Python数据分析-FIFA2018球员数据分析

#!/usr/bin/env python
# coding: utf-8

# TI=FIFA2018球员数据分析
# 明确分析目的
# 	运动员数量前十名的国家，以及平均身价
# 	各大联赛运动员数量，以及球员平均身价
# 	各俱乐部的平均周薪
# 	英超联赛English Premier League各个俱乐部球员的平均周薪
# 	球员年龄分布情况，不同年龄段平均身价分布

# 引入使用的库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# 加载数据文件
df = pd.read_csv('./FIFA_2018_player.csv')

# 查看数据具有哪些列，什么类型
df.info()
# 可见共17994行，league和club有缺失值

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 17994 entries, 0 to 17993
Data columns (total 12 columns):
ID             17994 non-null int64
name           17994 non-null object
full_name      17994 non-null object
nationality    17994 non-null object
league         17741 non-null object
club           17741 non-null object
age            17994 non-null int64
birth_date     17994 non-null object
height_cm      17994 non-null float64
weight_kg      17994 non-null float64
eur_value      17994 non-null float64
eur_wage       17994 non-null float64
dtypes: float64(4), int64(2), object(6)
memory usage: 1.6+ MB

df.head()

	ID	name	full_name	nationality	league	club	age	birth_date	height_cm	weight_kg	eur_value	eur_wage
0	20801	Cristiano Ronaldo	C. Ronaldo dos Santos Aveiro	Portugal	Spanish Primera División	Real Madrid CF	32	1985-02-05	185.0	80.0	95500000.0	565000.0
1	158023	L. Messi	Lionel Messi	Argentina	Spanish Primera División	FC Barcelona	30	1987-06-24	170.0	72.0	105000000.0	565000.0
2	190871	Neymar	Neymar da Silva Santos Jr.	Brazil	French Ligue 1	Paris Saint-Germain	25	1992-02-05	175.0	68.0	123000000.0	280000.0
3	176580	L. Suárez	Luis Suárez	Uruguay	Spanish Primera División	FC Barcelona	30	1987-01-24	182.0	86.0	97000000.0	510000.0
4	167495	M. Neuer	Manuel Neuer	Germany	German Bundesliga	FC Bayern Munich	31	1986-03-27	193.0	92.0	61000000.0	230000.0

df.describe()

	ID	age	height_cm	weight_kg	eur_value	eur_wage
count	17994.000000	17994.000000	17994.000000	17994.000000	1.799400e+04	17994.000000
mean	207791.796543	25.120151	181.271980	75.400856	2.370511e+06	11503.834612
std	32328.527723	4.617428	6.690392	6.994824	5.347250e+06	23050.661073
min	16.000000	16.000000	155.000000	49.000000	0.000000e+00	0.000000
25%	192621.250000	21.000000	177.000000	70.000000	3.000000e+05	2000.000000
50%	214186.000000	25.000000	181.000000	75.000000	7.000000e+05	4000.000000
75%	231615.750000	28.000000	186.000000	80.000000	2.000000e+06	12000.000000
max	241489.000000	47.000000	205.000000	110.000000	1.230000e+08	565000.000000

df.count()
# 可见league 和 club有缺失值

ID             17994
name           17994
full_name      17994
nationality    17994
league         17741
club           17741
age            17994
birth_date     17994
height_cm      17994
weight_kg      17994
eur_value      17994
eur_wage       17994
dtype: int64

# 对于本次的分析目的，其实在加载数据时就可以只加载部分列
# 选出部分列 ID nationality league club age eur_value eur_wage
# 分析的是FIFA2018的数据，age按当年数据计算，birth_date省略
df = df[['ID', 'nationality', 'league', 'club', 'age', 'eur_value', 'eur_wage']]
df

	ID	nationality	league	club	age	eur_value	eur_wage
0	20801	Portugal	Spanish Primera División	Real Madrid CF	32	95500000.0	565000.0
1	158023	Argentina	Spanish Primera División	FC Barcelona	30	105000000.0	565000.0
2	190871	Brazil	French Ligue 1	Paris Saint-Germain	25	123000000.0	280000.0
3	176580	Uruguay	Spanish Primera División	FC Barcelona	30	97000000.0	510000.0
4	167495	Germany	German Bundesliga	FC Bayern Munich	31	61000000.0	230000.0
...	...	...	...	...	...	...	...
17989	237463	England	English League One	Scunthorpe United	17	50000.0	1000.0
17990	11728	England	English League Two	Wycombe Wanderers	47	0.0	1000.0
17991	231381	Scotland	English League Two	Swindon Town	17	60000.0	1000.0
17992	238813	England	English League Two	Crewe Alexandra	18	60000.0	1000.0
17993	238308	Ghana	English League One	Scunthorpe United	18	50000.0	1000.0

17994 rows × 7 columns

<