9.NBA球员数据分析

---

1.导入库

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import cv2
from pylab import mpl
#显示中文字体
mpl.rcParams["font.sans-serif"] = ["SimHei"]
#设置正常显示字符
mpl.rcParams["axes.unicode_minus"] = False

---

2.获取数据

# 读取数据信息
data = pd.read_csv('./2.code/data/nba_2017_nba_players_with_salary.csv')
data.head(10)

# 数据属性说明
img = cv2.imread('6.seabron_alignment.png',1)
cv2.imshow('imge',img,)
cv2.waitKey(0)

# 查看表结构
data.shape

(342, 38)

#查看表属性
data.describe()

	Rk	AGE	MP	FG	FGA	FG%	3P	3PA	3P%	2P	...	GP	MPG	ORPM	DRPM	RPM	WINS_RPM	PIE	PACE	W	SALARY_MILLIONS
count	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	320.000000	342.000000	...	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000	342.000000
mean	217.269006	26.444444	21.572515	3.483626	7.725439	0.446096	0.865789	2.440058	0.307016	2.620175	...	58.198830	21.572807	-0.676023	-0.005789	-0.681813	2.861725	9.186842	98.341053	28.950292	7.294006
std	136.403138	4.295686	8.804018	2.200872	4.646933	0.078992	0.780010	2.021716	0.134691	1.828714	...	22.282015	8.804121	2.063237	1.614293	2.522014	3.880914	3.585475	2.870091	14.603876	6.516326
min	1.000000	19.000000	2.200000	0.000000	0.800000	0.000000	0.000000	0.000000	0.000000	0.000000	...	2.000000	2.200000	-4.430000	-3.920000	-6.600000	-2.320000	-1.600000	87.460000	0.000000	0.030000
25%	100.250000	23.000000	15.025000	1.800000	4.225000	0.402250	0.200000	0.800000	0.280250	1.200000	...	43.500000	15.025000	-2.147500	-1.222500	-2.422500	0.102500	7.100000	96.850000	19.000000	2.185000
50%	205.500000	26.000000	21.650000	3.000000	6.700000	0.442000	0.700000	2.200000	0.340500	2.200000	...	66.000000	21.650000	-0.990000	-0.130000	-1.170000	1.410000	8.700000	98.205000	29.000000	4.920000
75%	327.750000	29.000000	29.075000	4.700000	10.400000	0.481000	1.400000	3.600000	0.373500	3.700000	...	76.000000	29.075000	0.257500	1.067500	0.865000	4.487500	10.900000	100.060000	39.000000	11.110000
max	482.000000	40.000000	37.800000	10.300000	24.000000	0.750000	4.100000	10.000000	1.000000	9.700000	...	82.000000	37.800000	7.270000	6.020000	8.420000	20.430000	23.000000	109.870000	66.000000	30.960000

8 rows × 35 columns

---

3.数据分析

3.1 数据相关性–heatmap()

data_cor = data.loc[:, ['RPM', 'AGE', 'SALARY_MILLIONS', 'ORB', 'DRB', 'TRB','AST', 'STL', 'BLK', 'TOV', 'PF', 'POINTS', 'GP', 'MPG', 'ORPM', 'DRPM']]
data_cor.head()

	RPM	AGE	SALARY_MILLIONS	ORB	DRB	TRB	AST	STL	BLK	TOV	PF	POINTS	GP	MPG	ORPM	DRPM
0	6.27	28	26.50	1.7	9.0	10.7	10.4	1.6	0.4	5.4	2.3	31.6	81	34.6	6.74	-0.47
1	4.81	27	26.50	1.2	7.0	8.1	11.2	1.5	0.5	5.7	2.7	29.1	81	36.4	6.38	-1.57
2	1.83	27	6.59	0.6	2.1	2.7	5.9	0.9	0.2	2.8	2.2	28.9	76	33.8	5.72	-3.89
3	4.35	23	22.12	2.3	9.5	11.8	2.1	1.3	2.2	2.4	2.2	28.0	75	36.1	0.45	3.90
4	4.20	26	16.96	2.1	8.9	11.0	4.6	1.4	1.3	3.7	3.9	27.0	72	34.2	3.56	0.64

#调用corr()方法 获取两列数据之间的相关性
# 返回改数据类型的相关系数矩阵（即每两个类型直接的相关性）
corr = data_cor.corr()
corr.head()

	RPM	AGE	SALARY_MILLIONS	ORB	DRB	TRB	AST	STL	BLK	TOV	PF	POINTS	GP	MPG	ORPM	DRPM
RPM	1.000000	0.175820	0.477542	0.388764	0.623515	0.587853	0.481971	0.599008	0.463097	0.492014	0.434226	0.604432	0.340810	0.549449	0.769822	0.578388
AGE	0.175820	1.000000	0.353312	-0.015752	0.088859	0.062064	0.114908	0.069892	-0.062917	0.030673	0.005512	0.031422	0.051863	0.099657	0.136177	0.100636
SALARY_MILLIONS	0.477542	0.353312	1.000000	0.264954	0.531569	0.482088	0.486159	0.446763	0.260288	0.536993	0.341512	0.635425	0.348093	0.594162	0.503682	0.102307
ORB	0.388764	-0.015752	0.264954	1.000000	0.731345	0.861103	-0.011632	0.169075	0.654265	0.274670	0.557957	0.284908	0.296975	0.342140	0.102113	0.476857
DRB	0.623515	0.088859	0.531569	0.731345	1.000000	0.976244	0.350786	0.485726	0.660733	0.598043	0.670708	0.648267	0.473376	0.684662	0.428433	0.426536

