Sumayyea commited on
Commit
a69a935
·
verified ·
1 Parent(s): c8a6f22

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +73 -0
app.py ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ import re
3
+ from datetime import datetime
4
+ from typing import Dict, Any, List
5
+
6
+ # -------------------------
7
+ # Document Classifier Class
8
+ # -------------------------
9
+
10
+ class DocumentClassifier:
11
+ def __init__(self):
12
+ self.categories = {
13
+ 'ADMINISTRATIVE': ['memo', 'circular', 'notification', 'order', 'policy'],
14
+ 'FINANCIAL': ['budget', 'expenditure', 'audit', 'payment', 'revenue'],
15
+ 'LEGAL': ['contract', 'agreement', 'legal', 'court', 'judgment'],
16
+ 'HR': ['recruitment', 'promotion', 'transfer', 'leave', 'employee'],
17
+ 'TECHNICAL': ['specification', 'tender', 'project', 'development', 'infrastructure']
18
+ }
19
+ self.confidence_threshold = 0.7
20
+
21
+ def extract_features(self, document_text: str) -> Dict[str, int]:
22
+ text_lower = document_text.lower()
23
+ features = {}
24
+ for category, keywords in self.categories.items():
25
+ feature_count = sum(text_lower.count(keyword) for keyword in keywords)
26
+ features[f'{category}_score'] = feature_count
27
+ features['word_count'] = len(text_lower.split())
28
+ features['has_date'] = 1 if re.search(r'\d{1,2}[-/]\d{1,2}[-/]\d{4}', document_text) else 0
29
+ features['has_reference'] = 1 if re.search(r'ref[:\s]*\w+', text_lower) else 0
30
+ return features
31
+
32
+ def classify_document(self, document_text: str, filename: str = "") -> Dict[str, Any]:
33
+ features = self.extract_features(document_text)
34
+ scores = {}
35
+ for category in self.categories.keys():
36
+ base_score = features.get(f'{category}_score', 0)
37
+ normalized_score = base_score / max(features['word_count'] / 100, 1)
38
+ scores[category] = normalized_score
39
+ best_category = max(scores, key=scores.get) if scores else 'UNCLASSIFIED'
40
+ confidence = min(scores[best_category] / 5.0, 1.0)
41
+ return {
42
+ 'filename': filename,
43
+ 'predicted_category': best_category,
44
+ 'confidence': confidence,
45
+ 'all_scores': scores,
46
+ 'classification_date': datetime.now().isoformat(),
47
+ 'features': features
48
+ }
49
+
50
+ # -------------------------
51
+ # Streamlit UI
52
+ # -------------------------
53
+
54
+ st.title("📄 AI-Based Document Classifier")
55
+ st.subheader("Upload government text files for automatic classification")
56
+
57
+ uploaded_files = st.file_uploader(
58
+ "Choose .txt files", type=["txt"], accept_multiple_files=True
59
+ )
60
+
61
+ if uploaded_files:
62
+ classifier = DocumentClassifier()
63
+ for uploaded_file in uploaded_files:
64
+ filename = uploaded_file.name
65
+ content = uploaded_file.read().decode("utf-8")
66
+ result = classifier.classify_document(content, filename)
67
+
68
+ st.markdown("---")
69
+ st.write(f"**Document:** {result['filename']}")
70
+ st.write(f"**Predicted Category:** `{result['predicted_category']}`")
71
+ st.write(f"**Confidence:** `{result['confidence']:.2f}`")
72
+ with st.expander("🔍 Feature Details"):
73
+ st.json(result['features'])