R2_Score() is inconsistent with other methods

[MaurizioSicorello]

When trying to compute R-Squared from predicted and actual values, the results from R2_Score() did not match other methods. (they were very large and negative).

Here is some R-Code to reproduce this issue:

`x = rnorm(20)
y = rnorm(20)

test = lm(y~x)
summary(test)
y_pred = predict(test)

MLmetrics

R2_Score(y, y_pred)

squared correlation

cor(y_pred, y)^2

sums of squares formula

PRESS = sum((y - y_pred)^2)
SS = sum((y - mean(y))^2)
1 - (PRESS/SS)`

[hadjipantelis]

The example presented uses the wrong order of input arguments.