Created
June 30, 2022 17:28
lightGBM Light Gradient Boosting Machine
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
library(lightgbm) | |
library(caret) | |
library(fastDummies) | |
#load("~/R_Cars_19/Data/cars_19.Rdata") | |
title <- "light gbm" | |
tmp <- cars_19[, c(4, 6, 7, 9:12)] | |
tmp1 <- dummy_cols(tmp) | |
tmp1 <- tmp1[,8:36] | |
d <- data.frame(cars_19[, c(1:3, 5, 8)], tmp1) | |
m <- as.matrix(d) | |
set.seed(123) | |
indices <- sample(1:nrow(cars_19), size = 0.75 * nrow(cars_19)) | |
train <- m[indices,] | |
test <- m[-indices,] | |
y_train <- train[,1] | |
y_test <- test[,1] | |
train_lgb <- lgb.Dataset(train[,2:34],label=y_train) | |
test_lgb <- lgb.Dataset.create.valid(train_lgb,test[,2:34],label = y_test) | |
#base untuned lightgbn | |
light_gbn_base <- lgb.train( | |
params = list( | |
objective = "regression", | |
metric = "l2" | |
), | |
data = train_lgb | |
) | |
yhat_fit_base <- predict(light_gbn_base,train[,2:34]) | |
yhat_predict_base <- predict(light_gbn_base,test[,2:34]) | |
rmse_fit_base <- RMSE(y_train,yhat_fit_base) | |
rmse_predict_base <- RMSE(y_test,yhat_predict_base) | |
################# | |
#grid search | |
#create hyperparameter grid | |
num_leaves =seq(20,28,1) | |
max_depth = round(log(num_leaves) / log(2),0) | |
num_iterations = seq(200,400,50) | |
early_stopping_rounds = round(num_iterations * .1,0) | |
hyper_grid <- expand.grid(max_depth = max_depth, | |
num_leaves =num_leaves, | |
num_iterations = num_iterations, | |
early_stopping_rounds=early_stopping_rounds, | |
learning_rate = seq(.45, .50, .005)) | |
hyper_grid <- unique(hyper_grid) | |
rmse_fit <- NULL | |
rmse_predict <- NULL | |
for (j in 1:nrow(hyper_grid)) { | |
set.seed(123) | |
light_gbn_tuned <- lgb.train( | |
params = list( | |
objective = "regression", | |
metric = "l2", | |
max_depth = hyper_grid$max_depth[j], | |
num_leaves =hyper_grid$num_leaves[j], | |
num_iterations = hyper_grid$num_iterations[j], | |
early_stopping_rounds=hyper_grid$early_stopping_rounds[j], | |
learning_rate = hyper_grid$learning_rate[j] | |
#feature_fraction = .9 | |
), | |
valids = list(test = test_lgb), | |
data = train_lgb | |
) | |
yhat_fit_tuned <- predict(light_gbn_tuned,train[,2:34]) | |
yhat_predict_tuned <- predict(light_gbn_tuned,test[,2:34]) | |
rmse_fit[j] <- RMSE(y_train,yhat_fit_tuned) | |
rmse_predict[j] <- RMSE(y_test,yhat_predict_tuned) | |
cat(j, "\n") | |
} | |
min(rmse_fit) | |
min(rmse_predict) | |
hyper_grid[which.min(rmse_fit),] | |
hyper_grid[which.min(rmse_predict),] | |
rmse_diff <- rmse_fit - rmse_predict | |
rmse_models <- data.frame(rmse_fit,rmse_predict, rmse_diff) | |
rmse_models_sort <- rmse_models[order(rmse_diff),] | |
set.seed(123) | |
light_gbn_final <- lgb.train( | |
params = list( | |
objective = "regression", | |
metric = "l2", | |
max_depth = 4, | |
num_leaves =23, | |
num_iterations = 400, | |
early_stopping_rounds=40, | |
learning_rate = .48 | |
#feature_fraction = .8 | |
), | |
valids = list(test = test_lgb), | |
data = train_lgb | |
) | |
yhat_fit_final <- predict(light_gbn_final,train[,2:34]) | |
yhat_predict_final <- predict(light_gbn_final,test[,2:34]) | |
rmse_fit_final<- RMSE(y_train,yhat_fit_final) | |
rmse_predict_final <- RMSE(y_test,yhat_predict_final) | |
plot(y_test,yhat_predict_final,main=title, xlab="actual", ylab="predicted") | |
abline(lm(yhat_predict_final~y_test)) | |
lgb_imp <- lgb.importance(light_gbn_final) | |
lgb.plot.importance(lgb_imp) | |
r <- y_test - yhat_predict_final | |
sum(abs(r) <= rmse_predict_final) / length(y_test) #[1] 0.7547771 | |
sum(abs(r) <= 2 * rmse_predict_final) / length(y_test) #[1] 0.9522293 | |
summary(r) | |
#Min. 1st Qu. Median Mean 3rd Qu. Max. | |
#-11.21159 -0.96398 0.06337 -0.02708 0.96796 5.77861 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment