專案全部程式碼 & 資料集都可以訪問我的KLab --【Pyecharts】奧運會資料集視覺化分析～獲取，點選Fork即可～
-
受疫情影響，2020東京奧運會將延期至2021年舉行；
-
雖然延期，但此次奧運會依舊會沿用「2020東京奧運會」這個名稱；
-
這也將是奧運會歷史上首次延期（1916年、1940年、1944年曾因一戰，二戰停辦）；
既然奧運會延期了，那我們就來回顧下整個奧運會的歷史吧??～
本專案將會從以下角度來呈現奧運會歷史：
-
?各國累計獎牌數；
-
⚽️各項運動產生金牌數
-
⛳️運動員層面
-
參賽人數趨勢
-
女性參賽比例趨勢
-
獲得金牌最多的運動員
-
獲得獎牌/金牌比例
-
各專案運動員平均體質資料
-
-
主要國家表現
-
??中國表現
-
??美國表現
-
-
?被單個國家統治的奧運會專案
匯入庫 & 資料
import pandas as pd
import numpy as np
import pyecharts
from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
athlete_data = pd.read_csv('/home/kesci/input/olympic/athlete_events.csv')
noc_region = pd.read_csv('/home/kesci/input/olympic/noc_regions.csv')
# 關聯代表國家
data = pd.merge(athlete_data, noc_region, on='NOC', how='left')
data.head()
累計獎牌數
夏季奧運會 & 冬季奧運會分別統計
-
?️夏季奧運會開始於1896年雅典奧運會；
-
❄️冬季奧運會開始於1924年慕尼黑冬奧會；
medal_data = data.groupby(['Year', 'Season', 'region',
'Medal'])['Event'].nunique().reset_index()
medal_data.columns = ['Year', 'Season', 'region', 'Medal', 'Nums']
medal_data = medal_data.sort_values(by="Year" , ascending=True)
medal_data = data.groupby(['Year', 'Season', 'region',
'Medal'])['Event'].nunique().reset_index()
medal_data.columns = ['Year', 'Season', 'region', 'Medal', 'Nums']
medal_data = medal_data.sort_values(by="Year" , ascending=True)
各國夏奧會累計獎牌數
-
截止2016年夏季奧運會，美俄分別獲得了2544和1577枚獎牌，位列一二位；
-
中國由於參加奧運會時間較晚，截止2016年累計獲得了545枚獎牌，位列第七位；
year_list = sorted(list(set(medal_data['Year'].to_list())), reverse=True)
tl = Timeline(init_opts=opts.InitOpts(theme='dark', width='1000px', height='1000px'))
tl.add_schema(is_timeline_show=True,is_rewind_play=True, is_inverse=False,
label_opts=opts.LabelOpts(is_show=False))
for year in year_list:
t_data = medal_stat(year)[::-1]
bar = (
Bar(init_opts=opts.InitOpts())
.add_xaxis([x[0] for x in t_data])
.add_yaxis("銅牌?", [x[3] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(218,165,32)'))
.add_yaxis("銀牌?", [x[2] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(192,192,192)'))
.add_yaxis("金牌?️", [x[1] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(255,215,0)'))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='insideRight',
font_style='italic'),)
.set_global_opts(
title_opts=opts.TitleOpts(title="各國累計獎牌數（夏季奧運會）"),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=True),
graphic_opts=[opts.GraphicGroup(graphic_item=opts.GraphicItem(
rotation=JsCode("Math.PI / 4"),
bounding="raw",
right=110,
bottom=110,
z=100),
children=[
opts.GraphicRect(
graphic_item=opts.GraphicItem(
left="center", top="center", z=100
),
graphic_shape_opts=opts.GraphicShapeOpts(
width=400, height=50
),
graphic_basicstyle_opts=opts.GraphicBasicStyleOpts(
fill="rgba(0,0,0,0.3)"
),
),
opts.GraphicText(
graphic_item=opts.GraphicItem(
left="center", top="center", z=100
),
graphic_textstyle_opts=opts.GraphicTextStyleOpts(
text=year,
font="bold 26px Microsoft YaHei",
graphic_basicstyle_opts=opts.GraphicBasicStyleOpts(
fill="#fff"
),
),
),
],
)
],)
.reversal_axis())
tl.add(bar, year)
tl.render_notebook()
各國冬奧會累計獎牌數
year_list = sorted(list(set(medal_data['Year'][medal_data.Season=='Winter'].to_list())), reverse=True)
tl = Timeline(init_opts=opts.InitOpts(theme='dark', width='1000px', height='1000px'))
tl.add_schema(is_timeline_show=True,is_rewind_play=True, is_inverse=False,
label_opts=opts.LabelOpts(is_show=False))
for year in year_list:
t_data = medal_stat(year, 'Winter')[::-1]
bar = (
Bar(init_opts=opts.InitOpts(theme='dark'))
.add_xaxis([x[0] for x in t_data])
.add_yaxis("銅牌?", [x[3] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(218,165,32)'))
.add_yaxis("銀牌?", [x[2] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(192,192,192)'))
.add_yaxis("金牌?️", [x[1] for x in t_data],
stack='stack1',
itemstyle_opts=opts.ItemStyleOpts(border_color='rgb(220,220,220)',color='rgb(255,215,0)'))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='insideRight',
font_style='italic'),)
.set_global_opts(
title_opts=opts.TitleOpts(title="各國累計獎牌數（冬季奧運會）"),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=True),
graphic_opts=[opts.GraphicGroup(graphic_item=opts.GraphicItem(
rotation=JsCode("Math.PI / 4"),
bounding="raw",
right=110,
bottom=110,
z=100),
children=[
opts.GraphicRect(
graphic_item=opts.GraphicItem(
left="center", top="center", z=100
),
graphic_shape_opts=opts.GraphicShapeOpts(
width=400, height=50
),
graphic_basicstyle_opts=opts.GraphicBasicStyleOpts(
fill="rgba(0,0,0,0.3)"
),
),
opts.GraphicText(
graphic_item=opts.GraphicItem(
left="center", top="center", z=100
),
graphic_textstyle_opts=opts.GraphicTextStyleOpts(
text='截止{}'.format(year),
font="bold 26px Microsoft YaHei",
graphic_basicstyle_opts=opts.GraphicBasicStyleOpts(
fill="#fff"
),
),
),
],
)
],)
.reversal_axis())
tl.add(bar, year)
tl.render_notebook()
各項運動產生金牌數
基於2016年夏奧會和2014年冬奧會統計；
- ?田徑 & 游泳是大項，在2016年夏奧會上分別產生了47和34枚金牌；
background_color_js = """new echarts.graphic.RadialGradient(0.5, 0.5, 1, [{
offset: 0,
color: '#696969'
}, {
offset: 1,
color: '#000000'
}])"""
tab = Tab()
temp = data[(data['Medal']=='Gold') & (data['Year']==2016) & (data['Season']=='Summer')]
event_medal = temp.groupby(['Sport'])['Event'].nunique().reset_index()
event_medal.columns = ['Sport', 'Nums']
event_medal = event_medal.sort_values(by="Nums" , ascending=False)
pie = (Pie(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='800px'))
.add('金牌?️', [(row['Sport'], row['Nums']) for _, row in event_medal.iterrows()],
radius=["30%", "75%"],
rosetype="radius")
.set_global_opts(title_opts=opts.TitleOpts(title="2016年夏季奧運會各項運動產生金牌佔比",
pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20), ),
legend_opts=opts.LegendOpts(is_show=False))
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {d}%"),
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),)
)
tab.add(pie, '2016年夏奧會')
temp = data[(data['Medal']=='Gold') & (data['Year']==2014) & (data['Season']=='Winter')]
event_medal = temp.groupby(['Sport'])['Event'].nunique().reset_index()
event_medal.columns = ['Sport', 'Nums']
event_medal = event_medal.sort_values(by="Nums" , ascending=False)
pie = (Pie(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='800px'))
.add('金牌?️', [(row['Sport'], row['Nums']) for _, row in event_medal.iterrows()],
radius=["30%", "75%"],
rosetype="radius")
.set_global_opts(title_opts=opts.TitleOpts(title="2014年冬季奧運會各項運動產生金牌佔比",
pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20), ),
legend_opts=opts.LegendOpts(is_show=False))
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {d}%"),
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"
),)
)
tab.add(pie, '2014年冬奧會')
tab.render_notebook()
運動員層面
歷年參賽人數趨勢
-
從人數來看，每屆夏奧會參賽人數都是冬奧會的4-5倍；
-
整體參賽人數是上漲趨勢，但由於歷史原因也出現過波動，如1980年莫斯科奧運會層遭遇65個國家抵制；
athlete = data.groupby(['Year', 'Season'])['Name'].nunique().reset_index()
athlete.columns = ['Year', 'Season', 'Nums']
athlete = athlete.sort_values(by="Year" , ascending=True)
x_list, y1_list, y2_list = [], [], []
for _, row in athlete.iterrows():
x_list.append(str(row['Year']))
if row['Season'] == 'Summer':
y1_list.append(row['Nums'])
y2_list.append(None)
else:
y2_list.append(row['Nums'])
y1_list.append(None)
background_color_js = (
"new echarts.graphic.LinearGradient(1, 1, 0, 0, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
line = (
Line(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='600px'))
.add_xaxis(x_list)
.add_yaxis("夏季奧運會",
y1_list,
is_smooth=True,
is_connect_nones=True,
symbol="circle",
symbol_size=6,
linestyle_opts=opts.LineStyleOpts(color="#fff"),
label_opts=opts.LabelOpts(is_show=False, position="top", color="white"),
