Practice problems
Colleges <- data.frame(
College = c("William and Mary", "Christopher Newport", "George Mason", "James Madison", "Longwood",
"Norfolk State", "Old Dominion", "Radford", "Mary Washington", "Virginia",
"Virginia Commonwealth", "Virginia Military Institute", "Virginia Tech", "Virginia State"),
Employees = c(2104, 922, 4043, 2833, 746, 919, 2369, 1273, 721, 7431, 5825, 550, 7303, 761),
TopSalary = c(425000, 381486, 536714, 428400, 328268, 295000, 448272, 312080, 449865, 561099,
503154, 364269, 500000, 356524),
MedianSalary = c(56496, 47895, 63029, 53080, 52000, 49605, 54416, 51000, 53045, 60048,
55000, 44999, 51656, 55925)
)
print(Colleges)
## College Employees TopSalary MedianSalary
## 1 William and Mary 2104 425000 56496
## 2 Christopher Newport 922 381486 47895
## 3 George Mason 4043 536714 63029
## 4 James Madison 2833 428400 53080
## 5 Longwood 746 328268 52000
## 6 Norfolk State 919 295000 49605
## 7 Old Dominion 2369 448272 54416
## 8 Radford 1273 312080 51000
## 9 Mary Washington 721 449865 53045
## 10 Virginia 7431 561099 60048
## 11 Virginia Commonwealth 5825 503154 55000
## 12 Virginia Military Institute 550 364269 44999
## 13 Virginia Tech 7303 500000 51656
## 14 Virginia State 761 356524 55925
Soal 1 (Memilih entri pertama, ketiga, kesepuluh, dan kedua belas
dari vektor TopSalary)
Colleges$TopSalary[c(1, 3, 10, 12)]
## [1] 425000 536714 561099 364269
Soal 3 (Memilih universitas dengan jumlah karyawan <= 1000)
Colleges[Colleges$Employees <= 1000, ]
## College Employees TopSalary MedianSalary
## 2 Christopher Newport 922 381486 47895
## 5 Longwood 746 328268 52000
## 6 Norfolk State 919 295000 49605
## 9 Mary Washington 721 449865 53045
## 12 Virginia Military Institute 550 364269 44999
## 14 Virginia State 761 356524 55925
Soal 4 (Memilih 5 universitas secara acak)
Colleges[sample(1:nrow(Colleges), size = 5), ]
## College Employees TopSalary MedianSalary
## 7 Old Dominion 2369 448272 54416
## 10 Virginia 7431 561099 60048
## 9 Mary Washington 721 449865 53045
## 13 Virginia Tech 7303 500000 51656
## 6 Norfolk State 919 295000 49605
Countries <- data.frame(
Nation = c("China", "India", "United States", "Indonesia", "Brazil", "Pakistan",
"Nigeria", "Bangladesh", "Russia", "Mexico"),
Region = c("Asia", "Asia", "North America", "Asia", "South America", "Asia",
"Africa", "Asia", "Europe", "North America"),
Population = c(1409517397, 1339180127, 324459463, 263991379, 209288278,
197015955, 190886311, 164669751, 143989754, 129163276),
PctIncrease = c(0.40, 1.10, 0.70, 1.10, 0.80, 2.00, 2.60, 1.10, 0.00, 1.30),
GDPcapita = c(8582, 1852, 57467, 3895, 10309, 1629, 2640, 1524, 10248, 8562)
)
# Melihat data frame
print(Countries)
## Nation Region Population PctIncrease GDPcapita
## 1 China Asia 1409517397 0.4 8582
## 2 India Asia 1339180127 1.1 1852
## 3 United States North America 324459463 0.7 57467
## 4 Indonesia Asia 263991379 1.1 3895
## 5 Brazil South America 209288278 0.8 10309
## 6 Pakistan Asia 197015955 2.0 1629
## 7 Nigeria Africa 190886311 2.6 2640
## 8 Bangladesh Asia 164669751 1.1 1524
## 9 Russia Europe 143989754 0.0 10248
## 10 Mexico North America 129163276 1.3 8562
Soal 5 (Memilih baris dengan GDP per capita kurang dari 10000 dan
bukan dari region Asia)
subset(Countries, GDPcapita < 10000 & Region != "Asia")
## Nation Region Population PctIncrease GDPcapita
## 7 Nigeria Africa 190886311 2.6 2640
## 10 Mexico North America 129163276 1.3 8562
Soal 6 (Memilih sampel acak dari 3 negara)
Countries[sample(nrow(Countries), 3), ]
