R Notebook
Preprocess the data
- August
library(tidyr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniond1<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/KiwiMotel/August.csv")
#
d2<-d1[-26,]
d2<-d2 %>% tidyr::gather(Days,Status,X1:X31)
head(d2)## Rooms Types Days Status
## 1 Unit 1 King Studios X1 0
## 2 Unit 2 King Studios X1 0
## 3 Unit 3 King Studios X1 0
## 4 Unit 4 King Studios X1 0
## 5 Unit 5 King Studios X1 1
## 6 Unit 6 King Studios X1 1#
d_rate<-d1[26,]
d_rate<-as.vector(d_rate)
d_rate<-data.frame(d_rate)
d_rate<-d_rate %>% tidyr::gather(Days,Rate,X1:X31)
d_rate<-d_rate[,c(3,4)]
head(d_rate)## Days Rate
## 1 X1 32
## 2 X2 52
## 3 X3 32
## 4 X4 36
## 5 X5 44
## 6 X6 52d_Aug<-full_join(d2,d_rate,by="Days")
d_Aug$Days<-gsub("X","",d_Aug$Days)
d_Aug$Month<-c("August")
head(d_Aug)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 0 32 August
## 2 Unit 2 King Studios 1 0 32 August
## 3 Unit 3 King Studios 1 0 32 August
## 4 Unit 4 King Studios 1 0 32 August
## 5 Unit 5 King Studios 1 1 32 August
## 6 Unit 6 King Studios 1 1 32 AugustAugust<-d_Aug
head(August)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 0 32 August
## 2 Unit 2 King Studios 1 0 32 August
## 3 Unit 3 King Studios 1 0 32 August
## 4 Unit 4 King Studios 1 0 32 August
## 5 Unit 5 King Studios 1 1 32 August
## 6 Unit 6 King Studios 1 1 32 August- September
# September
d1<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/KiwiMotel/September.csv")
#
d2<-d1[-26,]
d2<-d2 %>% tidyr::gather(Days,Status,X1:X30)
head(d2)## Rooms Types Days Status
## 1 Unit 1 King Studios X1 1
## 2 Unit 2 King Studios X1 1
## 3 Unit 3 King Studios X1 1
## 4 Unit 4 King Studios X1 1
## 5 Unit 5 King Studios X1 1
## 6 Unit 6 King Studios X1 0#
d_rate<-d1[26,]
d_rate<-as.vector(d_rate)
d_rate<-data.frame(d_rate)
d_rate<-d_rate %>% tidyr::gather(Days,Rate,X1:X30)
d_rate<-d_rate[,c(3,4)]
head(d_rate)## Days Rate
## 1 X1 92
## 2 X2 60
## 3 X3 88
## 4 X4 16
## 5 X5 40
## 6 X6 40d_Sep<-full_join(d2,d_rate,by="Days")
d_Sep$Days<-gsub("X","",d_Sep$Days)
d_Sep$Month<-c("September")
head(d_Sep)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 92 September
## 2 Unit 2 King Studios 1 1 92 September
## 3 Unit 3 King Studios 1 1 92 September
## 4 Unit 4 King Studios 1 1 92 September
## 5 Unit 5 King Studios 1 1 92 September
## 6 Unit 6 King Studios 1 0 92 SeptemberSeptember<-d_Sep
head(September)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 92 September
## 2 Unit 2 King Studios 1 1 92 September
## 3 Unit 3 King Studios 1 1 92 September
## 4 Unit 4 King Studios 1 1 92 September
## 5 Unit 5 King Studios 1 1 92 September
## 6 Unit 6 King Studios 1 0 92 September- October
# October
d1<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/KiwiMotel/October.csv")
#
d2<-d1[-26,]
d2<-d2 %>% tidyr::gather(Days,Status,X1:X31)
head(d2)## Rooms Types Days Status
## 1 Unit 1 King Studios X1 1
## 2 Unit 2 King Studios X1 0
## 3 Unit 3 King Studios X1 0
## 4 Unit 4 King Studios X1 0
## 5 Unit 5 King Studios X1 1
## 6 Unit 6 King Studios X1 0#
d_rate<-d1[26,]
d_rate<-as.vector(d_rate)
d_rate<-data.frame(d_rate)
d_rate<-d_rate %>% tidyr::gather(Days,Rate,X1:X31)
d_rate<-d_rate[,c(3,4)]
head(d_rate)## Days Rate
## 1 X1 56
## 2 X2 16
## 3 X3 36
## 4 X4 24
## 5 X5 52
## 6 X6 48d_Oct<-full_join(d2,d_rate,by="Days")
d_Oct$Days<-gsub("X","",d_Oct$Days)
d_Oct$Month<-c("October")
head(d_Oct)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 56 October
## 2 Unit 2 King Studios 1 0 56 October
## 3 Unit 3 King Studios 1 0 56 October
## 4 Unit 4 King Studios 1 0 56 October
## 5 Unit 5 King Studios 1 1 56 October
## 6 Unit 6 King Studios 1 0 56 OctoberOctober<-d_Oct
head(October)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 56 October
