jump_cars.qmd

---
title: "Plotting cars"
webr:
  packages: ['tidyverse']
editor: 
  mode: source  
---

## Learn and code

First, let's make a simple scatter plot. We'll use a famous dataset that is used in R a lot for educational purposes. This is the `mtcars` dataset. It stands for _"Motor Trend Car Road Tests"_. See [parameter overview](https://rstudio-pubs-static.s3.amazonaws.com/61800_faea93548c6b49cc91cd0c5ef5059894.html){target="_blank"} and [documentation](https://www.rdocumentation.org/packages/datasets/versions/3.6.2/topics/mtcars){target="_blank"} for info about the `mtcars` dataset. It is one of many datasets available from base R or tidyverse packages, so we can always call it without having to load it.

First, we will inspect the dataset. For this we will load the tidyverse:

``` {webr-r}

library(tidyverse)
```

Once tidyverse is loaded via the `library` call, it is available in your current session in your browser, so you do not have to load it each time. Let's have a look at the full dataset:

``` {webr-r}

mtcars
```

or

``` {webr-r}

#if you get an error here, 
# please load the library call to tidyverse
mtcars %>% glimpse()
```

or

``` {webr-r}

mtcars %>% head()
```

or

``` {webr-r}

mtcars %>% tail()
```

Let's select a small part of the data using `select` from the `dplyr` package:

``` {webr-r}

mtcars %>% 
    select(mpg, disp)
  
```

Next, make a simple plot with the miles per gallon (`mpg`) and displacement parameters (`disp`) in the `mtcars` dataset.

``` {webr-r}

mtcars %>% 
    select(mpg, disp) %>%
    ggplot(aes(x = mpg, y = disp))+
        geom_point(size = 4)
  
```

This is a very basic plot, without much formatting. Let's make it prettier!

Add color and bring in a third parameter:

``` {webr-r}

mtcars %>% 
    #added cyl to the selection here
    select(mpg, disp, cyl) %>% 
    ggplot(aes(x = mpg, 
               y = disp,
               color = cyl) #added color to the aesthetics here
               ) + 
               geom_point(size = 4)
  
```

Here we need to have a look at data-types. The `cyl` parameter is numerical. `ggplot` automatically assumes we want a continuous scale for this. Instead the `cyl` is more of a categorical data type (there are either 4, 6 or 8 cylinders in each car) so we can explicitly make the `cyl` parameter categorical like this:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = as.factor(cyl))) +
        geom_point(size = 4)
  
```

If you want to have different colors you can use one of the many color palettes available:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = as.factor(cyl)))+
        geom_point(size = 4)+
  #I also manually changed the name of the legend here
        scale_color_brewer(name = "cylinders", 
                            palette = "Set2")
  
```

Apart from color you can change the shape of the datapoints:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = as.factor(cyl),
#please note to also add shape to the aesthetics here
               shape = as.factor(cyl))) + 
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                            name = "cylinders")
  
```

`ggplot` can use different themes for your plots, and there are many many options to tweak your plots to the way you like. You can see some examples below:

Let's change titles:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")
```

Change the plotting theme and base size of the elements:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        theme_bw(base_size = 20)
```

Change the scaling of the axes. It is good practice to plot graphs from zero:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(limits = c(0, NA),
                           expand = c(0,NA))+
        scale_y_continuous(limits = c(0, NA),
                            expand = c(0,NA))+
        theme_bw(base_size = 20)
```

Now the datapoints at the maxima of the axis are not completely visible so it would be nice that we have some more space:

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
```

Now we have generated a nice visualisation of our data using `ggplot`. Please note that `ggplot` uses layers and we added each time a different layer of information to the ggplot. If you want you can go wild with `ggplot.` Please find a nice [overview](https://www.cedricscherer.com/2019/12/30/best-tidytuesday-2019/){target="_blank"} of visualisations using ggplot, tidy and R from Cedric Scherer. Also the underlying R code is available for those plots.

## Exercises

### Adding layers and changing the MTCARS plot

::: callout-tip
#### Exercise 1

Give the points in the ggplot some transparency (or opacity), so that individual points are better visible. TIP: use the `alpha` argument it should be a number from 0 to 1.

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4,
                   #type your extra code here:

                    )+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Exercise 1

Please note that the alpha we added is not part of an aesthetics (`aes`), meaning that the value of the alpha is not linked with a parameter in our data.

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
                color = as.factor(cyl),
                shape = as.factor(cyl)))+
        geom_point(size = 4,
                   #type your extra code here:
                    alpha = 0.7
                    )+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                        name = "cylinders")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
```
:::

::: callout-tip
#### Exercise 2

Add a layer that will generate a smooth linear regression line that shows the relation between `mpg` and `disp`. Use the `stat_smooth` command for this.

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp))+
        geom_point(size = 4,
                    alpha = 0.7)+
        # enter code here
        
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Exercise 2

Please make sure that the ggplot is not separated into groups. If the data is grouped by `color` or `shape` a different regression line for each group will be generated.

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp))+
        geom_point(size = 4,
                    alpha = 0.7)+
        # enter code here
        stat_smooth(geom = "line",
                    method = "lm",
                    formula = "y ~ x")+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
```
:::

::: callout-tip
#### Exercise 3

Use the `facet_wrap` command to make three separate plots for each cylinder.

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp))+
        geom_point(size = 4,
                    alpha = 0.7)+
        
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)
        # enter code here 
        #(and don't forget to at a plus to the last line)
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Exercise 3

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp))+
        geom_point(size = 4,
                    alpha = 0.7)+
        labs(title = "My cool MTCARS plot",
                x = "miles per gallon",
                y = "dispension")+
        scale_x_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        scale_y_continuous(
              limits = c(0, NA),
              expand = expansion(mult = c(0, 0.1)))+
        theme_bw(base_size = 20)+
        facet_wrap(~cyl)
```
:::

### Fixing common errors

Below is some code that is not working properly, because of coding semantics mistakes. Can you spot (and fix) the errors?

::: callout-important
#### Fix error 1

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp
               color = cyl))+
        geom_point(size = 4)
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Error 1

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, #the error was here
               color = cyl))+
        geom_point(size = 4)
```

Commas are often forgotten, but easily fixed. Within brackets arguments are separated with commas. R also generates an error that is helpful and can point you to the missing `,`.
:::

::: callout-important
#### Fix error 2

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
               color = cyl)) %>% 
        geom_point(size = 4)
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Error 2

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp, 
               color = cyl))+ #the error was in this line
        geom_point(size = 4)
```

`ggplot` layers are added with a `+` not with the `pipe` term.
:::

::: callout-important
#### Fix error 3

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp
               color = cyl)) +
        geom_point(size = 4) +
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Error 3

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = cyl))+
        geom_point(size = 4) #the error was in this line
```

Make sure that the end of a layer or line of code is not followed up with a `+` or `%>%`.
:::

::: callout-important
#### Fix error 4

Although R doesn't show you an error message, the code does not give you what you want. The plot should show the `cyl` parameter in different shapes, just like there are three different colors for each level of the `cyl` parameter.

``` {webr-r}

mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = as.factor(cyl)),
                shape = as.factor(cyl))+ 
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                            name = "cylinders")
```
:::

::: {.callout-caution collapse="true"}
#### Solution to Error 4

``` {webr-r}
mtcars %>% 
    select(mpg, cyl, disp) %>%
    ggplot(aes(x = mpg, y = disp,
               color = as.factor(cyl), #parenthesis error
               shape = as.factor(cyl)))+ 
        geom_point(size = 4)+
        scale_color_brewer(name = "cylinders",
                            palette = "Set2")+
        scale_shape(solid = TRUE,
                            name = "cylinders")
```

The `shape` argument should be included in the aesthetics (`aes`) part of the ggplot
:::

::: {.callout-note collapse="true"}
#### Solution to Error 4 using chatGPT

Since chatGPT can also solve basic programming problems <https://doi.org/10.1371/journal.pcbi.1011511>, I tried solving Error 4 also with chatGPT. In my chatGPT session, the following solution was given:

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             color = as.factor(cyl), 
             shape = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_shape_manual(
    name = "Cylinders",
    values = c(1, 2, 3), # Customize shape values as needed
    labels = c("4", "6", "8")
  )

```

chatGPT indeed put the `shape` in the `aes`, but also started making other changes. The remark that chatGPT made was: *"you should correct the syntax error and use scale_shape_manual() instead of scale_shape()."*... *"to customize the shape values and labels."*. I didn't really ask for that, and from there it went all downhill. Let's call that the "chatGPT loop of death". Let's see what happened. 

Running the "improved" code showed that there was still no `fill`, so it did not improve in a way that I wanted.

Next I said *"but now the shapes don't have a fill"* and chatGPT replied:

*"I see your concern. If you want to have both color and fill for the shapes, you can achieve this by mapping fill within the aes() call and using scale_fill_brewer() for the fill scale. Here's the modified code to achieve that:"*

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             color = as.factor(cyl), 
             shape = as.factor(cyl), 
             fill = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_fill_brewer(name = "Cylinders", palette = "Set2") +
  scale_shape_manual(
    name = "Cylinders",
    values = c(1, 2, 3), # Customize shape values as needed
    labels = c("4", "6", "8")
  )
```

This again did not give fill unfortunately. Asking for a different solution: *"the fill is not there, do you have another solution?"*

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             color = as.factor(cyl), 
             shape = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_fill_manual(
    name = "Cylinders",
    values = c("4" = "red", "6" = "blue", "8" = "green") 
  ) +
  scale_shape_manual(
    name = "Cylinders",
    values = c(1, 2, 3), # Customize shape values as needed
    labels = c("4", "6", "8")
  )

```

Also did not give me fill.

