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
|
# Authors: Denis Engemann <denis.engemann@gmail.com>
# License: BSD (3-clause)
import numpy as np
def find_outliers(X, threshold=3.0, max_iter=2):
"""Find outliers based on iterated Z-scoring.
This procedure compares the absolute z-score against the threshold.
After excluding local outliers, the comparison is repeated until no
local outlier is present any more.
Parameters
----------
X : np.ndarray of float, shape (n_elemenets,)
The scores for which to find outliers.
threshold : float
The value above which a feature is classified as outlier.
max_iter : int
The maximum number of iterations.
Returns
-------
bad_idx : np.ndarray of int, shape (n_features)
The outlier indices.
"""
from scipy.stats import zscore
my_mask = np.zeros(len(X), dtype=np.bool)
for _ in range(max_iter):
X = np.ma.masked_array(X, my_mask)
this_z = np.abs(zscore(X))
local_bad = this_z > threshold
my_mask = np.max([my_mask, local_bad], 0)
if not np.any(local_bad):
break
bad_idx = np.where(my_mask)[0]
return bad_idx
|
