_imdb_model.bin"
-TOKENIZER_PATH = "bert-base-uncased"
 
-if os.path.exists(MODEL_PATH):
-    print("Loading model from local file...")
-    model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
-    model.load_state_dict(torch.load(MODEL_PATH, map_location=torch.device('cpu')))
-else:
-    print(f"Error: Model file {MODEL_PATH} not found.")
-    exit(1)
+model_name = "philipobiorah/bert-imdb-model"
 
-model.eval()
-tokenizer = BertTokenizer.from_pretrained(TOKENIZER_PATH)
+# Load tokenizer and model
+tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+model = BertForSequenceClassification.from_pretrained(model_name)
 
-# ... rest of your code (keep the rest unchanged) ...
 
+model.eval()
+
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
 
 def predict_sentiment(text):
-    tokens = tokenizer.encode(text, add_special_tokens=True)
-    chunks = [tokens[i:i + 512] for i in range(0, len(tokens), 512)]
+    # 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, clean_up_tokenization_spaces=True)
+        # 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())
 
-    majority_sentiment = Counter(sentiments).most_common(1)[0][0]
+    # 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'
 
 @app.route('/')
 def upload_file():
     return render_template('upload.html')
 
+
 @app.route('/analyze_text', methods=['POST'])
 def analyze_text():
-    text = request.form['text']
-    sentiment = predict_sentiment(text)
-    return render_template('upload.html', sentiment=sentiment)
+    if request.method == 'POST':
+        text = request.form['text']
+        sentiment = predict_sentiment(text)
+        return render_template('upload.html', sentiment=sentiment)
+
 
 @app.route('/uploader', methods=['GET', 'POST'])
 def upload_file_post():
@@ -71,25 +64,38 @@ def upload_file_post():
         f = request.files['file']
         data = pd.read_csv(f)
 
+        # Predict sentiment for each review
         data['sentiment'] = data['review'].apply(predict_sentiment)
 
+        # Sentiment Analysis 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
         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
         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)
 
+
+
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=7860, debug=True)
+
+
+