gistfile1.r

cat("\014")
rm(list=ls())

seo_rev=read.csv("D:\\hsong\\SkyDrive\\Public\\seo_kw_rev_train.csv", header=T, skip=2, na.string='.')

names(seo_rev)<-tolower(names(seo_rev))
lapply(seo_rev, class)
str(seo_rev)
head(seo_rev)

all_var<-colnames(seo_rev)
## check which variables have missing value, and how many of the values are missing
getna<-function(x) sum(is.na(x)>0)
apply(seo_rev, 2, getna)