For this project, I used the H1B Visa data set - I tidied the data to specidically looks at H1B Visa Petitions for each country and year

Load Libraries and read csv file

library(tidyr)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(ggplot2)
library(knitr)
data <- read.csv('/Users/christinakasman/Desktop/H1B Data.csv', header=FALSE, sep=",", stringsAsFactors=FALSE)
my.new.data <-  data[-c(2), ]  
my.new.data <-  data[-c(3, 5, 16, 12, 17, 42, 43, 47, 48, 57, 58, 62, 63, 76, 80, 81), ]  
newdata <- as.data.frame(t(my.new.data))

Create Table for Countries - Change header to be first row of dataframe

Countries <- newdata[c(1:12) ,c(13:33, 35)]
as.data.frame(Countries)
##       18     19                          20          21          22     23
## V1        India China, People's Republic of Philippines South Korea Canada
## V2  2007 166575                       26370       12230       10730   8562
## V3  2008 157608                       24434       10713       10277   7111
## V4  2009 122475                       22411       10407       10704   7871
## V5  2010 135931                       21119        8887        8721   7342
## V6  2011 155791                       23227        9098        7480   6761
## V7  2012 197940                       22528        9400        7204   6688
## V8  2013 201114                       23924        7399        5576   5478
## V9  2014 227172                       27733        6772        4897   5267
## V10 2015 269677                       32485        4147        4298   5050
## V11 2016 300902                       35720        3704        4269   4547
## V12 2017 247927                       36362        3161        3203   3551
##         24     25             26       27     28     29    30    31     32
## V1  Taiwan Mexico United Kingdom Pakistan France Brazil Nepal Japan Turkey
## V2    5394   4259           5105     4259   4112   3056  2775  2913   2415
## V3    4088   3680           4241     3803   3687   2498  2538  2374   2028
## V4    4308   3599           4270     3683   3035   2495  2724  2253   2041
## V5    4325   3260           3651     3012   2660   2595  2467  2225   2023
## V6    4511   3439           3241     3033   2531   2644  2169  2172   2020
## V7    4172   3602           3130     2765   2292   2557  2066  2030   1966
## V8    3520   2985           2330     2381   2192   2346  1788  1755   1658
## V9    3267   2769           1988     2497   2024   2353  1598  1664   1665
## V10   2555   2462           1697     2512   2048   2111  1512  1553   1711
## V11   2287   2315           1528     2401   1998   1992  1504  1481   1709
## V12   2200   2239           1783     1536   1474   1517  1249  1077   1177
##          33   34    35     36        37    38        40
## V1  Germany Iran Italy Russia Venezuela Spain All Other
## V2     3168 2531  1353   2446      1262  1079     44027
## V3     2482 1930  1533   1760      1159   974     36557
## V4     2182 1952  1437   1544      1302   933     34500
## V5     1875 1897  1361   1434      1299  1018     31170
## V6     1737 1755  1613   1570      1398  1233     30989
## V7     1650 1676  1922   1499      1540  1140     30475
## V8     1319 1362  1722   1318      1370  1230     26923
## V9     1256 1331  1865   1323      1339  1201     25990
## V10    1164 1230  1894   1275      1247  1110     27114
## V11    1006 1152  1639   1154      1208  1094     25739
## V12    1127 1332   918    948       873   861     21592
colnames(Countries) = as.character(unlist(Countries[1,])) # the first row will be the header
Countries1 = Countries[-1, ] 
colnames(Countries1)[1] <- "Year"
Countries2 <- gather(Countries1, "Country", "H1B_Petitions_Filed", 2:22)
## Warning: attributes are not identical across measure variables;
## they will be dropped

Group by Country and summarise

#Have to change to .numeric for correct character type
Countries3 <- Countries2 %>% group_by(Country) %>% 
summarise(Total_H1B_Petitions_Filed = sum(as.numeric(H1B_Petitions_Filed)))
Countries3 <- arrange(Countries3, desc(as.numeric(Total_H1B_Petitions_Filed)))

Total H1B Visas from 2007-2017 per Country. India had the highest number of H1B Visa petitions, by more than 7 times any other country Why does india have the most: https://www.recode.net/2017/4/13/15281170/china-india-tech-h1b-visas

