File size: 10,668 Bytes
12a191a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
import pandas as pd
import numpy as np
from datetime import datetime
from typing import List, Dict
import re

# Valid ICD-10 code patterns (simplified)
ICD10_PATTERNS = [
    r'^[A-Z][0-9]{2}(\.[0-9]{1,4})?$',  # Standard ICD-10
    r'^[A-Z][0-9]{2}$',  # Without decimal
]

class ValidationEngine:
    def __init__(self):
        self.required_columns = [
            'patient_id', 'age', 'gender', 'diagnosis_code', 
            'treatment_cost', 'claim_date', 'hospital_id', 
            'provider_id', 'risk_score', 'duplicate_flag'
        ]
        self.date_formats = [
            '%Y-%m-%d',
            '%m/%d/%Y',
            '%d/%m/%Y',
            '%Y/%m/%d'
        ]
    
    def validate(self, df: pd.DataFrame) -> Dict:
        """Run all validation rules"""
        errors = []
        warnings = []
        
        # Check 1: Missing columns
        missing_cols = [col for col in self.required_columns if col not in df.columns]
        if missing_cols:
            errors.append({
                "type": "missing_columns",
                "severity": "high",
                "message": f"Missing required columns: {', '.join(missing_cols)}",
                "columns": missing_cols
            })
        
        # Check 2: Missing values
        for col in df.columns:
            missing_count = df[col].isna().sum()
            if missing_count > 0:
                missing_indices = df[df[col].isna()].index.tolist()
                errors.append({
                    "type": "missing_values",
                    "severity": "medium",
                    "column": col,
                    "count": int(missing_count),
                    "row_indices": missing_indices,
                    "message": f"Column '{col}' has {missing_count} missing values"
                })
        
        # Check 3: Date format validation
        if 'claim_date' in df.columns:
            date_errors = self._validate_dates(df['claim_date'])
            errors.extend(date_errors)
        
        # Check 4: Out-of-range values
        range_errors = self._validate_ranges(df)
        errors.extend(range_errors)
        
        # Check 5: Duplicate detection
        duplicate_errors = self._validate_duplicates(df)
        errors.extend(duplicate_errors)
        
        # Check 6: Invalid ICD codes
        if 'diagnosis_code' in df.columns:
            icd_errors = self._validate_icd_codes(df['diagnosis_code'])
            errors.extend(icd_errors)
        
        # Check 7: Statistical outliers
        outlier_errors = self._validate_outliers(df)
        errors.extend(outlier_errors)
        
        # Generate summary
        summary = {
            "total_records": len(df),
            "total_errors": len(errors),
            "errors_by_type": {},
            "errors_by_severity": {"high": 0, "medium": 0, "low": 0}
        }
        
        for error in errors:
            error_type = error.get("type", "unknown")
            summary["errors_by_type"][error_type] = summary["errors_by_type"].get(error_type, 0) + 1
            severity = error.get("severity", "low")
            summary["errors_by_severity"][severity] = summary["errors_by_severity"].get(severity, 0) + 1
        
        return {
            "valid": len(errors) == 0,
            "summary": summary,
            "errors": errors,
            "warnings": warnings
        }
    
    def _validate_dates(self, date_series: pd.Series) -> List[Dict]:
        """Validate date formats"""
        errors = []
        for idx, date_val in enumerate(date_series):
            if pd.isna(date_val):
                continue
            
            date_str = str(date_val)
            valid = False
            
            for fmt in self.date_formats:
                try:
                    datetime.strptime(date_str, fmt)
                    valid = True
                    break
                except:
                    continue
            
            if not valid:
                errors.append({
                    "type": "date_format_mismatch",
                    "severity": "medium",
                    "row_index": int(idx),
                    "value": date_str,
                    "message": f"Invalid date format at row {idx}: {date_str}"
                })
        
        return errors
    
    def _validate_ranges(self, df: pd.DataFrame) -> List[Dict]:
        """Validate value ranges"""
        errors = []
        
        # Age validation
        if 'age' in df.columns:
            age_series = pd.to_numeric(df['age'], errors='coerce')
            invalid_ages = (age_series < 0) | (age_series > 150) | age_series.isna()
            for idx in df[invalid_ages].index:
                errors.append({
                    "type": "out_of_range",
                    "severity": "high",
                    "column": "age",
                    "row_index": int(idx),
                    "value": df.loc[idx, 'age'],
                    "message": f"Age out of range (0-150) at row {idx}"
                })
        
