Final Project
{{Saurabh Nehete}}
2023-06-15
## 'data.frame': 103904 obs. of 25 variables:
## $ X : int 0 1 2 3 4 5 6 7 8 9 ...
## $ id : int 70172 5047 110028 24026 119299 111157 82113 96462 79485 65725 ...
## $ Gender : chr "Male" "Male" "Female" "Female" ...
## $ Customer.Type : chr "Loyal Customer" "disloyal Customer" "Loyal Customer" "Loyal Customer" ...
## $ Age : int 13 25 26 25 61 26 47 52 41 20 ...
## $ Type.of.Travel : chr "Personal Travel" "Business travel" "Business travel" "Business travel" ...
## $ Class : chr "Eco Plus" "Business" "Business" "Business" ...
## $ Flight.Distance : int 460 235 1142 562 214 1180 1276 2035 853 1061 ...
## $ Inflight.wifi.service : int 3 3 2 2 3 3 2 4 1 3 ...
## $ Departure.Arrival.time.convenient: int 4 2 2 5 3 4 4 3 2 3 ...
## $ Ease.of.Online.booking : int 3 3 2 5 3 2 2 4 2 3 ...
## $ Gate.location : int 1 3 2 5 3 1 3 4 2 4 ...
## $ Food.and.drink : int 5 1 5 2 4 1 2 5 4 2 ...
## $ Online.boarding : int 3 3 5 2 5 2 2 5 3 3 ...
## $ Seat.comfort : int 5 1 5 2 5 1 2 5 3 3 ...
## $ Inflight.entertainment : int 5 1 5 2 3 1 2 5 1 2 ...
## $ On.board.service : int 4 1 4 2 3 3 3 5 1 2 ...
## $ Leg.room.service : int 3 5 3 5 4 4 3 5 2 3 ...
## $ Baggage.handling : int 4 3 4 3 4 4 4 5 1 4 ...
## $ Checkin.service : int 4 1 4 1 3 4 3 4 4 4 ...
## $ Inflight.service : int 5 4 4 4 3 4 5 5 1 3 ...
## $ Cleanliness : int 5 1 5 2 3 1 2 4 2 2 ...
## $ Departure.Delay.in.Minutes : int 25 1 0 11 0 0 9 4 0 0 ...
## $ Arrival.Delay.in.Minutes : num 18 6 0 9 0 0 23 0 0 0 ...
## $ satisfaction : chr "neutral or dissatisfied" "neutral or dissatisfied" "satisfied" "neutral or dissatisfied" ...## X id Gender Customer.Type
## Min. : 0 Min. : 1 Length:103904 Length:103904
## 1st Qu.: 25976 1st Qu.: 32534 Class :character Class :character
## Median : 51952 Median : 64857 Mode :character Mode :character
## Mean : 51952 Mean : 64924
## 3rd Qu.: 77927 3rd Qu.: 97368
## Max. :103903 Max. :129880
##
## Age Type.of.Travel Class Flight.Distance
## Min. : 7.00 Length:103904 Length:103904 Min. : 31
## 1st Qu.:27.00 Class :character Class :character 1st Qu.: 414
## Median :40.00 Mode :character Mode :character Median : 843
## Mean :39.38 Mean :1189
## 3rd Qu.:51.00 3rd Qu.:1743
## Max. :85.00 Max. :4983
##
## Inflight.wifi.service Departure.Arrival.time.convenient Ease.of.Online.booking
## Min. :0.00 Min. :0.00 Min. :0.000
## 1st Qu.:2.00 1st Qu.:2.00 1st Qu.:2.000
## Median :3.00 Median :3.00 Median :3.000
## Mean :2.73 Mean :3.06 Mean :2.757
## 3rd Qu.:4.00 3rd Qu.:4.00 3rd Qu.:4.000
## Max. :5.00 Max. :5.00 Max. :5.000
##
## Gate.location Food.and.drink Online.boarding Seat.comfort
## Min. :0.000 Min. :0.000 Min. :0.00 Min. :0.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :3.00 Median :4.000
## Mean :2.977 Mean :3.202 Mean :3.25 Mean :3.439
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.000
