如何在R中使用h2o.group_by？

Question

我是h2o 3.10.4.8版本。

library(h2o) 

h2o.init(nthreads = -1, max_mem_size = "6g") 

data.url <- "https://raw.githubusercontent.com/DarrenCook/h2o/bk/datasets/" 

iris.hex <- paste0(data.url, "iris_wheader.csv") %>% 
    h2o.importFile(destination_frame = "iris.hex") 

y <- "class" 
x <- setdiff(names(iris.hex), y) 

現在，我想通過列class算在iris.hex行數只是爲了讓使用h2o.group_by的竅門。這是我閱讀文檔後嘗試：

h2o.group_by(iris.hex, by = list("class"), h2o.nrow) 

這將導致以下錯誤：

Error in is.H2OFrame(x) : object 'group.cols' not found 

的文件沒有提供一個例子使用，所以我不知道如果我甚至稱這功能正確。

Answer 1

爲了您的具體問題，你可以這樣做：

library(h2o) 
h2o.init(strict_version_check = F) 
iris_wheader = "http://h2o-public-test-data.s3.amazonaws.com/smalldata/iris/iris_wheader.csv" 

iris.hex = h2o.importFile(iris_wheader) 

iris_count <- h2o.group_by(data = iris.hex, by = "class", nrow('class'),gb.control=list(na.methods="rm")) 

你可以看到原來的框架和結果：

head(iris.hex) 

sepal_len sepal_wid petal_len petal_wid  class 
1  5.1  3.5  1.4  0.2 Iris-setosa 
2  4.9  3.0  1.4  0.2 Iris-setosa 
3  4.7  3.2  1.3  0.2 Iris-setosa 
4  4.6  3.1  1.5  0.2 Iris-setosa 
5  5.0  3.6  1.4  0.2 Iris-setosa 
6  5.4  3.9  1.7  0.4 Iris-setosa 

iris_count 

     class   nrow 
1  Iris-setosa 50 
2 Iris-versicolor 50 
3 Iris-virginica 50 

沒有爲將來的版本中添加的文檔，但這裏有一些示例

> library(h2o) 
> h2o.init() 

# Import the airlines data set and display a summary. 
> airlinesURL <- "https://s3.amazonaws.com/h2o-airlines-unpacked/allyears2k.csv" 
> airlines.hex <- h2o.importFile(path = airlinesURL, destination_frame = "airlines.hex") 
> summary(airlines.hex) 

# Find number of flights by airport 
> originFlights <- h2o.group_by(data = airlines.hex, by = "Origin", nrow("Origin"), gb.control=list(na.methods="rm")) 
> originFlights.R <- as.data.frame(originFlights) 
> originFlights.R 
Origin nrow_Origin 
1  ABE   59 
2  ABQ   876 
3  ACY   31 
... 

# Find number of flights per month 
> flightsByMonth <- h2o.group_by(data = airlines.hex, by = "Month", nrow("Month"), gb.control=list(na.methods="rm")) 
> flightsByMonth.R <- as.data.frame(flightsByMonth) 
> flightsByMonth.R 
Month nrow_Month 
1  1  41979 
2 10  1999 

# Find the number of flights in a given month based on the origin 
> cols <- c("Origin","Month") 
> flightsByOriginMonth <- h2o.group_by(data=airlines.hex, by=cols,nrow("NumberOfFlights"), gb.control=list(na.methods="rm") 
> flightsByOriginMonth.R <- as.data.frame(flightsByOriginMonth) 
> flightsByOriginMonth.R 
Origin Month nrow_NumberOfFlights 
1  ABE  1     59 
2  ABQ  1     846 
3  ABQ 10     30 
4  ACY  1     31 
5  ALB  1     75 
... 

# Find months with the highest cancellation ratio 
> which(colnames(airlines.hex)=="Cancelled") 
[1] 22 
> cancellationsByMonth <- h2o.group_by(data = airlines.hex, by = "Month", sum("Cancelled"), gb.control=list(na.methods="rm")) 
> cancellation_rate <- cancellationsByMonth$sum_Cancelled/flightsByMonth$nrow_Month 
> rates_table <- h2o.cbind(flightsByMonth$Month,cancellation_rate) 
> rates_table.R <- as.data.frame(rates_table) 
> rates_table.R 
Month sum_Cancelled 
1  1 0.025417471 
2 10 0.009504752 

# Use group_by with multiple columns. Summarize the destination, arrival delays, and departure delays for an origin 
> cols <- c("Dest", "IsArrDelayed", "IsDepDelayed") 
> originFlights <- h2o.group_by(data = airlines.hex[c("Origin",cols)], by = "Origin", sum(cols),gb.control = list(na.methods = "ignore", col.names = NULL)) 
# Note a warning because col.names null 
> res <- h2o.cbind(lapply(cols, function(x){h2o.group_by(airlines.hex,by="Origin",sum(x))}))[,c(1,2,4,6)] 
> res 
Origin sum_Dest sum_IsArrDelayed sum_IsDepDelayed 
1 ABE  5884    40    30 
2 ABQ 84505    545    370 
3 ACY  3131    9    7 
4 ALB  3646    49    50 
5 AMA  317    4    6 
6 ANC  100    0    1