Last active
August 24, 2018 18:49
-
-
Save fluency03/3074ec3b0d2d1f48c4303001c817fa5f to your computer and use it in GitHub Desktop.
This file contains 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
# Reference: http://stackoverflow.com/questions/22354094/pythonic-way-of-detecting-outliers-in-one-dimensional-observation-data/22357811#22357811 | |
import numpy as np | |
def is_outlier(points, thresh=3.5): | |
""" | |
Returns a boolean array with True if points are outliers and False | |
otherwise. | |
Parameters: | |
----------- | |
points : An numobservations by numdimensions array of observations | |
thresh : The modified z-score to use as a threshold. Observations with | |
a modified z-score (based on the median absolute deviation) greater | |
than this value will be classified as outliers. | |
Returns: | |
-------- | |
mask : A numobservations-length boolean array. | |
References: | |
---------- | |
Boris Iglewicz and David Hoaglin (1993), "Volume 16: How to Detect and | |
Handle Outliers", The ASQC Basic References in Quality Control: | |
Statistical Techniques, Edward F. Mykytka, Ph.D., Editor. | |
""" | |
if len(points.shape) == 1: | |
points = points[:,None] | |
median = np.median(points, axis=0) | |
diff = np.sum((points - median)**2, axis=-1) | |
diff = np.sqrt(diff) | |
med_abs_deviation = np.median(diff) | |
modified_z_score = 0.6745 * diff / med_abs_deviation | |
return modified_z_score > thresh | |
def mad(data, axis=None): | |
return np.median(np.abs(data - np.median(data, axis=0)), axis=0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment