基础图形可视化
数据分析的图形可视化是了解数据分布、波动和相关性等属性必不可少的手段。本文基于参考资料收集其可视化代码，如想了解更多，请查看参考链接。
边界散点图(Scatterplot With Encircling）
library(ggplot2)
library(ggalt)
midwest_select <- midwest[midwest$poptotal > 350000 &
midwest$poptotal <= 500000 &
midwest$area > 0.01 &
midwest$area < 0.1, ]
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")
边缘箱图/直方图(Marginal Histogram / Boxplot)
2、边缘箱图/直方图(Marginal Histogram / Boxplot)
library(ggplot2)
library(ggExtra)
data(mpg, package="ggplot2")
theme_set(theme_bw())
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")
#ggMarginal(g, type = "boxplot", fill="transparent")
拟合散点图
library(ggplot2)
theme_set(theme_bw())
data("midwest")
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")
相关系数图(Correlogram)
library(ggplot2)
library(ggcorrplot)
data(mtcars)
corr <- round(cor(mtcars), 1)
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)
水平发散型文本(Diverging Texts)
library(ggplot2)
library(dplyr)
library(tibble)
theme_set(theme_bw())
# Data Prep
data("mtcars")
plotdata <- mtcars %>% rownames_to_column("car_name") %>%
mutate(mpg_z=round((mpg - mean(mpg))/sd(mpg), 2),
mpg_type=ifelse(mpg_z < 0, "below", "above")) %>%
arrange(mpg_z)
plotdata$car_name <- factor(plotdata$car_name,
levels = as.character(plotdata$car_name))
ggplot(plotdata, aes(x=car_name, y=mpg_z, label=mpg_z)) +
geom_bar(stat='identity', aes(fill=mpg_type), width=.5) +
scale_fill_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) +
labs(subtitle="Normalised mileage from 'mtcars'",
title= "Diverging Bars") +
coord_flip()
水平棒棒糖图(Diverging Lollipop Chart)
ggplot(plotdata, aes(x=car_name, y=mpg_z, label=mpg_z)) +
geom_point(stat='identity', fill="black", size=6) +
geom_segment(aes(y = 0,
x = car_name,
yend = mpg_z,
xend = car_name),
color = "black") +
geom_text(color="white", size=2) +
labs(title="Diverging Lollipop Chart",
subtitle="Normalized mileage from 'mtcars': Lollipop") +
ylim(-2.5, 2.5) +
coord_flip()
去棒棒糖图(Diverging Dot Plot)
ggplot(plotdata, aes(x=car_name, y=mpg_z, label=mpg_z)) +
geom_point(stat='identity', aes(col=mpg_type), size=6) +
scale_color_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) +
geom_text(color="white", size=2) +
labs(title="Diverging Dot Plot",
subtitle="Normalized mileage from 'mtcars': Dotplot") +
ylim(-2.5, 2.5) +
coord_flip()
面积图(Area Chart)
library(ggplot2)
library(quantmod)
data("economics", package = "ggplot2")
economics$returns_perc <- c(0, diff(economics$psavert)/economics$psavert[-length(economics$psavert)])
brks <- economics$date[seq(1, length(economics$date), 12)]
lbls <- lubridate::year(economics$date[seq(1, length(economics$date), 12)])
ggplot(economics[1:100, ], aes(date, returns_perc)) +
geom_area() +
scale_x_date(breaks=brks, labels=lbls) +
theme(axis.text.x = element_text(angle=90)) +
labs(title="Area Chart",
subtitle = "Perc Returns for Personal Savings",
y="% Returns for Personal savings",
caption="Source: economics")
排序条形图(Ordered Bar Chart)
cty_mpg <- aggregate(mpg$cty, by=list(mpg$manufacturer), FUN=mean)
colnames(cty_mpg) <- c("make", "mileage")
cty_mpg <- cty_mpg[order(cty_mpg$mileage), ]
cty_mpg$make <- factor(cty_mpg$make, levels = cty_mpg$make)
library(ggplot2)
theme_set(theme_bw())
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))
直方图(Histogram)
library(ggplot2)
theme_set(theme_classic())
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")
library(ggplot2)
theme_set(theme_classic())
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")
核密度图(Density plot)
library(ggplot2)
theme_set(theme_classic())
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")
