Canada EDA Visualization - box plot
Group C
12/22/2021
Descriptive Analysis Question
Q5 - What are the minimum, median, maximum, inter quartile range, and outlier values for immigrants to Canada from 1980 to 2013 per decade. Visualized by box plot
Import the necessary libraries
library(tidyr) #For data manipulation and ggplot
library(dplyr) #For data manipulation##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggpubr) #For sub plotting## Loading required package: ggplot2DF <- read.csv('/Users/salahkaf/Desktop/UpdatedDF.csv') #Reading the DFWrangling the table part 1
total_decade80s = vector(mode = "list") # creating empty lists to append the values for each year using for loop
total_decade90s = vector(mode = "list")
total_decade2000s = vector(mode = "list")
Years20s <- for (country in DF$Country) {
a <- select(filter(DF, Country == country), X2000:X2009 )
total <- apply(a, 1, sum)
total_decade2000s <- append(total_decade2000s, total)
}
Years90s <- for (country in DF$Country) {
a <- select(filter(DF, Country == country), X1990:X1999 )
total <- apply(a, 1, sum)
total_decade90s <- append(total_decade90s, total)
}
Years80s <- for (country in DF$Country) {
a <- select(filter(DF, Country == country), X1980:X1989 )
total <- apply(a, 1, sum)
total_decade80s <- append(total_decade80s, total)
}Wrangling the table part 2
total_decade <- as.data.frame(cbind(DF$Country, total_decade80s,total_decade90s,total_decade2000s)) # making a data frame using the appended lists
total_decade <- total_decade[-nrow(total_decade),] #deleting the total row
names(total_decade) <- c("Country", "1980s", "1990s", "2000s")
total_decade$`1980s` <- as.integer(total_decade$`1980s`) # changing the values of each column to integer
total_decade$`1990s` <- as.integer(total_decade$`1990s`)
total_decade$`2000s` <- as.integer(total_decade$`2000s`)
total_decade## Country 1980s 1990s 2000s
## 1 Afghanistan 3693 15845 30501
## 2 Albania 9 2568 10799
## 3 Algeria 1271 13153 37833
## 4 American Samoa 3 2 1
## 5 Andorra 2 6 5
## 6 Angola 50 285 1563
## 7 Antigua and Barbuda 291 315 235
## 8 Argentina 3738 5686 8890
## 9 Armenia 0 602 1755
## 10 Australia 4564 6574 8804
## 11 Austria 1968 1546 1071
## 12 Azerbaijan 0 238 1846
## 13 Bahamas 243 195 190
## 14 Bahrain 29 145 181
## 15 Bangladesh 2376 18532 30816
## 16 Barbados 2935 2388 1153
## 17 Belarus 0 1755 4901
## 18 Belgium 3351 2430 3505
## 19 Belize 274 344 303
## 20 Benin 65 226 1199
## 21 Bhutan 2 18 951
## 22 Bolivia (Plurinational State of) 644 1062 1043
## 23 Bosnia and Herzegovina 0 17789 3518
## 24 Botswana 49 21 91
## 25 Brazil 2530 6931 12736
## 26 Brunei Darussalam 295 221 57
## 27 Bulgaria 337 7481 13608
## 28 Burkina Faso 48 154 920
## 29 Burundi 24 1085 4704
## 30 Cabo Verde 36 104 47
## 31 Cambodia 171 2175 3275
## 32 Cameroon 142 1137 6358
## 33 Canada 0 16 0
## 34 Central African Republic 17 69 206
## 35 Chad 28 260 1005
## 36 Chile 9475 6874 3932
## 37 China 32003 161528 340385
## 38 China, Hong Kong Special Administrative Region 0 681 5930
## 39 China, Macao Special Administrative Region 0 0 188
## 