kable(Countries3)
Country Total_H1B_Petitions_Filed
India 2183112
All Other 335076
China, People’s Republic of 296313
Philippines 85918
South Korea 77359
Canada 68228
Taiwan 40627
Mexico 34609
United Kingdom 32964
Pakistan 31882
France 28053
Brazil 26164
Nepal 22390
Japan 21497
Turkey 20413
Germany 18966
Iran 18148
Italy 17257
Russia 16271
Venezuela 13997
Spain 11873 
Countriesyear <- Countries2 %>% group_by(Country, Year) %>% 
  summarise(totalyear = sum(as.numeric(H1B_Petitions_Filed)))
kable(Countriesyear)
Country Year totalyear
All Other 2007 44027
All Other 2008 36557
All Other 2009 34500
All Other 2010 31170
All Other 2011 30989
All Other 2012 30475
All Other 2013 26923
All Other 2014 25990
All Other 2015 27114
All Other 2016 25739
All Other 2017 21592
Brazil 2007 3056
Brazil 2008 2498
Brazil 2009 2495
Brazil 2010 2595
Brazil 2011 2644
Brazil 2012 2557
Brazil 2013 2346
Brazil 2014 2353
Brazil 2015 2111
Brazil 2016 1992
Brazil 2017 1517
Canada 2007 8562
Canada 2008 7111
Canada 2009 7871
Canada 2010 7342
Canada 2011 6761
Canada 2012 6688
Canada 2013 5478
Canada 2014 5267
Canada 2015 5050
Canada 2016 4547
Canada 2017 3551
China, People’s Republic of 2007 26370
China, People’s Republic of 2008 24434
China, People’s Republic of 2009 22411
China, People’s Republic of 2010 21119
China, People’s Republic of 2011 23227
China, People’s Republic of 2012 22528
China, People’s Republic of 2013 23924
China, People’s Republic of 2014 27733
China, People’s Republic of 2015 32485
China, People’s Republic of 2016 35720
China, People’s Republic of 2017 36362
France 2007 4112
France 2008 3687
France 2009 3035
France 2010 2660
France 2011 2531
France 2012 2292
France 2013 2192
France 2014 2024
France 2015 2048
France 2016 1998
France 2017 1474
Germany 2007 3168
Germany 2008 2482
Germany 2009 2182
Germany 2010 1875
Germany 2011 1737
Germany 2012 1650
Germany 2013 1319
Germany 2014 1256
Germany 2015 1164
Germany 2016 1006
Germany 2017 1127
India 2007 166575
India 2008 157608
India 2009 122475
India 2010 135931
India 2011 155791
India 2012 197940
India 2013 201114
India 2014 227172
India 2015 269677
India 2016 300902
India 2017 247927
Iran 2007 2531
Iran 2008 1930
Iran 2009 1952
Iran 2010 1897
Iran 2011 1755
Iran 2012 1676
Iran 2013 1362
Iran 2014 1331
Iran 2015 1230
Iran 2016 1152
Iran 2017 1332
Italy 2007 1353
Italy 2008 1533
Italy 2009 1437
Italy 2010 1361
Italy 2011 1613
Italy 2012 1922
Italy 2013 1722
Italy 2014 1865
Italy 2015 1894
Italy 2016 1639
Italy 2017 918
Japan 2007 2913
Japan 2008 2374
Japan 2009 2253
Japan 2010 2225
Japan 2011 2172
Japan 2012 2030
Japan 2013 1755
Japan 2014 1664
Japan 2015 1553
Japan 2016 1481
Japan 2017 1077
Mexico 2007 4259
Mexico 2008 3680
Mexico 2009 3599
Mexico 2010 3260
Mexico 2011 3439
Mexico 2012 3602
Mexico 2013 2985
Mexico 2014 2769
Mexico 2015 2462
Mexico 2016 2315
Mexico 2017 2239
Nepal 2007 2775
Nepal 2008 2538
Nepal 2009 2724
Nepal 2010 2467
Nepal 2011 2169
Nepal 2012 2066
Nepal 2013 1788
Nepal 2014 1598
Nepal 2015 1512
Nepal 2016 1504
Nepal 2017 1249
Pakistan 2007 4259
Pakistan 2008 3803
Pakistan 2009 3683
Pakistan 2010 3012
Pakistan 2011 3033
Pakistan 2012 2765
Pakistan 2013 2381
Pakistan 2014 2497
Pakistan 2015 2512
Pakistan 2016 2401
Pakistan 2017 1536
Philippines 2007 12230
Philippines 2008 10713
Philippines 2009 10407
Philippines 2010 8887
Philippines 2011 9098
Philippines 2012 9400
Philippines 2013 7399
Philippines 2014 6772
Philippines 2015 4147
Philippines 2016 3704
Philippines 2017 3161
Russia 2007 2446
Russia 2008 1760
Russia 2009 1544
Russia 2010 1434
Russia 2011 1570
Russia 2012 1499
Russia 2013 1318
Russia 2014 1323
Russia 2015 1275
Russia 2016 1154
Russia 2017 948
South Korea 2007 10730
South Korea 2008 10277
South Korea 2009 10704
South Korea 2010 8721
South Korea 2011 7480
South Korea 2012 7204
South Korea 2013 5576
South Korea 2014 4897
South Korea 2015 4298
South Korea 2016 4269
South Korea 2017 3203
Spain 2007 1079
Spain 2008 974
Spain 2009 933
Spain 2010 1018
Spain 2011 1233
Spain 2012 1140
Spain 2013 1230
Spain 2014 1201
Spain 2015 1110
Spain 2016 1094
Spain 2017 861
Taiwan 2007 5394
Taiwan 2008 4088
Taiwan 2009 4308
Taiwan 2010 4325
Taiwan 2011 4511
Taiwan 2012 4172
Taiwan 2013 3520
Taiwan 2014 3267
Taiwan 2015 2555
Taiwan 2016 2287
Taiwan 2017 2200
Turkey 2007 2415
Turkey 2008 2028
Turkey 2009 2041
Turkey 2010 2023
Turkey 2011 2020
Turkey 2012 1966
Turkey 2013 1658
Turkey 2014 1665
Turkey 2015 1711
Turkey 2016 1709
Turkey 2017 1177
United Kingdom 2007 5105
United Kingdom 2008 4241
United Kingdom 2009 4270
United Kingdom 2010 3651
United Kingdom 2011 3241
United Kingdom 2012 3130
United Kingdom 2013 2330
United Kingdom 2014 1988
United Kingdom 2015 1697
United Kingdom 2016 1528
United Kingdom 2017 1783
Venezuela 2007 1262
Venezuela 2008 1159
Venezuela 2009 1302
Venezuela 2010 1299
Venezuela 2011 1398
Venezuela 2012 1540
Venezuela 2013 1370
Venezuela 2014 1339
Venezuela 2015 1247
Venezuela 2016 1208
Venezuela 2017 873 
ggplot(Countriesyear, aes(Year, totalyear)) + geom_bar(stat = "identity", fill="#009E73") +ggtitle("Petitions for H1B Visas per year")

As you can see from the barplot, 2016 had the highest number of H1B Visa petitions overall