# This R environment comes with all of CRAN preinstalled, as well as many other helpful packages
# The environment is defined by the kaggle/rstats docker image: https://github.com/kaggle/docker-rstats
# For example, here's several helpful packages to load in 

library(ggplot2) # Data visualization
library(readr) # CSV file I/O, e.g. the read_csv function
library(data.table)
library(rpart)
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

system("ls ../input")

# Any results you write to the current directory are saved as output.
click_train <- fread("../input/clicks_train.csv")
click_train <- click_train[(1:10000000),]

events <- fread("../input/events.csv")
#events <- events[-(303066),]

#m <- merge(click_train,events,by = "display_id")

#doc1 <- fread("../input/documents_topics.csv")
#doc1 <- doc1[c(1:1000000),]

#rm(click_train)
#rm(events)

#m1 <- merge(doc1,m,by = "document_id")

#m1 <- subset(m1,select=c("document_id","topic_id","confidence_level","display_id","ad_id","clicked","platform","timestamp"))

#m1$platform <- as.integer(m1$platform)

#str(m1)

#tree <- rpart(clicked ~ document_id + topic_id + confidence_level + display_id + ad_id + platform + timestamp, data = m1)

#rm(m1)

#click_test <- fread("../input/clicks_test.csv")

#events <- fread("../input/events.csv")
#events <- events[-(303066),]

#tm <- merge(click_test,events,by = "display_id")