data wrangling.Rmd

---
title: "Data wrangling"
author: "Helen Fredricks"
date: "October 22, 2018"
output: html_document
---

```{r}
install.packages("readr")
install.packages("diplyr")
install.packages("tidyverse")
library(readr)
library(diplyr)
library(tidyverse) 


```



```{r}
## read gapminder csv. Note the readr:: prefix identifies which package it's in
gapminder <- readr::read_csv('https://raw.githubusercontent.com/OHI-Science/data-science-training/master/data/gapminder.csv')
```
```{r}
filter(gapminder, lifeExp < 29)
filter(gapminder, country == "Mexico")
filter(gapminder, country %in% c("Mexico", "Peru", "Brazil"))

```
```{r}
# find mean life exp of sweden

sweden <- filter(gapminder, country == "Sweden")
mean(sweden$lifeExp)

```
```{r}

#select by columns

select(gapminder, year, lifeExp)

#everything but the columns you name
select(gapminder, -continent, -lifeExp)

#select and filter together
gap_cambodia <-filter(gapminder, country == "Cambodia")
gap_cambodia2 <- select(gap_cambodia, -continent, -lifeExp)

#lets improve this with pipes
gapcambodia2 <- gap_cambodia %>% 
  filter(country =="Cambodia") %>% 
  select(-continent, -lifeExp)

#pipes allows to simplify variables into more concise version

#keyboard shortcut, ctrl, shift, M




```
the pipe operator will change your life

```{r}
#this 

gapminder %>% head(3)

#is equivalent to

head(gapminder, 3)

#head shows the top 3 rows
```
```{r}
#mutate() adds new variables

gapminder %>% 
  mutate(index = 1:nrow(gapminder))

gapminder %>% 
  mutate(planet = "Earth")

gapminder %>% 
  mutate(gdp = pop * gdpPercap)



```
```{r}
# find the max gdpPerCap of Egypt and Vietnam. create a new column (one column)


gapminder %>% 
  filter(country %in% c("Egypt", "Vietnam")) %>% 
  mutate(gdp = pop * gdpPercap) %>% 
  mutate(max_gdp = max(gdp))


  
  
```
```{r}
gapminder %>%
  gap_grouped <- group_by(country) %>%
  mutate(gdp     = pop * gdpPercap,
         max_gdp = max(gdp)) %>%
  ungroup() # if you use group_by, also use ungroup() to save heartache later
```


```{r}
gapminder %>%
  group_by(country) %>%
  mutate(gdp     = pop * gdpPercap,
         max_gdp = max(gdp)) %>%
  ungroup() %>% 
  tail(30)
```


```{r}
## with summarise or summarize

gap_summarised <- gapminder %>% 
  group_by(country) %>% 
  mutate(gdp = pop * gdpPercap) %>% 
  summarise(max_gdp = max(gdp)) %>% 
  ungroup () %>% 
  arrange(max_gdp)
  
```