40 Colombia 3069 6252 45811
## 41 Comoros 11 26 81
## 42 Congo 17 237 1071
## 43 Costa Rica 735 1283 1827
## 44 Côte d'Ivoire 179 738 3478
## 45 Croatia 0 5260 2278
## 46 Cuba 1214 3969 10553
## 47 Cyprus 686 276 112
## 48 Czech Republic 0 1452 2097
## 49 Democratic People's Republic of Korea 13 31 119
## 50 Democratic Republic of the Congo 302 5184 13869
## 51 Denmark 1596 1074 871
## 52 Djibouti 24 266 741
## 53 Dominica 814 826 660
## 54 Dominican Republic 1986 3846 2949
## 55 Ecuador 2298 4398 4136
## 56 Egypt 7556 20040 24784
## 57 El Salvador 21648 24334 6138
## 58 Equatorial Guinea 1 8 29
## 59 Eritrea 0 427 4856
## 60 Estonia 0 474 347
## 61 Ethiopia 3263 10766 13609
## 62 Fiji 5721 9397 4279
## 63 Finland 1132 743 633
## 64 France 17137 30028 41297
## 65 Gabon 22 90 549
## 66 Gambia 38 244 209
## 67 Georgia 0 357 1174
## 68 Germany 18217 14186 23581
## 69 Ghana 2898 13480 7276
## 70 Greece 7361 3263 1139
## 71 Grenada 1938 3342 3118
## 72 Guatemala 6074 9693 2441
## 73 Guinea 67 493 2714
## 74 Guinea-Bissau 8 23 44
## 75 Guyana 32096 27260 13340
## 76 Haiti 22546 21710 19290
## 77 Honduras 756 3691 1613
## 78 Hungary 5522 5036 4898
## 79 Iceland 120 127 141
## 80 India 82154 180395 303591
## 81 Indonesia 1824 2554 6888
## 82 Iran (Islamic Republic of) 21477 54871 65794
## 83 Iraq 3985 18140 26568
## 84 Ireland 7647 3909 2596
## 85 Israel 11975 20792 24937
## 86 Italy 11487 5734 3610
## 87 Jamaica 34328 40329 22733
## 88 Japan 4296 8077 10705
## 89 Jordan 2733 10481 16265
## 90 Kazakhstan 0 2291 4631
## 91 Kenya 4468 4434 5845
## 92 Kiribati 3 5 5
## 93 Kuwait 67 987 725
## 94 Kyrgyzstan 0 207 1429
## 95 Lao People's Democratic Republic 180 368 425
## 96 Latvia 1 686 1051
## 97 Lebanon 24918 49245 30906
## 98 Lesotho 32 37 24
## 99 Liberia 31 384 1979
## 100 Libya 310 1051 2258
## 101 Liechtenstein 13 18 6
## 102 Lithuania 5 680 1398
## 103 Luxembourg 49 53 81
## 104 Madagascar 240 373 861
## 105 Malawi 36 85 110
## 106 Malaysia 9281 8172 5191
## 107 Maldives 1 7 13
## 108 Mali 44 422 1016
## 109 Malta 1111 193 204
## 110 Marshall Islands 0 0 2
## 111 Mauritania 27 71 656
## 112 Mauritius 3292 2286 5509
## 113 Mexico 6131 12170 24376
## 114 Monaco 3 9 8
## 115 Mongolia 0 15 498
## 116 Montenegro 0 0 37
## 117 Morocco 4792 11695 38000
## 118 Mozambique 27 50 57
## 119 Myanmar 466 1370 6030
## 120 Namibia 26 26 122
## 121 Nauru 2 1 14
## 122 Nepal 51 769 4388
## 123 Netherlands 10228 6857 7555
## 124 New Caledonia 0 0 3
## 125 New Zealand 2719 2344 3626
## 126 Nicaragua 4132 6581 963
## 127 Niger 7 86 489
## 128 Nigeria 993 5052 19063
## 129 Norway 720 718 682
## 130 Oman 12 50 114
## 131 Pakistan 10591 65302 127598
## 132 Palau 0 0 1
## 133 Panama 244 2173 553
## 134 Papua New Guinea 17 16 22
## 135 Paraguay 434 488 729
## 136 Peru 6424 10206 12384
## 137 Philippines 60764 138482 172904
## 138 Poland 57602 64864 13629
## 139 Portugal 40432 26904 4484
## 140 Qatar 2 43 71
## 141 Republic of Korea 16259 38189 68183
## 142 Republic of Moldova 0 1527 7852
## 143 Romania 7613 33659 45515
## 144 Russian Federation 0 19013 35535
