
ud <- read.table('~/Research/DataSets/MovieLens/ML100K/ml-100k/u.data',
   header=FALSE,sep='\t')
z <- tapply(ud$V3,ud$V1,mean)
uu <- read.table('~/Research/DataSets/MovieLens/ML100K/ml-100k/u.user',
   header=F,sep='|')
names(uu) <- c('userid','age','gender','occup','zip')
uu$gender <- as.integer(uu$gender == 'M')
uu$avg_rat <- z
q <- lm(avg_rat ~ age + gender,data=uu)
summary(q)

uu$ni <- tapply(ud$V3,ud$V1,length)
summary(lm(ni ~ age + gender,data=uu))

