Hotel room pricing
Neelam
29 December 2017
Read Data using read.csv and view Hotel room pricing
Cities <- read.csv(paste("Cities42.csv", sep=""))
View(Cities)Summary Statistics - mean, median, standard deviation
attach(Cities)
library(psych)## Warning: package 'psych' was built under R version 3.4.3describe(Cities)## vars n mean sd median trimmed
## CityName* 1 13232 18.07 11.72 16 17.29
## Population 2 13232 4416836.87 4258386.00 3046163 4040816.22
## CityRank 3 13232 14.83 13.51 9 13.30
## IsMetroCity 4 13232 0.28 0.45 0 0.23
## IsTouristDestination 5 13232 0.70 0.46 1 0.75
## IsWeekend 6 13232 0.62 0.48 1 0.65
## IsNewYearEve 7 13232 0.12 0.33 0 0.03
## Date* 8 13232 14.30 2.69 14 14.39
## HotelName* 9 13232 841.19 488.16 827 841.18
## RoomRent 10 13232 5473.99 7333.12 4000 4383.33
## StarRating 11 13232 3.46 0.76 3 3.40
## Airport 12 13232 21.16 22.76 15 16.39
## HotelAddress* 13 13232 1202.53 582.17 1261 1233.25
## HotelPincode 14 13232 397430.26 259837.50 395003 388540.47
## HotelDescription* 15 13224 581.34 363.26 567 575.37
## FreeWifi 16 13232 0.93 0.26 1 1.00
## FreeBreakfast 17 13232 0.65 0.48 1 0.69
## HotelCapacity 18 13232 62.51 76.66 34 46.03
## HasSwimmingPool 19 13232 0.36 0.48 0 0.32
## mad min max range skew
## CityName* 11.86 1.0 42 41.0 0.48
## Population 3846498.95 8096.0 12442373 12434277.0 0.68
## CityRank 11.86 0.0 44 44.0 0.69
## IsMetroCity 0.00 0.0 1 1.0 0.96
## IsTouristDestination 0.00 0.0 1 1.0 -0.86
## IsWeekend 0.00 0.0 1 1.0 -0.51
## IsNewYearEve 0.00 0.0 1 1.0 2.28
## Date* 2.97 1.0 20 19.0 -0.77
## HotelName* 641.97 1.0 1670 1669.0 0.01
## RoomRent 2653.85 299.0 322500 322201.0 16.75
## StarRating 0.74 0.0 5 5.0 0.48
## Airport 11.12 0.2 124 123.8 2.73
## HotelAddress* 668.65 1.0 2108 2107.0 -0.37
## HotelPincode 257975.37 100025.0 7000157 6900132.0 9.99
## HotelDescription* 472.95 1.0 1226 1225.0 0.11
## FreeWifi 0.00 0.0 1 1.0 -3.25
## FreeBreakfast 0.00 0.0 1 1.0 -0.62
## HotelCapacity 28.17 0.0 600 600.0 2.95
## HasSwimmingPool 0.00 0.0 1 1.0 0.60
## kurtosis se
## CityName* -0.88 0.10
## Population -1.08 37019.65
## CityRank -0.76 0.12
## IsMetroCity -1.08 0.00
## IsTouristDestination -1.26 0.00
## IsWeekend -1.74 0.00
## IsNewYearEve 3.18 0.00
## Date* 1.92 0.02
## HotelName* -1.25 4.24
## RoomRent 582.06 63.75
## StarRating 0.25 0.01
## Airport 7.89 0.20
## HotelAddress* -0.88 5.06
## HotelPincode 249.76 2258.86
## HotelDescription* -1.25 3.16
## FreeWifi 8.57 0.00
## FreeBreakfast -1.61 0.00
## HotelCapacity 11.39 0.67
## HasSwimmingPool -1.64 