Upload 7 files

api.py

@@ -0,0 +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)

fine_tuned_model/config.json

@@ -0,0 +1,34 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

fine_tuned_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba23b5ee5a6081da5cca7705f3ebe7acad7664f4ea8b9175da8d2f1c2a7d74cf
+size 267835644

fine_tuned_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fine_tuned_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

requirements.txt

@@ -0,0 +1,7 @@
+flask
+flask-cors
+torch
+transformers
+pandas
+openpyxl
+gunicorn