Created
September 7, 2019 20:46
-
-
Save ianjohns/9abd4980cb8136a8bc4e651e45b56864 to your computer and use it in GitHub Desktop.
R neuralnet package
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#cars_19 data set | |
#neural network with 2 hidden layers (7 neurons and 3 neurons) | |
#raw data | |
#https://www.fueleconomy.gov/feg/epadata/19data.zip | |
library(neuralnet) | |
library(caret) | |
#load("~/R_Cars_19/Data/cars_19.Rdata") | |
title <- "Neural Network" | |
maxs <- apply(cars_19[, c(1:3, 5, 8)], 2, max) | |
mins <- apply(cars_19[, c(1:3, 5, 8)], 2, min) | |
scaled <- as.data.frame(scale(cars_19[, c(1:3, 5, 8)], center = mins, scale = maxs - mins)) | |
tmp <- data.frame(scaled, cars_19[, c(4, 6, 7, 9:12)]) | |
n <- names(cars_19) | |
f <- as.formula(paste("fuel_economy_combined ~", paste(n[!n %in% "fuel_economy_combined"], collapse = " + "))) | |
m <- model.matrix(f, data = tmp) | |
m <- as.matrix(data.frame(m, tmp[, 1])) | |
colnames(m)[28] <- "fuel_economy_combined" | |
set.seed(123) | |
indices <- sample(1:nrow(cars_19), size = 0.75 * nrow(cars_19)) | |
train <- m[indices,] | |
test <- m[-indices,] | |
n <- colnames(m)[2:28] | |
f <- as.formula(paste("fuel_economy_combined ~", paste(n[!n %in% "fuel_economy_combined"], collapse = " + "))) | |
m1_nn <- neuralnet(f, | |
data = train, | |
hidden = c(7,3), | |
linear.output = TRUE) | |
pred_nn <- predict(m1_nn, test) | |
yhat <-pred_nn * (max(cars_19$fuel_economy_combined) - min(cars_19$fuel_economy_combined)) + min(cars_19$fuel_economy_combined) | |
y <- test[, 28] * (max(cars_19$fuel_economy_combined) - min(cars_19$fuel_economy_combined)) +min(cars_19$fuel_economy_combined) | |
postResample(yhat, y) | |
################################## | |
#20 fold cv | |
set.seed(123) | |
stats <- NULL | |
for (i in 1:20) { | |
indices <- sample(1:nrow(cars_19), size = 0.75 * nrow(cars_19)) | |
train_tmp <- m[indices, ] | |
test_tmp <- m[-indices, ] | |
nn_tmp <- neuralnet(f, | |
data = train_tmp, | |
hidden = c(7, 3), | |
linear.output = TRUE) | |
pred_nn_tmp <- predict(nn_tmp, test_tmp) | |
yhat <- pred_nn_tmp * (max(cars_19$fuel_economy_combined) - min(cars_19$fuel_economy_combined)) + min(cars_19$fuel_economy_combined) | |
y <- test_tmp[, 28] * (max(cars_19$fuel_economy_combined) - min(cars_19$fuel_economy_combined)) + min(cars_19$fuel_economy_combined) | |
stats_tmp <- postResample(yhat, y) | |
stats <- rbind(stats, stats_tmp) | |
cat(i, "\n") | |
} | |
mean(stats[, 1] ^ 2) #avg mse 4.261991 | |
mean(stats[, 1] ^ 2) ^ .5 #avg rmse 2.064459 | |
colMeans(stats) #ignore rmse | |
#RMSE Rsquared MAE | |
#xxx 0.880502 1.466458 | |
plot(nn_tmp,rep="best") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment