library(readr)

set.seed(0)

numTrain <- 10000
numTrees <- 25

train <- read_csv("../input/train.csv")
test <- read_csv("../input/test.csv")

rows <- sample(1:nrow(train), numTrain)
labels <- data.frame(train[rows,1])
test <- data.frame(train[-rows,-1])
testRes <- data.frame(train[-rows,1])
train <- data.frame(train[rows,-1])

isZero <- (labels$label=='4')
train$isZero <- isZero

model <- glm( isZero ~., family=binomial(link='logit'),data=train)
answers <- data.frame(Prediction=predict( model, newdata=test, type='response'))
print(dim(answers))
print(dim(testRes))
answers$expected <- ( testRes$label=='4' )
answers$correct <- testRes$label
answers$matched <- ((answers$Prediction>0.5)==answers$expected)
head( answers, 200 )