File size: 5,336 Bytes
eeb0f9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
"""
ViMedical Disease Dataset - Download & Process
Downloads and processes Vietnamese medical disease dataset into ChromaDB
Dataset: PB3002/ViMedical_Disease (603 diseases, 12K+ examples)
"""

import requests
import pandas as pd
import chromadb
from sentence_transformers import SentenceTransformer
import os
import re

def download_vimedical():
    """Download ViMedical dataset from HuggingFace"""
    
    print("📥 Downloading ViMedical Disease dataset...")
    
    # HuggingFace dataset URL
    url = "https://huggingface.co/datasets/PB3002/ViMedical_Disease/resolve/main/ViMedical_Disease.csv"
    
    # Create datasets directory
    os.makedirs("data_mining/datasets", exist_ok=True)
    output_path = "data_mining/datasets/vimedical_disease.csv"
    
    try:
        # Download
        response = requests.get(url, timeout=60)
        response.raise_for_status()
        
        # Save
        with open(output_path, 'wb') as f:
            f.write(response.content)
        
        # Check file size
        file_size = os.path.getsize(output_path) / (1024 * 1024)  # MB
        
        print(f"✅ Downloaded: {output_path}")
        print(f"📊 File size: {file_size:.2f} MB")
        
        return True
        
    except Exception as e:
        print(f"❌ Download failed: {e}")
        return False

def extract_symptoms(question):
    """Extract symptom description from question"""
    # Remove common prefixes
    prefixes = [
        'Tôi đang có triệu chứng như ',
        'Tôi thường xuyên ',
        'Tôi cảm thấy ',
        'Tôi bị ',
        'Tôi hay ',
        'Tôi có '
    ]
    
    symptom = question
    for prefix in prefixes:
        if symptom.startswith(prefix):
            symptom = symptom[len(prefix):]
            break
    
    # Remove question suffix
    suffixes = [
        '. Tôi bị bệnh gì?',
        '. Tôi có thể bị gì?',
        '. Đó là bệnh gì?'
    ]
    for suffix in suffixes:
        if symptom.endswith(suffix):
            symptom = symptom[:-len(suffix)]
            break
    
    return symptom.strip()

def process_vimedical():
    """Process ViMedical dataset and build ChromaDB"""
    
    print("\n🔨 Processing ViMedical dataset...")
    
    # Load dataset
    csv_path = "data_mining/datasets/vimedical_disease.csv"
    if not os.path.exists(csv_path):
        print(f"❌ Dataset not found: {csv_path}")
        return False
    
    df = pd.read_csv(csv_path)
    print(f"📊 Loaded {len(df)} records")
    print(f"📊 Unique diseases: {df['Disease'].nunique()}")
    
    # Initialize embedder
    print("🤖 Loading embedding model...")
    embedder = SentenceTransformer('keepitreal/vietnamese-sbert')
    
    # Initialize ChromaDB
    print("💾 Initializing ChromaDB...")
    os.makedirs("data_mining/output", exist_ok=True)
    client = chromadb.PersistentClient(path="data_mining/output/medical_chroma")
    
    # Create collection
    collection = client.get_or_create_collection(
        name="medical_diseases",
        metadata={"hnsw:space": "cosine"}
    )
    
    # Group by disease
    print("📝 Processing diseases...")
    disease_groups = df.groupby('Disease')
    
    processed = 0
    for disease_name, group in disease_groups:
        # Extract symptoms from all questions
        symptoms = []
        for question in group['Question']:
            symptom = extract_symptoms(question)
            if symptom:
                symptoms.append(symptom)
        
        # Create document text
        doc_text = f"Bệnh: {disease_name}\n\nTriệu chứng:\n"
        doc_text += "\n".join(f"- {s}" for s in symptoms[:10])  # Limit to 10 examples
        
        # Generate embedding
        embedding = embedder.encode(doc_text)
        
        # Add to ChromaDB
        collection.add(
            ids=[f"disease_{processed:04d}"],
            embeddings=[embedding.tolist()],
            documents=[doc_text],
            metadatas=[{
                'disease_name': disease_name,
                'num_examples': len(symptoms),
                'source': 'ViMedical_Disease'
            }]
        )
        
        processed += 1
        if processed % 50 == 0:
            print(f"  Processed {processed}/{len(disease_groups)} diseases...")
    
    print(f"✅ Processed {processed} diseases")
    print(f"💾 Database saved to: data_mining/output/medical_chroma/")
    
    # Get database size
    db_path = "data_mining/output/medical_chroma"
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(db_path):
        for filename in filenames:
            filepath = os.path.join(dirpath, filename)
            total_size += os.path.getsize(filepath)
    
    print(f"📊 Database size: {total_size / (1024 * 1024):.2f} MB")
    
    return True

def main():
    """Main function - download and process"""
    print("=" * 60)
    print("ViMedical Disease Dataset - Download & Process")
    print("=" * 60)
    
    # Step 1: Download
    if not download_vimedical():
        return False
    
    # Step 2: Process
    if not process_vimedical():
        return False
    
    print("\n" + "=" * 60)
    print("✅ ViMedical dataset ready!")
    print("=" * 60)
    return True

if __name__ == "__main__":
    success = main()
    exit(0 if success else 1)