# 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(dplyr)


# 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
train <- fread("../input/train.csv")
#system("ls ../input")

# Any results you write to the current directory are saved as output.
trainTable <- train$hotel_cluster %>% 
                table() %>% 
                data.table()

ggplot(data = trainTable, aes(x = factor(.), y = N)) + 
    geom_bar(stat = "identity") +
    xlab("cluster") + theme_bw() + 
    theme(axis.text.x = element_text(angle = 90, hjust = 1))