20200220_drug_ggplot2_goodies.R

################################################################################
## Intro to plotting with ggplot2: other goodies 2020-02-20
################################################################################


# Getting started ---------------------------------------------------------

# First let's download a data set called "portal_data_joined.csv"
# We'll put it in our data folder inside of our project directory.
# If you don't already have a data directory, you can create one in 
# the files pane. Alternatively, you can download the data by hand:
# https://tinyurl.com/y36xgftg

download.file(url = "https://tinyurl.com/y36xgftg", 
              destfile = "data/portal_data_joined.csv")

install.packages("tidyverse")
library(tidyverse)

surveys <- read_csv("data/portal_data_joined.csv")
str(surveys)
View(surveys)

# use dplyr to remove NAs

surveys_complete <- surveys %>%
  filter(!is.na(weight),
         !is.na(hindfoot_length),
         !is.na(sex))


# review: build a ggplot

ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal()


# titles, captions, and subtitles -----------------------------------------

# add a title
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  ggtitle("Hindfoot vs weight")

# add a subtitle
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  labs(title = "Hindfoot vs weight",
       subtitle = "Surveys Data")

# add a caption
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  labs(title = "Hindfoot vs weight",
       subtitle = "Surveys Data",
       caption = "Data collected from 1977 - 2002")

# captions and titles are scriptable
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  labs(title = "Hindfoot vs weight", 
       subtitle = "Surveys Data", 
       caption = paste0("Data collected from ", 
                        min(surveys_complete$year), 
                        "-", 
                        max(surveys_complete$year)))


# labeling points: ggrepel -----------------------------------------------

install.packages("ggrepel")
library(ggrepel)
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight, label = species_id)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  geom_text_repel()

# only label species codes for outliers
ggplot(surveys_complete, aes(x = hindfoot_length, y = weight)) +
  geom_point(alpha = .1) +
  theme_minimal() +
  geom_text_repel(data = filter(surveys_complete, hindfoot_length > 60),
                  aes(x = hindfoot_length, y = weight),
                  label = species_id)

# make interactive plots --------------------------------------------------

install.packages("plotly")
library(plotly)
plt <- ggplot(surveys_complete, aes(x = hindfoot_length, y = weight, label = species_id)) +
  geom_point(alpha = .1) +
  theme_minimal()

ggplotly(plt)