cri_data.csv

---
title: "WebscrapingCostofLivingIndex"
author: "Shanya Chaubey"
date: "2023-02-28"
output: html_document
---

```{r setup, include=FALSE, echo = TRUE}
knitr::opts_knit$set(root.dir = 'C:\\Users\\chaub\\Documents\\CU_Boulder\\Spring 2023\\STAT 5000')
```

```{r}

library(tidyverse)
library(dplyr)
library(tidyr)
library(compare)


```


```{r}
data <- read_csv('climate-risk-index-1.csv')
head(data)
columns <- as.list(colnames(data))
columns

```

```{r}
data <- data %>% select(-c('cartodb_id','the_geom', 'the_geom_webmercator', 'rw_country_name'))
head(data)

names(data)[names(data) == 'rw_country_code'] <- 'country_code'

head(data)
```

```{r}

pop_density <-  read_csv('population_density.csv')
head(pop_density)

#unit = people per sq. km of land area
pop_density <- pop_density %>% select(c('Country Code','2019 [YR2019]'))
head(pop_density)

pop_density$`2019 [YR2019]` <- as.numeric(pop_density$`2019 [YR2019]`)
head(pop_density)

colnames(pop_density)<- c('country_code', 'pop_den')

new_pop_den <- pop_density %>% distinct()


#change column name of Country Code  to country_code

```

```{r}
gdp_p_c <- read_csv('gdp_per_capita.csv')
head(gdp_p_c)

#unit-current US$
gdp_p_c <- gdp_p_c%>% select(c('Country Code', '2019 [YR2019]'))
head(gdp_p_c)

gdp_p_c$`2019 [YR2019]` <- as.numeric(gdp_p_c$`2019 [YR2019]`)
head(gdp_p_c)
#change column name of Country Code  to country_code

colnames(gdp_p_c) <- c('country_code', 'GDP_per_capita')
head(gdp_p_c)
```





```{r}
epi_2020 <- read_csv('2020_epi.csv')
head(epi_2020)


epi_score_2020<- epi_2020 %>% select(c( 'iso', 'EPI.new'))
head(epi_score_2020)


epi_2018 <- read_csv('2018_epi.csv')
head(epi_2018)


epi_score_2018<- epi_2018 %>% select(c( 'iso', 'EPI.current'))
head(epi_score_2018)


epi_2019 <- inner_join(epi_score_2018, epi_score_2020, by= "iso")
head(epi_2019)

print('Missing value in dataframe:')
sum(is.na(epi_2019))

epi_2019 <- epi_2019  %>% mutate(EPI_new = (EPI.current+EPI.new)/2) %>% select(c('iso', 'EPI_new'))
head(epi_2019)

colnames(epi_2019) <- c('country_code', 'EPI_score')
head(epi_2019)

```


```{r}

data_1 <- inner_join(data, pop_density, by = 'country_code')
data_2 <- inner_join(data_1, gdp_p_c, by = 'country_code')
data_3 <- inner_join(data_2, epi_2019, by = 'country_code', )
head(data_3)


```