Eliminate duplicated calculations and unnecessary work for linear regression (GH...

diff --git a/Lib/statistics.py b/Lib/statistics.py
index edb11c868c1c8794569630229e2f44be76574d24..db8c581068b7ddedf1aed16ce304bb97dc19903f 100644 (file)
--- a/Lib/statistics.py
+++ b/Lib/statistics.py
@@ -952,11 +952,16 @@ def linear_regression(regressor, dependent_variable, /):
         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')
+    x, y = regressor, dependent_variable
+    xbar = fsum(x) / n
+    ybar = fsum(y) / n
+    sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
+    s2x = fsum((xi - xbar) ** 2.0 for xi in x)
     try:
-        slope = covariance(regressor, dependent_variable) / variance(regressor)
+        slope = sxy / s2x
     except ZeroDivisionError:
         raise StatisticsError('regressor is constant')
-    intercept = fmean(dependent_variable) - slope * fmean(regressor)
+    intercept = ybar - slope * xbar
     return LinearRegression(intercept=intercept, slope=slope)