Last active
August 14, 2017 15:11
-
-
Save Perif/b693b86b71959fc54ce1e60811c45191 to your computer and use it in GitHub Desktop.
Bins Analysis with Numpy
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
import pickle as pkl | |
import numpy as np | |
import seaborn as sns | |
# load data | |
scores = pkl.load(open('y_scores_20.pkl','rb')) | |
# create bins | |
bins = np.linspace(0, 1, 157) # 157 is determined arbitrarily | |
digitized = np.digitize(scores, bins) | |
bin_means = [scores[digitized == i].mean() for i in range(1, len(bins))] | |
# get the histogram, https://docs.scipy.org/doc/numpy/reference/generated/numpy.histogram.html | |
hist = np.histogram(scores,bins='sturges') | |
np.savetxt('bins.csv',scores[scores > hist[1][1]],delimiter=';') # export without the first bin | |
# if visualized in tableau, bins are computed as follows: Number of Bins = 3 + log2(n) * log(n) | |
# ref: http://onlinehelp.tableau.com/current/pro/desktop/en-us/calculations_bins.html | |
# plot with seaborn | |
dist = sns.distplot(scores[scores > hist[1][1]]) # visualize without the first bin | |
dist.figure.savefig('output.png') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment