library(readr)

cat("reading the train and test data\n")
train <- read_csv("../input/train.csv")
test  <- read_csv("../input/test.csv")
store <- read_csv("../input/store.csv")

# removing the date column (since elements are extracted) and also StateHoliday which has a lot of NAs (may add it back in later)
train <- merge(train,store)
test <- merge(test,store)

# There are some NAs in the integer columns so conversion to zero
train[is.na(train)]   <- 0
test[is.na(test)]   <- 0

cat("train data column names and details\n")
names(train)
str(train)
summary(train)
cat("test data column names and details\n")
names(test)
str(test)
summary(test)

# looking at only stores that were open in the train set
# may change this later
train <- train[ which(train$Open=='1'),]
train <- train[ which(train$Sales!='0'),]
# seperating out the elements of the date column for the train set
train$month <- as.integer(format(train$Date, "%m"))
train$year <- as.integer(format(train$Date, "%y"))
train$day <- as.integer(format(train$Date, "%d"))

# removing the date column (since elements are extracted) and also StateHoliday which has a lot of NAs (may add it back in later)
train <- train[,-c(3,8)]

# seperating out the elements of the date column for the test set
test$month <- as.integer(format(test$Date, "%m"))
test$year <- as.integer(format(test$Date, "%y"))
test$day <- as.integer(format(test$Date, "%d"))

# removing the date column (since elements are extracted) and also StateHoliday which has a lot of NAs (may add it back in later)
test <- test[,-c(4,7)]

feature.names <- names(train)[c(1,2,5:19)]
cat("Feature Names\n")
feature.names

cat("assuming text variables are categorical & replacing them with numeric ids\n")
for (f in feature.names) {
  if (class(train[[f]])=="character") {
    levels <- unique(c(train[[f]], test[[f]]))
    train[[f]] <- as.integer(factor(train[[f]], levels=levels))
    test[[f]]  <- as.integer(factor(test[[f]],  levels=levels))
  }
}

cat("train data column names after slight feature engineering\n")
names(train)
cat("test data column names after slight feature engineering\n")
names(test)

DayOfWeek<-unique(test$DayOfWeek)
buf<-NULL

for(ic in DayOfWeek){
set.seed(200)

train1<-train[train$DayOfWeek==ic,]
test1<-test[test$DayOfWeek==ic,]

label=log(train1$Sales+1)
clf<-lm(label~., data=train1[,feature.names])

pr <- exp(predict(clf, test1[,feature.names])) -1
test1$Sales<-pr
buf<-rbind(buf,test1)
}   # end calc Store


sub <- data.frame(Id=buf$Id, Sales=buf$Sales)
cat("saving the submission file\n")
sub<-sub[order(sub$Id),]
write_csv(sub, "DayOfWeek_LM.csv")