0.00summary(Cities)## CityName Population CityRank IsMetroCity
## Delhi :2048 Min. : 8096 Min. : 0.00 Min. :0.0000
## Jaipur : 768 1st Qu.: 744983 1st Qu.: 2.00 1st Qu.:0.0000
## Mumbai : 712 Median : 3046163 Median : 9.00 Median :0.0000
## Bangalore: 656 Mean : 4416837 Mean :14.83 Mean :0.2842
## Goa : 624 3rd Qu.: 8443675 3rd Qu.:24.00 3rd Qu.:1.0000
## Kochi : 608 Max. :12442373 Max. :44.00 Max. :1.0000
## (Other) :7816
## IsTouristDestination IsWeekend IsNewYearEve Date
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Dec 21 2016:1611
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 Dec 24 2016:1611
## Median :1.0000 Median :1.0000 Median :0.0000 Dec 25 2016:1611
## Mean :0.6972 Mean :0.6228 Mean :0.1244 Dec 28 2016:1611
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:0.0000 Dec 31 2016:1611
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Dec 18 2016:1608
## (Other) :3569
## HotelName RoomRent StarRating
## Vivanta by Taj : 32 Min. : 299 Min. :0.000
## Goldfinch Hotel : 24 1st Qu.: 2436 1st Qu.:3.000
## OYO Rooms : 24 Median : 4000 Median :3.000
## The Gordon House Hotel: 24 Mean : 5474 Mean :3.459
## Apnayt Villa : 16 3rd Qu.: 6299 3rd Qu.:4.000
## Bentleys Hotel Colaba : 16 Max. :322500 Max. :5.000
## (Other) :13096
## Airport
## Min. : 0.20
## 1st Qu.: 8.40
## Median : 15.00
## Mean : 21.16
## 3rd Qu.: 24.00
## Max. :124.00
##
## HotelAddress
## The Mall, Shimla : 32
## #2-91/14/8, White Fields, Kondapur, Hitech City, Hyderabad, 500084 India: 16
## 121, City Terrace, Walchand Hirachand Marg, Mumbai, Maharashtra : 16
## 14-4507/9, Balmatta Road, Near Jyothi Circle, Hampankatta : 16
## 144/7, Rajiv Gandi Salai (OMR), Kottivakkam, Chennai, Tamil Nadu : 16
## 17, Oliver Road, Colaba, Mumbai, Maharashtra : 16
## (Other) :13120
## HotelPincode HotelDescription FreeWifi FreeBreakfast
## Min. : 100025 3 : 120 Min. :0.0000 Min. :0.0000
## 1st Qu.: 221001 Abc : 112 1st Qu.:1.0000 1st Qu.:0.0000
## Median : 395003 3-star hotel: 104 Median :1.0000 Median :1.0000
## Mean : 397430 3.5 : 88 Mean :0.9259 Mean :0.6491
## 3rd Qu.: 570001 4 : 72 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :7000157 (Other) :12728 Max. :1.0000 Max. :1.0000
## NA's : 8
## HotelCapacity HasSwimmingPool
## Min. : 0.00 Min. :0.0000
## 1st Qu.: 16.00 1st Qu.:0.0000
## Median : 34.00 Median :0.0000
## Mean : 62.51 Mean :0.3558
## 3rd Qu.: 75.00 3rd Qu.:1.0000
## Max. :600.00 Max. :1.0000
## Create one-way contingency tables for the categorical variables in your dataset
Table <- with(Cities,table(CityName))
