To meke predictions in memory

cmf_krr_pred_mem(model, kernels_pred, y_exp, print_pred = TRUE, plot_pred = TRUE, ...)

Arguments

model

kernels_pred

y_exp

print_pred

plot_pred

Details

Value

References

Note

See also

Examples

##---- Should be DIRECTLY executable !! ---- ##-- ==> Define data, use random, ##-- or do help(data=index) for the standard data sets. ## The function is currently defined as function (model, kernels_pred, y_exp, print_pred = TRUE, plot_pred = TRUE, ...) { alphas_pred <- kernels_pred$alphas y_train <- model$y_exp K_pred <- cmf_calc_combined_kernels(kernels_pred, model$h, model$alpha, alphas_pred) y_pred <- K_pred %*% model$a + model$b if (!is.na(y_exp[1])) { if (print_pred) { regr <- regr_param(y_pred, y_exp) r2ex <- regr_param_ex(y_pred, y_exp, model$y_exp) cat(sprintf("R2pred=%g RMSEpred=%g (%g%%) R2pred_ex=%g\n", regr$R2, regr$RMSE, regr$RMSE_pc, r2ex)) flush.console() } if (plot_pred) { cinf_plotxy(y_pred, y_exp, xlab = "Predicted", ylab = "Experiment", main = "Scatter Plot for External Prediction") abline(coef = c(0, 1)) } } y_pred }
#> function (model, kernels_pred, y_exp, print_pred = TRUE, plot_pred = TRUE, #> ...) #> { #> alphas_pred <- kernels_pred$alphas #> y_train <- model$y_exp #> K_pred <- cmf_calc_combined_kernels(kernels_pred, model$h, #> model$alpha, alphas_pred) #> y_pred <- K_pred %*% model$a + model$b #> if (!is.na(y_exp[1])) { #> if (print_pred) { #> regr <- regr_param(y_pred, y_exp) #> r2ex <- regr_param_ex(y_pred, y_exp, model$y_exp) #> cat(sprintf("R2pred=%g RMSEpred=%g (%g%%) R2pred_ex=%g\n", #> regr$R2, regr$RMSE, regr$RMSE_pc, r2ex)) #> flush.console() #> } #> if (plot_pred) { #> cinf_plotxy(y_pred, y_exp, xlab = "Predicted", ylab = "Experiment", #> main = "Scatter Plot for External Prediction") #> abline(coef = c(0, 1)) #> } #> } #> y_pred #> } #> <environment: 0x10ea59608>