数据可视化完美指南-R-python

从数据到图表

有什么样的数据做什么样的图

作者提供了一张树状图，帮助并引导我们找到合适自己数据的的可视化方式

What kind of data do you have? Pick the main type using the buttons below.
Then let the decision tree guide you toward your graphic possibilities.

这便是有名的网站：https://www.data-to-viz.com/。

Yan Holtz 和Conor Healys两个人关系很好，一起在业余时间开发了这个网站。基于R和Python做的源代码，这里我们不仅可以得到大量优秀的源代码，同时我们可以得到一张决策树，用于知道如何使用代码。这两个人相当厉害了，不仅仅给大家了工具，还叫大家如何使用。作为无私的分享，如果对大家有用，请在文章中致谢他们。如果我们需要交流代码，和谁交流呢？那必须是Yan Holtz，这位主要负责代码部分。Conor Healys负责图形设计工作。

可视化架构

原图地址：https://www.data-to-viz.com/img/poster/poster_big.png

基于网站我们来做一个示例

基于有顺序的二维数据框的出图

# Libraries
library(tidyverse)
## -- Attaching packages ----------------------------------------------------------------------------------------------------------- tidyverse 1.2.1 --
## √ ggplot2 3.2.0     √ purrr   0.3.2
## √ tibble  2.1.3     √ dplyr   0.8.3
## √ tidyr   0.8.3     √ stringr 1.4.0
## √ readr   1.3.1     √ forcats 0.4.0
## -- Conflicts -------------------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(hrbrthemes)
## NOTE: Either Arial Narrow or Roboto Condensed fonts are required to use these themes.
##       Please use hrbrthemes::import_roboto_condensed() to install Roboto Condensed and
##       if Arial Narrow is not on your system, please see https://bit.ly/arialnarrow
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
##     last_plot
## The following object is masked from 'package:stats':
##
##     filter
## The following object is masked from 'package:graphics':
##
##     layout
library(patchwork)
# install.packages("babynames")
library(babynames)
library(viridis)
## Loading required package: viridisLite
# ?as.Date
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/3_TwoNumOrdered.csv", header=T)
data$date <- as.Date(data$date)

这里仅仅提取最后的十个数据进行点线图的可视化

# Plot
data %>%
tail(10) %>%
ggplot( aes(x=date, y=value)) +
geom_line(color="#69b3a2") +
geom_point(color="#69b3a2", size=4) +
ggtitle("Evolution of Bitcoin price") +
ylab("bitcoin price ($)") +
theme_ipsum()

这里使用最后的60个数据进行可视化

# Plot
p1 <- data %>%
tail(60) %>%
ggplot( aes(x=date, y=value)) +
geom_line(color="#69b3a2") +
ggtitle("Line chart") +
ylab("bitcoin price ($)") +
theme_ipsum()

p2 <- data %>%
tail(60) %>%
ggplot( aes(x=date, y=value)) +
geom_line(color="#69b3a2") +
geom_point(color="#69b3a2", size=2) +
ggtitle("Connected scatterplot") +
ylab("bitcoin price ($)") +
theme_ipsum()

p = p1 + p2
p

散点图展示时间序列

# Plot
data %>%
tail(60) %>%
ggplot( aes(x=date, y=value)) +
geom_point(color="#69b3a2", size=2) +
ggtitle("Line chart") +
ylab("bitcoin price ($)") +
theme_ipsum()

分组时间序列可视化

library(babynames)

# Load dataset
data <- babynames %>%
filter(name %in% c("Ashley", "Amanda")) %>%
filter(sex=="F")

#plot
data %>%
ggplot( aes(x=year, y=n, group=name, color=name)) +
geom_line() +
scale_color_viridis(discrete = TRUE, name="") +
theme(legend.position="none") +
ggtitle("Popularity of American names in the previous 30 years") +
theme_ipsum()

geom_segment函数突出展示变化趋势

library(grid) # needed for arrow function
library(ggrepel)

# data
tmp <- data %>%
filter(year>1970) %>%
select(year, name, n) %>%
spread(key = name, value=n, -1)

# data for date
tmp_date <- tmp %>% sample_frac(0.3)

tmp%>%
ggplot(aes(x=Amanda, y=Ashley, label=year)) +
geom_point(color="#69b3a2") +
geom_text_repel(data=tmp_date) +
geom_segment(color="#69b3a2",
aes(
xend=c(tail(Amanda, n=-1), NA),
yend=c(tail(Ashley, n=-1), NA)
),
arrow=arrow(length=unit(0.3,"cm"))
) +
theme_ipsum()

data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/3_TwoNumOrdered.csv", header=T)
data$date <- as.Date(data$date)

p1 <- data %>%
tail(10) %>%
ggplot( aes(x=date, y=value)) +
geom_line(color="#69b3a2") +
geom_point(color="#69b3a2", size=4) +
ggtitle("Not cuting") +
ylab("bitcoin price ($)") +
theme_ipsum() +
ylim(0,10000)

p2 <- data %>%
tail(10) %>%
ggplot( aes(x=date, y=value)) +
geom_line(color="#69b3a2") +
geom_point(color="#69b3a2", size=4) +
ggtitle("Cuting") +
ylab("bitcoin price ($)") +
theme_ipsum()

p1 + p2

reference

https://www.data-to-viz.com/graph/connectedscatter.html