数据可视化总是看着简单，但实操起来bug频繁，究其原因，还是数据处理和ggplot2的相关参数等掌握不精。

1. 数据准备

#加载包
library(dplyr)
library(readr)
library(ggplot2)

#读取数据
athlete_events <- read_csv("athlete_events.csv")
noc_regions <- read_csv("noc_regions.csv")
head(athlete_events)

athletedata <- inner_join(athlete_events,noc_regions,c("NOC"))
head(athletedata)

2. 了解每个地区参数人数的分布情况(条形图)

region <- athletedata %>% 
    group_by(region) %>% 
    summarise(value=n()) %>% 
    arrange(desc(value)) #按照地区分组，计算每个地区的参赛人数，并按照从大到小的顺序输出

region30 <- region[1:30,]
region_plot <- ggplot(region30,aes(x=reorder(region,value),y=value)) +
    theme_bw(base_family = "STKaiti") +
    geom_bar(aes(fill=value),stat = "identity",show.legend = F) +
    coord_flip() +
    scale_fill_gradient(low = "blue",high = "red") +
    labs(x="地区",y="参赛人数",title = "每个地区参赛人数的分布情况") +
    theme(axis.text.x = element_text(vjust = 0.5),plot.title = element_text(hjust = 0.5))
region_plot

条形图

3. 了解不同时间、不同地区、不同性别的参赛人数的分布情况(热力图)

index <- region30$region[1:30] #取前30个地区为一组向量，而region30[1:30,1]仍为列表形式

region30_merge![](http://upload-images.jianshu.io/upload_images/25726527-67da2172b54802b3.jpg?imageMogr2/auto-orient/strip%7CimageView2/2/w/1080/q/50)

 <- athletedata %>% 
    filter(region %in% index) %>%
    group_by(Year,region,Sex) %>%
    summarise(value=n())

merge_plot <- ggplot(region30_merge,aes(x=Year,y=region)) +
    theme_bw(base_family = "STKaiti") +
    geom_tile(aes(fill=value),color="white") +
    scale_fill_gradientn(colors = c("blue","red")) +
    scale_x_continuous(breaks = unique(region30_merge$Year)) +
    theme(axis.text.x = element_text(hjust = 0.5,angle = 90)) +
    facet_wrap(~Sex,nrow = 2)
options(repr.plot.width=10, repr.plot.height=8)
merge_plot

热力图

4. 将USA、Germany、France、UK、Russia、China这6个地区每年奥运会奖牌的数量可视化(折线图)

index <- c("USA","Germany","France","UK","Russia","China")
region6 <- athletedata %>% 
    filter(region %in% index) %>% #只选择6个地区
    filter(Medal!="NA") %>% #只选择有奖牌获得
    group_by(region,Year) %>% 
    summarise(value=n())

region6_plot <- ggplot(region6,aes(x=Year,y=value)) +
    theme_bw(base_family = "STKaiti") +
    geom_line() +
    facet_wrap(~region,nrow = 3)
region6_plot

折线图

5. 动态展示不同地区每年的奖牌获得情况

library(gganimate)
index <- region30$region[1:30]
region30_medal <- athletedata %>% 
    filter(region %in% index) %>% 
    filter(Medal!="NA") %>% 
    group_by(region,Year) %>% 
    summarise(value=n())
region30_medal$Year <- as.integer(region30_medal$Year) #将year这一变量变为整型变量

region30_plot <- ggplot(region30_medal,aes(x=region,y = value)) +
    theme_bw() +
    geom_bar(stat = "identity",show.legend = F) +
    theme(axis.text.x = element_text(hjust = 0.5,angle = 90)) +
    transition_time(Year) +
    labs(title="Year: {frame_time}")
region30_plot

6. 对地区、运动员数量、性别、奖牌数量这些变量进行可视化分析(树图)

library(treemap)
#计算奖牌数量
medal <- athletedata %>% 
    filter(Medal!="NA") %>% 
    group_by(region,Sex) %>% 
    summarise(medalnum=n())

#计算运动员数量
athelete <- athletedata %>% 
    group_by(region,Sex) %>% 
    summarise(atheletenum=n())
data <- inner_join(medal,athelete,c("region","Sex"))

data_plot <- treemap(data,index = c("Sex","region"),vSize = "atheletenum",
                    vColor="medalnum",type="value",palette=c("blue","red"),
                    title="不同性别下不同地区运动员的数量",title.legend="奖牌数量",
                    fontfamily.title="STKaiti",fontfamily.legend="STKaiti")
data_plot

树图

日常废话：很多参数的设置都可以理解为图层的叠加，因此只要心中有大致的图形轮廓，围绕这个轮廓进行添枝加叶，就能更加灵活应用各种参数。可能每个新手都会同我一样，面对这些措手不及，甚至产生畏惧心理，觉得自己可能就不是学代码的这块料，自己就是不行，学啥都慢，等等。有这些想法都是正常的，因为很多知识都是我们需要用了才会去了解去掌握，为了进步为了更加优秀才会深入拓展，所以一定要给自己运用这些知识的机会，在实践中你才能享受到解决问题的快乐！！！