biglasso (version 1.0-1)

predict.cv.biglasso: Model predictions based on a fitted "cv.biglasso" object.

Description

Extract predictions from a fitted cv.biglasso object.

Usage

"predict"(object, X, row.idx = 1:nrow(X),  type = c("link", "response", "class", "coefficients", "vars", "nvars"),  lambda = object$lambda.min, which = object$min, ...)
"coef"(object, lambda = object$lambda.min, which = object$min, ...)

Arguments

object

A fitted "cv.biglasso" model object.

X

Matrix of values at which predictions are to be made. It must be a big.matrix object. Not used for type="coefficients".

row.idx

Similar to that in biglasso, it's a vector of the row indices of X that used for the prediction. 1:nrow(X) by default.

type

Type of prediction: "link" returns the linear predictors; "response" gives the fitted values; "class" returns the binomial outcome with the highest probability; "coefficients" returns the coefficients; "vars" returns a list containing the indices and names of the nonzero variables at each value of lambda; "nvars" returns the number of nonzero coefficients at each value of lambda.

lambda

Values of the regularization parameter lambda at which predictions are requested. The default value is the one corresponding to the minimum cross-validation error.

which

Indices of the penalty parameter lambda at which predictions are requested. The default value is the index of lambda corresponding to lambda.min. Note: this is overridden if lambda is specified.

...

Not used.

Value

type.

See Also

biglasso, cv.biglasso

Examples

## predict.cv.biglasso
data(heart)
X <- as.matrix(heart[,1:9])
y <- heart$chd
X <- as.big.matrix(X)
## Not run: 
# cvfit <- cv.biglasso(X, y, penalty = 'lasso', family = "binomial")
# coef(cvfit)
# predict(cvfit, X, type = "response")
# predict(cvfit, X, type = "link")
# predict(cvfit, X, type = "class")
# ## End(Not run)