traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Implement random.sample() using sets instead of dicts.

This commit is contained in:
Raymond Hettinger 2005-08-19 01:36:35 +00:00
parent e0245143af
commit 91e27c253c
1 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
Lib/random.py
View File

@ -41,7 +41,7 @@ General notes on the underlying Mersenne Twister core generator:
from warnings import warn as _warn from warnings import warn as _warn
from types import MethodType as _MethodType, BuiltinMethodType as _BuiltinMethodType from types import MethodType as _MethodType, BuiltinMethodType as _BuiltinMethodType
from math import log as _log, exp as _exp, pi as _pi, e as _e from math import log as _log, exp as _exp, pi as _pi, e as _e, ceil as _ceil
from math import sqrt as _sqrt, acos as _acos, cos as _cos, sin as _sin from math import sqrt as _sqrt, acos as _acos, cos as _cos, sin as _sin
from os import urandom as _urandom from os import urandom as _urandom
from binascii import hexlify as _hexlify from binascii import hexlify as _hexlify
@ -286,15 +286,14 @@ class Random(_random.Random):
""" """
# Sampling without replacement entails tracking either potential # Sampling without replacement entails tracking either potential
# selections (the pool) in a list or previous selections in a # selections (the pool) in a list or previous selections in a set.
# dictionary.
# When the number of selections is small compared to the # When the number of selections is small compared to the
# population, then tracking selections is efficient, requiring # population, then tracking selections is efficient, requiring
# only a small dictionary and an occasional reselection. For # only a small set and an occasional reselection. For
# a larger number of selections, the pool tracking method is # a larger number of selections, the pool tracking method is
# preferred since the list takes less space than the # preferred since the list takes less space than the
# dictionary and it doesn't suffer from frequent reselections. # set and it doesn't suffer from frequent reselections.
n = len(population) n = len(population)
if not 0 <= k <= n: if not 0 <= k <= n:
@ -302,7 +301,10 @@ class Random(_random.Random):
random = self.random random = self.random
_int = int _int = int
result = [None] * k result = [None] * k
if n < 6 * k: # if n len list takes less space than a k len dict setsize = 21 # size of a small set minus size of an empty list
if k > 5:
setsize += 4 ** _ceil(_log(k * 3, 4)) # table size for big sets
if n <= setsize: # is an n-length list smaller than a k-length set
pool = list(population) pool = list(population)
for i in xrange(k): # invariant: non-selected at [0,n-i) for i in xrange(k): # invariant: non-selected at [0,n-i)
j = _int(random() * (n-i)) j = _int(random() * (n-i))
@ -311,14 +313,16 @@ class Random(_random.Random):
else: else:
try: try:
n > 0 and (population[0], population[n//2], population[n-1]) n > 0 and (population[0], population[n//2], population[n-1])
except (TypeError, KeyError): # handle sets and dictionaries except (TypeError, KeyError): # handle non-sequence iterables
population = tuple(population) population = tuple(population)
selected = {} selected = set()
selected_add = selected.add
for i in xrange(k): for i in xrange(k):
j = _int(random() * n) j = _int(random() * n)
while j in selected: while j in selected:
j = _int(random() * n) j = _int(random() * n)
result[i] = selected[j] = population[j] selected_add(j)
result[i] = population[j]
return result return result
## -------------------- real-valued distributions ------------------- ## -------------------- real-valued distributions -------------------