• 原文来自 https://mp.weixin.qq.com/s/dgtli_3m8Mxw7TMRNvtA6A（异常感谢）
• 科比是我们80后每个篮球爱好者喜爱的球员，当年没少追，可惜英年早逝，只能用R来分析一生数据，以此纪念！
• 科比数据下载：
  https://share.weiyun.com/5cGUFvK

library(tidyverse)
library(gridExtra)
library(ggplot2)
library(ggpubr)
# Read the stats
shots <- read.csv("data.csv")

---

投球类型：

 # We use a different alpha value for jump shots to improve the visualization
ggplot() + 
  geom_point(data=shots %>% filter(combined_shot_type=="Jump Shot"),
             aes(x=lon, y=lat), colour="grey", alpha=0.3) +
  geom_point(data=shots %>% filter(combined_shot_type!="Jump Shot"),
             aes(x=lon, y=lat, colour=combined_shot_type), alpha=0.8) +
  labs(title="Shot type") +
  ylim(c(33.7, 34.0883)) +
  theme_void() + theme(legend.title=element_blank(),
        plot.title=element_text(hjust=0.5))

p1.png

投球范围

p2 <- ggplot(shots, aes(x=lon, y=lat)) +
  geom_point(aes(color=shot_zone_range)) +
  labs(title="Shot zone range") +
  ylim(c(33.7, 34.0883)) +
  theme_void() +
  theme(legend.position="none",
        plot.title=element_text(hjust=0.5))

p3 <- ggplot(shots, aes(x=fct_infreq(shot_zone_range))) + 
  geom_bar(aes(fill=shot_zone_range)) +
  labs(y="Frequency") +
  theme_bw() +
  theme(axis.title.x=element_blank(), 
        legend.position="none")
ggarrange(p2,p3,ncol=1,labels = "AUTO")

p2+3.png

投球区域：

# Shot zone area
p4 <- ggplot(shots, aes(x=lon, y=lat)) +
  geom_point(aes(colour=shot_zone_area)) +
  labs(title="Shot zone area") +
  ylim(c(33.7, 34.0883)) +
  theme_void() +
  theme(legend.position="none",
        plot.title=element_text(hjust=0.5))

p5 <- ggplot(shots, aes(x=fct_infreq(shot_zone_area))) + 
  geom_bar(aes(fill=shot_zone_area)) +
  labs(y="Frequency") +
  theme_bw() +
  theme(axis.text.x=element_text(size=7),
        axis.title.x=element_blank(), 
        legend.position="none")
ggarrange(p4,p5,ncol=1,labels = "AUTO")

p4+5.png

根据场线来划分：

p6 <- ggplot(shots, aes(x=lon, y=lat)) +
  geom_point(aes(color=shot_zone_basic)) +
  labs(title="Shot zone basic") +
  ylim(c(33.7, 34.0883)) +
  theme_void() +
  theme(legend.position="none",
        plot.title=element_text(hjust=0.5))

p7 <- ggplot(shots, aes(x=fct_infreq(shot_zone_basic))) + 
  geom_bar(aes(fill=shot_zone_basic)) +
  labs(y="Frequency") +
  theme_bw() +
  theme(axis.text.x=element_text(size=6.3),
        axis.title.x=element_blank(), 
        legend.position="none")
ggarrange(p6,p7,ncol=1,labels = "AUTO")

p6+7.png

不同投球的方式及其准确性

shots %>%
  group_by(action_type) %>%
  summarise(Accuracy=mean(shot_made_flag, na.rm = TRUE),
            counts=n()) %>%
  filter(counts>20) %>%
  ggplot(aes(x=reorder(action_type, Accuracy), y=Accuracy)) + 
  geom_point(aes(colour=Accuracy), size=3) +
  scale_colour_gradient(low="orangered", high="chartreuse3") +
  labs(title="Accuracy by shot type") +
  theme_bw() +
  theme(axis.title.y=element_blank(),
        legend.position="none",
        plot.title=element_text(hjust=0.5)) +
  coord_flip()

p8.png

准确度随着时间变化：

shots %>%
  group_by(season) %>%
  summarise(Accuracy=mean(shot_made_flag, na.rm = TRUE)) %>%
  ggplot(aes(x=season, y=Accuracy, group=1)) +
  geom_line(aes(colour=Accuracy)) +
  geom_point(aes(colour=Accuracy), size=3) +
  scale_colour_gradient(low="orangered", high="chartreuse3") +
  labs(title="Accuracy by season", x="Season") +
  theme_bw() +
  theme(legend.position="none",
        axis.text.x=element_text(angle=45, hjust=1),
        plot.title=element_text(hjust=0.5))

p9.png

准确率和赛季变化

shots %>%
  group_by(season) %>%
  summarise(Playoff=mean(shot_made_flag[playoffs==1], na.rm = TRUE),
            RegularSeason=mean(shot_made_flag[playoffs==0], na.rm = TRUE)) %>%
  ggplot(aes(x=season, group=1)) +
  geom_line(aes(y=Playoff, colour="Playoff")) +
  geom_line(aes(y=RegularSeason, colour="RegularSeason")) +
  geom_point(aes(y=Playoff, colour="Playoff"), size=3) +
  geom_point(aes(y=RegularSeason, colour="RegularSeason"), size=3) +
  labs(title="Accuracy by season", 
       subtitle="Playoff and Regular Season",
       x="Season", y="Accuracy") +
  theme_bw() +
  theme(legend.title=element_blank(),
        legend.position="bottom",
        axis.text.x=element_text(angle=45, hjust=1),
        plot.title=element_text(hjust=0.5),
        plot.subtitle=element_text(hjust=0.5))

p10.png