Created
October 18, 2018 06:55
-
-
Save sdia-zz/6f9190593abbc06a8397f28dadc16be8 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
#!/usr/bin/env python3 | |
#-*- coding:utf-8 -*- | |
import os | |
import numpy as np | |
MDE = .01 | |
POWER = .8 | |
BOOT_SIZE = 1000 | |
BOOT_RUNS = 256 | |
CURRENT_DIR = os.path.dirname(os.path.abspath(__file__)) | |
REPLIES_PER_DAU = os.path.join(CURRENT_DIR, 'replies_per_dau.tsv') | |
REPLIES_PER_DAU = np.loadtxt(REPLIES_PER_DAU) | |
REPLIES_PER_DAU_LO = REPLIES_PER_DAU - MDE * REPLIES_PER_DAU | |
REPLIES_PER_DAU_HI = REPLIES_PER_DAU + MDE * REPLIES_PER_DAU | |
LISTINGS_PER_DAU = os.path.join(CURRENT_DIR, 'listings_per_dau.tsv') | |
LISTINGS_PER_DAU = np.loadtxt(LISTINGS_PER_DAU) | |
LISTINGS_PER_DAU_LO = LISTINGS_PER_DAU - MDE * LISTINGS_PER_DAU | |
LISTINGS_PER_DAU_HI = LISTINGS_PER_DAU + MDE * LISTINGS_PER_DAU | |
def get_ci(a, bsize=BOOT_SIZE, bruns=BOOT_RUNS): | |
boot_means = [] | |
for i in range(bruns): | |
b = np.random.choice(a, size=bsize, replace=True) | |
boot_means.append(np.mean(b)) | |
lo = np.percentile(boot_means, 2.5) | |
hi = np.percentile(boot_means, 97.5) | |
return '{:2.2f}, {:2.2f}'.format(lo, hi) | |
def get_power(a, sample_size, ci_lo, ci_hi, bruns=BOOT_RUNS): | |
boot_means = [] | |
for i in range(bruns): | |
b = np.random.choice(a, size=sample_size, replace=True) | |
boot_means.append(np.mean(b)) | |
return 100.0 * len([o for o in boot_means if (o <= ci_lo or o >= ci_hi)]) / len(boot_means) | |
def generate_ci(a): | |
n = 64 | |
for i in range(16): | |
n *= 2 | |
print('{}, '.format(n), get_ci(a, bsize=n)) | |
def power_analysis(data, ci): | |
for d in ci: | |
sample_size = int(d) | |
ci_lo = ci[d][0] | |
ci_hi = ci[d][1] | |
power = get_power(data, sample_size=sample_size, | |
ci_lo=ci_lo, | |
ci_hi=ci_hi) | |
print('{:2.2f}\t{:2.2f}'.format(sample_size, power)) | |
if __name__ == '__main__': | |
CI_REPLIES_PER_DAU = { | |
'100' : (1.80, 3.04), | |
'1000' : (2.07, 2.58), | |
'10000' : (2.19, 2.32), | |
'100000' : (2.23, 2.28), | |
'1000000' : (2.25, 2.26) | |
} | |
CI_REPLIES_PER_DAU = { | |
'128' : (1.77, 2.82), | |
'256' : (1.92, 2.83), | |
'512' : (2.05, 2.68), | |
'1024' : (2.07, 2.50), | |
'2048' : (2.13, 2.41), | |
'4096' : (2.16, 2.42), | |
'8192' : (2.18, 2.35), | |
'16384' : (2.21, 2.32), | |
'32768' : (2.22, 2.29), | |
'65536' : (2.22, 2.28), | |
'131072' : (2.23, 2.27), | |
'262144' : (2.24, 2.27), | |
'524288' : (2.24, 2.26), | |
'1048576' : (2.24, 2.26) | |
} | |
CI_LISTINGS_PER_DAU = { | |
'100' : (1.36, 2.15), | |
'1000' : (1.56, 1.81), | |
'10000' : (1.64, 1.72), | |
'100000' : (1.66, 1.69), | |
'1000000' : (1.67, 1.68) | |
} | |
CI_LISTINGS_PER_DAU = { | |
'128' : (1.41, 2.14), | |
'256' : (1.47, 1.94), | |
'512' : (1.54, 1.89), | |
'1024' : (1.57, 1.81), | |
'2048' : (1.60, 1.76), | |
'4096' : (1.62, 1.74), | |
'8192' : (1.64, 1.72), | |
'16384' : (1.64, 1.71), | |
'32768' : (1.66, 1.70), | |
'65536' : (1.66, 1.69), | |
'131072' : (1.67, 1.69), | |
'262144' : (1.67, 1.68), | |
'524288' : (1.67, 1.68), | |
'1048576' : (1.67, 1.68) | |
} | |
power_analysis(REPLIES_PER_DAU_HI, CI_REPLIES_PER_DAU) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment