以下是我回答的问题:R或Python - 循环测试数据 - 预测验证接下来的24小时(每天96个值)
我想使用H2o软件包预测明天的情况。 您可以在上述链接中找到有关我的数据集的详细说明。
H2o中的数据维度不同。
因此,在进行预测后,我想计算MAPE。
我必须将训练和测试数据更改为H2o格式。
train_h2o <- as.h2o(train_data)
test_h2o <- as.h2o(test_data)
mape_calc <- function(sub_df) {
pred <- predict.glm(glm_model, sub_df)
actual <- sub_df$Ptot
mape <- 100 * mean(abs((actual - pred)/actual))
new_df <- data.frame(date = sub_df$date[[1]], mape = mape)
return(new_df)
}
# LIST OF ONE-ROW DATAFRAMES
df_list <- by(test_data, test_data$date, map_calc)
# FINAL DATAFRAME
final_df <- do.call(rbind, df_list)
上述代码可以很好地进行“非H2O”预测验证,并计算每天的MAPE。
我试图将H2O预测模型转换为普通格式,但根据以下链接所述,这是不可能的:https://dev59.com/xJrga4cB1Zd3GeqPkkzr#39221269。
要在H2O中进行预测:
例如,假设我们想创建一个随机森林模型。
y <- "RealPtot" #target
x <- names(train_h2o) %>% setdiff(y) #features
rforest.model <- h2o.randomForest(y=y, x=x, training_frame = train_h2o, ntrees = 2000, mtries = 3, max_depth = 4, seed = 1122)
然后,我们可以得到完整数据集的预测结果,如下所示。
predict.rforest <- as.data.frame(h2o.predict(rforest.model, test_h2o)
但是在我的情况下,我正在尝试使用mape_calc获得一天的预测。
注意:欢迎使用R或Python进行思考。
更新2(可重现的示例):**按照@Darren Cook的步骤:
我提供了一个更简单的示例 - 波士顿房屋数据集。
library(tidyverse)
library(h2o)
h2o.init(ip="localhost",port=54322,max_mem_size = "128g")
data(Boston, package = "MASS")
names(Boston)
[1] "crim" "zn" "indus" "chas" "nox" "rm" "age" "dis" "rad" "tax" "ptratio"
[12] "black" "lstat" "medv"
set.seed(4984)
#Added 15 minute Time and date interval
Boston$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)
我现在遇到的错误如下:
Error in .h2o.doSafeREST(h2oRestApiVersion = h2oRestApiVersion, urlSuffix = page, :
ERROR MESSAGE:
提供的列类型POSIXct未知。由于参数无效,无法继续解析。