{r setup, include=FALSE} knitr::opts_chunk$set(eval = FALSE)
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
</script>
本文于r format(Sys.Date(), "%Y-%m-%d")更新。 如发现问题或者有建议，欢迎提交 Issue
项目需求是给在一群运动员内选出最佳的几个，并给出相应的数据支持。
- 数据支持方面，需要给出几个指标供参考，最后做(无监督学习)，将指标聚合，最后使用一个综合得分进行选择的评价。
- 决策的方面，最后的数据支持是要展示出来，并知道决策的，因此最后会使用
ggplot包展示选出的最佳运动员，和其他运动员的比较，以此来说服需求方。
本文的数据、Code、思路参考 @Perry2018 。
思路具体如下，
- 创建四个指标
TotalDistance总成绩StandardDev成绩数据的标准差，体现风险Success成功次数diff后三次和前三次的成绩差
- 匹配权重，这里可以用PCA等完成，但不是本文重点，因此直接赋值。
- 找出最好的五位选手，用
max和mean水平来体现这五个选手的优势，这个idea很棒。
清洗数据
```{r} # Load the tidyverse package library(tidyverse)
Import the full dataset
data <- read_csv(’../../../picbackup/athletics.csv')
Select the results of interest: women’s javelin
javelin <- data %>% filter(Male_Female ==‘Female’,Event==‘Javelin’) %>% select(-Male_Female,-Event)
Give yourself a snapshot of your data
javelin %>% head() javelin %>% summary()
# 构建指标
```
# Assign the tidy data to javelin_long
javelin_long <- javelin %>%
gather(Flight,Distance,Flight1:Flight6)
# Make Flight a numeric
javelin_long <-
javelin_long %>%
mutate(Flight = str_extract(Flight,'[:digit:]{1,}')) %>%
mutate(Flight = as.numeric(Flight))
# Examine the first 6 rows
javelin_long %>% head()
javelin_totals <- javelin_long %>%
filter(Distance > 0) %>%
group_by(Athlete, EventID) %>%
summarise(
TotalDistance = sum(Distance)
,StandardDev = sd(Distance) %>% round(.,3)
,Success = n()
)
```{r} # View 10 rows of javelin_totals javelin_totals[11:20,]
javelin <- javelin %>% mutate(early = Flight1+Flight2+Flight3 # ,late = Flight2+Flight3+Flight4 ,late = Flight4+Flight5+Flight6 ) %>% mutate(diff = late - early) javelin %>% tail(10) # …. YOUR CODE FOR TASK 4 ….
# 构建综合评分和选出选手
```
# Examine the last ten rows
# .... YOUR CODE FOR TASK 4 ....
javelin_totals <-
javelin_totals %>%
left_join(javelin ,by=c('Athlete','EventID')) %>%
select(Athlete,TotalDistance,StandardDev,Success,diff)
javelin_totals %>%
head(10)
norm <- function(result) {
(result - min(result)) / (max(result) - min(result))
}
aggstats <- c("TotalDistance", "StandardDev", "Success", "diff")
javelin_norm <- javelin_totals %>%
ungroup() %>%
mutate_at(vars(aggstats),norm) %>%
group_by(Athlete) %>%
summarise_all(funs(mean(.)))
head(javelin_norm)
weights <- c(1, 2, 3, 4)
javelin_team <- javelin_norm %>%
mutate(TotalScore =
weights[1]*TotalDistance +
weights[2]*StandardDev +
weights[3]*Success +
weights[4]*diff
) %>%
arrange(desc(TotalScore)) %>%
select(Athlete,TotalScore) %>%
head(5)
javelin_team
构建可比水平
```{r} team_stats <- javelin_totals %>% # …. YOUR CODE FOR TASK 8 …. # …. YOUR CODE FOR TASK 8 …. filter(Athlete %in% javelin_team$Athlete) %>% summarise_all(funs(mean(.)))
pool_stats <- data.frame(do.call(‘cbind’, sapply(javelin_totals, function(x) if(is.numeric(x)) c(max(x), mean(x))))) pool_stats$MaxAve <- c(“Maximum”, “Average”) pool_stats <- pool_stats %>% gather(key=“Statistic”, value=“Aggregate”, -MaxAve)
Examine team stats
…. YOUR CODE FOR TASK 8 ….
team_stats
pool_stats
# 展示
```
p <- team_stats %>%
gather(Statistic,Aggregate,-Athlete) %>%
ggplot(aes(x=Athlete,y=Aggregate,fill=Athlete))+
geom_bar(stat="identity") +
facet_wrap (~Statistic, nrow = 2, ncol = 2, scales="free_y") +
geom_hline(data=pool_stats, aes(yintercept=Aggregate, group=Statistic, color=MaxAve), size=1) +
labs(title=".... Your Team Name....: Women's Javelin", color="Athlete pool maximum / average") +
scale_fill_hue(l=70) +
scale_color_hue(l=20) +
theme_minimal() +
theme(axis.text.x=element_blank(), axis.title.x=element_blank(), axis.title.y=element_blank())
p
模拟比赛结果
```{r} home <- c(1,2,3) away <- sample(1:nrow(javelin_totals), 3, replace=FALSE)
HomeTeam <- round(sum(team_stats$TotalDistance[home]),2) AwayTeam <- round(sum(javelin_totals$TotalDistance[away]),2)
print(paste0(“Javelin match, Final Score:”, HomeTeam, " - “, AwayTeam)) ifelse(HomeTeam > AwayTeam, print(“Win!”), print(“Sometimes you just have to take the L.”)) ```