Another attempt by chatGPT (still not working):

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  mutate(cyl_shape_fill = as.factor(cyl)) %>%
  ggplot(aes(x = mpg, y = disp, 
             shape = cyl_shape_fill, 
             color = cyl_shape_fill)) +
  geom_point(size = 4) +
  scale_shape_manual(
    name = "Cylinders",
    values = c("4" = 21, "6" = 22, "8" = 23), 
    labels = c("4", "6", "8")
  ) +
  scale_color_manual(
    name = "Cylinders",
    values = c("4" = "red", "6" = "blue", "8" = "green") 
  )

```

Another attempt by chatGPT (still not working):

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             shape = as.factor(cyl), 
             color = as.factor(cyl))) +
  geom_point(size = 4) +
  geom_point(aes(fill = as.factor(cyl)), size = 2, 
             show.legend = FALSE) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_fill_brewer(name = "Cylinders", palette = "Set2") +
  scale_shape_manual(
    name = "Cylinders",
    values = c(1, 2, 3), # Customize shape values as needed
    labels = c("4", "6", "8")
  )

```

Asking chatGPT to use `scale_shape` and `solid=TRUE` gives:

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             color = as.factor(cyl), 
             shape = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_shape(solid = TRUE,
              name = "Cylinders",
              breaks = c("4", "6", "8"),
              labels = c("4", "6", "8"),
              values = c(15, 16, 17),
              guide = guide_legend(
                override.aes = 
                    list(fill = c("red", "blue", "green")))
  )
```

.... but apparently chatGPT doesn't know how to use `scale_shape` (in the first instance), because it `scale_shape` cannot take `values` as an argument. So when I reply with the following *"I get the following error: Error: unused argument (values = c(15, 16, 17))"*, chatGPT goes back to use the 'scale_fill_manual`.

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             color = as.factor(cyl), 
             shape = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(name = "Cylinders", palette = "Set2") +
  scale_shape_manual(
    name = "Cylinders",
    breaks = c("4", "6", "8"),
    labels = c("4", "6", "8"),
    values = c(15, 16, 17)
  ) +
  scale_fill_manual(
    name = "Cylinders",
    breaks = c("4", "6", "8"),
    labels = c("4", "6", "8"),
    values = c("red", "blue", "green")
  )
```

AND FINALLY we have a nice and simple fill with one legend...... but also lots of unnecessary code. So after a few exchanges to make the code more concise this is what came out of it:

``` {webr-r}
mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             shape = as.factor(cyl), 
             color = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(palette = "Set2", 
                    name = "Cylinders") +
  scale_shape_manual(name = "Cylinders", 
                    values = c("4" = 15, 
                        "6" = 16, 
                        "8" = 17)) +
  scale_fill_brewer(palette = "Set2", 
                    name = "Cylinders")

```

Affter asking to use `scale_shape` instead of `scale_shape_manual`, chatGPT generates:

``` {webr-r}

mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             shape = as.factor(cyl), 
             color = as.factor(cyl))) +
  geom_point(size = 4, stroke = 1) +
  scale_color_brewer(palette = "Set2", name = "Cylinders") +
  scale_shape(solid = TRUE, name = "Cylinders")

```

This works nicely, but chatGPT introduces `stroke = 1`, which is not needed here, so again we have unnecessary code. So after I asked *"can I leave out the stroke argument?"* we get the easiest solution and exactly the same solution as I came up with myself **without chatGPT**.

``` {webr-r}

mtcars %>%
  select(mpg, cyl, disp) %>%
  ggplot(aes(x = mpg, y = disp, 
             shape = as.factor(cyl), 
             color = as.factor(cyl))) +
  geom_point(size = 4) +
  scale_color_brewer(palette = "Set2", name = "Cylinders") +
  scale_shape(solid = TRUE, name = "Cylinders")
  
```

Please note, that when building the ggplot example, I did use google (...off course) to get some solutions, I liked the `scale_shape` and `solid=TRUE` solution that I found, because it made the code so concise and I don't like to type in `values` and `breaks` manually.

ChatGPT use in science and coing is just dipping the toe in the water. ChatGPT is likely to better not be used as knowledge database but instead as **"reasoning or infering agents"** <https://www.nature.com/articles/s41591-023-02594-z>. ChatGPT can produce false information, also described as **"hallucinations"** <https://www.nature.com/articles/d41586-023-00816-5>, which makes it difficult to use it for getting knowledge and facts. That said, it can be used to gain knowledge and learn better coding skills. Here is a nice *quick tips* paper from PLOS computational biology on how to *"harness the power of chatGPT"* <https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011319>.


:::