itemstyle_opts=opts.ItemStyleOpts(
color="green", border_color="#fff", border_width=3),
tooltip_opts=opts.TooltipOpts(is_show=True))
.add_yaxis("冬季季奧運會",
y2_list,
is_smooth=True,
is_connect_nones=True,
symbol="circle",
symbol_size=6,
linestyle_opts=opts.LineStyleOpts(color="#FF4500"),
label_opts=opts.LabelOpts(is_show=False, position="top", color="white"),
itemstyle_opts=opts.ItemStyleOpts(
color="red", border_color="#fff", border_width=3),
tooltip_opts=opts.TooltipOpts(is_show=True))
.set_series_opts(
markarea_opts=opts.MarkAreaOpts(
label_opts=opts.LabelOpts(is_show=True, position="bottom", color="white"),
data=[
opts.MarkAreaItem(name="第一次世界大戰", x=(1914, 1918)),
opts.MarkAreaItem(name="第二次世界大戰", x=(1939, 1945)),
]
)
)
.set_global_opts(title_opts=opts.TitleOpts(title="歷屆奧運會參賽人數",
pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20),),
legend_opts=opts.LegendOpts(is_show=True, pos_top='5%',
textstyle_opts=opts.TextStyleOpts(color="white", font_size=12)),
xaxis_opts=opts.AxisOpts(type_="value",
min_=1904,
max_=2016,
boundary_gap=False,
axislabel_opts=opts.LabelOpts(margin=30, color="#ffffff63",
formatter=JsCode("""function (value)
{return value+'年';}""")),
axisline_opts=opts.AxisLineOpts(is_show=False),
axistick_opts=opts.AxisTickOpts(
is_show=True,
length=25,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f"),
),
splitline_opts=opts.SplitLineOpts(
is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
),
),
yaxis_opts=opts.AxisOpts(
type_="value",
position="right",
axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63"),
axisline_opts=opts.AxisLineOpts(
linestyle_opts=opts.LineStyleOpts(width=2, color="#fff")
),
axistick_opts=opts.AxisTickOpts(
is_show=True,
length=15,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f"),
),
splitline_opts=opts.SplitLineOpts(
is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
),
),)
)
line.render_notebook()
歷年女性運動員佔比趨勢
一開始奧運會基本是「男人的運動」，女性運動員僅為個位數，到近幾屆奧運會男女參賽人數基本趨於相等；
# 歷年男性運動員人數
m_data = data[data.Sex=='M'].groupby(['Year', 'Season'])['Name'].nunique().reset_index()
m_data.columns = ['Year', 'Season', 'M-Nums']
m_data = m_data.sort_values(by="Year" , ascending=True)
# 歷年女性運動員人數
f_data = data[data.Sex=='F'].groupby(['Year', 'Season'])['Name'].nunique().reset_index()
f_data.columns = ['Year', 'Season', 'F-Nums']
f_data = f_data.sort_values(by="Year" , ascending=True)
t_data = pd.merge(m_data, f_data, on=['Year', 'Season'])
t_data['F-rate'] = round(t_data['F-Nums'] / (t_data['F-Nums'] + t_data['M-Nums'] ), 4)
x_list, y1_list, y2_list = [], [], []
for _, row in t_data.iterrows():
x_list.append(str(row['Year']))
if row['Season'] == 'Summer':
y1_list.append(row['F-rate'])
y2_list.append(None)
else:
y2_list.append(row['F-rate'])
y1_list.append(None)
background_color_js = (
"new echarts.graphic.LinearGradient(0, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
line = (
Line(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='600px'))
.add_xaxis(x_list)
.add_yaxis("夏季奧運會",
y1_list,
is_smooth=True,
is_connect_nones=True,
symbol="circle",
symbol_size=6,
linestyle_opts=opts.LineStyleOpts(color="#fff"),
label_opts=opts.LabelOpts(is_show=False, position="top", color="white"),
itemstyle_opts=opts.ItemStyleOpts(color="green", border_color="#fff", border_width=3),
tooltip_opts=opts.TooltipOpts(is_show=True),)
.add_yaxis("冬季季奧運會",
y2_list,
is_smooth=True,
is_connect_nones=True,
symbol="circle",
symbol_size=6,
linestyle_opts=opts.LineStyleOpts(color="#FF4500"),
label_opts=opts.LabelOpts(is_show=False, position="top", color="white"),
itemstyle_opts=opts.ItemStyleOpts(color="red", border_color="#fff", border_width=3),
tooltip_opts=opts.TooltipOpts(is_show=True),)
.set_series_opts(tooltip_opts=opts.TooltipOpts(trigger="item", formatter=JsCode("""function (params)
