Students should extract subsets of data from particular groups within
their data set for this exercise. In the absense of that, you can run
the create_sample.py script to create the sample and then run the
compare_random_a_b.py script to compare the two groups.
Last active
August 29, 2015 14:03
-
-
Save deanmalmgren/5463f502847930c57598 to your computer and use it in GitHub Desktop.
how often is A better than B?
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
| sample_a.dat | |
| sample_b.dat |
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 python | |
| """Given two files that contain a list of data values, compute the | |
| differences in the sample means with a bootstrapping approach | |
| """ | |
| import random | |
| def read_data(filename): | |
| with open(filename) as stream: | |
| return map(float, stream.read().split()) | |
| m = 10000 | |
| a_data = read_data('sample_a.dat') | |
| b_data = read_data('sample_b.dat') | |
| # calculate how frequently a random a is greater than a random b | |
| count = 0 | |
| for j in xrange(m): | |
| a = random.choice(a_data) | |
| b = random.choice(b_data) | |
| if a > b: | |
| count += 1 | |
| p_a_gt_b = float(count) / m | |
| print("p(a > b) = %(p_a_gt_b)f" % locals()) |
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 python | |
| """I don't currently have access to the movie or horse racing data, so | |
| use this script to create the group a and group b data sets that are | |
| used in subsequent steps. | |
| """ | |
| import sys | |
| import random | |
| def write_sample(stream, n, lam): | |
| filename = stream.name | |
| sys.stderr.write(( | |
| '%(filename)s with %(n)d values from exponential distribution' | |
| 'with lam=%(lam)s\n' | |
| ) % locals()) | |
| for i in xrange(n): | |
| x = random.expovariate(lam) | |
| stream.write(str(x) + '\n') | |
| with open('sample_a.dat', 'w') as stream: | |
| write_sample(stream, 100000, 1.5) | |
| with open('sample_b.dat', 'w') as stream: | |
| write_sample(stream, 20000, 1.1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment