我希望你一切都好, 我想分别对每一天进行预测-每次选择96个值-每天- 15分钟采样-并计算每天的MAPE。这是一个可重现的示例。请随时编辑代码或根据需要提供示例。
library(tidyverse)
library(h2o)
h2o.init(ip="localhost",port=54322,max_mem_size = "128g")
data(Boston, package = "MASS")
names(Boston)
[1] "crim" "zn" "indus" "chas" "nox" "rm" "age" "dis" "rad" "tax" "ptratio"
[12] "black" "lstat" "medv"
set.seed(4984)
#Added 15 minute Time and date interval
Boston$date<- seq(as.POSIXct("01-09-2017 03:00", format = "%d-%m-%Y %H:%M",tz=""), by = "15 min", length = 506)
#select first 333 values to be trained and the rest to be test data
train = Boston[1:333,]
test = Boston[334:506,]
#Dropped the date and time
train_data_finialized <- subset(train, select=-c(date))
test_data_finialized <- test
#Converted the dataset to h2o object.
train_h2o<- as.h2o(train_data_finialized)
#test_h2o<- as.h2o(test)
#Select the target and feature variables for h2o model
y <- "medv" #target
x <- names(train_data_finialized) %>% setdiff(y) #feature variables
# Number of CV folds (to generate level-one data for stacking)
nfolds <- 5
#Replaced RF model by GBM because GBM run faster
# Train & Cross-validate a GBM
my_gbm <- h2o.gbm(x = x,
y = y,
training_frame = train_h2o,
nfolds = nfolds,
fold_assignment = "Modulo",
keep_cross_validation_predictions = TRUE,
seed = 1)
mape_calc <- function(sub_df) {
p <- h2o.predict(my_gbm, as.h2o(sub_df))
pred <- as.vector(p)
actual <- sub_df$medv
mape <- 100 * mean(abs((actual - pred)/actual))
new_df <- data.frame(date = sub_df$date[[1]], mape = mape)
return(new_df)
}
# LIST OF ONE-ROW DATAFRAMES
df_list <- by(test_data_finialized, test_data_finialized$date, mape_calc)
final_df <- do.call(rbind, df_list)