##
## Inflight.entertainment On.board.service Leg.room.service Baggage.handling
## Min. :0.000 Min. :0.000 Min. :0.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.358 Mean :3.382 Mean :3.351 Mean :3.632
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
##
## Checkin.service Inflight.service Cleanliness Departure.Delay.in.Minutes
## Min. :0.000 Min. :0.00 Min. :0.000 Min. : 0.00
## 1st Qu.:3.000 1st Qu.:3.00 1st Qu.:2.000 1st Qu.: 0.00
## Median :3.000 Median :4.00 Median :3.000 Median : 0.00
## Mean :3.304 Mean :3.64 Mean :3.286 Mean : 14.82
## 3rd Qu.:4.000 3rd Qu.:5.00 3rd Qu.:4.000 3rd Qu.: 12.00
## Max. :5.000 Max. :5.00 Max. :5.000 Max. :1592.00
##
## Arrival.Delay.in.Minutes satisfaction
## Min. : 0.00 Length:103904
## 1st Qu.: 0.00 Class :character
## Median : 0.00 Mode :character
## Mean : 15.18
## 3rd Qu.: 13.00
## Max. :1584.00
## NA's :310## X id Gender Customer.Type Age Type.of.Travel Class
## 1 0 70172 Male Loyal Customer 13 Personal Travel Eco Plus
## 2 1 5047 Male disloyal Customer 25 Business travel Business
## 3 2 110028 Female Loyal Customer 26 Business travel Business
## 4 3 24026 Female Loyal Customer 25 Business travel Business
## 5 4 119299 Male Loyal Customer 61 Business travel Business
## 6 5 111157 Female Loyal Customer 26 Personal Travel Eco
## Flight.Distance Inflight.wifi.service Departure.Arrival.time.convenient
## 1 460 3 4
## 2 235 3 2
## 3 1142 2 2
## 4 562 2 5
## 5 214 3 3
## 6 1180 3 4
## Ease.of.Online.booking Gate.location Food.and.drink Online.boarding
## 1 3 1 5 3
## 2 3 3 1 3
## 3 2 2 5 5
## 4 5 5 2 2
## 5 3 3 4 5
## 6 2 1 1 2
## Seat.comfort Inflight.entertainment On.board.service Leg.room.service
## 1 5 5 4 3
## 2 1 1 1 5
## 3 5 5 4 3
## 4 2 2 2 5
## 5 5 3 3 4
## 6 1 1 3 4
## Baggage.handling Checkin.service Inflight.service Cleanliness
## 1 4 4 5 5
## 2 3 1 4 1
## 3 4 4 4 5
## 4 3 1 4 2
## 5 4 3 3 3
## 6 4 4 4 1
## Departure.Delay.in.Minutes Arrival.Delay.in.Minutes satisfaction
## 1 25 18 neutral or dissatisfied
## 2 1 6 neutral or dissatisfied
## 3 0 0 satisfied
## 4 11 9 neutral or dissatisfied
## 5 0 0 satisfied
## 6 0 0 neutral or dissatisfiedPreprocessing
## Remove missing values
data1 <- data %>%
na.omit()
dim(data1)## [1] 103594 25glimpse(data1)## Rows: 103,594
## Columns: 25
## $ X <int> 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11…
## $ id <int> 70172, 5047, 110028, 24026, 119299, …
## $ Gender <chr> "Male", "Male", "Female", "Female", …
## $ Customer.Type <chr> "Loyal Customer", "disloyal Customer…
## $ Age <int> 13, 25, 26, 25, 61, 26, 47, 52, 41, …
## $ Type.of.Travel <chr> "Personal Travel", "Business travel"…
## $ Class <chr> "Eco Plus", "Business", "Business", …
## $ Flight.Distance <int> 460, 235, 1142, 562, 214, 1180, 1276…
## $ Inflight.wifi.service <int> 3, 3, 2, 2, 3, 3, 2, 4, 1, 3, 4, 2, …
## $ Departure.Arrival.time.convenient <int> 4, 2, 2, 5, 3, 4, 4, 3, 2, 3, 5, 4, …
## $ Ease.of.Online.booking <int> 3, 3, 2, 5, 3, 2, 2, 4, 2, 3, 5, 2, …
## $ Gate.location <int> 1, 3, 2, 5, 3, 1, 3, 4, 2, 4, 4, 2, …
## $ Food.and.drink <int> 5, 1, 5, 2, 4, 1, 2, 5, 4, 2, 2, 1, …
## $ Online.boarding <int> 3, 3, 5, 2, 5, 2, 2, 5, 3, 3, 5, 2, …
## $ Seat.comfort <int> 5, 1, 5, 2, 5, 1, 2, 5, 3, 3, 2, 1, …
## $ Inflight.entertainment <int> 5, 1, 5, 2, 3, 1, 2, 5, 1, 2, 2, 1, …
## $ On.board.service <int> 4, 1, 4, 2, 3, 3, 3, 5, 1, 2, 3, 1, …
## $ Leg.room.service <int> 3, 5, 3, 5, 4, 4, 3, 5, 2, 3, 3, 2, …
## $ Baggage.handling <int> 4, 3, 4, 3, 4, 4, 4, 5, 1, 4, 5, 5, …
## $ Checkin.service <int> 4, 1, 4, 1, 3, 4, 3, 4, 4, 4, 3, 5, …
## $ Inflight.service <int> 5, 4, 4, 4, 3, 4, 5, 5, 1, 3, 5, 5, …
## $ Cleanliness <int> 5, 1, 5, 2, 3, 1, 2, 4, 2, 2, 2, 1, …
## $ Departure.Delay.in.Minutes <int> 25, 1, 0, 11, 0, 0, 9, 4, 0, 0, 0, 0…
## $ Arrival.Delay.in.Minutes <dbl> 18, 6, 0, 9, 0, 0, 23, 0, 0, 0, 0, 0…
## $ satisfaction <chr> "neutral or dissatisfied", "neutral …summary(data1)## X id Gender Customer.Type
## Min. : 0 Min. : 1 Length:103594 Length:103594
## 1st Qu.: 25960 1st Qu.: 32562 Class :character Class :character
## Median : 51956 Median : 64890 Mode :character Mode :character
## Mean : 51950 Mean : 64942
## 3rd Qu.: 77925 3rd Qu.: 97371
## Max. :103903 Max. :129880
## Age Type.of.Travel Class Flight.Distance
## Min. : 7.00 Length:103594 Length:103594 Min. : 31
## 1st Qu.:27.00 Class :character Class :character 1st Qu.: 414
## Median :40.00 Mode :character Mode :character Median : 842
## Mean :39.38 Mean :1189
## 3rd Qu.:51.00 3rd Qu.:1743
## Max. :85.00 Max. :4983
## Inflight.wifi.service Departure.Arrival.time.convenient Ease.of.Online.booking
## Min. :0.00 Min. :0.00 Min. :0.000
## 1st Qu.:2.00 1st Qu.:2.00 1st Qu.:2.000
## Median :3.00 Median :3.00 Median :3.000
## Mean :2.73 Mean :3.06 Mean :2.757
## 3rd Qu.:4.00 3rd Qu.:4.00 3rd Qu.:4.000
## Max. :5.00 Max. :5.00 Max. :5.000
## Gate.location Food.and.drink Online.boarding Seat.comfort
## Min. :0.000 Min. :0.000 Min. :0.00 Min. :0.00
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:2.00
## Median :3.000 Median :3.000 Median :3.00 Median :4.00
## Mean :2.977 Mean :3.202 Mean :3.25 Mean :3.44
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:5.00
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.00
## Inflight.entertainment On.board.service Leg.room.service Baggage.handling
## Min. :0.000 Min. :0.000 Min. :0.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.358 Mean :3.383 Mean :3.351 Mean :3.632
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Checkin.service Inflight.service Cleanliness Departure.Delay.in.Minutes
## Min. :0.000 Min. :0.000 Min. :0.000 Min. : 0.00
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.: 0.00
## Median :3.000 Median :4.000 Median :3.000 Median : 0.00
## Mean :3.304 Mean :3.641 Mean :3.286 Mean : 14.75
## 3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 12.00
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :1592.00
## Arrival.Delay.in.Minutes satisfaction
## Min. : 0.00 Length:103594
## 1st Qu.: 0.00 Class :character
## Median : 0.00 Mode :character
## Mean : 15.18
## 3rd Qu.: 13.00
## Max. :1584.00##convert to factor/numeric
data1$satisfaction <- ordered(data1$satisfaction, levels=c("satisfied", "neutral or dissatisfied"))
data1$Gender <- ordered(data1$Gender, levels=c("Male", "Female"))
data1$Customer.Type <- ordered(data1$Customer.Type, levels=c("Loyal Customer", "disloyal Customer"))
data1$Class <- ordered(data1$Class, levels=c("Eco Plus", "Business", "Eco"))
data1$Type.of.Travel <- ordered(data1$Type.of.Travel, levels=c("Personal Travel", "Business travel"))
summary(data1)## X id Gender Customer.Type
## Min. : 0 Min. : 1 Male :51018 Loyal Customer :84662
## 1st Qu.: 25960 1st Qu.: 32562 Female:52576 disloyal Customer:18932
## Median : 51956 Median : 64890
## Mean : 51950 Mean : 64942
## 3rd Qu.: 77925 3rd Qu.: 97371
## Max. :103903 Max. :129880
## Age Type.of.Travel Class Flight.Distance
## Min. : 7.00 Personal Travel:32129 Eco Plus: 7468 Min. : 31
## 1st Qu.:27.00 Business travel:71465 Business:49533 1st Qu.: 414
## Median :40.00 Eco :46593 Median : 842
## Mean :39.38 Mean :1189
## 3rd Qu.:51.00 3rd Qu.:1743
## Max. :85.00 Max. :4983
## Inflight.wifi.service Departure.Arrival.time.convenient Ease.of.Online.booking
## Min. :0.00 Min. :0.00 Min. :0.000
## 1st Qu.:2.00 1st Qu.:2.00 1st Qu.:2.000
## Median :3.00 Median :3.00 Median :3.000
## Mean :2.73 Mean :3.06 Mean :2.757
## 3rd Qu.:4.00 3rd Qu.:4.00 3rd Qu.:4.000
## Max. :5.00 Max. :5.00 Max. :5.000
## Gate.location Food.and.drink Online.boarding Seat.comfort
## Min. :0.000 Min. :0.000 Min. :0.00 Min. :0.00
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:2.00
## Median :3.000 Median :3.000 Median :3.00 Median :4.00
## Mean :2.977 Mean :3.202 Mean :3.25 Mean :3.44
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:5.00
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.00
## Inflight.entertainment On.board.service Leg.room.service Baggage.handling
## Min. :0.000 Min. :0.000 Min. :0.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.358 Mean :3.383 Mean :3.351 Mean :3.632
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Checkin.service Inflight.service Cleanliness Departure.Delay.in.Minutes
