# load package and data
options(scipen=999) # turn-off scientific notation like 1e+48
library(ggplot2)
theme_set(theme_bw()) # pre-set the bw theme.
data("midwest", package = "ggplot2")
# midwest <- read.csv("http://goo.gl/G1K41K") # bkup data source
# Scatterplot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state, size=popdensity)) +
geom_smooth(method="loess", se=F) +
xlim(c(0, 0.1)) +
ylim(c(0, 500000)) +
labs(subtitle="Area Vs Population",
y="Population",
x="Area",
title="Scatterplot",
caption = "Source: midwest")
plot(gg)
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).
# install.packages("ggalt", repos = "cran.nexr.com")
options(scipen = 999)
library(ggplot2)
library(ggalt)
midwest_select <- midwest[midwest$poptotal > 350000 &
midwest$poptotal <= 500000 &
midwest$area > 0.01 &
midwest$area < 0.1, ]
# Plot
ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state, size=popdensity)) + # draw points
geom_smooth(method="loess", se=F) +
xlim(c(0, 0.1)) +
ylim(c(0, 500000)) + # draw smoothing line
geom_encircle(aes(x=area, y=poptotal),
data=midwest_select,
color="red",
size=2,
expand=0.08) + # encircle
labs(subtitle="Area Vs Population",
y="Population",
x="Area",
title="Scatterplot + Encircle",
caption="Source: midwest")
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).
# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
mpg_select <- mpg[mpg$manufacturer %in% c("audi", "ford", "honda", "hyundai"), ]
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg_select, aes(displ, cty)) +
labs(subtitle="mpg: Displacement vs City Mileage",
title="Bubble chart")
g + geom_jitter(aes(col=manufacturer, size=hwy)) +
geom_smooth(aes(col=manufacturer), method="lm", se=F)
# load package and data
library(ggplot2)
if(!require(ggExtra)) install.packages("ggExtra")
## Loading required package: ggExtra
library(ggExtra)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
mpg_select <- mpg[mpg$hwy >= 35 & mpg$cty > 27, ]
g <- ggplot(mpg, aes(cty, hwy)) +
geom_count() +
geom_smooth(method="lm", se=F)
ggMarginal(g, type = "histogram", fill="transparent")
theme_set(theme_bw()) # pre-set the bw theme.
g
ggMarginal(g, type = "boxplot", fill="transparent")
# ggMarginal(g, type = "density", fill="transparent")
# devtools::install_github("kassambara/ggcorrplot")
library(ggplot2)
library(ggcorrplot)
# Correlation matrix
data(mtcars)
corr <- round(cor(mtcars), 1)
# Plot
ggcorrplot(corr, hc.order = TRUE,
type = "lower",
lab = TRUE,
lab_size = 3,
method="circle",
colors = c("tomato2", "white", "springgreen3"),
title="Correlogram of mtcars",
ggtheme=theme_bw)
library(ggplot2)
theme_set(theme_bw())
# Data Prep
data("mtcars") # load data
mtcars$`car name` <- rownames(mtcars) # create new column for car names
mtcars$mpg_z <- round((mtcars$mpg - mean(mtcars$mpg))/sd(mtcars$mpg), 2) # compute normalized mpg
mtcars$mpg_type <- ifelse(mtcars$mpg_z < 0, "below", "above") # above / below avg flag
mtcars <- mtcars[order(mtcars$mpg_z), ] # sort
mtcars$`car name` <- factor(mtcars$`car name`, levels = mtcars$`car name`) # convert to factor to retain sorted order in plot.
# Diverging Barcharts
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
geom_bar(stat='identity', aes(fill=mpg_type), width=.5) +
scale_fill_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) +
labs(subtitle="Normalised mileage from 'mtcars'",
title= "Diverging Bars") +
coord_flip()
library(ggplot2)
theme_set(theme_bw())
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
geom_point(stat='identity', fill="black", size=6) +
geom_segment(aes(y = 0,
x = `car name`,
yend = mpg_z,
xend = `car name`),
color = "black") +
geom_text(color="white", size=2) +
labs(title="Diverging Lollipop Chart",
subtitle="Normalized mileage from 'mtcars': Lollipop") +
ylim(-2.5, 2.5) +
coord_flip()
library(ggplot2)
theme_set(theme_bw())
# Plot
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
geom_point(stat='identity', aes(col=mpg_type), size=6) +
scale_color_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) +
geom_text(color="white", size=2) +
labs(title="Diverging Dot Plot",
subtitle="Normalized mileage from 'mtcars': Dotplot") +
ylim(-2.5, 2.5) +
coord_flip()