## Nation Region Population PctIncrease GDPcapita
## 3 United States North America 324459463 0.7 57467
## 7 Nigeria Africa 190886311 2.6 2640
## 2 India Asia 1339180127 1.1 1852
Soal 7 (Memilih negara dengan persentase peningkatan populasi lebih
dari 1.5%)
subset(Countries, PctIncrease > 1.5)
## Nation Region Population PctIncrease GDPcapita
## 6 Pakistan Asia 197015955 2.0 1629
## 7 Nigeria Africa 190886311 2.6 2640
Olympics <- data.frame(
Year = c(1992, 1992, 1994, 1996, 1998, 2000, 2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018),
Type = c("Summer", "Winter", "Winter", "Summer", "Winter", "Summer", "Winter", "Summer",
"Winter", "Summer", "Winter", "Summer", "Winter", "Summer", "Winter"),
Host = c("Spain", "France", "Norway", "United States", "Japan", "Australia", "United States",
"Greece", "Italy", "China", "Canada", "United Kingdom", "Russia", "Brazil", "South Korea"),
Competitors = c(9356, 1801, 1737, 10318, 2176, 10651, 2399, 10625, 2508, 10942, 2566, 10768, 2873, 11238, 2922),
Events = c(257, 57, 61, 271, 68, 300, 78, 301, 84, 302, 86, 302, 98, 306, 102),
Nations = c(169, 64, 67, 197, 72, 199, 78, 201, 80, 204, 82, 204, 88, 207, 92),
Leader = c("Unified Team", "Germany", "Russia", "United States", "Germany", "United States",
"Norway", "United States", "Germany", "China", "Canada", "United States",
"Russia", "United States", "Norway")
)
print(Olympics)
## Year Type Host Competitors Events Nations Leader
## 1 1992 Summer Spain 9356 257 169 Unified Team
## 2 1992 Winter France 1801 57 64 Germany
## 3 1994 Winter Norway 1737 61 67 Russia
## 4 1996 Summer United States 10318 271 197 United States
## 5 1998 Winter Japan 2176 68 72 Germany
## 6 2000 Summer Australia 10651 300 199 United States
## 7 2002 Winter United States 2399 78 78 Norway
## 8 2004 Summer Greece 10625 301 201 United States
## 9 2006 Winter Italy 2508 84 80 Germany
## 10 2008 Summer China 10942 302 204 China
## 11 2010 Winter Canada 2566 86 82 Canada
## 12 2012 Summer United Kingdom 10768 302 204 United States
## 13 2014 Winter Russia 2873 98 88 Russia
## 14 2016 Summer Brazil 11238 306 207 United States
## 15 2018 Winter South Korea 2922 102 92 Norway
Soal 8 (Baris di mana Host adalah juga Leader)
host_leader <- Olympics[Olympics$Host == Olympics$Leader, ]
print(host_leader)
## Year Type Host Competitors Events Nations Leader
## 4 1996 Summer United States 10318 271 197 United States
## 10 2008 Summer China 10942 302 204 China
## 11 2010 Winter Canada 2566 86 82 Canada
## 13 2014 Winter Russia 2873 98 88 Russia
Soal 9 ( Baris di mana Competitors per Event lebih besar dari
35)
competitors_per_event <- Olympics[Olympics$Competitors / Olympics$Events > 35, ]
print(competitors_per_event)
## Year Type Host Competitors Events Nations Leader
## 1 1992 Summer Spain 9356 257 169 Unified Team
## 4 1996 Summer United States 10318 271 197 United States
## 6 2000 Summer Australia 10651 300 199 United States
## 8 2004 Summer Greece 10625 301 201 United States
## 10 2008 Summer China 10942 302 204 China
## 12 2012 Summer United Kingdom 10768 302 204 United States
## 14 2016 Summer Brazil 11238 306 207 United States
Soal 10 ( Baris di Olimpiade Musim Dingin dengan jumlah Nations
minimal 80)
winter_olympics_nations <- Olympics[Olympics$Type == "Winter" & Olympics$Nations >= 80, ]
print(winter_olympics_nations)
## Year Type Host Competitors Events Nations Leader
## 9 2006 Winter Italy 2508 84 80 Germany
## 11 2010 Winter Canada 2566 86 82 Canada
## 13 2014 Winter Russia 2873 98 88 Russia
## 15 2018 Winter South Korea 2922 102 92 Norway