Skip to content

Ch6>ex 10c 10d>The calculation of pred should include intercept #97

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.

Sign up for GitHub

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

Open
PhoebeDreamer wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Ch6>ex 10c 10d>The calculation of pred should include intercept #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 12 additions & 8 deletions ch6/10.Rmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,26 +15,29 @@ B[19] = 0
B[10] = 0
eps = rnorm(p)
y = x %*% B + eps

data.full = as.data.frame(x)
colnames(data.full) = paste("col", 1:p, sep="")
data.full$y = y
```

## b
```{r}
train = sample(seq(1000), 100, replace = FALSE)
y.train = y[train,]
y.test = y[-train,]
x.train = x[train,]
x.test = x[-train,]
y.train = data.full$y[train]
y.test = data.full$y[-train]
x.train = model.matrix(y~., data=data.full[train,])
x.test = model.matrix(y~., data=data.full[-train,])
```

## c
```{r}
library(leaps)
regfit.full = regsubsets(y~., data=data.frame(x=x.train, y=y.train), nvmax=p)
regfit.full = regsubsets(y~., data=data.full[train,], nvmax=p)
val.errors = rep(NA, p)
x_cols = colnames(x, do.NULL=FALSE, prefix="x.")
for (i in 1:p) {
coefi = coef(regfit.full, id=i)
pred = as.matrix(x.train[, x_cols %in% names(coefi)]) %*% coefi[names(coefi) %in% x_cols]
pred = x.train[, names(coefi)] %*% coefi
val.errors[i] = mean((y.train - pred)^2)
}
plot(val.errors, ylab="Training MSE", pch=19, type="b")
Expand All @@ -45,7 +48,7 @@ plot(val.errors, ylab="Training MSE", pch=19, type="b")
val.errors = rep(NA, p)
for (i in 1:p) {
coefi = coef(regfit.full, id=i)
pred = as.matrix(x.test[, x_cols %in% names(coefi)]) %*% coefi[names(coefi) %in% x_cols]
pred = as.matrix(x.test[, names(coefi)]) %*% coefi
val.errors[i] = mean((y.test - pred)^2)
}
plot(val.errors, ylab="Test MSE", pch=19, type="b")
Expand All @@ -68,6 +71,7 @@ Caught all but one zeroed out coefficient at x.19.
val.errors = rep(NA, p)
a = rep(NA, p)
b = rep(NA, p)
x_cols = colnames(x, do.NULL = FALSE, prefix = "col")
for (i in 1:p) {
coefi = coef(regfit.full, id=i)
a[i] = length(coefi)-1
Expand Down
Loading