# Prepare data: group mean city mileage by manufacturer.
cty_mpg <- aggregate(mpg$cty, by=list(mpg$manufacturer), FUN=mean) # aggregate
colnames(cty_mpg) <- c("make", "mileage") # change column names
cty_mpg <- cty_mpg[order(cty_mpg$mileage), ] # sort
cty_mpg$make <- factor(cty_mpg$make, levels = cty_mpg$make) # to retain the order in plot.
head(cty_mpg, 4)
## make mileage
## 9 lincoln 11.33333
## 8 land rover 11.50000
## 3 dodge 13.13514
## 10 mercury 13.25000
library(ggplot2)
theme_set(theme_bw())
# Draw plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_bar(stat="identity", width=.5, fill="tomato3") +
labs(title="Ordered Bar Chart",
subtitle="Make Vs Avg. Mileage",
caption="source: mpg") +
theme(axis.text.x = element_text(angle=65, vjust=0.6))
library(ggplot2)
library(scales)
theme_set(theme_classic())
# prep data
df <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/gdppercap.csv")
colnames(df) <- c("continent", "1952", "1957")
left_label <- paste(df$continent, round(df$`1952`),sep=", ")
right_label <- paste(df$continent, round(df$`1957`),sep=", ")
df$class <- ifelse((df$`1957` - df$`1952`) < 0, "red", "green")
# Plot
p <- ggplot(df) + geom_segment(aes(x=1, xend=2, y=`1952`, yend=`1957`, col=class), size=.75, show.legend=F) +
geom_vline(xintercept=1, linetype="dashed", size=.1) +
geom_vline(xintercept=2, linetype="dashed", size=.1) +
scale_color_manual(labels = c("Up", "Down"),
values = c("green"="#00ba38", "red"="#f8766d")) + # color of lines
labs(x="", y="Mean GdpPerCap") + # Axis labels
xlim(.5, 2.5) + ylim(0,(1.1*(max(df$`1952`, df$`1957`)))) # X and Y axis limits
# Add texts
p <- p + geom_text(label=left_label, y=df$`1952`, x=rep(1, NROW(df)), hjust=1.1, size=3.5)
p <- p + geom_text(label=right_label, y=df$`1957`, x=rep(2, NROW(df)), hjust=-0.1, size=3.5)
p <- p + geom_text(label="Time 1", x=1, y=1.1*(max(df$`1952`, df$`1957`)), hjust=1.2, size=5) # title
p <- p + geom_text(label="Time 2", x=2, y=1.1*(max(df$`1952`, df$`1957`)), hjust=-0.1, size=5) # title
# Minify theme
p + theme(panel.background = element_blank(),
panel.grid = element_blank(),
axis.ticks = element_blank(),
axis.text.x = element_blank(),
panel.border = element_blank(),
plot.margin = unit(c(1,2,1,2), "cm"))
library(ggplot2)
theme_set(theme_classic())
# Histogram on a Continuous (Numeric) Variable
g <- ggplot(mpg, aes(displ)) + scale_fill_brewer(palette = "Spectral")
g + geom_histogram(aes(fill=class),
binwidth = .1,
col="black",
size=.1) + # change binwidth
labs(title="Histogram with Auto Binning",
subtitle="Engine Displacement across Vehicle Classes")
g + geom_histogram(aes(fill=class),
bins=5,
col="black",
size=.1) + # change number of bins
labs(title="Histogram with Fixed Bins",
subtitle="Engine Displacement across Vehicle Classes")
theme_set(theme_classic())
# Histogram on a Categorical variable
g <- ggplot(mpg, aes(manufacturer))
g + geom_bar(aes(fill=class), width = 0.5) +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) +
labs(title="Histogram on Categorical Variable",
subtitle="Manufacturer across Vehicle Classes")
library(ggplot2)
theme_set(theme_classic())
# Plot
g <- ggplot(mpg, aes(cty))
g + geom_density(aes(fill=factor(cyl)), alpha=0.8) +
labs(title="Density plot",
subtitle="City Mileage Grouped by Number of cylinders",
caption="Source: mpg",
x="City Mileage",
fill="# Cylinders")
library(ggplot2)
theme_set(theme_bw())
# plot
g <- ggplot(mpg, aes(manufacturer, cty))
g + geom_boxplot() +
geom_dotplot(binaxis='y',
stackdir='center',
dotsize = .5,
fill="red") +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) +
labs(title="Box plot + Dot plot",
subtitle="City Mileage vs Class: Each dot represents 1 row in source data",
caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")