Table## CityName
## Agra Ahmedabad Amritsar Bangalore
## 432 424 136 656
## Bhubaneswar Chandigarh Chennai Darjeeling
## 120 336 416 136
## Delhi Gangtok Goa Guwahati
## 2048 128 624 48
## Haridwar Hyderabad Indore Jaipur
## 48 536 160 768
## Jaisalmer Jodhpur Kanpur Kochi
## 264 224 16 608
## Kolkata Lucknow Madurai Manali
## 512 128 112 288
## Mangalore Mumbai Munnar Mysore
## 104 712 328 160
## Nainital Ooty Panchkula Pune
## 144 136 64 600
## Puri Rajkot Rishikesh Shimla
## 56 128 88 280
## Srinagar Surat Thiruvanthipuram Thrissur
## 40 80 392 32
## Udaipur Varanasi
## 456 264Table1 <- with(Cities,table(IsMetroCity))
Table1## IsMetroCity
## 0 1
## 9472 3760Table2 <- with(Cities,table(IsTouristDestination))
Table2## IsTouristDestination
## 0 1
## 4007 9225Table3 <- with(Cities,table(IsWeekend))
Table3## IsWeekend
## 0 1
## 4991 8241Table4 <- with(Cities,table(IsNewYearEve))
Table4## IsNewYearEve
## 0 1
## 11586 1646Table5 <- with(Cities,table(HasSwimmingPool))
Table5## HasSwimmingPool
## 0 1
## 8524 4708Create two-way contingency tables for the categorical variables in your dataset.
t1 <- xtabs(~ StarRating + IsMetroCity, data=Cities)
t1## IsMetroCity
## StarRating 0 1
## 0 16 0
## 1 8 0
## 2 344 96
## 2.5 456 176
## 3 4336 1617
## 3.2 8 0
## 3.3 16 0
## 3.4 8 0
## 3.5 1312 440
## 3.6 0 8
## 3.7 24 0
## 3.8 16 0
## 3.9 32 0
## 4 1696 767
## 4.1 24 0
## 4.3 16 0
## 4.4 8 0
## 4.5 288 88
## 4.7 8 0
## 4.8 16 0
## 5 840 568t2 <- xtabs(~ FreeWifi+ FreeBreakfast, data=Cities)
t2## FreeBreakfast
## FreeWifi 0 1
## 0 606 375
## 1 4037 8214t3 <- xtabs(~ IsTouristDestination + IsNewYearEve, data=Cities)
t3## IsNewYearEve
## IsTouristDestination 0 1
## 0 3504 503
## 1 8082 1143Draw a boxplot of the variables that belong to your study.
hist(Cities$Population, main= "Population" ,xlab="Population" ,col = "blue")
hist(Cities$StarRating, main= "Star rating" ,xlab="Star rating",col = "blue")
hist(Cities$Airport, main = "Distance to nearest major airport distribution", xlab = "Distance to nearest major Airport in km",col = "blue")
hist(Cities$HotelCapacity, main = "Capacity of hotels", xlab = "Hotel Capacity", col = "blue")
hist(Cities$CityRank, main = "Distribution of rank of cities", xlab = "City rank", col = "blue")
boxplot(Cities$CityRank , horizontal =TRUE, main="city rank",col = "Red" )
boxplot(Cities$IsMetroCity, horizontal =TRUE, main="Metro city and Tourist destination",col = "light green" )
boxplot(Cities$IsTouristDestination, horizontal =TRUE, main="Metro city and Tourist destination",col = "light green" )
#Corrgram of Cities
library(corrgram)## Warning: package 'corrgram' was built under R version 3.4.3corrgram(Cities, order = TRUE, upper.panel = panel.pie)
Create a correlation matrix.
x<-Cities[,c("RoomRent","StarRating","Airport","HotelCapacity")]
y<-Cities[,c("RoomRent","StarRating","Airport","HotelCapacity")]
cor(x,y)## RoomRent StarRating Airport HotelCapacity
## RoomRent 1.00000000 0.36937343 0.04965324 0.1578733
## StarRating 0.36937343 1.00000000 -0.06091918 0.6374303
## Airport 0.04965324 -0.06091918 1.00000000 -0.1176721
## HotelCapacity 0.15787331 0.63743034 -0.11767207 1.0000000Visualize your correlation matrix using corrgram.
corrgram(Cities[c("RoomRent","StarRating","Airport","HotelCapacity")], upper.panel = panel.pie)
Create a scatter plot matrix for your data set.
library(car) ## Warning: package 'car' was built under R version 3.4.3##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitscatterplot(RoomRent~StarRating, data=cities,
spread=FALSE, smoother.args=list(lty=2),
main="Scatter plot of Star Rating vs Room rent",
ylab="Room Rent",
xlab="Star Rating")
library(car)
scatterplot(RoomRent~CityRank, data=cities,
spread=FALSE, smoother.args=list(lty=2),
main="Scatter plot of City rank vs Room rent",
ylab="Room Rent",
xlab="Rank of City")
library(car)
scatterplot(RoomRent~ HasSwimmingPool, data=Cities,
spread=FALSE, smoother.args=list(lty=2),
main="Scatter plot of hotel with Swimming pool vs Room rent",
ylab="Room Rent",
xlab="Hotel with swimming pool")
library(car)
scatterplotMatrix(formula = ~ RoomRent + IsWeekend + IsNewYearEve +Airport , data = Cities, pch = 16)## Warning in smoother(x, y, col = col[2], log.x = FALSE, log.y = FALSE,
## spread = spread, : could not fit smooth
## Warning in smoother(x, y, col = col[2], log.x = FALSE, log.y = FALSE,
## spread = spread, : could not fit smooth
T-Test
test1: Null Hypothesis - Their is no Difference between the Room Rent on weekdays and on weekends
t.test(Cities$RoomRent ~ Cities$IsWeekend)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$IsWeekend