# 绘制热力图
plt.figure(figsize=(20,8),dpi=100)
sns.heatmap(corr,square=True,linewidths=0.1,annot=True)

3.2 球员数据分析

# 按照效率值排名
data.loc[:, ["PLAYER", "RPM","SALARY_MILLIONS", "AGE","MPG"]].sort_values(by="RPM", ascending=False).head()

	PLAYER	RPM	SALARY_MILLIONS	AGE	MPG
6	LeBron James	8.42	30.96	32	37.8
37	Chris Paul	7.92	22.87	31	31.5
8	Stephen Curry	7.41	12.11	28	33.4
120	Draymond Green	7.14	15.33	26	32.5
7	Kawhi Leonard	7.08	17.64	25	33.4

# 按照出场时间排名
data.loc[:, ["PLAYER", "RPM","SALARY_MILLIONS", "AGE","MPG"]].sort_values(by="MPG", ascending=False).head()

	PLAYER	RPM	SALARY_MILLIONS	AGE	MPG
6	LeBron James	8.42	30.96	32	37.8
32	Zach LaVine	-2.97	2.24	21	37.2
14	Andrew Wiggins	-1.60	6.01	21	37.2
11	Karl-Anthony Towns	2.13	5.96	21	37.0
12	Jimmy Butler	6.62	17.55	27	37.0

3.3 seaborn常用的三个可视化方法

3.3.1 单变量–distplot()

# 利用seaborn中的distplot绘图来分别看一下球员薪水、效率值、年龄这三个信息的分布情况

#设置seaborn的风格 
sns.set_style("darkgrid")

#设置画板的大小
plt.figure(figsize=(10, 10))

#设置画板的放图位置 hist：条形 kde：线条 

#查看薪水
sns.distplot(data["SALARY_MILLIONS"],hist=True, kde=True,bins=50)
plt.ylabel("salary")

#查看效率值
plt.subplot(3, 1, 2)
sns.distplot(data["RPM"],hist=True, kde=True,bins=50)
plt.ylabel("RPM")

#查看年龄
plt.subplot(3, 1, 3)
sns.distplot(data["AGE"],hist=True, kde=True,bins=20)
plt.ylabel("AGE")

Text(0, 0.5, 'AGE')

3.3.2 双变量–jointplot()

# 利用jointplot()查看年龄和薪水之间的关系

# kind => ked:等高线 hex:六边形   heihgt => 高度
sns.jointplot(data.AGE, data.SALARY_MILLIONS, height=5)
sns.jointplot(data.AGE, data.SALARY_MILLIONS, kind="hex",height=5)
sns.jointplot(data.AGE, data.SALARY_MILLIONS, kind="kde",height=5)

3.3.3 多变量–pairplot()

#将需要对比的数据提取出来
data = data.loc[:, ['RPM','SALARY_MILLIONS','AGE','POINTS']]
# data.head()

#用pairplot() 方法 进行数据对比
sns.pairplot(data)

3.4 多变量衍生

# 定义一个方法 按年龄划分属性
def age_cut(df):
    '年龄划分'
    if df.AGE <= 24:
        return 'young'
    elif df.AGE >=30:
        return 'old'
    else:
        return 'best'

# 使用apply对年龄进行划分
data['age_cut']=data.apply(lambda x:age_cut(x),axis=1)

# 方便计算
data['cut'] = 1

# 基于年龄段对球员薪水和效率值进行分析
sns.set_style("darkgrid")
plt.figure(figsize=(10,10), dpi=100)
plt.title("RPM and Salary")

x1 = data.loc[data.age_cut == "old"].SALARY_MILLIONS
y1 = data.loc[data.age_cut == "old"].RPM
plt.plot(x1, y1,"^")
# plt.plot(x,y_beijing,label = "北京")

x2 = data.loc[data.age_cut == "best"].SALARY_MILLIONS
y2 = data.loc[data.age_cut == "best"].RPM
plt.plot(x2, y2,"*")

x3 = data.loc[data.age_cut == "young"].SALARY_MILLIONS
y3 = data.loc[data.age_cut == "young"].RPM
plt.plot(x3, y3,".")

plt.xlabel("SALARY_MILLIONS",fontsize = 20)
plt.ylabel("RPM",fontsize = 20)

Text(0, 0.5, 'RPM')

---

4.资料网盘

百度云盘：https://pan.baidu.com/s/1puAwMn8QFGiUcrmQtnoiPw ；
提取码：echo