## `stat_bindot()` using `bins = 30`. Pick better value with `binwidth`.
library(ggplot2)
theme_set(theme_bw())
# plot
g <- ggplot(mpg, aes(class, cty))
g + geom_violin() +
labs(title="Violin plot",
subtitle="City Mileage vs Class of vehicle",
caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")
library(ggplot2)
library(ggthemes)
options(scipen = 999) # turns of scientific notations like 1e+40
# Read data
email_campaign_funnel <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/email_campaign_funnel.csv")
# X Axis Breaks and Labels
brks <- seq(-15000000, 15000000, 5000000)
lbls = paste0(as.character(c(seq(15, 0, -5), seq(5, 15, 5))), "m")
# Plot
ggplot(email_campaign_funnel, aes(x = Stage, y = Users, fill = Gender)) + # Fill column
geom_bar(stat = "identity", width = .6) + # draw the bars
scale_y_continuous(breaks = brks, # Breaks
labels = lbls) + # Labels
coord_flip() + # Flip axes
labs(title="Email Campaign Funnel") +
theme_tufte() + # Tufte theme from ggfortify
theme(plot.title = element_text(hjust = .5),
axis.ticks = element_blank()) + # Centre plot title
scale_fill_brewer(palette = "Dark2") # Color palette
library(ggplot2)
library(lubridate)
##
## Attaching package: 'lubridate'
## The following object is masked from 'package:base':
##
## date
theme_set(theme_bw())
df <- economics_long[economics_long$variable %in% c("psavert", "uempmed"), ]
df <- df[lubridate::year(df$date) %in% c(1967:1981), ]
# labels and breaks for X axis text
brks <- df$date[seq(1, length(df$date), 12)]
lbls <- lubridate::year(brks)
# plot
ggplot(df, aes(x=date)) +
geom_line(aes(y=value, col=variable)) +
labs(title="Time Series of Returns Percentage",
subtitle="Drawn from Long Data format",
caption="Source: Economics",
y="Returns %",
color=NULL) + # title and caption
scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
scale_color_manual(labels = c("psavert", "uempmed"),
values = c("psavert"="#00ba38", "uempmed"="#f8766d")) + # line color
theme(axis.text.x = element_text(angle = 90, vjust=0.5, size = 8), # rotate x axis text
panel.grid.minor = element_blank()) # turn off minor grid
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:lubridate':
##
## intersect, setdiff, union
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
theme_set(theme_classic())
source_df <- read.csv("https://raw.githubusercontent.com/jkeirstead/r-slopegraph/master/cancer_survival_rates.csv")
# Define functions. Source: https://github.com/jkeirstead/r-slopegraph
tufte_sort <- function(df, x="year", y="value", group="group", method="tufte", min.space=0.05) {
## First rename the columns for consistency
ids <- match(c(x, y, group), names(df))
df <- df[,ids]
names(df) <- c("x", "y", "group")
## Expand grid to ensure every combination has a defined value
tmp <- expand.grid(x=unique(df$x), group=unique(df$group))
tmp <- merge(df, tmp, all.y=TRUE)
df <- mutate(tmp, y=ifelse(is.na(y), 0, y))
## Cast into a matrix shape and arrange by first column
require(reshape2)
tmp <- dcast(df, group ~ x, value.var="y")
ord <- order(tmp[,2])
tmp <- tmp[ord,]
min.space <- min.space*diff(range(tmp[,-1]))
yshift <- numeric(nrow(tmp))
## Start at "bottom" row
## Repeat for rest of the rows until you hit the top
for (i in 2:nrow(tmp)) {