## 2 Unit 2 King Studios 1 0 56 October
## 3 Unit 3 King Studios 1 0 56 October
## 4 Unit 4 King Studios 1 0 56 October
## 5 Unit 5 King Studios 1 1 56 October
## 6 Unit 6 King Studios 1 0 56 October- November
# November
d1<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/KiwiMotel/November.csv")
#
d2<-d1[-26,]
d2<-d2 %>% tidyr::gather(Days,Status,X1:X30)
head(d2)## Rooms Types Days Status
## 1 Unit 1 King Studios X1 1
## 2 Unit 2 King Studios X1 1
## 3 Unit 3 King Studios X1 1
## 4 Unit 4 King Studios X1 0
## 5 Unit 5 King Studios X1 0
## 6 Unit 6 King Studios X1 1#
d_rate<-d1[26,]
d_rate<-as.vector(d_rate)
d_rate<-data.frame(d_rate)
d_rate<-d_rate %>% tidyr::gather(Days,Rate,X1:X30)
d_rate<-d_rate[,c(3,4)]
head(d_rate)## Days Rate
## 1 X1 36
## 2 X2 36
## 3 X3 32
## 4 X4 44
## 5 X5 40
## 6 X6 8d_Nov<-full_join(d2,d_rate,by="Days")
d_Nov$Days<-gsub("X","",d_Nov$Days)
d_Nov$Month<-c("November")
November<-d_Nov
head(November)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 36 November
## 2 Unit 2 King Studios 1 1 36 November
## 3 Unit 3 King Studios 1 1 36 November
## 4 Unit 4 King Studios 1 0 36 November
## 5 Unit 5 King Studios 1 0 36 November
## 6 Unit 6 King Studios 1 1 36 November- December
# December
d1<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/KiwiMotel/December.csv")
#
d2<-d1[-26,]
d2<-d2 %>% tidyr::gather(Days,Status,X1:X30)
head(d2)## Rooms Types Days Status
## 1 Unit 1 King Studios X1 1
## 2 Unit 2 King Studios X1 0
## 3 Unit 3 King Studios X1 1
## 4 Unit 4 King Studios X1 0
## 5 Unit 5 King Studios X1 1
## 6 Unit 6 King Studios X1 0#
d_rate<-d1[26,]
d_rate<-as.vector(d_rate)
d_rate<-data.frame(d_rate)
d_rate<-d_rate %>% tidyr::gather(Days,Rate,X1:X30)
d_rate<-d_rate[,c(3,4)]
head(d_rate)## Days Rate
## 1 X1 32
## 2 X2 28
## 3 X3 24
## 4 X4 8
## 5 X5 32
## 6 X6 40d_Dec<-full_join(d2,d_rate,by="Days")
d_Dec$Days<-gsub("X","",d_Dec$Days)
d_Dec$Month<-c("December")
head(d_Dec)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 32 December
## 2 Unit 2 King Studios 1 0 32 December
## 3 Unit 3 King Studios 1 1 32 December
## 4 Unit 4 King Studios 1 0 32 December
## 5 Unit 5 King Studios 1 1 32 December
## 6 Unit 6 King Studios 1 0 32 DecemberDecember<-d_Dec
head(December)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 1 32 December
## 2 Unit 2 King Studios 1 0 32 December
## 3 Unit 3 King Studios 1 1 32 December
## 4 Unit 4 King Studios 1 0 32 December
## 5 Unit 5 King Studios 1 1 32 December
## 6 Unit 6 King Studios 1 0 32 December- Combining all months to form a complete dataset
df<-rbind(August,September,October,November,December)
head(df)## Rooms Types Days Status Rate Month
## 1 Unit 1 King Studios 1 0 32 August
## 2 Unit 2 King Studios 1 0 32 August
## 3 Unit 3 King Studios 1 0 32 August
## 4 Unit 4 King Studios 1 0 32 August
## 5 Unit 5 King Studios 1 1 32 August
## 6 Unit 6 King Studios 1 1 32 August- Plot some basic graphs
df$Days<-as.numeric(df$Days)
df$Status<-as.factor(df$Status)
glimpse(df)## Observations: 3,800
## Variables: 6
## $ Rooms <fctr> Unit 1, Unit 2, Unit 3, Unit 4, Unit 5, Unit 6, Unit 7...
## $ Types <fctr> King Studios, King Studios, King Studios, King Studios...
## $ Days <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ Status <fctr> 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, ...
## $ Rate <int> 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32,...
## $ Month <chr> "August", "August", "August", "August", "August", "Augu...# Boxplot
library(ggplot2)
ggplot(data=df,aes(x=Month,y=Rate)) + geom_boxplot(color=4,fill=3)
August
# Boxplot
# August
df1<-df[df$Month=="August",]
ggplot(data=df1,aes(x=Days,y=Rate)) + geom_line(color=4)
ggplot(data=df1,aes(x=Status,y=Rate)) + geom_boxplot(aes(fill=Status))
ggplot(data=df,aes(x=Days,y=Rate)) + geom_line(color=4)