## 145 Rwanda 62 1360 3404
## 146 Saint Kitts and Nevis 225 245 110
## 147 Saint Lucia 848 994 1676
## 148 Saint Vincent and the Grenadines 1724 2487 3550
## 149 Samoa 23 25 20
## 150 San Marino 2 1 1
## 151 Sao Tome and Principe 0 2 5
## 152 Saudi Arabia 90 585 1589
## 153 Senegal 135 809 3146
## 154 Serbia 0 0 677
## 155 Seychelles 117 998 120
## 156 Sierra Leone 158 461 2438
## 157 Singapore 3969 4612 4687
## 158 Slovakia 0 1617 3836
## 159 Slovenia 0 237 205
## 160 Somalia 905 23103 11428
## 161 South Africa 8679 14019 13190
## 162 Spain 1740 1100 1232
## 163 Sri Lanka 14796 70421 49678
## 164 State of Palestine 0 360 3948
## 165 Sudan 357 4950 11269
## 166 Suriname 172 352 171
## 167 Swaziland 36 32 48
## 168 Sweden 2011 1652 1630
## 169 Switzerland 5151 6198 3334
## 170 Syrian Arab Republic 5799 11340 10643
## 171 Tajikistan 0 36 295
## 172 Thailand 954 2091 4538
## 173 The former Yugoslav Republic of Macedonia 0 978 3103
## 174 Togo 82 416 1817
## 175 Tonga 41 60 26
## 176 Trinidad and Tobago 12851 25719 8930
## 177 Tunisia 840 2718 8154
## 178 Turkey 4369 8680 14186
## 179 Turkmenistan 0 24 202
## 180 Tuvalu 3 1 3
## 181 Uganda 362 707 1524
## 182 Ukraine 0 14644 26340
## 183 United Arab Emirates 34 198 358
## 184 United Kingdom of Great Britain and Northern Ireland 179171 261966 83413
## 185 United Republic of Tanzania 5630 3490 2555
## 186 United States of America 76824 56915 75173
## 187 Uruguay 1342 1833 1261
## 188 Uzbekistan 0 459 2056
## 189 Vanuatu 0 5 6
## 190 Venezuela (Bolivarian Republic of) 1816 4826 9780
## 191 Viet Nam 30638 37726 21274
## 192 Western Sahara 0 1 1
## 193 Yemen 72 756 1395
## 194 Zambia 221 548 632
## 195 Zimbabwe 790 667 5369
## 196 Unknown 201844 249985 53780total_decade <- filter(total_decade , `1980s`<1000 & `1990s`<1000 & `2000s`<2500 ) #filtering the data to avoid outliers
total_decade <- gather(total_decade, Decades, value, 2:4) #reshaping the data to a from suitable for box plotting
total_decade## Country Decades value
## 1 American Samoa 1980s 3
## 2 Andorra 1980s 2
## 3 Angola 1980s 50
## 4 Antigua and Barbuda 1980s 291
## 5 Armenia 1980s 0
## 6 Azerbaijan 1980s 0
## 7 Bahamas 1980s 243
## 8 Bahrain 1980s 29
## 9 Belize 1980s 274
## 10 Benin 1980s 65
## 11 Bhutan 1980s 2
## 12 Botswana 1980s 49
## 13 Brunei Darussalam 1980s 295
## 14 Burkina Faso 1980s 48
## 15 Cabo Verde 1980s 36
## 16 Canada 1980s 0
## 17 Central African Republic 1980s 17
## 18 Chad 1980s 28
## 19 China, Macao Special Administrative Region 1980s 0
## 20 Comoros 1980s 11
## 21 Congo 1980s 17
## 22 Cyprus 1980s 686
## 23 Democratic People's Republic of Korea 1980s 13
## 24 Djibouti 1980s 24
## 25 Dominica 1980s 814
## 26 Equatorial Guinea 1980s 1
## 27 Estonia 1980s 0
## 28 Gabon 1980s 22
## 29 Gambia 1980s 38
## 30 Georgia 1980s 0
## 31 Guinea-Bissau 1980s 8
## 32 Iceland 1980s 120
## 33 Kiribati 1980s 3
## 34 Kuwait 1980s 67
## 35 Kyrgyzstan 1980s 0
## 36 Lao People's Democratic Republic 1980s 180
## 37 Latvia 1980s 1
## 38 Lesotho 1980s 32
## 39 Liberia 1980s 31
## 40 Liechtenstein 1980s 13
## 41 Lithuania 1980s 