python数据分析

#python数据分析| 来源: 网络整理| 查看: 265

import pandas as pd import numpy as np import seaborn as sns import itertools import io import base64 import os import folium import folium.plugins import matplotlib.pyplot as plt from matplotlib import rc,animation from mpl_toolkits.mplot3d import Axes3D from wordcloud import WordCloud,STOPWORDS 读取数据 matches = pd.read_csv('./WorldCupMatches.csv') players = pd.read_csv('./WorldCupPlayers.csv') cups = pd.read_csv('./WorldCups.csv') 看一下数据前三行 matches.head(3) Year Datetime Stage Stadium City Home Team Name Home Team Goals Away Team Goals Away Team Name Win conditions Attendance Half-time Home Goals Half-time Away Goals Referee Assistant 1 Assistant 2 RoundID MatchID Home Team Initials Away Team Initials 0 1930.0 13 Jul 1930 - 15:00 Group 1 Pocitos Montevideo France 4.0 1.0 Mexico 4444.0 3.0 0.0 LOMBARDI Domingo (URU) CRISTOPHE Henry (BEL) REGO Gilberto (BRA) 201.0 1096.0 FRA MEX 1 1930.0 13 Jul 1930 - 15:00 Group 4 Parque Central Montevideo USA 3.0 0.0 Belgium 18346.0 2.0 0.0 MACIAS Jose (ARG) MATEUCCI Francisco (URU) WARNKEN Alberto (CHI) 201.0 1090.0 USA BEL 2 1930.0 14 Jul 1930 - 12:45 Group 2 Parque Central Montevideo Yugoslavia 2.0 1.0 Brazil 24059.0 2.0 0.0 TEJADA Anibal (URU) VALLARINO Ricardo (URU) BALWAY Thomas (FRA) 201.0 1093.0 YUG BRA players.head(3) RoundID MatchID Team Initials Coach Name Line-up Shirt Number Player Name Position Event 0 201 1096 FRA CAUDRON Raoul (FRA) S 0 Alex THEPOT GK NaN 1 201 1096 MEX LUQUE Juan (MEX) S 0 Oscar BONFIGLIO GK NaN 2 201 1096 FRA CAUDRON Raoul (FRA) S 0 Marcel LANGILLER NaN G40' cups.head(3) Year Country Winner Runners-Up Third Fourth GoalsScored QualifiedTeams MatchesPlayed Attendance 0 1930 Uruguay Uruguay Argentina USA Yugoslavia 70 13 18 590.549 1 1934 Italy Italy Czechoslovakia Germany Austria 70 16 17 363.000 2 1938 France Italy Hungary Brazil Sweden 84 15 18 375.700 统计历届世界杯的观众总数

先去掉世界杯比赛中Attendance字段的重复数据，根据Year字段对其进行累加，再使用Seaborn和Matplotlib可视化

matches.isnull().sum() sns.set_style("darkgrid") matches = matches.drop_duplicates(subset="MatchID",keep="first") matches = matches[matches["Year"].notnull()] att = matches.groupby("Year")["Attendance"].sum().reset_index() att["Year"] = att["Year"].astype(int) plt.figure(figsize=(12,7)) sns.barplot(att["Year"],att["Attendance"],linewidth=1,edgecolor="k"*len(att)) plt.grid(True) plt.title("Attendence by year",color='b') plt.show()

在这里插入图片描述考虑到赛制改变等因素，历届世界杯的比赛场次数量存在一定的差异，进一步计算每届世界杯观众数的平均值，进一步分析历届世界杯的影响力

att1 = matches.groupby("Year")["Attendance"].mean().reset_index() att1["Year"] = att1["Year"].astype(int) plt.figure(figsize=(12,7)) ax = sns.pointplot(att1["Year"],att1["Attendance"],color="w") ax.set_facecolor("k") plt.grid(True,color="grey",alpha=.3) plt.title("Average attendence by year",color='b') plt.show()

在这里插入图片描述总体呈上升趋势，1994年最高，2006-2014年总人数稳定在较高水平接下来，计算各个比赛城市的平均观众人数，并用可视化的形式展示平均值最高的20个城市。

ct_at = matches.groupby("City")["Attendance"].mean().reset_index() ct_at = ct_at.sort_values(by="Attendance",ascending=False) plt.figure(figsize=(10,10)) ax = sns.barplot("Attendance","City", data=ct_at[:20], linewidth = 1, edgecolor = "k"*20, palette = "Spectral_r") for i,j in enumerate(" Average attendance : "+np.around(ct_at["Attendance"][:20],0).astype(str)):ax.text(.7,i,j,fontsize=12) plt.grid(True) plt.title("Average attendance by city",color='b') plt.show()

在这里插入图片描述

一个城市可能有多个场馆，各个场馆的观众数可能也不相同：计算各个场馆的平均观众人数，并取观众数最多的14个场馆进行可视化，与上面的结果略有出入。

matches["Year"] = matches["Year"].astype(int)#学习这种转化数据类型的方式，机器学习会用到 matches["Datetime"] = matches["Datetime"].str.split("-").str[0] matches["Stadium"] = matches["Stadium"].str.replace('Estadio do Maracana',"Maracanã Stadium") matches["Stadium"] = matches["Stadium"].str.replace('Maracan� - Est�dio Jornalista M�rio Filho',"Maracanã Stadium") std = matches.groupby(["Stadium","City"])["Attendance"].mean().reset_index().sort_values(by = "Attendance",ascending =False) plt.figure(figsize=(8,9

【本文地址】

python数据分析

python数据分析

今日新闻

推荐新闻