人是一个非常的视觉动物，当你有一个结果的时候，一个好的展示更加能够让人接受。分享一些绘图
散点图
最常见的图可能就是散点图了：
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)
image.png
在呈现结果时，有时我会在图表中包围某些特殊的点或区域组，以引起对那些特殊情况的注意。 这可以使用ggalt包中的geom_encircle()方便地完成。
在geom_encircle（）中，将数据设置为仅包含点（行）或兴趣的新数据帧。
#
# install 'ggalt' pkg
# devtools::install_github("hrbrmstr/ggalt")
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")
image.png
Jitter Plot
# load package and data
library(ggplot2)
data(mpg, package="ggplot2") # alternate source: "http://goo.gl/uEeRGu")
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg, aes(cty, hwy))
# Scatterplot
g + geom_point() +
geom_smooth(method="lm", se=F) +
labs(subtitle="mpg: city vs highway mileage",
y="hwy",
x="cty",
title="Scatterplot with overlapping points",
caption="Source: midwest")
image.png
我们这里有一个mpg数据集中城市和公路里程的散点图。 我们已经看到了类似的散点图，这看起来很整洁，并且清楚地了解了城市里程（cty）和公路里程（hwy）如何相关性。
但是，这个途中似乎隐藏着什么
原始数据有234个数据点，但图表似乎显示的点数较少。 发生了什么？ 这是因为有许多重叠点出现为单个点。 事实上，cty和hwy都是源数据集中的整数，这使得隐藏这个细节变得更加方便。 因此，下次使用整数制作散点图时，请格外小心。
那么如何处理呢？ 几乎没有选择。 我们可以用 jitter_geom（）制作一个抖动图。 顾名思义，重叠点基于由width参数控制的阈值在其原始位置周围随机抖动。
# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg, aes(cty, hwy))
g + geom_jitter(width = .5, size=1) +
labs(subtitle="mpg: city vs highway mileage",
y="hwy",
x="cty",
title="Jittered Points")
image.png
可以看到，更多的点被体现出来了
count chart
克服数据点重叠问题的第二个选择是使用所谓的计数图表。 无论有多点重叠，圆的大小都会变大。
# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg, aes(cty, hwy))
g + geom_count(col="tomato3", show.legend=F) +
labs(subtitle="mpg: city vs highway mileage",
y="hwy",
x="cty",
title="Counts Plot")
image.png
Bubble plot
我们描述数据，x，y两个坐标轴可以描述两个维度，如果有三个维度，可以使用三维坐标轴。也可以使用二维坐标轴，用颜色，或者大小去描述第三个维度。
# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
mpg_select <- mpg[mpg$manufacturer %in% c("audi", "ford", "honda", "hyundai"), ]
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg_select, aes(displ, cty)) +
labs(subtitle="mpg: Displacement vs City Mileage",
title="Bubble chart")
g + geom_jitter(aes(col=manufacturer, size=hwy)) +
geom_smooth(aes(col=manufacturer), method="lm", se=F)
image.png
也就是说，颜色和大小可以分别描述两个维度
Marginal Histogram / Boxplot
如果要在同一图表中显示关系以及分布，请使用边缘直方图。 它在散点图的边缘有一个X和Y变量的直方图。
这可以使用'ggExtra'包中的ggMarginal（）函数来实现。 除了直方图之外，还可以通过设置相应的类型选项来选择绘制边缘箱线图或密度图。
# load package and data
library(ggplot2)
library(ggExtra)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme.
mpg_select <- mpg[mpg$hwy >= 35 & mpg$cty > 27, ]
g <- ggplot(mpg, aes(cty, hwy)) +
geom_count() +
geom_smooth(method="lm", se=F)
ggMarginal(g, type = "histogram", fill="transparent")
ggMarginal(g, type = "boxplot", fill="transparent")
# ggMarginal(g, type = "density", fill="transparent")
image.png
image.png
相关性图
描述数据的相关性
library(ggplot2)
library(ggcorrplot)
# Correlation matrix
data(mtcars)
corr <- round(cor(mtcars), 1)
# Plot
ggcorrplot(corr, hc.order = TRUE,
type = "lower",
lab = TRUE,
lab_size = 3,
method="circle",
colors = c("tomato2", "white", "springgreen3"),
title="Correlogram of mtcars",
ggtheme=theme_bw)
image.png
条形图
library(ggplot2)
theme_set(theme_bw())
# Data Prep
data("mtcars") # load data
mtcars$`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()
image.png
Diverging Lollipop Chart
我不知道怎么翻译这个图，就叫原名吧,其含义和条形图一样
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()
image.png
面积图
library(ggplot2)
library(quantmod)
data("economics", package = "ggplot2")
# Compute % Returns
economics$returns_perc <- c(0, diff(economics$psavert)/economics$psavert[-length(economics$psavert)])
# Create break points and labels for axis ticks
brks <- economics$date[seq(1, length(economics$date), 12)]
lbls <- lubridate::year(economics$date[seq(1, length(economics$date), 12)])
# Plot
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")
image.png
直方图
直方图用于看数据的分布
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")
image.png
image.png
密度图
含义与直方图类似
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")
image.png
箱线图
同样可以用来看分布，与此同时，还可以查看数据的极端之
library(ggplot2)
theme_set(theme_classic())
# Plot
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(varwidth=T, fill="plum") +
labs(title="Box plot",
subtitle="City Mileage grouped by Class of vehicle",
caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")
image.png
小提琴图
箱线图的升级版
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")
image.png
华夫饼图
这种图是看数据的组成
华夫饼图是显示总人口的分类组成的好方法。 虽然没有直接的功能，但可以通过使用geom_tile（）函数巧妙地操纵ggplot2来表达它。 下面的模板应该可以帮助创建自己的华夫饼干。
var <- mpg$class # the categorical data
## Prep data (nothing to change here)
nrows <- 10
df <- expand.grid(y = 1:nrows, x = 1:nrows)
categ_table <- round(table(var) * ((nrows*nrows)/(length(var))))
categ_table
#> 2seater compact midsize minivan pickup subcompact suv
#> 2 20 18 5 14 15 26
df$category <- factor(rep(names(categ_table), categ_table))
# NOTE: if sum(categ_table) is not 100 (i.e. nrows^2), it will need adjustment to make the sum to 100.
## Plot
ggplot(df, aes(x = x, y = y, fill = category)) +
geom_tile(color = "black", size = 0.5) +
scale_x_continuous(expand = c(0, 0)) +
scale_y_continuous(expand = c(0, 0), trans = 'reverse') +
scale_fill_brewer(palette = "Set3") +
labs(title="Waffle Chart", subtitle="'Class' of vehicles",
caption="Source: mpg") +
theme(panel.border = element_rect(size = 2),
plot.title = element_text(size = rel(1.2)),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(),
legend.title = element_blank(),
legend.position = "right")
image.png
饼图
这种图也是看数据的组成
library(ggplot2)
theme_set(theme_classic())
# Source: Frequency table
df <- as.data.frame(table(mpg$class))
colnames(df) <- c("class", "freq")
pie <- ggplot(df, aes(x = "", y=freq, fill = factor(class))) +
geom_bar(width = 1, stat = "identity") +
theme(axis.line = element_blank(),
plot.title = element_text(hjust=0.5)) +
labs(fill="class",
x=NULL,
y=NULL,
title="Pie Chart of class",
caption="Source: mpg")
pie + coord_polar(theta = "y", start=0)
# Source: Categorical variable.
# mpg$class
pie <- ggplot(mpg, aes(x = "", fill = factor(class))) +
geom_bar(width = 1) +
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)
image.png