Skip to content

bpo-40541: Add optional *counts* parameter to random.sample() #19970

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rhettinger merged 10 commits into from
May 8, 2020
Merged

bpo-40541: Add optional *counts* parameter to random.sample() #19970

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4ad778b
Add weights to random.sample()
rhettinger May 6, 2020
eaed7b3
Add docs
rhettinger May 6, 2020
787ec38
Add blurb
rhettinger May 6, 2020
ab6b380
Add tests
rhettinger May 6, 2020
ea5e42e
Update Doc/library/random.rst
rhettinger May 6, 2020
672f739
Add exact equidistribution test
rhettinger May 7, 2020
556582d
Earlier test for zero total weight
rhettinger May 7, 2020
4fb554a
Change parameter name from "weights" to "counts". Add another test.
rhettinger May 7, 2020
55e948e
Sync-up docstring with the main docs
rhettinger May 7, 2020
1f36ad3
Fix typo and improve formatting
rhettinger May 8, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Add tests
  • Loading branch information
@rhettinger
rhettinger committed May 6, 2020
commit ab6b380d020bf7c5d7b6521711bb425295701de0
4 changes: 3 additions & 1 deletion Lib/random.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -383,8 +383,11 @@ def sample(self, population, k, *, weights=None):
population = tuple(population)
if not isinstance(population, _Sequence):
raise TypeError("Population must be a sequence. For dicts or sets, use sorted(d).")
n = len(population)
if weights is not None:
cum_weights = list(_accumulate(weights))
Comment thread
rhettinger marked this conversation as resolved.
Outdated
if len(cum_weights) != n:
raise ValueError('The number of weights does not match the population')
total = cum_weights.pop()
if not isinstance(total, int):
raise TypeError('Weights must be integers')
Expand All @@ -394,7 +397,6 @@ def sample(self, population, k, *, weights=None):
bisect = _bisect
return [population[bisect(cum_weights, s)] for s in selections]
randbelow = self._randbelow
n = len(population)
if not 0 <= k <= n:
raise ValueError("Sample larger than population or is negative")
result = [None] * k
Expand Down
39 changes: 38 additions & 1 deletion Lib/test/test_random.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
from math import log, exp, pi, fsum, sin, factorial
from test import support
from fractions import Fraction

from collections import Counter

class TestBasicOps:
# Superclass with tests common to all generators.
Expand Down Expand Up @@ -161,6 +161,43 @@ def test_sample_on_sets(self):
population = {10, 20, 30, 40, 50, 60, 70}
self.gen.sample(population, k=5)

def test_sample_with_weights(self):
sample = self.gen.sample

# General case
colors = ['red', 'green', 'blue', 'orange', 'black', 'brown', 'amber']
weights = [500, 200, 20, 10, 5, 0, 1 ]
k = 700
summary = Counter(sample(colors, weights=weights, k=k))
self.assertEqual(sum(summary.values()), k)
for color, weight in zip(colors, weights):
self.assertLessEqual(summary[color], weight)
self.assertNotIn('brown', summary)

# Case that exhausts the population
k = sum(weights)
summary = Counter(sample(colors, weights=weights, k=k))
self.assertEqual(sum(summary.values()), k)
for color, weight in zip(colors, weights):
self.assertLessEqual(summary[color], weight)
self.assertNotIn('brown', summary)

# Case with population size of 1
summary = Counter(sample(['x'], weights=[10], k=8))
self.assertEqual(summary, Counter(x=8))

# Test error handling
with self.assertRaises(TypeError):
sample(['red', 'green', 'blue'], weights=10, k=10) # weights not iterable
with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], weights=[-3, -7, -8], k=2) # weights are negative
with self.assertRaises(ValueError):
sample(['red', 'green'], weights=[10, 10], k=21) # population too small
with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], weights=[1, 2], k=2) # too few weights
with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], weights=[1, 2, 3, 4], k=2) # too many weights

def test_choices(self):
choices = self.gen.choices
data = ['red', 'green', 'blue', 'yellow']
Expand Down