library(tidyverse)
library(mosaic) # Our all-in-one package
library(skimr) # Looking at data
library(ggformula) # Our plotting package
library(visdat) # Mapping missing data
library(naniar) # Missing data visualization and munging
library(janitor) # Clean the data
library(tinytable) # Printing Tables for our data
library(DT) # Interactive Tables for our data
##
# devtools::install_github("rpruim/Lock5withR")
library(Lock5withR)
library(Lock5Data) # Some neat little datasets from a lovely textbook
Charts and How they are generated from Data
2021-11-01
““He is one of those who don’t want millions, but an answer to their questions.”
— Alyosha, in The Brothers Karamazov
Plot Fonts and Theme
Code
library(systemfonts)
library(showtext)
## Clean the slate
systemfonts::clear_local_fonts()
systemfonts::clear_registry()
##
showtext_opts(dpi = 96) # set DPI for showtext
sysfonts::font_add(
family = "Alegreya",
regular = "../../../../../../fonts/Alegreya-Regular.ttf",
bold = "../../../../../../fonts/Alegreya-Bold.ttf",
italic = "../../../../../../fonts/Alegreya-Italic.ttf",
bolditalic = "../../../../../../fonts/Alegreya-BoldItalic.ttf"
)
sysfonts::font_add(
family = "Roboto Condensed",
regular = "../../../../../../fonts/RobotoCondensed-Regular.ttf",
bold = "../../../../../../fonts/RobotoCondensed-Bold.ttf",
italic = "../../../../../../fonts/RobotoCondensed-Italic.ttf",
bolditalic = "../../../../../../fonts/RobotoCondensed-BoldItalic.ttf"
)
showtext_auto(enable = TRUE) # enable showtext
##
theme_custom <- function() {
theme_bw(base_size = 10) +
#
# theme(panel.widths = unit(11, "cm"),
# panel.heights = unit(6.79, "cm")) + # Golden Ratio
#
theme(
plot.margin = margin_auto(t = 1, r = 2, b = 1, l = 1, unit = "cm"),
plot.background = element_rect(
fill = "bisque",
colour = "black",
linewidth = 1
)
) +
theme_sub_axis(
title = element_text(
family = "Roboto Condensed",
size = 10
),
text = element_text(
family = "Roboto Condensed",
size = 8
)
) +
theme_sub_legend(
text = element_text(
family = "Roboto Condensed",
size = 6
),
title = element_text(
family = "Alegreya",
size = 8
)
) +
theme_sub_plot(
title = element_text(
family = "Alegreya",
size = 14, face = "bold"
),
title.position = "plot",
subtitle = element_text(
family = "Alegreya",
size = 10
),
caption = element_text(
family = "Alegreya",
size = 6
),
caption.position = "plot"
)
}
## Use available fonts in ggplot text geoms too!
ggplot2::update_geom_defaults(geom = "text", new = list(
family = "Roboto Condensed",
face = "plain",
size = 3.5,
color = "#2b2b2b"
))
ggplot2::update_geom_defaults(geom = "label", new = list(
family = "Roboto Condensed",
face = "plain",
size = 3.5,
color = "#2b2b2b"
))
ggplot2::update_geom_defaults(geom = "marquee", new = list(
family = "Roboto Condensed",
face = "plain",
size = 3.5,
color = "#2b2b2b"
))
ggplot2::update_geom_defaults(geom = "text_repel", new = list(
family = "Roboto Condensed",
face = "plain",
size = 3.5,
color = "#2b2b2b"
))
ggplot2::update_geom_defaults(geom = "label_repel", new = list(
family = "Roboto Condensed",
face = "plain",
size = 3.5,
color = "#2b2b2b"
))
## Set the theme
ggplot2::theme_set(new = theme_custom())
## tinytable options
options("tinytable_tt_digits" = 2)
options("tinytable_format_num_fmt" = "significant_cell")
options(tinytable_html_mathjax = TRUE)
## Set defaults for flextable
flextable::set_flextable_defaults(font.family = "Roboto Condensed")Some Pictures
- It helps sift facts from mere statements: for example:
- Visuals are a good starting point to make hypotheses of what may be happening in the situation represented by the data
What is Tidy Data?
Let us recall first what we meant by tidy data:
- How many geometric things do we know?
- Shapes? Lines? Axes? Curves? Angles? Patterns? Textures? Colours? Sizes? Positions? Lengths? Heights? Breadths? Radii? Textures?
- All these are geometric aspects or aesthetics, each with a unique property.
- Some “geometric things” which we might consider are shown in the figure below.
A Data Visualization Example
Code
set.seed(1947)
diamonds %>%
slice_sample(n = 150, weight_by = cut) %>%
gf_point(price ~ carat,
colour = ~cut,
shape = ~cut,
size = 2, data = .
) %>%
gf_labs(
title = "Plot Title = DIAMONDS ARE FOREVER",
subtitle = "Plot Subtitle = AND A GIRL'S BEST FRIEND",
caption = "Plot Caption = From the diamonds dataset",
x = "x-Axis Title = CARAT",
y = "y-Axis Title = PRICE"
) %>%
# Use same name for scales to merge legends
gf_refine(
scale_color_brewer(
name = "Legend = DIAMOND QUALITY",
palette = "Set1"
),
scale_shape_manual(
name = "Legend = DIAMOND QUALITY",
values = c(15:21)
)
) %>%
gf_annotate("text",
x = 1.0, y = 16000,
label = "These DIAMONDS are\n Super Affordable!!",
fontface = "bold",
size = 2
) %>%
gf_annotate("curve",
x = 0.9,
y = 14500,
yend = 8000,
xend = 0.95,
linewidth = 0.5,
curvature = 0.5,
arrow = arrow(length = unit(0.25, "cm"))
) %>%
gf_annotate(
"rect",
xmin = 1,
xmax = 1.25,
ymin = 2250,
ymax = 10000,
alpha = 0.5,
fill = "grey80",
col = "black"
)
Facets
- Finally, if the graph is too busy, with lots of colours and shapes, then we can split the graph into many small multiples or facets, each showing a subset of the data.
- This is called faceting and is a powerful way to reduce cognitive load on the viewer.
Code
set.seed(1947)
diamonds %>%
slice_sample(n = 150, weight_by = cut) %>%
gf_point(price ~ carat | clarity,
colour = ~cut,
shape = ~cut,
size = 2, data = .
) %>%
gf_labs(
title = "Plot Title = DIAMONDS ARE FOREVER",
subtitle = "Plot Subtitle = AND A GIRL'S BEST FRIEND",
caption = "Plot Caption = From the diamonds dataset",
x = "x-Axis Title = CARAT",
y = "y-Axis Title = PRICE"
) %>%
# Use same name for scales to merge legends
gf_refine(
scale_color_brewer(
name = "Legend = DIAMOND QUALITY",
palette = "Set1"
),
scale_shape_manual(
name = "Legend = DIAMOND QUALITY",
values = c(15:21)
)
)
Data Science Workflow