## Min. :0.000 Min. :0.000 Min. :0.000 Min. : 0.00
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.: 0.00
## Median :3.000 Median :4.000 Median :3.000 Median : 0.00
## Mean :3.304 Mean :3.641 Mean :3.286 Mean : 14.75
## 3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 12.00
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :1592.00
## Arrival.Delay.in.Minutes satisfaction
## Min. : 0.00 satisfied :44897
## 1st Qu.: 0.00 neutral or dissatisfied:58697
## Median : 0.00
## Mean : 15.18
## 3rd Qu.: 13.00
## Max. :1584.00str(data1)## 'data.frame': 103594 obs. of 25 variables:
## $ X : int 0 1 2 3 4 5 6 7 8 9 ...
## $ id : int 70172 5047 110028 24026 119299 111157 82113 96462 79485 65725 ...
## $ Gender : Ord.factor w/ 2 levels "Male"<"Female": 1 1 2 2 1 2 1 2 2 1 ...
## $ Customer.Type : Ord.factor w/ 2 levels "Loyal Customer"<..: 1 2 1 1 1 1 1 1 1 2 ...
## $ Age : int 13 25 26 25 61 26 47 52 41 20 ...
## $ Type.of.Travel : Ord.factor w/ 2 levels "Personal Travel"<..: 1 2 2 2 2 1 1 2 2 2 ...
## $ Class : Ord.factor w/ 3 levels "Eco Plus"<"Business"<..: 1 2 2 2 2 3 3 2 2 3 ...
## $ Flight.Distance : int 460 235 1142 562 214 1180 1276 2035 853 1061 ...
## $ Inflight.wifi.service : int 3 3 2 2 3 3 2 4 1 3 ...
## $ Departure.Arrival.time.convenient: int 4 2 2 5 3 4 4 3 2 3 ...
## $ Ease.of.Online.booking : int 3 3 2 5 3 2 2 4 2 3 ...
## $ Gate.location : int 1 3 2 5 3 1 3 4 2 4 ...
## $ Food.and.drink : int 5 1 5 2 4 1 2 5 4 2 ...
## $ Online.boarding : int 3 3 5 2 5 2 2 5 3 3 ...
## $ Seat.comfort : int 5 1 5 2 5 1 2 5 3 3 ...
## $ Inflight.entertainment : int 5 1 5 2 3 1 2 5 1 2 ...
## $ On.board.service : int 4 1 4 2 3 3 3 5 1 2 ...
## $ Leg.room.service : int 3 5 3 5 4 4 3 5 2 3 ...
## $ Baggage.handling : int 4 3 4 3 4 4 4 5 1 4 ...
## $ Checkin.service : int 4 1 4 1 3 4 3 4 4 4 ...
## $ Inflight.service : int 5 4 4 4 3 4 5 5 1 3 ...
## $ Cleanliness : int 5 1 5 2 3 1 2 4 2 2 ...
## $ Departure.Delay.in.Minutes : int 25 1 0 11 0 0 9 4 0 0 ...
## $ Arrival.Delay.in.Minutes : num 18 6 0 9 0 0 23 0 0 0 ...
## $ satisfaction : Ord.factor w/ 2 levels "satisfied"<"neutral or dissatisfied": 2 2 1 2 1 2 2 1 2 2 ...
## - attr(*, "na.action")= 'omit' Named int [1:310] 214 1125 1530 2005 2109 2486 2631 3622 4042 4491 ...
## ..- attr(*, "names")= chr [1:310] "214" "1125" "1530" "2005" ...#EDA
#categorical variables
ggplot(gather(data1 %>% select_if(is.factor)), aes(value)) +
geom_bar(bins = 10,fill="firebrick") +
facet_wrap(~key, scales = 'free_x') + labs(x="Categorical",
y="Value")## Warning: attributes are not identical across measure variables; they will be
## dropped## Warning in geom_bar(bins = 10, fill = "firebrick"): Ignoring unknown
## parameters: `bins`
#numerical variables
ggplot(gather(data1 %>% select_if(is.numeric)), aes(value)) +
geom_histogram(bins = 10, fill="turquoise4") +
facet_wrap(~key, scales = 'free_x')
#library(corrplot)
#as.numeric(data1)
#M = cor(data1)
#corrplot(M, method = 'number')Chi squared test and contingency tables
## Seat.comfort
## satisfaction 0 1 2 3 4 5
## satisfied 0 2690 3330 3944 17775 17158
## neutral or dissatisfied 1 9341 11516 14697 13907 9235## Cleanliness
## satisfaction 0 1 2 3 4 5
## satisfied 0 2607 3428 10581 14513 13768
## neutral or dissatisfied 12 10669 12653 13925 12587 8851## Inflight.service
## satisfaction 0 1 2 3 4 5
## satisfied 0 2046 3439 4833 18082 16497
## neutral or dissatisfied 3 5017 7975 15394 19764 10544## Inflight.entertainment
## satisfaction 0 1 2 3 4 5
## satisfied 0 1740 3750 5146 17954 16307
## neutral or dissatisfied 14 10701 13829 13934 11381 8838## Checkin.service
## satisfaction 0 1 2 3 4 5
## satisfied 0 3076 3248 12717 13324 12532
## neutral or dissatisfied 1 9776 9606 15639 15651 8024## Gate.location
## satisfaction 0 1 2 3 4 5
## satisfied 1 8677 8949 9889 9458 