Update api.py

api.py

@@ -1,95 +1,95 @@
-from flask import Flask, request, send_file, jsonify
-from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
-import pandas as pd
-import torch
-import tempfile
-import os
-import re
-from collections import Counter
-from flask_cors import CORS
-
-app = Flask(__name__)
-CORS(app)
-
-# Load model from Hugging Face Hub
-model_name = "AbdoIR/x-sentiment-analysis"
-model = DistilBertForSequenceClassification.from_pretrained(model_name)
-tokenizer = DistilBertTokenizer.from_pretrained(model_name)
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
-model.eval()
-
-# Predict sentiment
-def predict_sentiment(texts):
-  encodings = tokenizer(texts, truncation=True, padding=True, max_length=128, return_tensors="pt")
-  encodings = {key: val.to(device) for key, val in encodings.items()}
-  with torch.no_grad():
-      outputs = model(**encodings)
-      predictions = torch.argmax(outputs.logits, dim=1)
-  sentiment_map = {0: "Negative", 1: "Neutral", 2: "Positive"}
-  return [sentiment_map[p.item()] for p in predictions]
-
-# Top frequent words
-def get_top_words(texts, n=30):
-  all_words = []
-  for text in texts:
-      tokens = re.findall(r'\b\w{3,}\b', str(text).lower())
-      all_words.extend(tokens)
-  counter = Counter(all_words)
-  most_common = counter.most_common(n)
-  return pd.DataFrame(most_common, columns=['word', 'count'])
-
-# POST /predict
-@app.route('/predict', methods=['POST'])
-def predict():
-  if 'file' not in request.files:
-      return jsonify({'error': 'No file uploaded'}), 400
-
-  file = request.files['file']
-  try:
-      df = pd.read_csv(file)
-  except Exception:
-      try:
-          file.seek(0)
-          df = pd.read_excel(file)
-      except Exception:
-          return jsonify({'error': 'Unable to read the file'}), 400
-
-  if 'content' in df.columns:
-      text_col = 'content'
-  elif 'tweet' in df.columns:
-      text_col = 'tweet'
-  else:
-      return jsonify({'error': 'No "content" or "tweet" column found'}), 400
-
-  texts = df[text_col].astype(str).tolist()
-  df['sentiment'] = predict_sentiment(texts)
-
-  top_words_df = get_top_words(texts)
-
-  temp_dir = tempfile.mkdtemp()
-
-  sentiment_path = os.path.join(temp_dir, 'final_data.csv')
-  df.to_csv(sentiment_path, index=False)
-
-  words_path = os.path.join(temp_dir, 'word_frequent.csv')
-  top_words_df.to_csv(words_path, index=False)
-
-  return jsonify({
-      'sentiment_file': f'/download?file={sentiment_path}',
-      'top_words_file': f'/download?file={words_path}',
-      'sentiment_data': df.to_dict(orient='records'),
-      'top_words_data': top_words_df.to_dict(orient='records')
-  })
-
-# GET /download
-@app.route('/download')
-def download():
-  file_path = request.args.get('file')
-  if not file_path or not os.path.exists(file_path):
-      return jsonify({'error': 'File not found'}), 404
-  return send_file(file_path, as_attachment=True)
-
-if __name__ == '__main__':
-  app.run(host="0.0.0.0", port=5000, debug=True)
+from flask import Flask, request, send_file, jsonify
+from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
+import pandas as pd
+import torch
+import tempfile
+import os
+import re
+from collections import Counter
+from flask_cors import CORS
+
+app = Flask(__name__)
+CORS(app)
+
+# Load model from Hugging Face Hub
+model_name = "AbdoIR/x-sentiment-analysis/fine_tuned_model"
+model = DistilBertForSequenceClassification.from_pretrained(model_name)
+tokenizer = DistilBertTokenizer.from_pretrained(model_name)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+model.eval()
+
+# Predict sentiment
+def predict_sentiment(texts):
+  encodings = tokenizer(texts, truncation=True, padding=True, max_length=128, return_tensors="pt")
+  encodings = {key: val.to(device) for key, val in encodings.items()}
+  with torch.no_grad():
+      outputs = model(**encodings)
+      predictions = torch.argmax(outputs.logits, dim=1)
+  sentiment_map = {0: "Negative", 1: "Neutral", 2: "Positive"}
+  return [sentiment_map[p.item()] for p in predictions]
+
+# Top frequent words
+def get_top_words(texts, n=30):
+  all_words = []
+  for text in texts:
+      tokens = re.findall(r'\b\w{3,}\b', str(text).lower())
+      all_words.extend(tokens)
+  counter = Counter(all_words)
+  most_common = counter.most_common(n)
+  return pd.DataFrame(most_common, columns=['word', 'count'])
+
+# POST /predict
+@app.route('/predict', methods=['POST'])
+def predict():
+  if 'file' not in request.files:
+      return jsonify({'error': 'No file uploaded'}), 400
+
+  file = request.files['file']
+  try:
+      df = pd.read_csv(file)
+  except Exception:
+      try:
+          file.seek(0)
+          df = pd.read_excel(file)
+      except Exception:
+          return jsonify({'error': 'Unable to read the file'}), 400
+
+  if 'content' in df.columns:
+      text_col = 'content'
+  elif 'tweet' in df.columns:
+      text_col = 'tweet'
+  else:
+      return jsonify({'error': 'No "content" or "tweet" column found'}), 400
+
+  texts = df[text_col].astype(str).tolist()
+  df['sentiment'] = predict_sentiment(texts)
+
+  top_words_df = get_top_words(texts)
+
+  temp_dir = tempfile.mkdtemp()
+
+  sentiment_path = os.path.join(temp_dir, 'final_data.csv')
+  df.to_csv(sentiment_path, index=False)
+
+  words_path = os.path.join(temp_dir, 'word_frequent.csv')
+  top_words_df.to_csv(words_path, index=False)
+
+  return jsonify({
+      'sentiment_file': f'/download?file={sentiment_path}',
+      'top_words_file': f'/download?file={words_path}',
+      'sentiment_data': df.to_dict(orient='records'),
+      'top_words_data': top_words_df.to_dict(orient='records')
+  })
+
+# GET /download
+@app.route('/download')
+def download():
+  file_path = request.args.get('file')
+  if not file_path or not os.path.exists(file_path):
+      return jsonify({'error': 'File not found'}), 404
+  return send_file(file_path, as_attachment=True)
+
+if __name__ == '__main__':
+  app.run(host="0.0.0.0", port=5000, debug=True)