from data_quality_auditor import DataQualityAuditor

auditor = DataQualityAuditor()
auditor.load_csv("customers.csv")

undefined

undefined

undefined

class DataQualityAuditor:
    def __init__(self)

    # Data loading
    def load_csv(self, filepath: str, **kwargs) -> 'DataQualityAuditor'
    def load_dataframe(self, df: pd.DataFrame) -> 'DataQualityAuditor'

    # Full audit
    def audit(self) -> dict
    def quality_score(self) -> float

    # Individual checks
    def check_missing(self) -> dict
    def check_duplicates(self, subset: list = None) -> dict
    def check_types(self) -> dict
    def check_uniqueness(self) -> dict
    def check_patterns(self, column: str, pattern: str) -> dict

    # Validation
    def validate_column(self, column: str, rules: dict) -> dict
    def validate_dataset(self, rules: dict) -> dict

    # Reports
    def generate_report(self, output: str, format: str = "html") -> str
    def summary(self) -> str

missing = auditor.check_missing()

undefined

dups = auditor.check_duplicates()

undefined

types = auditor.check_types()

undefined

{
    "columns": {
        "email": {
            "required": true,
            "unique": true,
            "pattern": "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$"
        },
        "age": {
            "type": "integer",
            "min": 0,
            "max": 120
        },
        "status": {
            "allowed_values": ["active", "inactive", "pending"]
        },
        "created_at": {
            "type": "date",
            "format": "%Y-%m-%d"
        }
    }
}

results = auditor.validate_dataset(rules)

score = auditor.quality_score()

undefined

{
    "file": "data.csv",
    "rows": 1000,
    "columns": 15,
    "quality_score": 85.5,
    "completeness": {
        "score": 92.0,
        "missing_cells": 800,
        "details": {...}
    },
    "uniqueness": {
        "score": 97.5,
        "duplicate_rows": 25,
        "details": {...}
    },
    "validity": {
        "score": 78.0,
        "type_issues": [...],
        "details": {...}
    },
    "consistency": {
        "score": 80.0,
        "pattern_issues": [...],
        "details": {...}
    },
    "recommendations": [
        "Column 'phone' has 10% missing values",
        "25 duplicate rows detected",
        "Column 'date' has inconsistent formats"
    ]
}

auditor = DataQualityAuditor()
auditor.load_csv("import_data.csv")

report = auditor.audit()
if report['quality_score'] < 80:
    print("Data quality below threshold!")
    for rec in report['recommendations']:
        print(f"  - {rec}")
    exit(1)

auditor = DataQualityAuditor()
auditor.load_dataframe(transformed_df)

undefined

auditor = DataQualityAuditor()
auditor.load_csv("dataset.csv")

undefined