'data.frame': 8693 obs. of 14 variables:
$ PassengerId : chr "0001_01" "0002_01" "0003_01" "0003_02" ...
$ HomePlanet : chr "Europa" "Earth" "Europa" "Europa" ...
$ CryoSleep : chr "False" "False" "False" "False" ...
$ Cabin : chr "B/0/P" "F/0/S" "A/0/S" "A/0/S" ...
$ Destination : chr "TRAPPIST-1e" "TRAPPIST-1e" "TRAPPIST-1e" "TRAPPIST-1e" ...
$ Age : num 39 24 58 33 16 44 26 28 35 14 ...
$ VIP : chr "False" "False" "True" "False" ...
$ RoomService : num 0 109 43 0 303 0 42 0 0 0 ...
$ FoodCourt : num 0 9 3576 1283 70 ...
$ ShoppingMall: num 0 25 0 371 151 0 3 0 17 0 ...
$ Spa : num 0 549 6715 3329 565 ...
$ VRDeck : num 0 44 49 193 2 0 0 NA 0 0 ...
$ Name : chr "Maham Ofracculy" "Juanna Vines" "Altark Susent" "Solam Susent" ...
$ Transported : chr "False" "True" "False" "False" ...Spaceship Titanic Project
The objective of this project is to conduct an exploratory data analysis of the Spaceship Titanic data set using statistics summary and visualization approaches to explore the data and to identify interesting patterns and significant information within the data.
Check data structure
Getting insights from the variables
1. Where were the home planets of the passengers departed from?
The passengers departed from three main home planets Earth, Europa, and Mars. About half of those passengers (53%) were from Earth. There’re small number (2%) of passengers whose their home planets information are missing.
Passenger count by HomePlanet:
HomePlanet Count Total %
Earth 4602 53
Europa 2131 25
Mars 1759 20
Unknown 201 2
Sum 8693 100
2. Which planet destination most passengers would be debarking to?
There are three destinations the passengers would be debarking to 55 Cancri e, PSO J318.5-22, and TRAPPIST-1e. TRAPPIST-1e appears to be the top destination; 68% of the passengers were to emigrate there.
Passenger count by Destination:
Destination Count Total %
55 Cancri e 1800 21
PSO J318.5-22 796 9
TRAPPIST-1e 5915 68
Unknown 182 2
Sum 8693 100
3. Top 3 HomePlanet and Destination pairs
The majority of passengers were emigrating from Earth to TRAPPIST-1e (36% of the passengers). The 2nd and 3rd were Mars to TRAPPIST-1e and Europa to TRAPPIST-1e respectively. Though, there were higher number of passengers from Earth who were being transported to TRAPPIST-1e, those from Mars shows higher likelihood to emigrate to TRAPPIST-1e than Earth passengers (84% of passengers from Mars opted to emigrate to TRAPPIST-1e vs. 67% of those from Earth). Passengers from Europa were the only group that shows most interest in emigrating to 55 Cancri e (42% of Europa Passengers were heading there). PSO J318.5-22 appears to be the least appealing destination among the passengers.
HomePlanet & Destination pairs (count):
HomePlanet Destination n percent_total
1 Earth TRAPPIST-1e 3101 36
2 Mars TRAPPIST-1e 1475 17
3 Europa TRAPPIST-1e 1189 14
4 Europa 55 Cancri e 886 10
5 Earth PSO J318.5-22 712 8
6 Earth 55 Cancri e 690 8
7 Mars 55 Cancri e 193 2
8 Unknown TRAPPIST-1e 150 2
9 Earth Unknown 99 1
10 Mars PSO J318.5-22 49 1
11 Mars Unknown 42 0
12 Europa Unknown 37 0
13 Unknown 55 Cancri e 31 0
14 Europa PSO J318.5-22 19 0
15 Unknown PSO J318.5-22 16 0
16 Unknown Unknown 4 0Crosstab of HomePlanet & Destination (row %):
Destination 55 Cancri e PSO J318.5-22 TRAPPIST-1e Unknown Sum
HomePlanet
Earth 14.99 15.47 67.38 2.15 100.00
Europa 41.58 0.89 55.80 1.74 100.00
Mars 10.97 2.79 83.85 2.39 100.00
Unknown 15.42 7.96 74.63 1.99 100.004. Who got transported based on HomePlanet and Destination?
Despite the higher number of passengers from Earth on board comparing to the other two home planets, there was a higher percentage among passengers from Europa who got transported (66% of passengers from Europa were transported vs. 42% of passengers from Earth). Home planet Earth appears to have a higher likelihood of those passengers who were not transported.
Passengers of 55 Cancri e destination show the highest portion of being transported (61% of passengers got transported comparing to 47% of those with TRAPPIST-1e destination).
