library(randomForest)
library(readr)

set.seed(1)

numTrain <- 10000
numTrees <- 25

train <- read_csv("../input/train.csv")
train <- train[1:20000,]
rows <- sample(1:nrow(train), numTrain)
labels <- as.factor(train[rows,1]$label)
test <- train[-rows,]
train <- train[rows,-1]


rf <- randomForest(train, labels, xtest=test[,-1], ntree=numTrees)
predicted <- data.frame(rf$test$predicted)

predicted['actual']=test[,1]
colnames(predicted)[1]='predicted'
predicted['matched']=(predicted['actual']==predicted['predicted'])
head(predicted,20)
print(colSums(predicted['matched']))