        # Treatment cost validation
        if 'treatment_cost' in df.columns:
            cost_series = pd.to_numeric(df['treatment_cost'], errors='coerce')
            invalid_costs = (cost_series < 0) | (cost_series > 1000000) | cost_series.isna()
            for idx in df[invalid_costs].index:
                errors.append({
                    "type": "out_of_range",
                    "severity": "medium",
                    "column": "treatment_cost",
                    "row_index": int(idx),
                    "value": df.loc[idx, 'treatment_cost'],
                    "message": f"Treatment cost out of range at row {idx}"
                })
        
        # Risk score validation
        if 'risk_score' in df.columns:
            risk_series = pd.to_numeric(df['risk_score'], errors='coerce')
            invalid_risks = (risk_series < 0) | (risk_series > 10) | risk_series.isna()
            for idx in df[invalid_risks].index:
                errors.append({
                    "type": "out_of_range",
                    "severity": "medium",
                    "column": "risk_score",
                    "row_index": int(idx),
                    "value": df.loc[idx, 'risk_score'],
                    "message": f"Risk score out of range (0-10) at row {idx}"
                })
        
        # Gender validation
        if 'gender' in df.columns:
            valid_genders = ['M', 'F', 'Male', 'Female', 'm', 'f', 'male', 'female']
            invalid_genders = ~df['gender'].isin(valid_genders)
            for idx in df[invalid_genders].index:
                errors.append({
                    "type": "out_of_range",
                    "severity": "low",
                    "column": "gender",
                    "row_index": int(idx),
                    "value": df.loc[idx, 'gender'],
                    "message": f"Invalid gender value at row {idx}"
                })
        
        return errors
    
    def _validate_duplicates(self, df: pd.DataFrame) -> List[Dict]:
        """Detect duplicate records"""
        errors = []
        
        if 'patient_id' in df.columns:
            duplicates = df[df.duplicated(subset=['patient_id'], keep=False)]
            if len(duplicates) > 0:
                duplicate_indices = duplicates.index.tolist()
                errors.append({
                    "type": "duplicate_detection",
                    "severity": "high",
                    "row_indices": [int(idx) for idx in duplicate_indices],
                    "count": len(duplicate_indices),
                    "message": f"Found {len(duplicate_indices)} duplicate patient IDs"
                })
        
        # Check for exact duplicate rows
        exact_duplicates = df[df.duplicated(keep=False)]
        if len(exact_duplicates) > 0:
            duplicate_indices = exact_duplicates.index.tolist()
            errors.append({
                "type": "duplicate_detection",
                "severity": "high",
                "row_indices": [int(idx) for idx in duplicate_indices],
                "count": len(duplicate_indices),
                "message": f"Found {len(duplicate_indices)} exact duplicate rows"
            })
        
        return errors
    
    def _validate_icd_codes(self, code_series: pd.Series) -> List[Dict]:
        """Validate ICD-10 diagnosis codes"""
        errors = []
        
        for idx, code in enumerate(code_series):
            if pd.isna(code):
                continue
            
            code_str = str(code).strip().upper()
            valid = False
            
            for pattern in ICD10_PATTERNS:
                if re.match(pattern, code_str):
                    valid = True
                    break
            
            if not valid:
                errors.append({
                    "type": "invalid_icd_code",
                    "severity": "medium",
                    "row_index": int(idx),
                    "value": code_str,
                    "message": f"Invalid ICD-10 code at row {idx}: {code_str}"
                })
        
        return errors
    
    def _validate_outliers(self, df: pd.DataFrame) -> List[Dict]:
        """Detect statistical outliers using IQR method"""
        errors = []
        
        numeric_cols = ['age', 'treatment_cost', 'risk_score']
        
        for col in numeric_cols:
            if col not in df.columns:
                continue
            
            series = pd.to_numeric(df[col], errors='coerce')
            Q1 = series.quantile(0.25)
            Q3 = series.quantile(0.75)
            IQR = Q3 - Q1
            
            lower_bound = Q1 - 1.5 * IQR
            upper_bound = Q3 + 1.5 * IQR
            
            outliers = (series < lower_bound) | (series > upper_bound)
            outlier_indices = df[outliers].index.tolist()
            
            if len(outlier_indices) > 0:
                errors.append({
                    "type": "statistical_outlier",
                    "severity": "low",
                    "column": col,
                    "row_indices": [int(idx) for idx in outlier_indices],
                    "count": len(outlier_indices),
                    "message": f"Found {len(outlier_indices)} statistical outliers in '{col}'"
                })
        
        return errors