# small function to display plots only if it's interactive
p_ <- GGally::print_if_interactive
data(baseball)
# Keep players from 1990-1995 with at least one at bat
# Add how many singles a player hit
# (must do in two steps as X1b is used in calculations)
dt <- transform(
subset(baseball, year >= 1990 & year <= 1995 & ab > 0),
X1b = h - X2b - X3b - hr
)
# Add
# the player's batting average,
# the player's slugging percentage,
# and the player's on base percentage
# Make factor a year, as each season is discrete
dt <- transform(
dt,
batting_avg = h / ab,
slug = (X1b + 2 * X2b + 3 * X3b + 4 * hr) / ab,
on_base = (h + bb + hbp) / (ab + bb + hbp),
year = as.factor(year)
)
pm <- ggduo(
dt,
c("year", "g", "ab", "lg"),
c("batting_avg", "slug", "on_base"),
mapping = ggplot2::aes(color = lg)
)
# Prints, but
# there is severe over plotting in the continuous plots
# the labels could be better
# want to add more hitting information
p_(pm)
# address overplotting issues and add a title
pm <- ggduo(
dt,
c("year", "g", "ab", "lg"),
c("batting_avg", "slug", "on_base"),
columnLabelsX = c("year", "player game count", "player at bat count", "league"),
columnLabelsY = c("batting avg", "slug %", "on base %"),
title = "Baseball Hitting Stats from 1990-1995",
mapping = ggplot2::aes(color = lg),
types = list(
# change the shape and add some transparency to the points
continuous = wrap("smooth_loess", alpha = 0.50, shape = "+")
),
showStrips = FALSE
)
p_(pm)
# Use "auto" to adapt width of the sub-plots
pm <- ggduo(
dt,
c("year", "g", "ab", "lg"),
c("batting_avg", "slug", "on_base"),
mapping = ggplot2::aes(color = lg),
xProportions = "auto"
)
p_(pm)
# Custom widths & heights of the sub-plots
pm <- ggduo(
dt,
c("year", "g", "ab", "lg"),
c("batting_avg", "slug", "on_base"),
mapping = ggplot2::aes(color = lg),
xProportions = c(6, 4, 3, 2),
yProportions = c(1, 2, 1)
)
p_(pm)
# Example derived from:
## R Data Analysis Examples | Canonical Correlation Analysis. UCLA: Institute for Digital
## Research and Education.
## from http://www.stats.idre.ucla.edu/r/dae/canonical-correlation-analysis
## (accessed May 22, 2017).
# "Example 1. A researcher has collected data on three psychological variables, four
# academic variables (standardized test scores) and gender for 600 college freshman.
# She is interested in how the set of psychological variables relates to the academic
# variables and gender. In particular, the researcher is interested in how many
# dimensions (canonical variables) are necessary to understand the association between
# the two sets of variables."
data(psychademic)
summary(psychademic)
(psych_variables <- attr(psychademic, "psychology"))
(academic_variables <- attr(psychademic, "academic"))
## Within correlation
p_(ggpairs(psychademic, columns = psych_variables))
p_(ggpairs(psychademic, columns = academic_variables))
## Between correlation
loess_with_cor <- function(data, mapping, ..., method = "pearson") {
x <- eval_data_col(data, mapping$x)
y <- eval_data_col(data, mapping$y)
cor <- cor(x, y, method = method)
ggally_smooth_loess(data, mapping, ...) +
ggplot2::geom_label(
data = data.frame(
x = min(x, na.rm = TRUE),
y = max(y, na.rm = TRUE),
lab = round(cor, digits = 3)
),
mapping = ggplot2::aes(x = x, y = y, label = lab),
hjust = 0, vjust = 1,
size = 5, fontface = "bold",
inherit.aes = FALSE # do not inherit anything from the ...
)
}
pm <- ggduo(
psychademic,
rev(psych_variables), academic_variables,
types = list(continuous = loess_with_cor),
showStrips = FALSE
)
suppressWarnings(p_(pm)) # ignore warnings from loess
# add color according to sex
pm <- ggduo(
psychademic,
mapping = ggplot2::aes(color = sex),
rev(psych_variables), academic_variables,
types = list(continuous = loess_with_cor),
showStrips = FALSE,
legend = c(5, 2)
)
suppressWarnings(p_(pm))
# add color according to sex
pm <- ggduo(
psychademic,
mapping = ggplot2::aes(color = motivation),
rev(psych_variables), academic_variables,
types = list(continuous = loess_with_cor),
showStrips = FALSE,
legend = c(5, 2)
) +
ggplot2::theme(legend.position = "bottom")
suppressWarnings(p_(pm))
# dt,
# c("year", "g", "ab", "lg", "lg"),
# c("batting_avg", "slug", "on_base", "hit_type"),
# columnLabelsX = c("year", "player game count", "player at bat count", "league", ""),
# columnLabelsY = c("batting avg", "slug %", "on base %", "hit type"),
# title = "Baseball Hitting Stats from 1990-1995 (player strike in 1994)",
# mapping = aes(color = year),
# types = list(
# continuous = wrap("smooth_loess", alpha = 0.50, shape = "+"),
# comboHorizontal = wrap(display_hit_type_combo, binwidth = 15),
# discrete = wrap(display_hit_type_discrete, color = "black", size = 0.15)
# ),
# showStrips = FALSE
## make the 5th column blank, except for the legend
# australia_PISA2012,
# c("gender", "age", "homework", "possessions"),
# c("PV1MATH", "PV2MATH", "PV3MATH", "PV4MATH", "PV5MATH"),
# types = list(
# continuous = "points",
# combo = "box",
# discrete = "ratio"
# )
# australia_PISA2012,
# c("gender", "age", "homework", "possessions"),
# c("PV1MATH", "PV2MATH", "PV3MATH", "PV4MATH", "PV5MATH"),
# mapping = ggplot2::aes(color = gender),
# types = list(
# continuous = wrap("smooth", alpha = 0.25, method = "loess"),
# combo = "box",
# discrete = "ratio"
# )
Run the code above in your browser using DataLab