# You can write R code here and then click "Run" to run it on our platform

library(readr)
library(MASS)
library(randomForest)
# The competition datafiles are in the directory ../input
# Read competition data files:
training <- read_csv("../input/train.csv")
test <- read_csv("../input/test.csv")

test$label<-rep(NA,nrow(test))
data<-rbind(training,test)
data$label<-as.factor(data$label)

data2<-data[,-(which(colSums (data[,2:785], na.rm = FALSE, dims = 1)<= 2610)+1)]

model.rf<-randomForest(label~.,data = data2[1:42000,],ntree=50)
model.pre<-predict(model.rf,newdata=data2[1:42000,])
mean(data2$label[1:42000]==model.pre)
model.test<-predict(model.rf,newdata=data2[42001:70000,])
output<-data.frame(ImageId=1:28000, Label=model.test)

write.csv(output, file = 'digit_recognition_sol.csv', row.names = F)