5
## 42 Luxembourg 1980s 49
## 43 Madagascar 1980s 240
## 44 Malawi 1980s 36
## 45 Maldives 1980s 1
## 46 Mali 1980s 44
## 47 Marshall Islands 1980s 0
## 48 Mauritania 1980s 27
## 49 Monaco 1980s 3
## 50 Mongolia 1980s 0
## 51 Montenegro 1980s 0
## 52 Mozambique 1980s 27
## 53 Namibia 1980s 26
## 54 Nauru 1980s 2
## 55 New Caledonia 1980s 0
## 56 Niger 1980s 7
## 57 Norway 1980s 720
## 58 Oman 1980s 12
## 59 Palau 1980s 0
## 60 Papua New Guinea 1980s 17
## 61 Paraguay 1980s 434
## 62 Qatar 1980s 2
## 63 Saint Kitts and Nevis 1980s 225
## 64 Saint Lucia 1980s 848
## 65 Samoa 1980s 23
## 66 San Marino 1980s 2
## 67 Sao Tome and Principe 1980s 0
## 68 Saudi Arabia 1980s 90
## 69 Serbia 1980s 0
## 70 Seychelles 1980s 117
## 71 Sierra Leone 1980s 158
## 72 Slovenia 1980s 0
## 73 Suriname 1980s 172
## 74 Swaziland 1980s 36
## 75 Tajikistan 1980s 0
## 76 Togo 1980s 82
## 77 Tonga 1980s 41
## 78 Turkmenistan 1980s 0
## 79 Tuvalu 1980s 3
## 80 Uganda 1980s 362
## 81 United Arab Emirates 1980s 34
## 82 Uzbekistan 1980s 0
## 83 Vanuatu 1980s 0
## 84 Western Sahara 1980s 0
## 85 Yemen 1980s 72
## 86 Zambia 1980s 221
## 87 American Samoa 1990s 2
## 88 Andorra 1990s 6
## 89 Angola 1990s 285
## 90 Antigua and Barbuda 1990s 315
## 91 Armenia 1990s 602
## 92 Azerbaijan 1990s 238
## 93 Bahamas 1990s 195
## 94 Bahrain 1990s 145
## 95 Belize 1990s 344
## 96 Benin 1990s 226
## 97 Bhutan 1990s 18
## 98 Botswana 1990s 21
## 99 Brunei Darussalam 1990s 221
## 100 Burkina Faso 1990s 154
## 101 Cabo Verde 1990s 104
## 102 Canada 1990s 16
## 103 Central African Republic 1990s 69
## 104 Chad 1990s 260
## 105 China, Macao Special Administrative Region 1990s 0
## 106 Comoros 1990s 26
## 107 Congo 1990s 237
## 108 Cyprus 1990s 276
## 109 Democratic People's Republic of Korea 1990s 31
## 110 Djibouti 1990s 266
## 111 Dominica 1990s 826
## 112 Equatorial Guinea 1990s 8
## 113 Estonia 1990s 474
## 114 Gabon 1990s 90
## 115 Gambia 1990s 244
## 116 Georgia 1990s 357
## 117 Guinea-Bissau 1990s 23
## 118 Iceland 1990s 127
## 119 Kiribati 1990s 5
## 120 Kuwait 1990s 987
## 121 Kyrgyzstan 1990s 207
## 122 Lao People's Democratic Republic 1990s 368
## 123 Latvia 1990s 686
## 124 Lesotho 1990s 37
## 125 Liberia 1990s 384
## 126 Liechtenstein 1990s 18
## 127 Lithuania 1990s 680
## 128 Luxembourg 1990s 53
## 129 Madagascar 1990s 373
## 130 Malawi 1990s 85
## 131 Maldives 1990s 7
## 132 Mali 1990s 422
## 133 Marshall Islands 1990s 0
## 134 Mauritania 1990s 71
## 135 Monaco 1990s 9
## 136 Mongolia 1990s 15
## 137 Montenegro 1990s 0
## 138 Mozambique 1990s 50
## 139 Namibia 1990s 26
## 140 Nauru 1990s 1
## 141 New Caledonia 1990s 0
## 142 Niger 1990s 86
## 143 Norway 1990s 718
## 144 Oman 1990s 50
## 145 Palau 1990s 0
## 146 Papua New Guinea 1990s 16
## 147 Paraguay 1990s 488
## 148 Qatar 1990s 43
## 149 Saint Kitts and Nevis 1990s 245
## 150 Saint Lucia 1990s 994
## 151 Samoa 1990s 25
## 152 San Marino 1990s 1
## 153 Sao Tome and Principe 1990s 2
## 154 Saudi Arabia 1990s 585
## 155 Serbia 1990s 0
## 156 Seychelles 1990s 998
## 157 Sierra Leone 1990s 461
## 158 Slovenia 1990s 