part2-solution.Rmd

---
title: "R Notebook"
output: html_notebook
---

# Part 2 Solutions

```{r}
### Load the libraries will we need
library(readr)
library(dplyr)
library(ggplot2)
```

Read the data and check

```{r}
gapminder <- read_csv("raw_data/gapminder.csv")
head(gapminder)
```


## In-class exercises

Create a subset of the data where the population less than a million in the year 2002

```{r}
filter(gapminder, pop < 1e6, year == 2002)
```

Create a subset of the data where the life expectancy is greater than 75 in the years prior to 1987

```{r}
filter(gapminder, lifeExp > 75, year < 1987)
```

Create a subset of the European data where the life expectancy is between 75 and 80 in the years 2002 or 2007.

```{r}
filter(gapminder, continent == "Europe", lifeExp > 75, lifeExp < 80 , year == 2002 | year == 2007)
```
Can also use the `between` function from `dplyr` and the `%in%` function

```{r}
filter(gapminder, continent == "Europe", 
       between(lifeExp, 75,80), 
       year %in% c(2002,2007))
```


Write a workflow to do the following:- 

- Filter the data to include just observations from the year 2002
- Re-arrange the table so that the countries from each continent are ordered according to decreasing wealth. i.e. the wealthiest countries first
- Select all the columns apart from year
- Write the data frame out to a file in out_data/ folder

```{r}
# Less-efficient solution before pipes are introduced

# create out_data folder before we start (no warning given if it already exists)
dir.create("out_data", showWarnings = FALSE)

gapminder2 <- filter(gapminder, year == 2002)
gapminder3 <- arrange(gapminder2, continent, desc(gdpPercap))
gapminder4 <- select(gapminder3, -year)
write_csv(gapminder4, "out_data/gapminder_2002.csv")
```

Re-written using pipes

```{r}
filter(gapminder, year == 2002) %>% 
  arrange(continent, desc(gdpPercap)) %>% 
  select(-year) %>% 
write_csv("out_data/gapminder_piped_2002.csv")

```


The violin plot is a popular alternative to the boxplot. Create a violin plot with geom_violin to visualise the differences in GDP between different continents.

```{r}
ggplot(gapminder, aes(x = continent, y = gdpPercap)) + geom_violin()
```

Create a subset of the gapminder data frame containing just the rows for your country of birth

```{r}

# don't forget that R is case-sensitive!

uk_data <- filter(gapminder, country == "United Kingdom")
```

Has there been an increase in life expectancy over time?
 - visualise the trend using a scatter plot (geom_point), line graph (geom_line) or smoothed line (geom_smooth).

```{r}
ggplot(uk_data, aes(x = year, y = lifeExp)) + geom_point()
```

```{r}
ggplot(uk_data, aes(x = year, y = lifeExp)) + geom_line()
```

```{r}
ggplot(uk_data, aes(x = year, y = lifeExp)) + geom_smooth()
```


```{r}
## can combine all plots
ggplot(uk_data, aes(x = year, y = lifeExp)) + geom_point() + geom_smooth()
```

Note: this exercise could also make use of the piping technique

```{r}
filter(gapminder, country == "United Kingdom") %>% 
  ggplot(aes(x = year, y = lifeExp)) + geom_point() + geom_smooth()
```
What happens when you modify the geom_boxplot example to compare the gdp distributions for different years?
- Look at the message ggplot2 prints above the plot and try to modify the code to give a separate boxplot for each year

```{r}
# this is how we might expect the code to look like
ggplot(gapminder, aes(x = year, y = gdpPercap)) + geom_boxplot()
```

The previous output hints that you might want to group by year - otherwise it thinks that year is a numerical variable

```{r}
ggplot(gapminder, aes(x = year, y = gdpPercap, group=year)) + geom_boxplot()
```
You will often see this alternative of using the as.factor function to make year into a categorical variable.

```{r}
ggplot(gapminder, aes(x = as.factor(year), y = gdpPercap)) + geom_boxplot()

```

## Homework



### Task 1

Add an extra column; the first letter of each country name. Assigning a new variable on each line

```{r}
gapminder2 <- mutate(gapminder, FirstLetter = substr(country, 1,1))
gapminder3 <- filter(gapminder2, FirstLetter == "Z")
gapminder3
```

A more efficient solution

```{r}
gapminder %>% 
  mutate(FirstLetter = substr(country,1,1)) %>% 
  filter(FirstLetter == "Z")
```

### Task 2 - Heatmap of life expectancy

```{r}
## Get the European countries
filter(gapminder, continent == "Europe") %>% 
## make heatmap. See the fill aesthetic to be life expectancy
ggplot(aes(x=year,y=country,fill=lifeExp)) + geom_tile()
```