Incorporate count() suggestion from #2, add code line highlighting

01-readr.Rmd

@@ -71,22 +71,22 @@ background-size: 80px
 
 .panelset[
 .panel[.panel-name[Read data in]
-.center[Both options will get you the same dataset!]
-.pull-left[
+.center[
+### Both options below will get you the same dataset!]
+
+Option 1
 ```{r}
 # option 1: load using URL ----
 raw_adelie_url <- read_csv("https://portal.edirepository.org/nis/dataviewer?packageid=knb-lter-pal.219.3&entityid=002f3893385f710df69eeebe893144ff")
 ```
-]
-.pull-right[
+
+Option 2
 ```{r}
 # option 2: load using filepath ----
 raw_adelie_filepath <- read_csv("tutorial/raw_adelie.csv")
 ```
 ]
 
-]
-
 .panel[.panel-name[Save data]
 
 Lucky for us, the `palmerpenguins` `r emo::ji("package")` compiles data from all three species together for us!

03-ggplot2.Rmd

@@ -81,14 +81,16 @@ Let's see if body mass varies by penguin sex
 
 .pull-left[
 ```{r eval=FALSE}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) + #<<
   geom_point()
 ```
 ]
 
 .pull-right[
 ```{r, echo=FALSE, warning=FALSE, fig.height=5}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) +
   geom_point()
 ```
 ]
@@ -98,14 +100,16 @@ ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
 
 .pull-left[
 ```{r eval=FALSE}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
-  geom_boxplot()
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) +
+  geom_boxplot() #<<
 ```
 ]
 
 .pull-right[
 ```{r echo=FALSE, warning=FALSE, fig.height=5}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) +
   geom_boxplot()
 ```
 ]
@@ -115,17 +119,19 @@ ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
 
 .pull-left[
 ```{r eval=FALSE}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
-  geom_boxplot(aes(fill = species))
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) +
+  geom_boxplot(aes(fill = species)) #<<
 ```
 
 ### <br/> What do you notice?
 ]
 
 .pull-right[
 ```{r echo=FALSE, warning=FALSE, fig.height=5}
-ggplot(data = penguins, aes(x = sex, y = body_mass_g)) +
-  geom_boxplot(aes(fill = species)) #<<
+ggplot(data = penguins, 
+       aes(x = sex, y = body_mass_g)) +
+  geom_boxplot(aes(fill = species))
 ```
 ]
 ]
@@ -149,7 +155,7 @@ Next stop, `dplyr`!
 ```{r echo=FALSE, warning=FALSE, fig.height=5}
 penguins %>%
   ggplot(aes(x = sex, y = body_mass_g)) +
-  geom_boxplot(aes(fill = species)) #<<
+  geom_boxplot(aes(fill = species))
 ```
 ]
 ]

04-dplyr.Rmd

@@ -34,12 +34,13 @@ background-size: 80px
 - ...and more!
 ]
 .pull-right[
-#### Pick observations by their values with `filter()`.
-#### Reorder the rows with `arrange()`.
-#### Pick variables by their names `select()`.
-#### Create new variables with functions of existing variables `mutate()`.
-#### Collapse many values down to a single summary `summarize()`.
-#### and `group_by()` gets the above functions to operate group-by-group rather than on the entire dataset
+- Pick observations by their values with `filter()`.
+- Reorder the rows with `arrange()`.
+- Pick variables by their names `select()`.
+- Create new variables with functions of existing variables with `mutate()`.
+- Collapse many values down to a single summary with `summarize()`.
+- `group_by()` gets the above functions to operate group-by-group rather than on the entire dataset. 
+- and `count()` + `add_count()` simplify `group_by()` + `summarize()` when you just want to count
 ]
 ]
 
@@ -73,6 +74,7 @@ background-size: 80px
 # dplyr: exercise
 
 .panelset[
+
 .panel[.panel-name[Select]
 .center[ 
 ### Can you spot the difference in performing the same operation?
@@ -82,6 +84,7 @@ background-size: 80px
 select(penguins, species, sex, body_mass_g)
 ```
 ]
+
 .pull-right[
 ```{r}
 penguins %>%
@@ -91,6 +94,9 @@ penguins %>%
 ]
 