237
## 159 Suriname 1990s 352
## 160 Swaziland 1990s 32
## 161 Tajikistan 1990s 36
## 162 Togo 1990s 416
## 163 Tonga 1990s 60
## 164 Turkmenistan 1990s 24
## 165 Tuvalu 1990s 1
## 166 Uganda 1990s 707
## 167 United Arab Emirates 1990s 198
## 168 Uzbekistan 1990s 459
## 169 Vanuatu 1990s 5
## 170 Western Sahara 1990s 1
## 171 Yemen 1990s 756
## 172 Zambia 1990s 548
## 173 American Samoa 2000s 1
## 174 Andorra 2000s 5
## 175 Angola 2000s 1563
## 176 Antigua and Barbuda 2000s 235
## 177 Armenia 2000s 1755
## 178 Azerbaijan 2000s 1846
## 179 Bahamas 2000s 190
## 180 Bahrain 2000s 181
## 181 Belize 2000s 303
## 182 Benin 2000s 1199
## 183 Bhutan 2000s 951
## 184 Botswana 2000s 91
## 185 Brunei Darussalam 2000s 57
## 186 Burkina Faso 2000s 920
## 187 Cabo Verde 2000s 47
## 188 Canada 2000s 0
## 189 Central African Republic 2000s 206
## 190 Chad 2000s 1005
## 191 China, Macao Special Administrative Region 2000s 188
## 192 Comoros 2000s 81
## 193 Congo 2000s 1071
## 194 Cyprus 2000s 112
## 195 Democratic People's Republic of Korea 2000s 119
## 196 Djibouti 2000s 741
## 197 Dominica 2000s 660
## 198 Equatorial Guinea 2000s 29
## 199 Estonia 2000s 347
## 200 Gabon 2000s 549
## 201 Gambia 2000s 209
## 202 Georgia 2000s 1174
## 203 Guinea-Bissau 2000s 44
## 204 Iceland 2000s 141
## 205 Kiribati 2000s 5
## 206 Kuwait 2000s 725
## 207 Kyrgyzstan 2000s 1429
## 208 Lao People's Democratic Republic 2000s 425
## 209 Latvia 2000s 1051
## 210 Lesotho 2000s 24
## 211 Liberia 2000s 1979
## 212 Liechtenstein 2000s 6
## 213 Lithuania 2000s 1398
## 214 Luxembourg 2000s 81
## 215 Madagascar 2000s 861
## 216 Malawi 2000s 110
## 217 Maldives 2000s 13
## 218 Mali 2000s 1016
## 219 Marshall Islands 2000s 2
## 220 Mauritania 2000s 656
## 221 Monaco 2000s 8
## 222 Mongolia 2000s 498
## 223 Montenegro 2000s 37
## 224 Mozambique 2000s 57
## 225 Namibia 2000s 122
## 226 Nauru 2000s 14
## 227 New Caledonia 2000s 3
## 228 Niger 2000s 489
## 229 Norway 2000s 682
## 230 Oman 2000s 114
## 231 Palau 2000s 1
## 232 Papua New Guinea 2000s 22
## 233 Paraguay 2000s 729
## 234 Qatar 2000s 71
## 235 Saint Kitts and Nevis 2000s 110
## 236 Saint Lucia 2000s 1676
## 237 Samoa 2000s 20
## 238 San Marino 2000s 1
## 239 Sao Tome and Principe 2000s 5
## 240 Saudi Arabia 2000s 1589
## 241 Serbia 2000s 677
## 242 Seychelles 2000s 120
## 243 Sierra Leone 2000s 2438
## 244 Slovenia 2000s 205
## 245 Suriname 2000s 171
## 246 Swaziland 2000s 48
## 247 Tajikistan 2000s 295
## 248 Togo 2000s 1817
## 249 Tonga 2000s 26
## 250 Turkmenistan 2000s 202
## 251 Tuvalu 2000s 3
## 252 Uganda 2000s 1524
## 253 United Arab Emirates 2000s 358
## 254 Uzbekistan 2000s 2056
## 255 Vanuatu 2000s 6
## 256 Western Sahara 2000s 1
## 257 Yemen 2000s 1395
## 258 Zambia 2000s 632Plot the boxplot graph
Q5plot_box <- ggplot(total_decade, aes(x = Decades, y = value, fill = Decades)) +
geom_boxplot(aes(x=country, y=value)) +
coord_cartesian(ylim = c(0,1500)) +
ggtitle("Number of Immigrants for each decade") +
theme(plot.title = element_text(hjust = 0.5)) +
xlab("decades") + ylab("Number of Immigrants")
Q5plot_box 