点图结合箱图(Dot + Box Plot)
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")
小提琴图(Violin Plot)
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")
饼图
library(ggplot2)
theme_set(theme_classic())
# Source: Frequency table
df <- as.data.frame(table(mpg$class))
colnames(df) <- c("class", "freq")
pie <- ggplot(df, aes(x = "", y=freq, fill = factor(class))) +
geom_bar(width = 1, stat = "identity") +
theme(axis.line = element_blank(),
plot.title = element_text(hjust=0.5)) +
labs(fill="class",
x=NULL,
y=NULL,
title="Pie Chart of class",
caption="Source: mpg")
pie + coord_polar(theta = "y", start=0)
时间序列图(Time Series多图)
## From Timeseries object (ts)
library(ggplot2)
library(ggfortify)
theme_set(theme_classic())
# Plot
autoplot(AirPassengers) +
labs(title="AirPassengers") +
theme(plot.title = element_text(hjust=0.5))
library(ggplot2)
theme_set(theme_classic())
# Allow Default X Axis Labels
ggplot(economics, aes(x=date)) +
geom_line(aes(y=returns_perc)) +
labs(title="Time Series Chart",
subtitle="Returns Percentage from 'Economics' Dataset",
caption="Source: Economics",
y="Returns %")
data(economics_long, package = "ggplot2")
library(ggplot2)
library(lubridate)
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
堆叠面积图(Stacked Area Chart)
library(ggplot2)
library(lubridate)
theme_set(theme_bw())
df <- economics[, c("date", "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$date), 12)]
lbls <- lubridate::year(brks)
# plot
ggplot(df, aes(x=date)) +
geom_area(aes(y=psavert+uempmed, fill="psavert")) +
geom_area(aes(y=uempmed, fill="uempmed")) +
labs(title="Area Chart of Returns Percentage",
subtitle="From Wide Data format",
caption="Source: Economics",
y="Returns %") + # title and caption
scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
scale_fill_manual(name="",
values = c("psavert"="#00ba38", "uempmed"="#f8766d")) + # line color
theme(panel.grid.minor = element_blank()) # turn off minor grid
分层树形图(Hierarchical Dendrogram)
library(ggplot2)
library(ggdendro)
theme_set(theme_bw())
hc <- hclust(dist(USArrests), "ave") # hierarchical clustering
# plot
ggdendrogram(hc, rotate = TRUE, size = 2)
聚类图(Clusters)
library(ggplot2)
library(ggalt)
library(ggfortify)
theme_set(theme_classic())
# Compute data with principal components ------------------
df <- iris[c(1, 2, 3, 4)]
pca_mod <- prcomp(df) # compute principal components
# Data frame of principal components ----------------------
df_pc <- data.frame(pca_mod$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))
气泡图
# Libraries
library(ggplot2)
library(dplyr)
library(plotly)
library(viridis)
library(hrbrthemes)
# The dataset is provided in the gapminder library
library(gapminder)
data <- gapminder %>% filter(year=="2007") %>% dplyr::select(-year)
# Interactive version
p <- data %>%
mutate(gdpPercap=round(gdpPercap,0)) %>%
mutate(pop=round(pop/1000000,2)) %>%
mutate(lifeExp=round(lifeExp,1)) %>%
# Reorder countries to having big bubbles on top
arrange(desc(pop)) %>%
mutate(country = factor(country, country)) %>%
# prepare text for tooltip
mutate(text = paste("Country: ", country, "\nPopulation (M): ", pop, "\nLife Expectancy: ", lifeExp, "\nGdp per capita: ", gdpPercap, sep="")) %>%
# Classic ggplot
ggplot( aes(x=gdpPercap, y=lifeExp, size = pop, color = continent, text=text)) +
geom_point(alpha=0.7) +
scale_size(range = c(1.4, 19), name="Population (M)") +
scale_color_viridis(discrete=TRUE, guide=FALSE) +
theme_ipsum() +
theme(legend.position="none")
# turn ggplot interactive with plotly
pp <- ggplotly(p, tooltip="text")
pp