## t = -0.51853, df = 9999.4, p-value = 0.6041
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -331.2427 192.6559
## sample estimates:
## mean in group 0 mean in group 1
## 5430.835 5500.129As we can see the P-Value = 0.6 (>0.05) , We Fail To reject the Null Hypothesis.
It Shows that Their is No Significant Difference Between the Room rents on Weekdays and Weekends.
test2: Null Hypothesis - Their is no Difference between the Room Rent on new year’s eve and on other days
t.test(Cities$RoomRent ~ Cities$IsNewYearEve)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$IsNewYearEve
## t = -4.1793, df = 2065, p-value = 3.046e-05
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1256.5297 -453.9099
## sample estimates:
## mean in group 0 mean in group 1
## 5367.606 6222.826P-Value = 3.046e-05 (<0.05) Which is small enough for Rejecting the Null Hupothesis.
Hence there is significant difference between the Room Rent on new year’s eve and on other days
test3: Null Hypothesis - Their is no Difference between the Room Rent of Metro Cities and other cities
t.test(Cities$RoomRent ~ Cities$IsMetroCity)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$IsMetroCity
## t = 10.721, df = 13224, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 888.0308 1285.4102
## sample estimates:
## mean in group 0 mean in group 1
## 5782.794 4696.073P-Value = 2.2e-16 (<0.05) Which is small enough for Rejecting the Null Hupothesis.
Hence there is significant difference between the Room Rent of Metro Cities and other cities
test4: Null Hypothesis - Their is no Difference between the Room Rent where wifi is free and other rooms.
t.test(Cities$RoomRent ~ Cities$FreeWifi)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$FreeWifi
## t = -0.76847, df = 1804.7, p-value = 0.4423
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -360.5977 157.5701
## sample estimates:
## mean in group 0 mean in group 1
## 5380.004 5481.518As we can see the P-Value = 0.44 (>0.05) , We Fail To reject the Null Hypothesis.
It Shows that Their is No Significant Difference Between the Room Rent where wifi is free and other rooms.
test5: Null Hypothesis: Their is no difference in the means of room Rent where free Breakfast is available or not
t.test(Cities$RoomRent ~ Cities$FreeBreakfast)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$FreeBreakfast
## t = 0.98095, df = 6212.3, p-value = 0.3267
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -153.5017 460.9935
## sample estimates:
## mean in group 0 mean in group 1
## 5573.790 5420.044The difference between The two means is not different as p-value = 0.32 (>0.05) so we fail to reject the Null hypothesis.
It Means The Room rents Are same for all room whether free Breakfast is available or not.
test6: null Hypothesis: The correlation between RoomRent and Star Rating is Zero
cor.test(Cities$RoomRent , Cities$StarRating)##
## Pearson's product-moment correlation
##
## data: Cities$RoomRent and Cities$StarRating
## t = 45.719, df = 13230, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3545660 0.3839956
## sample estimates:
## cor
## 0.3693734We Can clearly see that the corrrelation between RoomRent and StarRating = 36.9% or approx 37%.and this relation is significant because the p-value = 2.2e-16 (<0.05) which suggests us to reject the Null hypothesis.