7923
## neutral or dissatisfied 0 8834 10447 18600 14895 5921## Baggage.handling
## satisfaction 1 2 3 4 5
## satisfied 2148 3397 4848 17929 16575
## neutral or dissatisfied 5075 8086 15719 19345 10472## Departure.Arrival.time.convenient
## satisfaction 0 1 2 3 4 5
## satisfied 2516 7519 7639 7847 9879 9497
## neutral or dissatisfied 2774 7933 9503 10056 15595 12836## X^2 df P(> X^2)
## Likelihood Ratio 16317 5 0
## Pearson 15685 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.363
## Cramer's V : 0.389Mosaic Display
#(inflight1 <- xtabs(~satisfaction + Seat.comfort, data=data1))
df1<-table(data1$satisfaction, data1$Seat.comfort)
df1##
## 0 1 2 3 4 5
## satisfied 0 2690 3330 3944 17775 17158
## neutral or dissatisfied 1 9341 11516 14697 13907 9235a= data1[, c("satisfaction", "Seat.comfort")]
da= xtabs(~ satisfaction + Seat.comfort, data = a)
loglm(~ satisfaction + Seat.comfort, data = da)## Call:
## loglm(formula = ~satisfaction + Seat.comfort, data = da)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 16317.00 5 0
## Pearson 15685.04 5 0assocstats(df1)## X^2 df P(> X^2)
## Likelihood Ratio 16317 5 0
## Pearson 15685 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.363
## Cramer's V : 0.389mosaic(~satisfaction + Seat.comfort, data = a, expected = ~satisfaction + Seat.comfort, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(inflight2 <- xtabs(~satisfaction + Cleanliness, data=data1))
df2<-table(data1$satisfaction, data1$Cleanliness)
df2##
## 0 1 2 3 4 5
## satisfied 0 2607 3428 10581 14513 13768
## neutral or dissatisfied 12 10669 12653 13925 12587 8851b= data1[, c("satisfaction", "Cleanliness")]
db= xtabs(~ satisfaction + Cleanliness, data = b)
loglm(~ satisfaction + Cleanliness, data = db)## Call:
## loglm(formula = ~satisfaction + Cleanliness, data = db)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 10726.50 5 0
## Pearson 10204.56 5 0assocstats(df2)## X^2 df P(> X^2)
## Likelihood Ratio 10726 5 0
## Pearson 10205 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.299
## Cramer's V : 0.314mosaic(~satisfaction + Cleanliness, data = b,expected = ~satisfaction + Cleanliness, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(inflight3 <- xtabs(~satisfaction + Inflight.service, data=data1))
df3<-table(data1$satisfaction, data1$Inflight.service)
df3##
## 0 1 2 3 4 5
## satisfied 0 2046 3439 4833 18082 16497
## neutral or dissatisfied 3 5017 7975 15394 19764 10544c= data1[, c("satisfaction", "Inflight.service")]
dc= xtabs(~ satisfaction + Inflight.service, data = c)
loglm(~ satisfaction + Inflight.service, data = dc)## Call:
## loglm(formula = ~satisfaction + Inflight.service, data = dc)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 8496.132 5 0
## Pearson 8263.110 5 0assocstats(df3)## X^2 df P(> X^2)
## Likelihood Ratio 8496.1 5 0
## Pearson 8263.1 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.272
## Cramer's V : 0.282mosaic(~satisfaction + Inflight.service, data = c,expected = ~satisfaction + Inflight.service, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(inflight4 <- xtabs(~satisfaction + Inflight.entertainment, data=data1))
df4<-table(data1$satisfaction, data1$Inflight.entertainment)
df4##
## 0 1 2 3 4 5
## satisfied 0 1740 3750 5146 17954 16307
## neutral or dissatisfied 14 10701 13829 13934 11381 8838d= data1[, c("satisfaction", "Inflight.entertainment")]
dd= xtabs(~ satisfaction + Inflight.entertainment, data = d)
loglm(~ satisfaction + Inflight.entertainment, data = dd)## Call:
## loglm(formula = ~satisfaction + Inflight.entertainment, data = dd)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 19441.14 5 0
## Pearson 18475.80 5 0assocstats(df4)## X^2 df P(> X^2)
## Likelihood Ratio 19441 5 0
## Pearson 18476 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.389
## Cramer's V : 0.422mosaic(~satisfaction + Inflight.entertainment, data = d,expected = ~satisfaction + Inflight.entertainment, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(offflight1 <- xtabs(~satisfaction + Checkin.service, data=data1))
df5<-table(data1$satisfaction, data1$Checkin.service)