{return params.data[0]+ '年: ' + Number(params.data[1])*100 +'%';}""")),)
.set_global_opts(title_opts=opts.TitleOpts(title="歷屆奧運會參賽女性佔比趨勢",
pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20),),
legend_opts=opts.LegendOpts(is_show=True, pos_top='5%',
textstyle_opts=opts.TextStyleOpts(color="white", font_size=12)),
xaxis_opts=opts.AxisOpts(type_="value",
min_=1904,
max_=2016,
boundary_gap=False,
axislabel_opts=opts.LabelOpts(margin=30, color="#ffffff63",
formatter=JsCode("""function (value)
{return value+'年';}""")),
axisline_opts=opts.AxisLineOpts(is_show=False),
axistick_opts=opts.AxisTickOpts(
is_show=True,
length=25,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f"),
),
splitline_opts=opts.SplitLineOpts(
is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
),
),
yaxis_opts=opts.AxisOpts(
type_="value",
position="right",
axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63",
formatter=JsCode("""function (value)
{return Number(value *100)+'%';}""")),
axisline_opts=opts.AxisLineOpts(
linestyle_opts=opts.LineStyleOpts(width=2, color="#fff")
),
axistick_opts=opts.AxisTickOpts(
is_show=True,
length=15,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f"),
),
splitline_opts=opts.SplitLineOpts(
is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
),
),)
)
line.render_notebook()
獲得金牌最多的運動員
-
排在第一的是美國泳壇名將「菲爾普斯」，截止2016年奧運會總共獲得了23枚金牌；
-
博爾特累計獲得8枚奧運會金牌；
temp = data[(data['Medal']=='Gold')]
athlete = temp.groupby(['Name'])['Medal'].count().reset_index()
athlete.columns = ['Name', 'Nums']
athlete = athlete.sort_values(by="Nums" , ascending=True)
background_color_js = (
"new echarts.graphic.LinearGradient(0, 0, 1, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
pb = (
PictorialBar(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='800px'))
.add_xaxis([x.replace(' ','\n') for x in athlete['Name'].tail(10).tolist()])
.add_yaxis(
"",
athlete['Nums'].tail(10).tolist(),
label_opts=opts.LabelOpts(is_show=False),
symbol_size=25,
symbol_repeat='fixed',
symbol_offset=[0, 0],
is_symbol_clip=True,
symbol='image://https://cdn.kesci.com/upload/image/q8f8otrlfc.png')
.reversal_axis()
.set_global_opts(
title_opts=opts.TitleOpts(title="獲得金牌數量最多的運動員", pos_left='center',
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20),),
xaxis_opts=opts.AxisOpts(is_show=False,),
yaxis_opts=opts.AxisOpts(
axistick_opts=opts.AxisTickOpts(is_show=False),
axisline_opts=opts.AxisLineOpts(
linestyle_opts=opts.LineStyleOpts(opacity=0)
),
),
))
pb.render_notebook()
獲得金牌/獎牌比例
看菲爾普斯拿金牌拿到手軟，但實際上想獲得一塊金牌的難度高嗎？
-
整個奧運會（包括夏季，冬季奧運會）歷史上參賽人數為134732，獲得過金牌的運動員只有10413，佔比7.7%;
-
獲得過獎牌（包括金銀銅）的運動員有28202人，佔比20.93%；
total_athlete = len(set(data['Name']))
medal_athlete = len(set(data['Name'][data['Medal'].isin(['Gold', 'Silver', 'Bronze'])]))
gold_athlete = len(set(data['Name'][data['Medal']=='Gold']))
l1 = Liquid(init_opts=opts.InitOpts(theme='dark', width='1000px', height='800px'))
l1.add("獲得獎牌", [medal_athlete/total_athlete],
center=["70%", "50%"],
label_opts=opts.LabelOpts(font_size=50,
formatter=JsCode(
"""function (param) {
return (Math.floor(param.value * 10000) / 100) + '%';
}"""),
position="inside",
))
l1.set_global_opts(title_opts=opts.TitleOpts(title="獲得過獎牌比例", pos_left='62%', pos_top='8%'))
l1.set_series_opts(tooltip_opts=opts.TooltipOpts(is_show=False))
l2 = Liquid(init_opts=opts.InitOpts(theme='dark', width='1000px', height='800px'))
l2.add("獲得金牌",
[gold_athlete/total_athlete],
center=["25%", "50%"],
label_opts=opts.LabelOpts(font_size=50,
formatter=JsCode(
"""function (param) {
return (Math.floor(param.value * 10000) / 100) + '%';
}"""),
position="inside",
),)
l2.set_global_opts(title_opts=opts.TitleOpts(title="獲得過金牌比例", pos_left='17%', pos_top='8%'))