test7: Null hypothesis: The correlation between RoomRent and Distance to the airport is Zero
cor.test(Cities$RoomRent , Cities$Airport)##
## Pearson's product-moment correlation
##
## data: Cities$RoomRent and Cities$Airport
## t = 5.7183, df = 13230, p-value = 1.099e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03264192 0.06663581
## sample estimates:
## cor
## 0.04965324We can see that the correlation is small 5% But it is significant as the p-value < 0.05.
test8: null Hypothesis: The correlation between RoomRent and Hotel Capacity is Zero
cor.test(Cities$RoomRent , Cities$HotelCapacity)##
## Pearson's product-moment correlation
##
## data: Cities$RoomRent and Cities$HotelCapacity
## t = 18.389, df = 13230, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1412142 0.1744430
## sample estimates:
## cor
## 0.1578733As the p-value = 2.2e-16 (<0.05) We can reject the Null hypothesis that Means Their exists a significant relation between Room Rent and Hotel Capacity and as we see it is approx 16%
test9: Null Hypothesis: Their is no difference in the means of room Rent where Swimming Pool is available or not
t.test(Cities$RoomRent~ Cities$HasSwimmingPool)##
## Welch Two Sample t-test
##
## data: Cities$RoomRent by Cities$HasSwimmingPool
## t = -29.013, df = 5011.3, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -5096.030 -4450.942
## sample estimates:
## mean in group 0 mean in group 1
## 3775.566 8549.052The difference between The two means is different as p-value = 2.2e-16 (<0.05) so we reject the Null hypothesis. It Means The Room rents have effect whether the hotel has the swimming pool or not.
linear regression
let us assume that We create a model that shows how the variables effect the Room Rent
Our model will be like y = B0 + B1x1 + B2x2 + B3x3.. + E
y - Room Rent (dependent variable). B0 - intercept. B1, B2, B3 .- Beta coefficients for different variables.And x1, x2, x3. x1, x2, x3 - StarRating, Dist to airport, FreeWifi, etc (independent variables).
E - error term.
Model1 <- lm(RoomRent ~ StarRating + Airport + FreeWifi + FreeBreakfast + HotelCapacity + HasSwimmingPool, data = Cities)
summary(Model1)##
## Call:
## lm(formula = RoomRent ~ StarRating + Airport + FreeWifi + FreeBreakfast +
## HotelCapacity + HasSwimmingPool, data = Cities)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10783 -2286 -875 967 310387
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -7455.073 396.215 -18.816 <2e-16 ***
## StarRating 3519.285 111.754 31.491 <2e-16 ***
## Airport 25.627 2.604 9.840 <2e-16 ***
## FreeWifi 227.843 226.177 1.007 0.314
## FreeBreakfast -59.313 123.964 -0.478 0.632
## HotelCapacity -14.786 1.009 -14.660 <2e-16 ***
## HasSwimmingPool 2714.146 158.681 17.104 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6687 on 13225 degrees of freedom
## Multiple R-squared: 0.1689, Adjusted R-squared: 0.1685
## F-statistic: 447.9 on 6 and 13225 DF, p-value: < 2.2e-16Final model
let us assume that We create a model that shows how the variables effect the Room Rent
Our model will be like y = B0 + B1x1 + B2x2 + B3x3 + E
y - Room Rent (dependent variable). B0 - intercept. B1, B2, B3 . - Beta coefficients for different variables. x1, x2, x3. x1, x2, x3 - dates, external factors, internal factors (independent variables). E - error term.
Model2 <- lm(RoomRent ~ IsNewYearEve + IsMetroCity + IsTouristDestination + StarRating + Airport + HotelCapacity + HasSwimmingPool, data = Cities)
summary(Model2)##
## Call:
## lm(formula = RoomRent ~ IsNewYearEve + IsMetroCity + IsTouristDestination +
## StarRating + Airport + HotelCapacity + HasSwimmingPool, data = Cities)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11621 -2342 -706 1039 309463
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -8362.318 351.306 -23.804 < 2e-16 ***
## IsNewYearEve 843.295 174.085 4.844 1.29e-06 ***
## IsMetroCity -1502.844 137.569 -10.924 < 2e-16 ***
## IsTouristDestination 2074.969 133.499 15.543 < 2e-16 ***
## StarRating 3583.270 110.317 32.482 < 2e-16 ***
## Airport 11.057 2.699 4.096 4.22e-05 ***
## HotelCapacity -11.252 1.020 -11.030 < 2e-16 ***
## HasSwimmingPool 2211.800 159.259 13.888 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6609 on 13224 degrees of freedom
## Multiple R-squared: 0.1882, Adjusted R-squared: 0.1878
## F-statistic: 438 on 7 and 13224 DF, p-value: < 2.2e-16