## Shift subsequent row up by equal space so gap between
## two entries is >= minimum
mat <- as.matrix(tmp[(i-1):i, -1])
d.min <- min(diff(mat))
yshift[i] <- ifelse(d.min < min.space, min.space - d.min, 0)
}
tmp <- cbind(tmp, yshift=cumsum(yshift))
scale <- 1
tmp <- melt(tmp, id=c("group", "yshift"), variable.name="x", value.name="y")
## Store these gaps in a separate variable so that they can be scaled ypos = a*yshift + y
tmp <- transform(tmp, ypos=y + scale*yshift)
return(tmp)
}
plot_slopegraph <- function(df) {
ylabs <- subset(df, x==head(x,1))$group
yvals <- subset(df, x==head(x,1))$ypos
fontSize <- 3
gg <- ggplot(df,aes(x=x,y=ypos)) +
geom_line(aes(group=group),colour="grey80") +
geom_point(colour="white",size=8) +
geom_text(aes(label=y), size=fontSize, family="American Typewriter") +
scale_y_continuous(name="", breaks=yvals, labels=ylabs)
return(gg)
}
## Prepare data
df <- tufte_sort(source_df,
x="year",
y="value",
group="group",
method="tufte",
min.space=0.05)
## Loading required package: reshape2
df <- transform(df,
x=factor(x, levels=c(5,10,15,20),
labels=c("5 years","10 years","15 years","20 years")),
y=round(y))
## Plot
plot_slopegraph(df) + labs(title="Estimates of % survival rates") +
theme(axis.title=element_blank(),
axis.ticks = element_blank(),
plot.title = element_text(hjust=0.5,
family = "American Typewriter",
face="bold"),
axis.text = element_text(family = "American Typewriter",
face="bold"))
library(ggplot2)
library(forecast)
theme_set(theme_classic())
# Subset data
nottem_small <- window(nottem, start=c(1920, 1), end=c(1925, 12)) # subset a smaller timewindow
# Plot
ggseasonplot(AirPassengers) + labs(title="Seasonal plot: International Airline Passengers")
ggseasonplot(nottem_small) + labs(title="Seasonal plot: Air temperatures at Nottingham Castle")
# install.packages("ggdendro")
library(ggplot2)
library(ggdendro)
theme_set(theme_bw())
hc <- hclust(dist(USArrests), "ave") # hierarchical clustering
# plot
ggdendrogram(hc, rotate = TRUE, size = 2)
# devtools::install_github("hrbrmstr/ggalt")
library(ggplot2)
library(ggalt)
library(ggfortify)
##
## Attaching package: 'ggfortify'
## The following object is masked from 'package:forecast':
##
## gglagplot
theme_set(theme_classic())
# Compute data with principal components ------------------
df <- iris[c(1, 2, 3, 4)]
pca_mod <- prcomp(df) # compute principal components
# Data frame of principal components ----------------------
df_pc <- data.frame(pca_mod$x, Species=iris$Species) # dataframe of principal components
df_pc_vir <- df_pc[df_pc$Species == "virginica", ] # df for 'virginica'
df_pc_set <- df_pc[df_pc$Species == "setosa", ] # df for 'setosa'
df_pc_ver <- df_pc[df_pc$Species == "versicolor", ] # df for 'versicolor'
# Plot ----------------------------------------------------
ggplot(df_pc, aes(PC1, PC2, col=Species)) +
geom_point(aes(shape=Species), size=2) + # draw points
labs(title="Iris Clustering",
subtitle="With principal components PC1 and PC2 as X and Y axis",
caption="Source: Iris") +
coord_cartesian(xlim = 1.2 * c(min(df_pc$PC1), max(df_pc$PC1)),
ylim = 1.2 * c(min(df_pc$PC2), max(df_pc$PC2))) + # change axis limits
geom_encircle(data = df_pc_vir, aes(x=PC1, y=PC2)) + # draw circles
geom_encircle(data = df_pc_set, aes(x=PC1, y=PC2)) +
geom_encircle(data = df_pc_ver, aes(x=PC1, y=PC2))