l2.set_series_opts(tooltip_opts=opts.TooltipOpts(is_show=False))
grid = Grid().add(l1, grid_opts=opts.GridOpts()).add(l2, grid_opts=opts.GridOpts())
grid.render_notebook()
運動員平均體質資料
根據不同的運動專案進行統計
-
運動員平均身高最高的專案是籃球，女子平均身高達182cm，男子平均身高達到194cm；
-
在男子專案中，運動員平均體重最大的專案是拔河，平均體重達到96kg（拔河自第七屆奧運會後已取消）；
-
運動員平均年齡最大的專案是Art competition（自行百度這奇怪的專案），平均年齡46歲，除此之外便是馬術和射擊，男子平均年齡分別為34.4歲和34.2歲，女子平均年齡34.22歲和29.12s歲；
tool_js = """function (param) {return param.data[2] +'<br/>'
+'平均體重： '+Number(param.data[0]).toFixed(2)+' kg<br/>'
+'平均身高： '+Number(param.data[1]).toFixed(2)+' cm<br/>'
+'平均年齡： '+Number(param.data[3]).toFixed(2);}"""
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
temp_data = data[data['Sex']=='M'].groupby(['Sport'])['Age', 'Height', 'Weight'].mean().reset_index().dropna(how='any')
scatter = (Scatter(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='600px'))
.add_xaxis(temp_data['Weight'].tolist())
.add_yaxis("男性", [[row['Height'], row['Sport'], row['Age']] for _, row in temp_data.iterrows()],
# 漸變效果實現部分
color=JsCode("""new echarts.graphic.RadialGradient(0.4, 0.3, 1, [{
offset: 0,
color: 'rgb(129, 227, 238)'
}, {
offset: 1,
color: 'rgb(25, 183, 207)'
}])"""))
.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
.set_global_opts(
title_opts=opts.TitleOpts(title="各專案運動員平均升高體重年齡",pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20)),
legend_opts=opts.LegendOpts(is_show=True, pos_top='5%',
textstyle_opts=opts.TextStyleOpts(color="white", font_size=12)),
tooltip_opts = opts.TooltipOpts(formatter=JsCode(tool_js)),
xaxis_opts=opts.AxisOpts(
name='體重/kg',
# 設定座標軸為數值型別
type_="value",
is_scale=True,
# 顯示分割線
axislabel_opts=opts.LabelOpts(margin=30, color="white"),
axisline_opts=opts.AxisLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")),
axistick_opts=opts.AxisTickOpts(is_show=True, length=25,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")),
splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
)),
yaxis_opts=opts.AxisOpts(
name='身高/cm',
# 設定座標軸為數值型別
type_="value",
# 預設為False表示起始為0
is_scale=True,
axislabel_opts=opts.LabelOpts(margin=30, color="white"),
axisline_opts=opts.AxisLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")),
axistick_opts=opts.AxisTickOpts(is_show=True, length=25,
linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")),
splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color="#ffffff1f")
)),
visualmap_opts=opts.VisualMapOpts(is_show=False, type_='size', range_size=[5,50], min_=10, max_=40)
))
temp_data = data[data['Sex']=='F'].groupby(['Sport'])['Age', 'Height', 'Weight'].mean().reset_index().dropna(how='any')
scatter1 = (Scatter()
.add_xaxis(temp_data['Weight'].tolist())
.add_yaxis("女性", [[row['Height'], row['Sport'], row['Age']] for _, row in temp_data.iterrows()],
itemstyle_opts=opts.ItemStyleOpts(
color=JsCode("""new echarts.graphic.RadialGradient(0.4, 0.3, 1, [{
offset: 0,
color: 'rgb(251, 118, 123)'
}, {
offset: 1,
color: 'rgb(204, 46, 72)'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
)
scatter.overlap(scatter1)
scatter.render_notebook()
??中國奧運會表現
CN_data = data[data.region=='China']
CN_data.head()
歷屆奧運會參賽人數
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
athlete = CN_data.groupby(['Year', 'Season'])['Name'].nunique().reset_index()
athlete.columns = ['Year', 'Season', 'Nums']
athlete = athlete.sort_values(by="Year" , ascending=False)
s_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis([row['Year'] for _, row in athlete[athlete.Season=='Summer'].iterrows()])
.add_yaxis("參賽人數", [row['Nums'] for _, row in athlete[athlete.Season=='Summer'].iterrows()],
category_gap='40%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 1,
color: '#00BFFF'
}, {
offset: 0,
