Python可视化分析球员裁判数据(二、单变量分析，缺失值可视化)

最新推荐文章于 2025-08-13 20:42:55 发布

原创最新推荐文章于 2025-08-13 20:42:55 发布 · 924 阅读

1 ·

CC 4.0 BY-SA版权

Python 专栏收录该内容

30 篇文章

订阅专栏

本文通过使用Python的数据处理库如Pandas和可视化库Matplotlib等，对足球运动员数据进行深入分析，包括数据清洗、缺失值处理、相关性分析及位置分布等。

from __future__ import absolute_import,division,print_function
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib.pyplot import GridSpec
import seaborn as sns
import numpy as np
import pandas as pda
import os ,sys
from tqdm import tqdm
import warnings
warnings.filterwarnings("ignore")
sns.set_context("poster",font_scale=1.3)
import missingno as msno
import pandas_profiling
from sklearn.datasets import make_blobs
import time
#读入数据
data=pda.read_csv("redcard.csv.gz",compression="gzip")

print("==================开始分析数据==================================")

def load_subgroup(filename,index_col=[0]):
    return pda.read_csv(filename,compression="gzip",index_col=index_col,encoding="UTF-8")

players=load_subgroup("raw_players.csv.gz")
print(players.head())
print(players.shape)

msno.matrix(players,figsize=(16,7),width_ratios=(15,1))
msno.bar(players.sample(500),color="r")
msno.heatmap(players,figsize=(16,7))#缺失值比例关系
plt.show()

print("样本数量：",len(players))

print("rater1缺失数量：",len(players[pda.isnull(players["rater1"])]))
print("rater2缺失数量：",len(players[pda.isnull(players["rater2"])]))
print("rater1,2都缺失数量：",len(players[pda.isnull(players["rater1"])&pda.isnull(players["rater2"])]))

#费缺失值
print("rater1非缺失数量：",len(players[players.rater1.notnull()]))
players=players[players.rater1.notnull()]
msno.bar(players,color="r")
plt.show()

fig,ax=plt.subplots(figsize=(12,8))
sns.heatmap(pda.crosstab(players.rater1,players.rater2),cmap="Blues",annot=True,fmt="d",ax=ax)
ax.set_title("Correlation between Rater 1 and Rater2\n")
fig.tight_layout()
plt.show()
print("=========================")
print(pda.crosstab(players.rater1,players.rater2))

players["skinone"]=players[["rater1","rater2"]].mean(axis=1)
print(players.head())

sns.distplot(players["skinone"],kde=True)#直方图
sns.distplot(players["skinone"],kde=False)#直方图
plt.show()

#
fig,ax=plt.subplots(figsize=(12,10))
players.position.value_counts(dropna=False,ascending=True).plot(kind="barh",ax=ax)
ax.set_ylabel("Postion")
ax.set_xlabel("Counts")
fig.tight_layout()
plt.show()

position_types=players.position.unique()
print(position_types)

defense=['Center Back', 'Defensive Midfielder','Left Fullback','Right Fullback']
midfield=[ 'Right Midfielder','Center Midfielder','Left Midfielder']
forword=['Attacking Midfielder','Left Winger', 'Right Winger','Center Forward']
keeper=['Goalkeeper']

players.loc[players["position"].isin(defense),"postion_new"]="Defense"
players.loc[players["position"].isin(midfield),"postion_new"]="Midfield"
players.loc[players["position"].isin(forword),"postion_new"]="Forword"
players.loc[players["position"].isin(keeper),"postion_new"]="Keeper"
print(players.head())

fig,ax=plt.subplots(figsize=(12,10))
players.postion_new.value_counts(dropna=False,ascending=True).plot(kind="barh",ax=ax)
ax.set_ylabel("postion_new")
ax.set_xlabel("Counts")
fig.tight_layout()
plt.show()