H2o Data import and Data export

首先给出的是h2o在R语言里面的下载，

if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }

# Next, we download packages that H2O depends on.
pkgs <- c("RCurl","jsonlite")
for (pkg in pkgs) {
  if (! (pkg %in% rownames(installed.packages()))) { install.packages(pkg) }
}

# Now we download, install and initialize the H2O package for R.
install.packages("h2o", type="source", repos="http://h2o-release.s3.amazonaws.com/h2o/rel-wright/8/R")

# Finally, let's load H2O and start up an H2O cluster
library(h2o)
h2o.init()

直接复制粘贴到你的r里面运行就好了

Load file

# Load CSV file
df <- h2o.importFile()
df <- h2o.uploadFile()

# Load Directly from R
as.h2o() 

数据管理

# 管理数据
h2o.rm()
h2o.removeAll()
h2o.ls()

数据的基本描述

# Data summaries
h2o.describe(data)
h2o.quantile(data)
h2o.levels(data)

一些简单的函数

# 数据转换
h2o.sd()
h2o.mean()
h2o.cor()

分组聚合

# 分组聚合
iris.h2o <- as.h2o(iris)
h2o.group_by(iris.h2o,by = 'Species',nrow('Species'),mean('Sepal.Length'),
             mean('Sepal.Width'),mean('Petal.Length'),mean('Petal.Width'))

mean('Sepal.Width'),mean('Petal.Length'),mean('Petal.Width'))
     Species nrow mean_Sepal.Length mean_Sepal.Width
1     setosa   50             5.006            3.428
2 versicolor   50             5.936            2.770
3  virginica   50             6.588            2.974
  mean_Petal.Length mean_Petal.Width
1             1.462            0.246
2             4.260            1.326
3             5.552            2.026

[3 rows x 6 columns] 

数据划分

# 数据划分
part <- h2o.splitFrame(iris.h2o,ratios = c(0.6,0.2))
trin <- part[[1]]
test <- part[[2]]
valid <- part[[3]]
rm(part)

export data

# Get data out of h2o
h2o.downloadCSV()
h2o.download_mojo()
h2o.download_pojo()
h2o.exportFile()
h2o.saveModel()