gistfile1.txt

# Get an idea if it will be correct join
head(left_join(gdp_per_capita, child_mortality, by=c("Country", "Years")))

##               Country Years GDP per capita Child mortality
## 1         Afghanistan  1800       634.4000          468.58
## 2             Albania  1800       860.5880          375.20
## 3             Algeria  1800      1360.0000          460.21
## 4             Andorra  1800      1260.0000              NA
## 5              Angola  1800       650.0000          485.68
## 6 Antigua and Barbuda  1800       796.5934          473.60

# perform the left join
gapdata <- left_join(gdp_per_capita, child_mortality, by=c("Country","Years"))
head(gapdata)

##               Country Years GDP per capita Child mortality
## 1         Afghanistan  1800       634.4000          468.58
## 2             Albania  1800       860.5880          375.20
## 3             Algeria  1800      1360.0000          460.21
## 4             Andorra  1800      1260.0000              NA
## 5              Angola  1800       650.0000          485.68
## 6 Antigua and Barbuda  1800       796.5934          473.60

# Join the democracy_score data frame
gapdata <- left_join(gapdata, democracy_score, by=c("Country", "Years"))
# Join the life_expectancy data frame
gapdata <- left_join(gapdata, life_expectancy, by=c("Country", "Years"))
# Join the population data frame
gapdata <- left_join(gapdata, population, by=c("Country", "Years"))
str(gapdata)

## 'data.frame':    43252 obs. of  7 variables:
##  $ Country        : chr  "Afghanistan" "Albania" "Algeria" "Andorra" ...
##  $ Years          : num  1800 1800 1800 1800 1800 1800 1800 1800 1800 1800 ...
##  $ GDP per capita : num  634 861 1360 1260 650 ...
##  $ Child mortality: num  469 375 460 NA 486 ...
##  $ Democracy Score: num  -6 NA NA NA NA NA NA NA NA NA ...
##  $ Life Expectancy: num  28.2 35.4 28.8 NA 27 ...
##  $ Population     : num  3280000 410445 2503218 2654 1567028 ...

# join the gapdata and countries data frame
# see if we are doing the right thing
head(left_join(gapdata, countries, by="Country")) 

##               Country Years GDP per capita Child mortality Democracy Score
## 1         Afghanistan  1800       634.4000          468.58              -6
## 2             Albania  1800       860.5880          375.20              NA
## 3             Algeria  1800      1360.0000          460.21              NA
## 4             Andorra  1800      1260.0000              NA              NA
## 5              Angola  1800       650.0000          485.68              NA
## 6 Antigua and Barbuda  1800       796.5934          473.60              NA
##   Life Expectancy Population Code   Region      Sub.Region
## 1         28.2110    3280000    4     Asia   Southern Asia
## 2         35.4000     410445    8   Europe Southern Europe
## 3         28.8224    2503218   12   Africa Northern Africa
## 4              NA       2654   20   Europe Southern Europe
## 5         26.9800    1567028   24   Africa   Middle Africa
## 6         33.5360      37000   28 Americas       Caribbean

gapdata <- left_join(gapdata, countries, by=c("Country"))