Detect Outliers in CSV Data Using Z-Score in Python

import csv
import statistics
from math import sqrt

def detect_outliers(csv_path, column_name, threshold=2.0):
    """Detect outliers in a numeric column using z-score method."""
    values = []
    with open(csv_path, 'r', newline='') as f:
        reader = csv.DictReader(f)
        if column_name not in reader.fieldnames:
            raise ValueError(f"Column '{column_name}' not found")
        for row in reader:
            try:
                val = float(row[column_name])
                values.append(val)
            except (ValueError, TypeError):
                continue
    
    if len(values) < 2:
        return []
    
    mean = statistics.mean(values)
    stdev = statistics.stdev(values)
    if stdev == 0:
        return []
    
    outliers = []
    for i, val in enumerate(values):
        z_score = (val - mean) / stdev
        if abs(z_score) > threshold:
            outliers.append((i, val, z_score))
    return outliers

if __name__ == "__main__":
    # Example: create sample CSV data
    sample_data = "value\n10\n12\n11\n13\n100\n9\n11\n12\n10\n200\n14\n"
    with open('sample.csv', 'w') as f:
        f.write(sample_data)
    
    result = detect_outliers('sample.csv', 'value')
    print("Outliers detected (index, value, z-score):")
    for idx, val, z in result:
        print(f"  Row {idx+1}: {val} (z={z:.2f})")