mirror of
https://github.com/python/cpython
synced 2024-09-16 00:07:33 +00:00
gh-108322: Optimize statistics.NormalDist.samples() (gh-108324)
This commit is contained in:
parent
09343dba44
commit
042aa88bcc
|
@ -828,6 +828,11 @@ of applications in statistics.
|
|||
number generator. This is useful for creating reproducible results,
|
||||
even in a multi-threading context.
|
||||
|
||||
.. versionchanged:: 3.13
|
||||
|
||||
Switched to a faster algorithm. To reproduce samples from previous
|
||||
versions, use :func:`random.seed` and :func:`random.gauss`.
|
||||
|
||||
.. method:: NormalDist.pdf(x)
|
||||
|
||||
Using a `probability density function (pdf)
|
||||
|
|
|
@ -1135,7 +1135,7 @@ def linear_regression(x, y, /, *, proportional=False):
|
|||
>>> noise = NormalDist().samples(5, seed=42)
|
||||
>>> y = [3 * x[i] + 2 + noise[i] for i in range(5)]
|
||||
>>> linear_regression(x, y) #doctest: +ELLIPSIS
|
||||
LinearRegression(slope=3.09078914170..., intercept=1.75684970486...)
|
||||
LinearRegression(slope=3.17495..., intercept=1.00925...)
|
||||
|
||||
If *proportional* is true, the independent variable *x* and the
|
||||
dependent variable *y* are assumed to be directly proportional.
|
||||
|
@ -1148,7 +1148,7 @@ def linear_regression(x, y, /, *, proportional=False):
|
|||
|
||||
>>> y = [3 * x[i] + noise[i] for i in range(5)]
|
||||
>>> linear_regression(x, y, proportional=True) #doctest: +ELLIPSIS
|
||||
LinearRegression(slope=3.02447542484..., intercept=0.0)
|
||||
LinearRegression(slope=2.90475..., intercept=0.0)
|
||||
|
||||
"""
|
||||
n = len(x)
|
||||
|
@ -1279,9 +1279,11 @@ def from_samples(cls, data):
|
|||
|
||||
def samples(self, n, *, seed=None):
|
||||
"Generate *n* samples for a given mean and standard deviation."
|
||||
gauss = random.gauss if seed is None else random.Random(seed).gauss
|
||||
mu, sigma = self._mu, self._sigma
|
||||
return [gauss(mu, sigma) for _ in repeat(None, n)]
|
||||
rnd = random.random if seed is None else random.Random(seed).random
|
||||
inv_cdf = _normal_dist_inv_cdf
|
||||
mu = self._mu
|
||||
sigma = self._sigma
|
||||
return [inv_cdf(rnd(), mu, sigma) for _ in repeat(None, n)]
|
||||
|
||||
def pdf(self, x):
|
||||
"Probability density function. P(x <= X < x+dx) / dx"
|
||||
|
|
|
@ -0,0 +1,2 @@
|
|||
Speed-up NormalDist.samples() by using the inverse CDF method instead of
|
||||
calling random.gauss().
|
Loading…
Reference in a new issue