color: '#32CD32'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="中國曆年奧運會參賽人數-夏奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=0, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
w_bar = (
Bar(init_opts=opts.InitOpts(theme='dark',width='1000px', height='300px'))
.add_xaxis([row['Year'] for _, row in athlete[athlete.Season=='Winter'].iterrows()])
.add_yaxis("參賽人數", [row['Nums'] for _, row in athlete[athlete.Season=='Winter'].iterrows()],
category_gap='50%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 1,
color: '#00BFFF'
}, {
offset: 0.8,
color: '#FFC0CB'
}, {
offset: 0,
color: '#40E0D0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="中國曆年奧運會參賽人數-冬奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=-300, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
page = (
Page()
.add(s_bar,)
.add(w_bar,)
)
page.render_notebook()
歷屆奧運會獎牌數
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
CN_medals = CN_data.groupby(['Year', 'Season', 'Medal'])['Event'].nunique().reset_index()
CN_medals.columns = ['Year', 'Season', 'Medal', 'Nums']
CN_medals = CN_medals.sort_values(by="Year" , ascending=False)
s_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis(sorted(list(set([row['Year'] for _, row in CN_medals[CN_medals.Season=='Summer'].iterrows()])), reverse=True))
.add_yaxis("金牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Summer') & (CN_medals.Medal=='Gold')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#FFD700'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銀牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Summer') & (CN_medals.Medal=='Silver')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#C0C0C0'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銅牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Summer') & (CN_medals.Medal=='Bronze')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#DAA520'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="中國曆年奧運會獲得獎牌數數-夏奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=0, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
w_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis(sorted(list(set([row['Year'] for _, row in CN_medals[CN_medals.Season=='Winter'].iterrows()])), reverse=True))
.add_yaxis("金牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Winter') & (CN_medals.Medal=='Gold')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#FFD700'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銀牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Winter') & (CN_medals.Medal=='Silver')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#C0C0C0'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銅牌", [row['Nums'] for _, row in CN_medals[(CN_medals.Season=='Winter') & (CN_medals.Medal=='Bronze')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#DAA520'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="中國曆年奧運會獲得獎牌數-冬奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=-300, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
page = (
Page()
.add(s_bar,)
.add(w_bar,)
)
page.render_notebook()
優勢專案
跳水，體操，射擊，舉重，乒乓球，羽毛球
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0.5, color: '#FFC0CB'}, {offset: 1, color: '#F0FFFF'}, {offset: 0, color: '#EE82EE'}], false)"
)
CN_events = CN_data[CN_data.Medal=='Gold'].groupby(['Year', 'Sport'])['Event'].nunique().reset_index()
CN_events = CN_events.groupby(['Sport'])['Event'].sum().reset_index()
CN_events.columns = ['Sport', 'Nums']
data_pair = [(row['Sport'], row['Nums']) for _, row in CN_events.iterrows()]
wc = (WordCloud(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='600px'))
.add("", data_pair,word_size_range=[30, 80])
.set_global_opts(title_opts=opts.TitleOpts(title="中國獲得過金牌運動專案",pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20)))
