Sumayyea commited on
Commit
e9d51a7
Β·
verified Β·
1 Parent(s): a69a935

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +37 -9
app.py CHANGED
@@ -1,7 +1,8 @@
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
@@ -21,23 +22,44 @@ class DocumentClassifier:
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,
@@ -47,10 +69,12 @@ class DocumentClassifier:
47
  'features': features
48
  }
49
 
 
50
  # -------------------------
51
  # Streamlit UI
52
  # -------------------------
53
 
 
54
  st.title("πŸ“„ AI-Based Document Classifier")
55
  st.subheader("Upload government text files for automatic classification")
56
 
@@ -66,8 +90,12 @@ if uploaded_files:
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("πŸ” Feature Details"):
 
73
  st.json(result['features'])
 
 
 
 
1
  import streamlit as st
2
  import re
3
  from datetime import datetime
4
+ from typing import Dict, Any
5
+
6
 
7
  # -------------------------
8
  # Document Classifier Class
 
22
  def extract_features(self, document_text: str) -> Dict[str, int]:
23
  text_lower = document_text.lower()
24
  features = {}
25
+
26
+ # Score each category based on keywords
27
  for category, keywords in self.categories.items():
28
  feature_count = sum(text_lower.count(keyword) for keyword in keywords)
29
  features[f'{category}_score'] = feature_count
30
+
31
  features['word_count'] = len(text_lower.split())
32
+
33
+ # Date patterns (DD Month YYYY, 7th January 2025, 12/02/2023 etc.)
34
+ date_patterns = [
35
+ r'\b\d{1,2}[-/]\d{1,2}[-/]\d{4}\b', # e.g., 12/02/2023
36
+ r'\b\d{1,2}(?:st|nd|rd|th)?\s+[A-Z][a-z]+,\s+\d{4}\b', # e.g., 7th January, 2025
37
+ r'\b\d{1,2}(?:st|nd|rd|th)?\s+[A-Z][a-z]+\s+\d{4}\b', # e.g., 29 January 2025
38
+ r'\b[A-Z][a-z]+\s+\d{1,2},\s+\d{4}\b', # e.g., January 29, 2025
39
+ ]
40
+ features['has_date'] = 1 if any(re.search(p, document_text) for p in date_patterns) else 0
41
+
42
+ # Reference patterns (e.g., "No. DD (STI)/5(1)2024-25" or "Ref No: XYZ")
43
+ ref_patterns = [
44
+ r'\bref[.\s:]*[A-Za-z0-9/\-()]+', # Ref No: XYZ-123
45
+ r'\bno[.\s:]*[A-Za-z0-9/\-()]+', # No. DD/XYZ-123
46
+ ]
47
+ features['has_reference'] = 1 if any(re.search(p, text_lower) for p in ref_patterns) else 0
48
+
49
  return features
50
 
51
  def classify_document(self, document_text: str, filename: str = "") -> Dict[str, Any]:
52
  features = self.extract_features(document_text)
53
  scores = {}
54
+
55
+ for category in self.categories:
56
  base_score = features.get(f'{category}_score', 0)
57
  normalized_score = base_score / max(features['word_count'] / 100, 1)
58
  scores[category] = normalized_score
59
+
60
+ best_category = max(scores, key=scores.get)
61
  confidence = min(scores[best_category] / 5.0, 1.0)
62
+
63
  return {
64
  'filename': filename,
65
  'predicted_category': best_category,
 
69
  'features': features
70
  }
71
 
72
+
73
  # -------------------------
74
  # Streamlit UI
75
  # -------------------------
76
 
77
+ st.set_page_config(page_title="Document Classifier", layout="wide")
78
  st.title("πŸ“„ AI-Based Document Classifier")
79
  st.subheader("Upload government text files for automatic classification")
80
 
 
90
  result = classifier.classify_document(content, filename)
91
 
92
  st.markdown("---")
93
+ st.write(f"**πŸ“ Document:** `{result['filename']}`")
94
+ st.write(f"**πŸ“‚ Predicted Category:** `{result['predicted_category']}`")
95
+ st.write(f"**πŸ“Š Confidence:** `{result['confidence']:.2f}`")
96
+
97
+ with st.expander("πŸ” Feature Details", expanded=False):
98
  st.json(result['features'])
99
+
100
+ with st.expander("πŸ“œ Full Text", expanded=False):
101
+ st.text(content)