Week 3: Importing and visualizing data

class: center, middle, inverse, title-slide

# Week 3: Importing and visualizing data
### STAT 021 with Suzanne Thornton
### Swarthmore College

---

.scroll-output {
  height: 75%;
  overflow-y: scroll;
}

.scroll-small {
  height: 50%;
  overflow-y: scroll;
}
   
.red{color: #ce151e;}
.green{color: #26b421;}
.blue{color: #426EF0;}
</style>

# Creating a tibble of data

Think of data in terms of a spreadsheet (or matrix) where

- Rows are the observations,
  
  - Columns are the different variable names.

.scroll-output[

```r
## Data object (in this example we're looking at miles per hour and number of passengers)
car_data <- tibble(mph = c(22, 35, 20, 25, 24, 20, 34, 31, 30, 32, 33, 25, 29, 24),
                  passengers = c(1, 1, 3, 2, 5, 2, 1, 1, 2, 1, 3, 1, 1, 2)) 
car_data
```

```
## # A tibble: 14 x 2
##      mph passengers
##    <dbl>      <dbl>
##  1    22          1
##  2    35          1
##  3    20          3
##  4    25          2
##  5    24          5
##  6    20          2
##  7    34          1
##  8    31          1
##  9    30          2
## 10    32          1
## 11    33          3
## 12    25          1
## 13    29          1
## 14    24          2
```
]

---
## Plotting in the `tidyverse`
### Scatterplot and plot basics

.scroll-output[
The components for building a plot in the `tidyverse` pack are:

- the data object (typically a `tibble` or `data.frame`), 
  
  - the plot initialization page (where you reference the data object and orient the axes), and then 
  
  - the plot itself (histogram, density curve, box plot, etc).

```r
## Plot initialization (aes() stands for aesthetics)
ggplot(car_data, aes(x=passengers, y=mph)) +
  
## The actual plot (a scatterplot in this example)
         geom_point()
```
]

---
## Plotting in the `tidyverse`
### Scatterplot and plot basics

---
## Plotting in the `tidyverse`
### Scatterplot and plot basics

.scroll-output[

We finish the plot by adding labels and trimming the x and y axes with the `xlim` and `ylim ` functions.

```r
## Plot initialization (aes() stands for aesthetics)
ggplot(car_data, aes(x=passengers, y=mph)) +
  
## The actual plot (a scatterplot in this example)
         geom_point() + 
         ylim(10,40) + xlim(0,6) + 
         labs(title="Scatterplot") + xlab("Number of passengers") + ylab("Miles per hour")
```
]

---
## Plotting in the `tidyverse`
### Scatterplot and plot basics

---
## Plotting in the `tidyverse`
### Histograms

.scroll-output[

Often, to visualize a single numeric variable, we create a histogram.

```r
ggplot(car_data, aes(x=mph)) +
         geom_histogram(bins=5) +
         labs(title="Histogram") + 
         xlab("Miles per hour") + 
         ylab("Count")
```
]

---
## Plotting in the `tidyverse`
### Histograms