Crosstab of HomePlanet & Transported:
Count Row %
Transported False True False True
HomePlanet
Earth 2651 1951 58 42
Europa 727 1404 34 66
Mars 839 920 48 52
Unknown 98 103 49 51Crosstab of Destination & Transported:
Count Row %
Transported False True False True
Destination
55 Cancri e 702 1098 39 61
PSO J318.5-22 395 401 50 50
TRAPPIST-1e 3128 2787 53 47
Unknown 90 92 49 51Transported passengers by HomePlanet and Destination:
5. What did the age groups look like among the passengers?
Average age of the passengers were 29, youngest passengers were 0 (assuming they were newborns who hadn’t reach 1 year old), and the oldest passengers were 79. The majority of the passengers (53%) were adult between 20-39. There were much smaller passengers among those children 0-12 (9%) and senior 60+ (3%).
Among the transported passengers, children 0-12 shows the highest likelihood of being transported (70%) than the older age groups.
Summary statistics (Age):
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
0.00 19.00 27.00 28.83 38.00 79.00 179 Age distribution of the passengers:
Age group (count):
Age_group Count Total %
Children 0-12 806 9
Teen 13-19 1352 16
Adult 20-39 4497 53
Adult 40-59 1605 19
Senior 60+ 254 3
Sum 8514 100Crosstab of Age group & Transported:
Count Row %
Transported False True Sum False True Sum
Age_group
Children 0-12 242 564 806 30 70 100
Teen 13-19 645 707 1352 48 52 100
Adult 20-39 2405 2092 4497 53 47 100
Adult 40-59 799 806 1605 50 50 100
Senior 60+ 135 119 254 53 47 100Age distribution of the passengers by Transported groups:
6. Who used CryoSleep during the voyage?
More passengers (64%) opted to not be put into CryoSleep. Younger passengers (children 0-12 and teens 13-19) appears to have slightly higher percentage to use CryoSleep than older groups. There’s significant percentage indicating those who opted to use CryoSleep had a higher chance (82%) being transported comparing to those who didn’t opt CryoSleep with more likelihood 67% for not being transported.
Passenger opting CryoSleep (count):
CryoSleep Count Total %
False 5439 64
True 3037 36
Sum 8476 100CryoSleep vs Avg passenger age:
# A tibble: 3 × 2
CryoSleep Avg_age
<chr> <dbl>
1 False 30
2 True 27
3 <NA> 28Crosstab of Age group & CryoSleep:
Count Row %
CryoSleep False True Sum False True Sum
Age_group
Children 0-12 406 377 783 52 48 100
Teen 13-19 758 555 1313 58 42 100
Adult 20-39 2973 1416 4389 68 32 100
Adult 40-59 1042 524 1566 67 33 100
Senior 60+ 164 83 247 66 34 100Crosstab of CryoSleep & Transported:
Count Row %
Transported False True Sum False True Sum
CryoSleep
False 3650 1789 5439 67 33 100
True 554 2483 3037 18 82 100Passengers in cryosleep vs Transported:
Count of passengers opting CryoSleep by HomePlanet and Destination:
HomePlanet 55 Cancri e PSO J318.5-22 TRAPPIST-1e Unknown Total
Earth 205 355 809 13 1382
Europa 441 9 447 14 911
Mars 76 11 561 21 669
Unknown 17 8 50 0 75
Total 739 383 1867 48 30377. Who were those VIP passengers? Did many of them get transported?
There was only a small group (2%) of the passengers who paid for VIP service during the voyage. Among those VIP passengers were adult and senior age groups. Interestingly, there were no passengers from Earth paid for VIP - only those from Europa and Mars paid for the service.
More than half (62%) of those VIP passengers didn’t get transported to their destination.
VIP passengers (count):
VIP Count Total %
False 8291 98
True 199 2
Sum 8490 100VIP passengers vs Avg age:
# A tibble: 3 × 2
VIP Avg_age
<chr> <dbl>
1 False 29
2 True 37
3 <NA> 28VIP passengers vs Age group:
Count Row %
VIP False True Sum False True Sum
Age_group
Children 0-12 782 0 782 100 0 100
Teen 13-19 1317 2 1319 100 0 100
Adult 20-39 4270 131 4401 97 3 100
Adult 40-59 1515 54 1569 97 3 100
Senior 60+ 235 11 246 96 4 100VIP passengers vs Transported:
Count Row %
Transported False True Sum False True Sum
VIP
False 4093 4198 8291 49 51 100
True 123 76 199 62 38 100Count of VIP passengers by HomePlanet and Destination (% column):
HomePlanet 55 Cancri e PSO J318.5-22 TRAPPIST-1e Unknown Total
Europa 96.9% (63) 55.6% (10) 49.1% (56) 100.0% (2) 65.8% (131)
Mars 0.0% (0) 44.4% (8) 48.2% (55) 0.0% (0) 31.7% (63)
Unknown 3.1% (2) 0.0% (0) 2.6% (3) 0.0% (0) 2.5% (5)
Total 100.0% (65) 100.0% (18) 100.0% (114) 100.0% (2) 100.0% (199)VIP passengers vs Transported:
