ggplot_part1
2023-03-28
#Download Packages and Dependencies
# List of packages and dependencies
my_packages <- c("devtools", "Rtools", "rlang", "tidyverse", "broom", "coefplot", "cowplot", "gapminder", "GGally", "ggrepel", "ggridges", "gridExtra","here", "interplot", "margins", "maps", "mapproj", "mapdata", "MASS", "quantreg", "rlang", "scales", "survey", "srvyr", "viridis", "viridisLite")
# Install the packages directly from the CRAN
install.packages(my_packages, repos = "http://cran.rstudio.com")## Installing packages into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)## Warning: packages 'Rtools', 'margins', 'MASS' are not available for this version of R
## 'MASS' version 7.3-60.2 is in the repositories but depends on R (>= 4.4.0)
## 'MASS' version 7.3-60.2 is in the repositories but depends on R (>= 4.5)
##
## Versions of these packages for your version of R might be available elsewhere,
## see the ideas at
## https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packages## Warning: dependency 'Matrix' is not available## also installing the dependencies 'curl', 'vctrs', 'credentials', 'httr2', 'htmltools', 'sass', 'labelled', 'nloptr', 'RcppEigen', 'gert', 'gh', 'whisker', 'bslib', 'downlit', 'htmlwidgets', 'xopen', 'brew', 'brio', 'digest', 'evaluate', 'jsonlite', 'praise', 'processx', 'ps', 'waldo', 'assertthat', 'zoo', 'xts', 'lazyeval', 'crosstalk', 'broom.helpers', 'patchwork', 'lme4', 'coda', 'usethis', 'desc', 'miniUI', 'pkgbuild', 'pkgdown', 'pkgload', 'profvis', 'rcmdcheck', 'remotes', 'roxygen2', 'rversions', 'sessioninfo', 'testthat', 'urlchecker', 'plyr', 'reshape2', 'useful', 'dygraphs', 'plotly', 'ggplot2', 'ggstats', 'rprojroot', 'abind', 'arm', 'interactionTest', 'SparseM', 'MatrixModels', 'minqa', 'numDeriv', 'mitools', 'RcppArmadillo'## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'RcppEigen' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'MatrixModels' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'quantreg' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'survey' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'srvyr' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'lme4' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'arm' had non-zero exit status## Warning in install.packages(my_packages, repos = "http://cran.rstudio.com"):
## installation of package 'interplot' had non-zero exit statusLoad the gapminder dataset
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.1 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(gapminder)
gapminder## # A tibble: 1,704 × 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779.
## 2 Afghanistan Asia 1957 30.3 9240934 821.
## 3 Afghanistan Asia 1962 32.0 10267083 853.
## 4 Afghanistan Asia 1967 34.0 11537966 836.
## 5 Afghanistan Asia 1972 36.1 13079460 740.
## 6 Afghanistan Asia 1977 38.4 14880372 786.
## 7 Afghanistan Asia 1982 39.9 12881816 978.
## 8 Afghanistan Asia 1987 40.8 13867957 852.
## 9 Afghanistan Asia 1992 41.7 16317921 649.
## 10 Afghanistan Asia 1997 41.8 22227415 635.
## # ℹ 1,694 more rows# Define the data
p <- ggplot(data = gapminder)
p
# Specify x and y aesthetics mapping
p <- ggplot(data = gapminder, mapping = aes(x = gdpPercap,
y = lifeExp))
p
geom_point() - to add the points from the mapped data, add a geom_point() to the ggplot()
p <- ggplot(data = gapminder, mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point()
p
Layer 1: Smoothing
p <- ggplot(data = gapminder, mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_smooth()
p## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
Layer 2: Add points - Add the geom_point() with geom_smooth to place points in the smoothed line
# Add the geom_point first, then geom_smooth
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point() +
geom_smooth()
p## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
Smoothing: Alternative methods - geom_smooth() using the GAM (Generalized Additive Model) by default for smoothing. You can specify the method by using the method parameter in geom_smooth()
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point() +
geom_smooth(method="lm")
p## `geom_smooth()` using formula = 'y ~ x'
Set the smoothing method to “loess”
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point() +
geom_smooth(method="loess")
p## `geom_smooth()` using formula = 'y ~ x'
Scaling data - in previous graph, GDP per capitais really bunched up. Let’s trasnform the data by scaling it with log base 10
# Scale the GDP using log base 10 and the gam method
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point() +
geom_smooth(method="gam") +
scale_x_log10()
p## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'
Scaling: adding labels - to add labels to the x-axis, we can specify them using the “labels” attribute in the scale (scale_x_log10() function. Some helpful functions are in the “scales” package. You can import “scales” package as library(scales) or refereence it explicitly in the code, without the import)
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point() +
geom_smooth(method="gam") +
scale_x_log10(labels = scales::dollar)
p## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'
Setting Aesthetics - to set the size and shape of the data, define the aesthetics in the geom_ function.
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point(color="red", size = 0.5) +
geom_smooth(method="gam") +
scale_x_log10(labels = scales::dollar)
p## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'
You can set as many aesthetic properties as you would like to each geom_ in the plot.
# For the smooth line, set it to green, use the lm smoothing
# no standard error and a line size of 5
# For the points, let's make them slightly transparent
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point(color="#f7797d", size = 0.3) +
geom_smooth(color = "darkblue", method="lm", se = FALSE, size = 0.5) +
scale_x_log10(labels = scales::dollar)## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.p## `geom_smooth()` using formula = 'y ~ x'
Titles, labels, and captions - to provide the audience with critical information, we should add label, title, and captions to our graphs. To do so, we use the “labs” function and add it to our ggplot
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point(color="#f7797d", size = 0.3) +
geom_smooth(color = "darkblue", method="lm", se = FALSE, size = 0.5) +
scale_x_log10(labels = scales::dollar) +
labs(x = "GDP per capita",
y = "Life Expectancy in Years",
title = "Economics Growth and Life Expectancy",
subtitle = "Data points are country-years",
caption = "Source: Gapminder, scaling log 10")
p## `geom_smooth()` using formula = 'y ~ x'
Mapping data to aesthetics - to make aesthetics dependent of data, we set the attribute in the aesthetics mapping of aes:
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp,
color = continent)) +
geom_point(size = 0.5) +
geom_smooth(method="loess", size = 0.5) +
scale_x_log10(labels = scales::dollar) +
labs(x = "GDP per capita",
y = "Life Expectancy in Years",
title = "Economics Growth and Life Expectancy",
subtitle = "Data points are country-years",
caption = "Source: Gapminder, scaling log 10")
p## `geom_smooth()` using formula = 'y ~ x'
Mapping Aesthetics per Geom - instead of mapping the entier plot’s aesthetics, you can map the aesthetics for individual geoms by specifying the mapping = aes() for that geom.
p <- ggplot(data = gapminder,
mapping = aes(x = gdpPercap,
y = lifeExp)) +
geom_point(mapping = aes(color = continent),size = 0.5) +
geom_smooth(method="loess", size = 0.5) +
scale_x_log10(labels = scales::dollar) +
labs(x = "GDP per capita",
y = "Life Expectancy in Years",
title = "Economics Growth and Life Expectancy",
subtitle = "Data points are country-years",
caption = "Source: Gapminder, scaling log 10")
p## `geom_smooth()` using formula = 'y ~ x'