 .panel[.panel-name[Arrange]
+
+We can use `arrange()` to arrange our data in descending order by **body_mass_g**
+
 .pull-left[
 ```{r}
 glimpse(penguins)
@@ -100,45 +106,117 @@ glimpse(penguins)
 ```{r}
 penguins %>%
   select(species, sex, body_mass_g) %>%
-  arrange(desc(body_mass_g))
+  arrange(desc(body_mass_g)) #<<
 ```
 ]
 ]
 
 .panel[.panel-name[Group By & Summarize]
-#### Summarizing the data using `group_by()` and `summarize()`
+
+.pull-left[
+We can summarize the data using `group_by()` and `summarize()` to obtain counts by **species** and **sex**
 ```{r}
 penguins %>% 
-  group_by(species, sex) %>%
-  summarize(count = n())
+  group_by(species, sex) %>% #<<
+  summarize(n = n())         #<<
 ```
 ]
 
-.panel[.panel-name[Mutate]
-#### Creating new variables with `mutate()`
+.pull-right[
+And because we're just _counting_, we also have the option to use `count()` which simplifies our code!
+
+.small-text[Example kindly [contributed by Alison Hill (@apreshill)](https://github.com/spcanelon/2020-rladies-chi-tidyverse/issues/2)]
+
+```{r}
+penguins %>%
+  count(species, sex) #<<
+```
+]
+]
+
+.panel[.panel-name[Mutate: Ex. 1]
+
+.pull-left[
+We can use `mutate()` to create a new variable **n_species** that adds up all observations per **species**
 ```{r}
 penguins %>% 
   group_by(species) %>%
-  mutate(count_species = n()) %>%
+  mutate(n_species = n()) %>% #<<
   ungroup() %>%
-  group_by(species, sex, count_species) %>%
+  group_by(species, sex, n_species) %>%
+  summarize(n = n()) 
+```
+]
+
+.pull-right[
+**OR** we can use `count()`'s friend `add_count()` to create **n_species**, again because we're just _counting_
+
+.small-text[Example kindly [contributed by Alison Hill (@apreshill)](https://github.com/spcanelon/2020-rladies-chi-tidyverse/issues/2)]
+```{r}
+penguins %>% 
+  count(species, sex) %>%
+  add_count(species, wt = n,    #<<
+            name = "n_species") #<<
+```
+]
+]
+
+.panel[.panel-name[Mutate: Ex. 2]
+
+With either approach, we can use `mutate()` to create a new variable **prop**, which represents the proportion of penguins of each **sex**, grouped by **species**
+
+.pull-left[
+```{r}
+penguins %>% 
+  group_by(species) %>%
+  mutate(n_species = n()) %>%
+  ungroup() %>%
+  group_by(species, sex, n_species) %>%
   summarize(count = n()) %>%
-  mutate(prop = count/count_species*100)
+  mutate(prop = count/n_species*100) #<<
+```
+
+]
+.pull-right[
+.small-text[Example kindly [contributed by Alison Hill (@apreshill)](https://github.com/spcanelon/2020-rladies-chi-tidyverse/issues/2)]
+
+```{r}
+penguins %>% 
+  count(species, sex) %>%
+  add_count(species, wt = n, 
+            name = "n_species") %>%
+  mutate(prop = n/n_species*100) #<<
 ```
 ]
+]
 
 .panel[.panel-name[Filter]
-#### Filtering rows using `filter()`
+
+Finally, we can filter rows to only show us **Chinstrap** penguin summaries by adding `filter()` to our pipeline
+
+.pull-left[
 ```{r}
 penguins %>% 
   group_by(species) %>%
-  mutate(count_species = n()) %>%
+  mutate(n_species = n()) %>%
   ungroup() %>%
-  group_by(species, sex, count_species) %>%
+  group_by(species, sex, n_species) %>%
   summarize(count = n()) %>%
-  mutate(percentage = count/count_species*100) %>%
-  filter(species == "Chinstrap")
+  mutate(prop = count/n_species*100) %>%
+  filter(species == "Chinstrap") #<<
 ```
+
+]
+.pull-right[
+```{r}
+penguins %>% 
+  count(species, sex) %>%
+  add_count(species, wt = n, 
+            name = "n_species") %>%
+  mutate(prop = n/n_species*100) %>%
+  filter(species == "Chinstrap") #<<
+```
+]
 ]
 
 ]

05-forcats.Rmd

@@ -71,7 +71,9 @@ background-size: 80px
 ### The `factor()` function is perfect for this.
 ```{r eval=FALSE}
 penguins %>%
-  mutate(year_factor = factor(year, levels = unique(year)))
+  mutate(year_factor = 
+           factor(year,                   #<<
+                  levels = unique(year))) #<<
 ```
 ]
 
@@ -84,14 +86,17 @@ penguins %>%
 ```{r}
 penguins_new <-
   penguins %>%
-  mutate(year_factor = factor(year, levels = unique(year)))
+  mutate(year_factor = 
+           factor(year,                   #<<
+                  levels = unique(year))) #<<
 penguins_new
 ```
 ]
 
 .pull-right[
 ```{r}
 class(penguins_new$year_factor)
+
 levels(penguins_new$year_factor)
 ```
 ]

06-stringr.Rmd

@@ -79,7 +79,7 @@ background-size: 80px
 ```{r}
 penguins %>%
   select(species, island) %>%
-  mutate(ISLAND = str_to_upper(island))
+  mutate(ISLAND = str_to_upper(island)) #<<
 ```
 ]
 
@@ -90,7 +90,7 @@ penguins %>%
 penguins %>%
   select(species, island) %>%
   mutate(ISLAND = str_to_upper(island)) %>%
-  mutate(species_island = str_c(species, ISLAND, sep = "_"))
+  mutate(species_island = str_c(species, ISLAND, sep = "_")) #<<
 ```
 ]
 ]

07-tidyr.Rmd

@@ -91,9 +91,9 @@ untidy_penguins
 
 ```{r}
 untidy_penguins %>%
-  pivot_longer(cols = male:`NA`, 
-               names_to = "sex",
-               values_to = "body_mass_g")
+  pivot_longer(cols = male:`NA`,           #<<
+               names_to = "sex",           #<<
+               values_to = "body_mass_g")  #<<
 ```
 ]
 ]