---
title: "Class 5"
author: "Colin Kuehl"
date: "`r format(Sys.time(), '%B %d, %Y')`"
output: pdf_document
editor_options: 
  chunk_output_type: console
---

# Introduction

Today we're going to use data from wbstats package. This package allows us to pull data directly from online data provided by the world bank. Find more information [here](https://cran.r-project.org/web/packages/wbstats/vignettes/wbstats.html)

```{r}
# install.packages("wbstats")
# install.packages("tidyr") 

library(wbstats)
library(dplyr)
library(tidyr)
```

Always setwd, in this case we can save data here.

```{r}
setwd("~/Dropbox/POLS 641/CMU Su26/cmucourse26/ClassCode/Day 5")
```

```{r}

df <- wb_data(
  indicator = c(
    gdp_pc            = "NY.GDP.PCAP.CD",
    gdp_growth        = "NY.GDP.MKTP.KD.ZG",
    inflation         = "FP.CPI.TOTL.ZG",
    unemployment      = "SL.UEM.TOTL.ZS",
    gini              = "SI.POV.GINI",
    population        = "SP.POP.TOTL",
    urban_pct         = "SP.URB.TOTL.IN.ZS",
    life_expectancy   = "SP.DYN.LE00.IN",
    fertility         = "SP.DYN.TFRT.IN",
    net_migration     = "SM.POP.NETM",
    migrant_stock_pct = "SM.POP.TOTL.ZS",
    remittances_pct   = "BX.TRF.PWKR.DT.GD.ZS",
    enroll_secondary  = "SE.SEC.ENRR",
    enroll_tertiary   = "SE.TER.ENRR",
    ed_exp_pct_gdp    = "SE.XPD.TOTL.GD.ZS",
    soc_net_adeq = "per_sa_allsa.adq_pop_tot"
  ),
  country = "countries_only",
  start_date = 2020, end_date = 2020)
```

```{r}


```

```{r}
education_inds<- wb_search("education")

wb_search("disability")

gendervars <- wb_search("gender")
```

Measures of central tendency, variance, Standard deviation, boxplots exploring a single variable

First, pick one of the wb indicators from above and get summary statistics

(you're familiar with most of these. Just replace x with your dataset\$variablename)

```{r}
mean(df$remittances_pct, na.rm = TRUE)      # mean
median(df$remittances_pct, na.rm = TRUE)    # median — less pulled by outliers than the mean
var(df$remittances_pct, na.rm = TRUE)       # variance (squared units — hard to interpret directly)
sd(df$remittances_pct, na.rm = TRUE)        # standard deviation (same units as df$remittances_pct)
range(df$remittances_pct, na.rm = TRUE)     # min and madf$remittances_pct
IQR(df$remittances_pct, na.rm = TRUE)       # interquartile range (Q3 - Q1), a robust spread measure
quantile(df$remittances_pct, na.rm = TRUE)  # 0, 25, 50, 75, 100th percentiles
summary(df$remittances_pct)
```

```{r}

hist(df$life_expectancy,
     breaks = 20,
     main = "Life expectancy across countries, 2020",
     xlab = "Years", col = "grey85", border = "white")
abline(v = mean(df$life_expectancy, na.rm=T),  col = "red",  lwd = 2)
abline(v = median(df$life_expectancy, na.rm=T), col = "blue", lwd = 2, lty = 2)

mean(df$life_expectancy)


hist(df$gdp_pc,
     breaks = 20,
     main = "GDP Per Capita across countries, 2020",
     xlab = "Dollars", col = "grey85", border = "white")
abline(v = mean(df$gdp_pc, na.rm=T),  col = "red",  lwd = 2)
abline(v = median(df$gdp_pc, na.rm=T), col = "blue", lwd = 2, lty = 2)
```

```{r}

boxplot(df$life_expectancy,
        main = "Life expectancy across countries, 2020",
        ylab = "Years")


boxplot(df$gdp_pc,
        main = "GDP per capita across countries, 2020",
        ylab = "Years")

```