)
wc.render_notebook()
??美國奧運會表現
USA_data = data[data.region=='USA']
USA_data.head()
歷屆奧運會參加人數
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
athlete = USA_data.groupby(['Year', 'Season'])['Name'].nunique().reset_index()
athlete.columns = ['Year', 'Season', 'Nums']
athlete = athlete.sort_values(by="Year" , ascending=False)
s_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis([row['Year'] for _, row in athlete[athlete.Season=='Summer'].iterrows()])
.add_yaxis("參賽人數", [row['Nums'] for _, row in athlete[athlete.Season=='Summer'].iterrows()],
category_gap='40%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 1,
color: '#00BFFF'
}, {
offset: 0,
color: '#32CD32'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="美國曆年奧運會參賽人數-夏奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=0, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
w_bar = (
Bar(init_opts=opts.InitOpts(theme='dark',width='1000px', height='300px'))
.add_xaxis([row['Year'] for _, row in athlete[athlete.Season=='Winter'].iterrows()])
.add_yaxis("參賽人數", [row['Nums'] for _, row in athlete[athlete.Season=='Winter'].iterrows()],
category_gap='50%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 1,
color: '#00BFFF'
}, {
offset: 0.8,
color: '#FFC0CB'
}, {
offset: 0,
color: '#40E0D0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="美國曆年奧運會參賽人數-冬奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=-300, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
page = (
Page()
.add(s_bar,)
.add(w_bar,)
)
page.render_notebook()
歷屆奧運會獲得獎牌數
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
medals = USA_data.groupby(['Year', 'Season', 'Medal'])['Event'].nunique().reset_index()
medals.columns = ['Year', 'Season', 'Medal', 'Nums']
medals = medals.sort_values(by="Year" , ascending=False)
s_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis(sorted(list(set([row['Year'] for _, row in medals[medals.Season=='Summer'].iterrows()])), reverse=True))
.add_yaxis("金牌", [row['Nums'] for _, row in medals[(medals.Season=='Summer') & (medals.Medal=='Gold')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#FFD700'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銀牌", [row['Nums'] for _, row in medals[(medals.Season=='Summer') & (medals.Medal=='Silver')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#C0C0C0'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銅牌", [row['Nums'] for _, row in medals[(medals.Season=='Summer') & (medals.Medal=='Bronze')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#DAA520'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="美國曆年奧運會獲得獎牌數數-夏奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=0, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
w_bar = (
Bar(init_opts=opts.InitOpts(theme='dark', width='1000px', height='300px'))
.add_xaxis(sorted(list(set([row['Year'] for _, row in medals[medals.Season=='Winter'].iterrows()])), reverse=True))
.add_yaxis("金牌", [row['Nums'] for _, row in medals[(medals.Season=='Winter') & (medals.Medal=='Gold')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#FFD700'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銀牌", [row['Nums'] for _, row in medals[(medals.Season=='Winter') & (medals.Medal=='Silver')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#C0C0C0'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.add_yaxis("銅牌", [row['Nums'] for _, row in medals[(medals.Season=='Winter') & (medals.Medal=='Bronze')].iterrows()],
category_gap='20%',
itemstyle_opts=opts.ItemStyleOpts(
border_color='rgb(220,220,220)',
color=JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1,
[{
offset: 0,
color: '#DAA520'
}, {
offset: 1,
color: '#FFFFF0'
}])""")))
.set_series_opts(label_opts=opts.LabelOpts(is_show=True,
position='top',