8. Who were those big spenders on board?
It appears Europa passengers were the biggest spender on the luxury amenities; 6.8 million in total bill with an average of 3.5 thousand per passenger. Earth passengers appears to be the second in spending by total billed at 2.8 million. But because Earth passengers were the largest group on board, they were actually the least spenders with an average of 688 per passenger. Adult 20-39 group was the top spender by total billed (6.8 million) while Senior 60+ was the top spender by average spending per passenger (around 2 thousand per passenger).
Top 5 spenders by Total bill:
Name Age HomePlanet Destination VIP Transported Total_bill
1 Markar Radisiouss 68 Europa 55 Cancri e False False 35987
2 Pulchib Quidedbolt 41 Europa 55 Cancri e True True 31076
3 Scharab Conale 31 Europa 55 Cancri e True True 31074
4 Mirfar Optionful 18 Europa TRAPPIST-1e False False 30478
5 Maiam Oilloody 36 Europa 55 Cancri e False False 29608Sum of Total bill by HomePlanet:
# A tibble: 4 × 2
HomePlanet Sum_Total_bill
<chr> <dbl>
1 Europa 6828385
2 Earth 2823306
3 Mars 1696039
4 Unknown 209893Average Total bill by HomePlanet:
# A tibble: 4 × 2
HomePlanet Avg_Total_bill
<chr> <dbl>
1 Europa 3553.
2 Unknown 1147.
3 Mars 1074.
4 Earth 688.Boxplot of HomePlanet vs Total bill:
Sum of Total bill by Destination:
# A tibble: 4 × 2
Destination Sum_Total_bill
<chr> <dbl>
1 TRAPPIST-1e 7316054
2 55 Cancri e 3606677
3 PSO J318.5-22 416911
4 Unknown 217981Average Total bill by Destination:
# A tibble: 4 × 2
Destination Avg_Total_bill
<chr> <dbl>
1 55 Cancri e 2235.
2 TRAPPIST-1e 1382.
3 Unknown 1337.
4 PSO J318.5-22 582.Sum of Total bill by Age group:
# A tibble: 6 × 2
Age_group Sum_Total_bill
<fct> <dbl>
1 Adult 20-39 6896604
2 Adult 40-59 2841561
3 Teen 13-19 1154290
4 Senior 60+ 460733
5 <NA> 204435
6 Children 0-12 0Average Total bill by Age group:
# A tibble: 6 × 2
Age_group Avg_Total_bill
<fct> <dbl>
1 Senior 60+ 2012.
2 Adult 40-59 1971.
3 Adult 20-39 1717.
4 <NA> 1239
5 Teen 13-19 952.
6 Children 0-12 0 Boxplot of Age group vs Total bill:
Sum of Total bill by Transported:
# A tibble: 2 × 2
Transported Sum_Total_bill
<chr> <dbl>
1 False 7938955
2 True 3618668Boxplot of Transported vs Total bill:
9. How many passengers got transported?
Half of the passengers on board got transported to another dimension.
Passengers count by Transported:
Transported Count Total %
False 4315.0 49.6
True 4378.0 50.4
Sum 8693.0 100.0Conclusion
The Spaceship Titanic data has records of 8,693 passengers (observations) who were on the spaceship emigrating to new habitable planets. The dataset collects the passenger information including their Name, HomePlanet, Destination, Age, amenity usage like CryoSleep, their spending on luxury amenities, VIP status, and whether they were transported to another dimension.
After analyzing the data, it was found that the passengers were from Earth, Europa, and Mars emigrating to these three new destinations 55 Cancri e, PSO J318.5-22, and TRAPPIST-1e. Earth passengers were the largest group among all passengers (4,602 / 53%). TRAPPIST-1e was the destination where the majority of the passengers were debarking to (5,915 / 68%). The passenger age ranges from youngest (less than 1 year old) to oldest 79 years old. The largest age group were those adult age 20-39 (4,497 / 53%). More passengers (5,439 / 64%) opted to not be put into CryoSleep for the duration of the voyage. There was very small group of passengers (199 / 2%) who paid for VIP service. The passengers from Europa were dominating the VIP service and they were also the biggest spenders on the luxury amenities.
Among the passengers who were transported to an alternate dimension, a combination of the following factors indicate higher chance of being transported. The passengers from Europa (61%), those who would be debarking to 55 Cancri e (61%), those children age group between 0-12 (70%), those who opted to use CryoSleep (82%), and those who spent less on amenities and non-VIP.