Created
December 3, 2020 16:46
-
-
Save asifr/9115fe8420139e90ca6dd1a6f690a3d4 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| def outlier_detect(data, threshold=1, method="IQR"): | |
| assert method in ["IQR", "STD", "MAD"], "Method must be one of IQR|STD|MAD" | |
| if method == "IQR": | |
| IQR = np.quantile(data, 0.75) - np.quantile(data, 0.25) | |
| lower = np.quantile(data, 0.25) - (IQR * threshold) | |
| upper = np.quantile(data, 0.75) + (IQR * threshold) | |
| if method == "STD": | |
| upper = np.nanmean(data) + threshold * np.nanstd(data) | |
| lower = np.nanmean(data) - threshold * np.nanstd(data) | |
| if method == "MAD": | |
| median = data.median() | |
| median_absolute_deviation = np.median([np.abs(y - median) for y in data]) | |
| modified_z_scores = [ | |
| 0.6745 * (y - median) / median_absolute_deviation for y in data | |
| ] | |
| outlier_index = np.abs(modified_z_scores) > threshold | |
| return outlier_index, (median_absolute_deviation, median_absolute_deviation) | |
| upper_lower = (upper, lower) | |
| outlier_index = np.any(np.concatenate([data > upper, data < lower])) | |
| return outlier_index, upper_lower |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment