120年奥运会数据分析：从参赛人数到金牌榜

120年奥运会数据分析：从参赛人数到金牌榜

引用

CSDN

1.

https://blog.csdn.net/weixin_42363541/article/details/135629390

本文将对120年来的奥运会数据集（夏季奥运会）进行简单分析。主要探讨以下几个方面：

1. 奥运会里的男性与女性运动员
2. 奥运会历年来的Top国家
3. 中国的奥运会历史

数据下载

项目的代码和数据可以从以下链接下载：

奥运会数据集下载

项目背景

本项目是对120年来的奥运会数据集（夏季奥运会）的简单分析。主要探讨的是以下三个方面：

1. 奥运会里的男性与女性运动员
2. 奥运会历年来的Top国家
3. 中国的奥运会历史

项目分析

数据说明

该数据集包含两个文件：

• athlete_events.csv：参赛运动员基本生物数据和奖牌结果
• noc_regions.csv：国家奥委会3个字母的代码与对应国家信息

文件athlete_events.csv中包含15个字段，具体信息如下：

文件noc_regions.csv中包含3个字段，具体信息如下：

数据处理

a. 准备数据处理的包

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from plotly.graph_objs import *
import plotly.graph_objs as go
import colorlover as cl
from plotly.offline import init_notebook_mode, iplot

b. 读取前五行数据

f_p = 'athlete_events.csv'
athlete_events = pd.read_csv(f_p)
athlete_events.head()

c. 数据大小

athlete_events.shape

(271116, 15)

d. 数据中各个字段的空值的个数

athlete_events.isnull().sum()

e. 字段信息

athlete_events.info()

f. 数据统计

athlete_events.describe()

词云（通过创建词云展示奥运会的热门运动项目，字体越大代表越热门）

print(' Total of',athlete_events['Sport'].nunique(),'unique sports were played. \n \n Following is the list:\n \n', athlete_events['Sport'].unique())

from wordcloud import WordCloud, STOPWORDS
stopwords = set(STOPWORDS)
def show_wordcloud(data, title = None):
    wordcloud = WordCloud(
        background_color='black',
        stopwords=stopwords,
        max_words=200,
        max_font_size=40, 
        scale=3,
        random_state=1 # chosen at random by flipping a coin; it was heads
).generate(str(data))
    fig = plt.figure(1, figsize=(15, 15))
    plt.axis('off')
    if title: 
        fig.suptitle(title, fontsize=20)
        fig.subplots_adjust(top=2.3)
    plt.imshow(wordcloud)
    plt.show()
show_wordcloud(athlete_events['Sport'])

饼图 查看奥运会男女参赛人数的比例

fig = {
  "data": [
    {
      "values": athlete_events['Sex'].value_counts(),
      "labels": [
        "Male",
        "Female",
      ],
        'marker': {'colors': ['rgb(175, 49, 35)',
                                  'rgb(177, 180, 34)']},
      "name": "Sex Ratio of Participants",
      "hoverinfo":"label+percent+name",
      "hole": .4,
      "type": "pie"
    }],
     "layout": {
        "title":"Sex Ratio of Participants"
     }
}
iplot(fig, filename='donut')

金牌数最多的前20个国家

df_medals=athlete_events.loc[athlete_events['Medal']=='Gold']
cnt_srs = df_medals['Team'].value_counts().head(20)
trace = go.Bar(
    x=cnt_srs.index,
    y=cnt_srs.values,
    marker=dict(
        color="blue",
        #colorscale = 'Blues',
        reversescale = True
    ),
)
layout = go.Layout(
    title='Top 20 countries with Maximum Gold Medals'
)
data = [trace]
fig = go.Figure(data=data, layout=layout)
iplot(fig, filename="medal")  

最受欢迎的运动

cnt_srs = athlete_events['Sport'].value_counts()
trace = go.Bar(
    x=cnt_srs.index,
    y=cnt_srs.values,
    marker=dict(
        color=cnt_srs.values,
        colorscale = 'Picnic',
        reversescale = True
    ),
)
layout = go.Layout(
    title='Most Popular Sport'
)
data = [trace]
fig = go.Figure(data=data, layout=layout)
iplot(fig, filename="sport")

美国最好的10项体育运动

df_usa=athlete_events.loc[(athlete_events['Team']=='United States')]
df_usa_medal=df_usa.loc[df_usa['Medal']=='Gold']
medal_map = {'Gold':1}
df_usa_medal['Medal'] = df_usa_medal['Medal'].map(medal_map)
df_usa_sport=df_usa_medal.groupby(['Sport'],as_index=False)['Medal'].agg('sum')
df_usa_sport=df_usa_sport.sort_values(['Medal'],ascending=False)
df_usa_sport=df_usa_sport.head(10)
colors = ['#91BBF4', '#91F4F4', '#F79981', '#F7E781', '#C0F781','rgb(32,155,160)', 'rgb(253,93,124)', 'rgb(28,119,139)', 'rgb(182,231,235)', 'rgb(35,154,160)']

n_phase = len(df_usa_sport['Sport'])
plot_width = 200
# height of a section and difference between sections 
section_h = 100
section_d = 10
# multiplication factor to calculate the width of other sections
unit_width = plot_width / max(df_usa_sport['Medal'])
# width of each funnel section relative to the plot width
phase_w = [int(value * unit_width) for value in df_usa_sport['Medal']]
height = section_h * n_phase + section_d * (n_phase - 1)
# list containing all the plot shapes
shapes = []
# list containing the Y-axis location for each section's name and value text
label_y = []
for i in range(n_phase):
        if (i == n_phase-1):
                points = [phase_w[i] / 2, height, phase_w[i] / 2, height - section_h]
        else:
                points = [phase_w[i] / 2, height, phase_w[i+1] / 2, height - section_h]
        path = 'M {0} {1} L {2} {3} L -{2} {3} L -{0} {1} Z'.format(*points)
        shape = {
                'type': 'path',
                'path': path,
                'fillcolor': colors[i],
                'line': {
                    'width': 1,
                    'color': colors[i]
                }
        }
        shapes.append(shape)
        
        # Y-axis location for this section's details (text)
        label_y.append(height - (section_h / 2))
        height = height - (section_h + section_d)
        
label_trace = go.Scatter(
    x=[-200]*n_phase,
    y=label_y,
    mode='text',
    text=df_usa_sport['Sport'],
    textfont=dict(
        color='rgb(200,200,200)',
        size=15
    )
)
 
# For phase values
value_trace = go.Scatter(
    x=[-350]*n_phase,
    y=label_y,
    mode='text',
    text=df_usa_sport['Medal'],
    textfont=dict(
        color='rgb(200,200,200)',
        size=12
    )
)
data = [label_trace, value_trace]
 
layout = go.Layout(
    title="<b>Top 10 Sports in which USA is best</b>",
    titlefont=dict(
        size=12,
        color='rgb(203,203,203)'
    ),
    shapes=shapes,
    height=600,
    width=800,
    showlegend=False,
    paper_bgcolor='rgba(44,58,71,1)',
    plot_bgcolor='rgba(44,58,71,1)',
    xaxis=dict(
        showticklabels=False,
        zeroline=False,
    ),
    yaxis=dict(
        showticklabels=False,
        zeroline=False
    )
)
 
fig = go.Figure(data=data, layout=layout)
iplot(fig)