预测变量中不允许出现随机森林错误NA

Question

Hi I am using the following r script to build a random forest:

# load the necessary libraries                      
library(randomForest)


testPP<-numeric()


# load the dataset
QdataTrain <- read.csv('train.csv',header = FALSE)
QdataTest <- read.csv('test.csv',header = FALSE)

QdataTrainX <- subset(QdataTrain,select=-V1)
QdataTrainY<-as.factor(QdataTrain$V1)   

QdataTestX <- subset(QdataTest,select=-V1)
QdataTestY<-as.factor(QdataTest$V1)
mdl <- randomForest(QdataTrainX, QdataTrainY) 

where I am getting the following error:

Error in randomForest.default(QdataTrainX, QdataTrainY) : 
  NA not permitted in predictors

however i see no occurence of NA in my data.

for reference here is my data:

https://docs.google.com/file/d/0B0iDswLYaZ0zUFFsT01BYlRZU0E/edit

does anyone know why this error is being thrown? I'll keep looking in the mean time. Thanks in advance for any help!

Answer 1

The given data does contain some missing values (7 in particular):

sapply(QdataTrainX, function(x) sum(is.na(x)))

## V2  V3  V4  V5  V6  V7  V8  V9 V10 V11 V12 V13 V14 V15 V16 
## 0   0   0   0   0   0   0   0   0   0   0   0   0   0   0 
## V17 V18 V19 V20 V21 V22 V23 V24 V25 V26 V27 V28 V29 
## 0   0   0   0   0   0   1   1   1   1   1   1   1 

Therefore columns V23 to V29 have one missing value each

which(is.na(QdataTrainX$V23))

## 318

Gives the row number for that.