Last active
September 13, 2018 22:10
-
-
Save mistycheney/e321683d3cfc9a05fe89c02d415878a0 to your computer and use it in GitHub Desktop.
Count anomalies based on scores
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
# Various ways to find peaks in Python | |
# https://github.com/MonsieurV/py-findpeaks | |
def count_anomalies_from_scores(scores, plot=False): | |
from scipy.signal import find_peaks | |
is_outlier = detect_outlier(scores) | |
peaks, _ = find_peaks(is_outlier, distance=60) # 60 means peaks must be separated by 60 mins | |
num_anomalies = np.count_nonzero(peaks) | |
if plot: | |
fig, axes = plt.subplots(3, 1, figsize=(16,5), squeeze=True) | |
axes[0].plot((score-score.min())/(score.max()-score.min())); | |
axes[0].set_title('Score (normalized)'); | |
axes[1].plot(is_outlier); | |
axes[1].set_title('Is outlier'); | |
peak_mask = np.zeros_like(is_outlier, dtype=bool) | |
peak_mask[peaks] = 1 | |
axes[2].plot(peak_mask); | |
axes[2].set_title('Is peak'); | |
plt.tight_layout(); | |
print('Found %d anomalies' % num_anomalies) | |
return num_anomalies, peaks, is_outlier | |
def detect_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. | |
""" | |
# https://stackoverflow.com/questions/11882393/matplotlib-disregard-outliers-when-plotting | |
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 | |
mask = modified_z_score > thresh | |
return mask & (points[:, 0] - median > 0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment