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

library(readr)

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

# Write to the log:
cat(sprintf("Training set has %d rows and %d columns\n", nrow(train), ncol(train)))
cat(sprintf("Test set has %d rows and %d columns\n", nrow(test), ncol(test)))

# Generate output files with write_csv(), plot() or ggplot()
# Any files you write to the current directory get shown as outputs
# Creates a simple random forest benchmark

library(randomForest)
library(readr)

set.seed(0)

numTrain <- 10000
numTrees <- 100

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

rows <- sample(1:nrow(train), numTrain)
labels <- as.factor(train[rows,1])
train <- train[rows,-1]

rf <- randomForest(train, labels, xtest=test, ntree=numTrees)
predictions <- data.frame(ImageId=1:nrow(test), Label=levels(labels)[rf$test$predicted])
head(predictions)

write_csv(predictions, "rf_benchmark.csv")