10000 GH-102670: Use sumprod() to simplify, speed up, and improve accuracy of statistics functions by rhettinger · Pull Request #102649 · python/cpython · GitHub
[go: up one dir, main page]

Skip to content

GH-102670: Use sumprod() to simplify, speed up, and improve accuracy of statistics functions #102649

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.

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
merged 11 commits into from
Mar 14, 2023
26 changes: 14 additions & 12 deletions Lib/statistics.py
D643
Original file line number Diff line number Diff line change
Expand Up @@ -1036,7 +1036,7 @@ def covariance(x, y, /):
raise StatisticsError('covariance requires at least two data points')
xbar = fsum(x) / n
ybar = fsum(y) / n
sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
sxy = sumprod((xi - xbar for xi in x), (yi - ybar for yi in y))
return sxy / (n - 1)


Expand Down Expand Up @@ -1074,11 +1074,14 @@ def correlation(x, y, /, *, method='linear'):
start = (n - 1) / -2 # Center rankings around zero
x = _rank(x, start=start)
y = _rank(y, start=start)
xbar = fsum(x) / n
ybar = fsum(y) / n
sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
sxx = fsum((d := xi - xbar) * d for xi in x)
syy = fsum((d := yi - ybar) * d for yi in y)
else:
xbar = fsum(x) / n
ybar = fsum(y) / n
x = [xi - xbar for xi in x]
y = [yi - ybar for yi in y]
sxy = sumprod(x, y)
sxx = sumprod(x, x)
syy = sumprod(y, y)
try:
return sxy / sqrt(sxx * syy)
except ZeroDivisionError:
Expand Down Expand Up @@ -1131,14 +1134,13 @@ def linear_regression(x, y, /, *, proportional=False):
raise StatisticsError('linear regression requires that both inputs have same number of data points')
if n < 2:
raise StatisticsError('linear regression requires at least two data points')
if proportional:
sxy = fsum(xi * yi for xi, yi in zip(x, y))
sxx = fsum(xi * xi for xi in x)
else:
if not proportional:
xbar = fsum(x) / n
ybar = fsum(y) / n
sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
sxx = fsum((d := xi - xbar) * d for xi in x)
x = [xi - xbar for xi in x] # List because used three times below
y = (yi - ybar for yi in y) # Generator because only used once below
sxy = sumprod(x, y)
sxx = sumprod(x, x)
try:
slope = sxy / sxx # equivalent to: covariance(x, y) / variance(x)
except ZeroDivisionError:
Expand Down
0