df5##
## 0 1 2 3 4 5
## satisfied 0 3076 3248 12717 13324 12532
## neutral or dissatisfied 1 9776 9606 15639 15651 8024e= data1[, c("satisfaction", "Checkin.service")]
de= xtabs(~ satisfaction + Checkin.service, data = e)
loglm(~ satisfaction + Checkin.service, data = de)## Call:
## loglm(formula = ~satisfaction + Checkin.service, data = de)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 6601.884 5 0
## Pearson 6390.388 5 0assocstats(df5)## X^2 df P(> X^2)
## Likelihood Ratio 6601.9 5 0
## Pearson 6390.4 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.241
## Cramer's V : 0.248mosaic(~satisfaction + Checkin.service, data = e,expected = ~satisfaction + Checkin.service, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(offflight2 <- xtabs(~satisfaction + Gate.location, data=data1))
df6<-table(data1$satisfaction, data1$Gate.location)
df6##
## 0 1 2 3 4 5
## satisfied 1 8677 8949 9889 9458 7923
## neutral or dissatisfied 0 8834 10447 18600 14895 5921f= data1[, c("satisfaction", "Gate.location")]
df= xtabs(~ satisfaction + Gate.location, data = f)
loglm(~ satisfaction + Gate.location, data = df)## Call:
## loglm(formula = ~satisfaction + Gate.location, data = df)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 2496.147 5 0
## Pearson 2490.876 5 0assocstats(df6)## X^2 df P(> X^2)
## Likelihood Ratio 2496.1 5 0
## Pearson 2490.9 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.153
## Cramer's V : 0.155mosaic(~satisfaction + Gate.location, data = f,expected = ~satisfaction + Gate.location, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(offflight3 <- xtabs(~satisfaction + Baggage.handling, data=data1))
df7<-table(data1$satisfaction, data1$Baggage.handling)
df7##
## 1 2 3 4 5
## satisfied 2148 3397 4848 17929 16575
## neutral or dissatisfied 5075 8086 15719 19345 10472g= data1[, c("satisfaction", "Baggage.handling")]
dg= xtabs(~ satisfaction + Baggage.handling, data = g)
loglm(~ satisfaction + Baggage.handling, data = dg)## Call:
## loglm(formula = ~satisfaction + Baggage.handling, data = dg)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 8840.719 4 0
## Pearson 8591.906 4 0assocstats(dg)## X^2 df P(> X^2)
## Likelihood Ratio 8840.7 4 0
## Pearson 8591.9 4 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.277
## Cramer's V : 0.288mosaic(~satisfaction + Baggage.handling, data = g,expected = ~satisfaction + Baggage.handling, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#(offflight4 <- xtabs(~satisfaction + Departure.Arrival.time.convenient, data=data1))
df8<-table(data1$satisfaction, data1$Departure.Arrival.time.convenient)
df8##
## 0 1 2 3 4 5
## satisfied 2516 7519 7639 7847 9879 9497
## neutral or dissatisfied 2774 7933 9503 10056 15595 12836h= data1[, c("satisfaction", "Departure.Arrival.time.convenient")]
dh= xtabs(~ satisfaction + Departure.Arrival.time.convenient, data = h)
loglm(~ satisfaction + Departure.Arrival.time.convenient, data = dh)## Call:
## loglm(formula = ~satisfaction + Departure.Arrival.time.convenient,
## data = dh)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 450.8870 5 0
## Pearson 450.3896 5 0assocstats(df8)## X^2 df P(> X^2)
## Likelihood Ratio 450.89 5 0
## Pearson 450.39 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.066
## Cramer's V : 0.066mosaic(~satisfaction + Departure.Arrival.time.convenient, data = h,expected = ~satisfaction + Departure.Arrival.time.convenient, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
#interactions
#do these factors cause frustration for users?
