Challenge-3

Creating a Dataframe

ua = GET("https://api.teleport.org/api/urban_areas/")
ua = fromJSON(rawToChar(ua$content))

df1 = data.frame('country' = NA, 'continent' = NA, 'ua_name' = NA,
                 'housing' = NA, 'cost_of_living' = NA, 
                 'startups' = NA, 'venture_capital' = NA, 
                 'travel_connectivity' = NA, 'commute' = NA, 
                 'business_freedom' = NA, 'safety' = NA, 
                 'healthcare' = NA, 'education' = NA, 'enviromental_quality' = NA,
                 'economy' = NA, 'taxation' = NA, 'internet_access' = NA, 
                 'leisure_culture' = NA, 'tolerance' = NA, 'outdoors'= NA)

for(i in 1:266){
mydata = GET(paste(ua$`_links`$`ua:item`$href[i], 'scores', sep = ''))
mydata = fromJSON(rawToChar(mydata$content))
scores = mydata$categories$score_out_of_10

ua_names = GET(ua$`_links`$`ua:item`$href[i])
ua_names = fromJSON(rawToChar(ua_names$content))
full_data = c(strsplit(ua_names$full_name, ", ")[[1]][2], ua_names$continent, 
              strsplit(ua_names$full_name, ", ")[[1]][1], scores)

df1 = rbind(full_data, df1)
}

df1 = na.omit(df1)
for(i in 4:20){
  df1[,i] = as.numeric(df1[,i])
}

Correlation Matrix

x = correlate(df1[4:20], use = "pairwise.complete.obs", method = "pearson")

## 
## Correlation method: 'pearson'
## Missing treated using: 'pairwise.complete.obs'

## # A tibble: 17 x 18
##    rowname  housing cost_of_living startups venture_capital travel_connecti~
##    <chr>      <dbl>          <dbl>    <dbl>           <dbl>            <dbl>
##  1 housing NA              0.795   -0.354           -0.469           -0.241 
##  2 cost_o~  0.795         NA        0.00993         -0.143           -0.149 
##  3 startu~ -0.354          0.00993 NA                0.795            0.270 
##  4 ventur~ -0.469         -0.143    0.795           NA                0.365 
##  5 travel~ -0.241         -0.149    0.270            0.365           NA     
##  6 commute  0.167          0.238    0.0570           0.0867           0.326 
##  7 busine~ -0.461         -0.470    0.199            0.243            0.251 
##  8 safety   0.0180        -0.0682  -0.202           -0.115            0.271 
##  9 health~ -0.465         -0.516    0.0864           0.187            0.280 
## 10 educat~ -0.561         -0.453    0.369            0.521            0.463 
## 11 enviro~ -0.417         -0.468    0.0132           0.105            0.112 
## 12 economy -0.516         -0.368    0.330            0.368            0.0217
## 13 taxati~ -0.00812        0.0486  -0.0271          -0.103           -0.166 
## 14 intern~ -0.299         -0.253    0.201            0.272            0.240 
## 15 leisur~ -0.0157         0.172    0.441            0.328            0.306 
## 16 tolera~ -0.228         -0.330   -0.136           -0.0901           0.0243
## 17 outdoo~ -0.168         -0.0360   0.252            0.268            0.135 
## # ... with 12 more variables: commute <dbl>, business_freedom <dbl>,
## #   safety <dbl>, healthcare <dbl>, education <dbl>,
## #   enviromental_quality <dbl>, economy <dbl>, taxation <dbl>,
## #   internet_access <dbl>, leisure_culture <dbl>, tolerance <dbl>,
## #   outdoors <dbl>

Parallel Plots

df1 %>% ggparcoord(columns = c(19,4, 5 ,12), groupColumn = 2, scale="globalminmax",
  showPoints = TRUE, title = "", alphaLines = 0.3
) +  scale_color_viridis(discrete = T) + 
  theme_ipsum() + theme(plot.title = element_text(size=10)) + xlab("") + ylab("")

df1 %>% ggparcoord(columns = c(13,12,14,10), groupColumn = 2, scale="globalminmax",
                   showPoints = TRUE, title = "", alphaLines = 0.3
) +  scale_color_viridis(discrete = T, option = 'B') + 
  theme_ipsum() + theme(plot.title = element_text(size=10)) + xlab("") + ylab("")