mick001

# Load the raw training data and replace missing values with NA
training.data.raw <- read.csv('train.csv',header=T,na.strings=c(""))

# Output the number of missing values for each column
sapply(training.data.raw,function(x) sum(is.na(x)))

# Quick check for how many different values for each feature
sapply(training.data.raw, function(x) length(unique(x)))

# A visual way to check for missing data