【2020东京奥运会】奥运榜单以及各国参赛运动员数据可视化~

项目

本文中的代码是基于notebook写的,可以访问https://www.heywhale.com/mw/project/61015e73aca24600179ec778获取完整notebook.

奖牌榜数据

通过咪咕视频的接口获取奖牌榜单的数据，貌似也没做什么反爬虫，直接就可以获取到数据：

import requests 

rank_url = 'https://app-sc.miguvideo.com/vms-livedata/olympic-medal/total-table/15/110000004609'
data = requests.get(rank_url).json()

数据处理，将json数据转化为dataframe：

df = pd.DataFrame()

for item in data['body']['allMedalData']:
    df = df.append([[
        item['rank'],
        item['countryName'],
        item['goldMedalNum'],
        item['silverMedalNum'],
        item['bronzeMedalNum'],
        item['totalMedalNum']]])
df.columns = ['排名', '国家', '金牌', '银牌', '铜牌', '奖牌']
df = df.reset_index(drop=True)

使用plotly展示榜单前30个国家：

import plotly.graph_objects as go
from plotly.colors import n_colors
import numpy as np
np.random.seed(1)

colors = n_colors('rgb(225,255,255)', 'rgb(255,192,203)', 10, colortype='rgb')
fig = go.Figure(
    data=[go.Table(
        columnwidth=[20, 80, 80, 80, 80],
        header=dict(values=["<span style='font-size:16px;color:#fff;font-weight:bold';>{}</span><br>".format(c) for c in df.columns],
                    line_color='darkslategray',
                    fill_color='rgb(255,0,0)',
                    align=['center'],
                    # font=dict(color='white', size=13),
                    height=40),
        cells=dict(values=df.head(30).T,
                   line_color='darkslategray',
                   fill=dict(color=[colors, 'white']),
                   align=['center'],
                   font_size=13,
                   height=30))
          ])
fig.update_layout(
    height=1200,
    title_text="<span style='font-size:20px;color:#0000FF;font-weight:bolder';>2020东京奥运会奖牌榜</span><br><span style='font-size:12px;color:#C0C0C0';>更新时间：{}</span>".format(update_time),
)
fig.show()

运动员数据

• 2020年东京奥运会全部参赛人员名单数据来自奥委会官网（https://olympics.com/tokyo-2020/olympic-games/zh/results/all-sports/athletes.htm）；
• 整体数据来看，总共206个国家或地区的代表团共11309名选手参赛，比2016年里约奥运会的11180人多出129人，为史上参赛人数最多的一届奥运会；

获取国家简称和项目的中文名称对应表：

# 获取国家简称对应的中文名称
noc = 'https://olympics.com/tokyo-2020/olympic-games/zh/results/all-sports/nocs-list.htm'

r = requests.get(noc)
para = r'</li>.*?country="(?P<简称>.*?)">.*?<div class="mx-auto font-weight-bold">(?P<中文名称>.*?)</div>'

patterns = re.compile(para)

noc_dict = {}
for k, v in patterns.findall(r.text):
    noc_dict[k] = v

# 获取项目简称对应的中文代码
sports = 'https://olympics.com/tokyo-2020/zh/sports/'
r = requests.get(sports)
para = r'<div class="tk-disciplines__picto tk-picto-(.*?)"></div>\s+.*?title">\s+(.*?)\s+'

patterns = re.compile(para)
sports_dict = {}
for k, v in patterns.findall(r.text):
    sports_dict[k.upper()] = v

获取运动员数据

athlete_url = 'https://olympics.com/tokyo-2020/olympic-games/zh/results/all-sports/zzje001a.json'
data = requests.get(athlete_url).json()

athletes_df = pd.DataFrame(columns=['姓名', '国家', '项目'])
for item in data['data']:
    athletes_df = athletes_df.append(
        [{'姓名': item['name'], '国家':noc_dict[item['noc']], '项目':sports_dict[item['dis']]}])

athletes_df = athletes_df.reset_index(drop=True)

按国家维度聚合统计：

df_t = athletes_df.groupby(['国家', '项目'])['姓名'].count().reset_index()
df_t.columns = ['国家', '项目', '人数']

data = []
country = []
for idx, row in df_t.iterrows():
    if row['国家'] in country:
        data[-1]['children'].append(dict(name=row['项目'], value=row['人数']))
    else:
        data.append(dict(name=row['国家'], children=[dict(name=row['项目'], value=row['人数'])]))
    country.append(row['国家'])

tree = TreeMap(    
    init_opts=opts.InitOpts(
        theme='light',
        width='1000px',
        height='600px',
        # bg_color='rgb(0,0,0)'
        ))
tree.add(
    "参赛人数", 
    data,
    leaf_depth=1,
    label_opts=opts.LabelOpts(position="inside", formatter='{b}：{c}名'),
    levels=[
            opts.TreeMapLevelsOpts(
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color="#555", border_width=4, gap_width=4
                )
            ),
            opts.TreeMapLevelsOpts(
                color_saturation=[0.3, 0.6],
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color_saturation=0.7, gap_width=2, border_width=2
                ),
            ),
            opts.TreeMapLevelsOpts(
                color_saturation=[0.3, 0.5],
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color_saturation=0.6, gap_width=1
                ),
            ),
            # opts.TreeMapLevelsOpts(color_saturation=[0.3, 0.5]),
        ],
    )
tree.set_global_opts(
    title_opts=opts.TitleOpts(title="2020东京奥运会参赛人数统计（国家/地区）", pos_left='center', title_textstyle_opts=opts.TextStyleOpts(color='#00BFFF', font_size=20)),
    legend_opts=opts.LegendOpts(is_show=False)
    )

tree.render_notebook()

**按运动项目聚合统计： **

df_t = athletes_df.groupby(['项目', '国家'])['姓名'].count().reset_index()
df_t.columns = ['项目', '国家', '人数']

data = []
event = []
for idx, row in df_t.iterrows():
    if row['项目'] in event:
        data[-1]['children'].append(dict(name=row['国家'], value=row['人数']))
    else:
        data.append(dict(name=row['项目'], children=[dict(name=row['国家'], value=row['人数'])]))
    event.append(row['项目'])

tree = TreeMap(    
    init_opts=opts.InitOpts(
        theme='light',
        width='1000px',
        height='600px',
        # bg_color='rgb(0,0,0)'
        ))
tree.add(
    "参赛人数", 
    data,
    leaf_depth=1,
    label_opts=opts.LabelOpts(position="inside", formatter='{b}：{c}名'),
    levels=[
            opts.TreeMapLevelsOpts(
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color="#555", border_width=4, gap_width=4
                )
            ),
            opts.TreeMapLevelsOpts(
                color_saturation=[0.3, 0.6],
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color_saturation=0.7, gap_width=2, border_width=2
                ),
            ),
            opts.TreeMapLevelsOpts(
                color_saturation=[0.3, 0.5],
                treemap_itemstyle_opts=opts.TreeMapItemStyleOpts(
                    border_color_saturation=0.6, gap_width=1
                ),
            ),
            # opts.TreeMapLevelsOpts(color_saturation=[0.3, 0.5]),
        ],
    )
tree.set_global_opts(
    title_opts=opts.TitleOpts(
        title="2020东京奥运会参赛人数统计（项目）", 
        pos_left='center', 
        title_textstyle_opts=opts.TextStyleOpts(color='#00BFFF', font_size=20)
        ),
    legend_opts=opts.LegendOpts(
        is_show=False
        )
    )

tree.render_notebook()

** 主要国家各项目参数人数对比**

pie = Pie(
    init_opts=opts.InitOpts(
        theme='light',
        width='1000px',
        height='800px',
    )
)
titles = [dict(
            text='2020东京奥运会各国主要项目参赛运动员比例',
            left='center',
            top='0%',
            textStyle=dict(
                color='#000',
                fontSize=20)
                )
                ]
for i, c in enumerate(country_list):
    d = df_t[df_t['国家'] == c].reset_index()
    data_pair = []
    else_num = 0
    for idx, row in d.iterrows():
        if idx < 5:
            data_pair.append(
                opts.PieItem(
                    name=row['项目'],
                    value=row['人数'],
                    label_opts=opts.LabelOpts(
                        is_show=True, formatter='{b}:{d}%')
                )
            )
        else:
            else_num += row['人数']
    data_pair.append(
        opts.PieItem(
            name='其他',
            value=else_num,
            label_opts=opts.LabelOpts(
                is_show=True, formatter='{b}:{d}%')
        )
    )

    pos_x = '{}%'.format(int(i / 4) * 33 + 16)
    pos_y = '{}%'.format(i % 4 * 24 + 15)

    titles.append(
        dict(
            text=c+' ',
            left=pos_x,
            top=pos_y,
            textAlign='center',
            textVerticalAlign='middle',
            textStyle=dict(
                color='#00BFFF',
                fontSize=12)
                )
    )

    pie.add(
        c,
        data_pair,
        center=[pos_x, pos_y],
        radius=['8%', '12%']
    )

pie.set_global_opts(
    legend_opts=opts.LegendOpts(is_show=False),
    title_opts=titles
)
pie.render_notebook()