df9<-table(data1$satisfaction, data1$Inflight.service, data1$Departure.Arrival.time.convenient )
df9## , , = 0
##
##
## 0 1 2 3 4 5
## satisfied 0 236 284 299 850 847
## neutral or dissatisfied 0 314 305 444 936 775
##
## , , = 1
##
##
## 0 1 2 3 4 5
## satisfied 0 297 565 800 3133 2724
## neutral or dissatisfied 0 694 1471 2880 2385 503
##
## , , = 2
##
##
## 0 1 2 3 4 5
## satisfied 0 270 587 854 3155 2773
## neutral or dissatisfied 0 702 1411 3434 3181 775
##
## , , = 3
##
##
## 0 1 2 3 4 5
## satisfied 0 326 627 857 3109 2928
## neutral or dissatisfied 1 952 1572 3279 3100 1152
##
## , , = 4
##
##
## 0 1 2 3 4 5
## satisfied 0 429 691 1073 4016 3670
## neutral or dissatisfied 0 1209 1682 3210 5740 3754
##
## , , = 5
##
##
## 0 1 2 3 4 5
## satisfied 0 488 685 950 3819 3555
## neutral or dissatisfied 2 1146 1534 2147 4422 3585p= data1[, c("satisfaction", "Inflight.service", "Departure.Arrival.time.convenient")]
dp= xtabs(~ satisfaction + Inflight.service +Departure.Arrival.time.convenient, data = p)
loglm(~ satisfaction + Inflight.service + Departure.Arrival.time.convenient, data = dp)## Call:
## loglm(formula = ~satisfaction + Inflight.service + Departure.Arrival.time.convenient,
## data = dp)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 13977.01 60 0
## Pearson 12988.15 60 0assocstats(df9)## $`:0`
## X^2 df P(> X^2)
## Likelihood Ratio 35.08 5 1.4505e-06
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaN
##
## $`:1`
## X^2 df P(> X^2)
## Likelihood Ratio 3600.4 5 0
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaN
##
## $`:2`
## X^2 df P(> X^2)
## Likelihood Ratio 3202.8 5 0
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaN
##
## $`:3`
## X^2 df P(> X^2)
## Likelihood Ratio 2780.7 5 0
## Pearson 2673.3 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.36
## Cramer's V : 0.386
##
## $`:4`
## X^2 df P(> X^2)
## Likelihood Ratio 942.96 5 0
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaN
##
## $`:5`
## X^2 df P(> X^2)
## Likelihood Ratio 626.79 5 0
## Pearson 613.19 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.163
## Cramer's V : 0.166mosaic(~satisfaction + Inflight.service + Departure.Arrival.time.convenient, data = p,expected = ~satisfaction + Inflight.service + Departure.Arrival.time.convenient, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
df10<-table(data1$satisfaction, data1$Inflight.service, data1$Class)
df10## , , = Eco Plus
##
##
## 0 1 2 3 4 5
## satisfied 0 242 303 354 503 434
## neutral or dissatisfied 0 446 647 1609 2010 920
##
## , , = Business
##
##
## 0 1 2 3 4 5
## satisfied 0 809 1916 3070 14882 13713
## neutral or dissatisfied 3 1590 2692 4103 4575 2180
##
## , , = Eco
##
##
## 0 1 2 3 4 5
## satisfied 0 995 1220 1409 2697 2350
## neutral or dissatisfied 0 2981 4636 9682 13179 7444q= data1[, c("satisfaction", "Inflight.service", "Class")]
dq= xtabs(~ satisfaction + Inflight.service + Class, data = q)
loglm(~ satisfaction + Inflight.service + Class, data = dq)## Call:
## loglm(formula = ~satisfaction + Inflight.service + Class, data = dq)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 40014.16 27 0
## Pearson 41635.17 27 0assocstats(df10)## $`:Eco Plus`
## X^2 df P(> X^2)
## Likelihood Ratio 180.86 5 0
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaN
##
## $`:Business`
## X^2 df P(> X^2)
## Likelihood Ratio 7938.3 5 0
## Pearson 8111.7 5 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.375
## Cramer's V : 0.405
##
## $`:Eco`
## X^2 df P(> X^2)
## Likelihood Ratio 602.7 5 0
## Pearson NaN 5 NaN
##
## Phi-Coefficient : NA
## Contingency Coeff.: NaN
## Cramer's V : NaNmosaic(~satisfaction + Inflight.service + Class, data = q, expected = ~satisfaction + Inflight.service + Class, shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))
df1<-table(data1$satisfaction, data1$Class)
df1##
## Eco Plus Business Eco
## satisfied 1836 34390 8671
## neutral or dissatisfied 5632 15143 37922a= data1[, c("satisfaction","Class")]
da= xtabs(~ satisfaction + Class, data = a)
loglm(~ satisfaction + Class, data = da)## Call:
## loglm(formula = ~satisfaction + Class, data = da)
##
## Statistics:
## X^2 df P(> X^2)
## Likelihood Ratio 27672.09 2 0
## Pearson 26402.22 2 0assocstats(df1)## X^2 df P(> X^2)
## Likelihood Ratio 27672 2 0
## Pearson 26402 2 0
##
## Phi-Coefficient : NA
## Contingency Coeff.: 0.451
## Cramer's V : 0.505mosaic(~satisfaction + Class, data = da,expected = ~satisfaction * Class,shade = TRUE, labeling = labeling_values, supress=0,rot_labels=c(0,0,0,90))## Warning in legend(residuals, gpfun, residuals_type): All residuals are zero.