font_style='italic'))
.set_global_opts(
title_opts=opts.TitleOpts(title="美國曆年奧運會獲得獎牌數-冬奧會", pos_left='center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)),
legend_opts=opts.LegendOpts(is_show=False),
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63")),
graphic_opts=[
opts.GraphicImage(
graphic_item=opts.GraphicItem(
id_="logo", right=0, top=-300, z=-10, bounding="raw", origin=[75, 75]
),
graphic_imagestyle_opts=opts.GraphicImageStyleOpts(
image="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1586619952245&di=981a36305048f93eec791980acc99cf7&imgtype=0&src=http%3A%2F%2Fimg5.mtime.cn%2Fmg%2F2017%2F01%2F06%2F172210.42721559.jpg",
width=1000,
height=600,
opacity=0.6,),
)
],)
)
page = (
Page()
.add(s_bar,)
.add(w_bar,)
)
page.render_notebook()
優勢專案
田徑，游泳
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0.5, color: '#FFC0CB'}, {offset: 1, color: '#F0FFFF'}, {offset: 0, color: '#EE82EE'}], false)"
)
events = USA_data[USA_data.Medal=='Gold'].groupby(['Year', 'Sport'])['Event'].nunique().reset_index()
events = events.groupby(['Sport'])['Event'].sum().reset_index()
events.columns = ['Sport', 'Nums']
data_pair = [(row['Sport'], row['Nums']) for _, row in events.iterrows()]
wc = (WordCloud(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js), width='1000px', height='600px'))
.add("", data_pair,word_size_range=[30, 80])
.set_global_opts(title_opts=opts.TitleOpts(title="美國獲得過金牌運動專案",pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20)))
)
wc.render_notebook()
被單個國家統治的奧運會專案
很多運動長期以來一直是被某個國家統治，譬如我們熟知的中國??的乒乓球，美國??的籃球；
此次篩選了近5屆奧運會（2000年悉尼奧運會之後）上累計產生10枚金牌以上且存在單個國家「奪金率」超過50%的專案；
-
俄羅斯??包攬了2000年以後花樣游泳 & 藝術體操兩個專案上所有的20枚金牌；
-
中國??在乒乓球專案上獲得了2000年之後10枚金牌中的9枚，丟失金牌的一次是在04年雅典奧運會男單專案上；
-
美國??在籃球專案上同樣獲得了過去10枚金牌中的9枚，丟失金牌的一次同樣在04年，男籃半決賽中輸給了阿根廷，最終獲得銅牌；
-
跳水專案上，中國??獲得了過去40枚金牌中的31枚，夢之隊名不虛傳；
-
射箭專案上，韓國??獲得了過去20枚金牌中的15枚；
-
羽毛球專案上，中國??獲得了過去25枚金牌中的17枚；
-
沙灘排球專案上，美國??獲得了過去10枚金牌中的5枚；
f1 = lambda x:max(x['Event']) / sum(x['Event'])
f2 = lambda x: x.sort_values('Event', ascending=False).head(1)
t_data = data[(data.Medal=='Gold') & (data.Year>=2000) &(data.Season=='Summer')].groupby(['Year', 'Sport', 'region'])['Event'].nunique().reset_index()
t_data = t_data.groupby(['Sport', 'region'])['Event'].sum().reset_index()
t1 = t_data.groupby(['Sport']).apply(f2).reset_index(drop=True)
t2 = t_data.groupby(['Sport'])['Event'].sum().reset_index()
t_data = pd.merge(t1, t2, on='Sport', how='inner')
t_data['gold_rate'] = t_data.Event_x/ t_data.Event_y
t_data = t_data.sort_values('gold_rate', ascending=False).reset_index(drop=True)
t_data = t_data[(t_data.gold_rate>=0.5) & (t_data.Event_y>=10)]
background_color_js = (
"new echarts.graphic.LinearGradient(1, 0, 0, 1, "
"[{offset: 0, color: '#008B8B'}, {offset: 1, color: '#FF6347'}], false)"
)
fn = """
function(params) {
if(params.name == '其他國家')
return '\\n\\n\\n' + params.name + ' : ' + params.value ;
return params.seriesName+ '\\n' + params.name + ' : ' + params.value;
}
"""
def new_label_opts():
return opts.LabelOpts(formatter=JsCode(fn), position="center")
pie = Pie(init_opts=opts.InitOpts(theme='dark', width='1000px', height='1000px'))
idx = 0
for _, row in t_data.iterrows():
if idx % 2 == 0:
x = 30
y = int(idx/2) * 22 + 18
else:
x = 70
y = int(idx/2) * 22 + 18
idx += 1
pos_x = str(x)+'%'
pos_y = str(y)+'%'
pie.add(
row['Sport'],
[[row['region'], row['Event_x']], ['其他國家', row['Event_y']-row['Event_x']]],
center=[pos_x, pos_y],
radius=[70, 100],
label_opts=new_label_opts(),)
pie.set_global_opts(
title_opts=opts.TitleOpts(title="被單個國家統治的專案",
subtitle='統計週期：2000年悉尼奧運會起',
pos_left="center",
title_textstyle_opts=opts.TextStyleOpts(color="white", font_size=20)),
legend_opts=opts.LegendOpts(is_show=False),
)
pie.render_notebook()
歡迎點贊支援❤️???