python采集最新世界大学排名, 来看看你的母校上榜没~

前言

大家早好、午好、晚好吖 ❤ ~

本次内容:

Python 采集世界大学排行榜并做数据可视化

知识点:

动态数据抓包
requests发送请求
结构化+非结构化数据解析

开发环境:

python 3.8 运行代码
pycharm 2021.2 辅助敲代码
requests 第三方模块 pip install 模块名

本次文章案例教程、源码料找小钰老师微信: python5180 
+ python安装包 安装教程视频
+ pycharm 社区版 专业版 及 免费

代码展示

数据采集

代码里网址被我删了好过审核， ( 源码、教程、文档、软件点击此处跳转跳转文末名片+找管理员领取呀~ )

import requests         # 发送请求 第三方模块
import re
import csv

def replace(str):
    str = re.sub('<.*?>', '', str)
    return str

乱码和代码没关系, 软件有关系

每一个软件打开文件的编码方式不一样

f = open('排名.csv',  mode='a', encoding='utf-8', newline='')
csv_writer = csv.writer(f)

请求链接

url = 'https://www.***.cn/sites/default/files/qs-rankings-data/cn/2057712.txt?_=1669724480772'

发送请求

response = requests.get(url)

获取数据

.text: 获取文本数据的

.json(): 获取 {}/[] 所包裹的数据字符串类型 ==> 字典/列表 Python基础里面的数据容器

.content: 获取音频/视频/图片数据的

json_data = response.json()

解析数据提取数据

data_list = json_data['data']
for data in data_list:
    country = data['country']
    title = replace(data['title'])
    ind_0 = replace(data['ind_0'])
    ind_1 = replace(data['ind_1'])
    ind_2 = replace(data['ind_2'])
    rank_0 = data['rank_0']
    rank_d_0 = replace(data['rank_d_0'])
    rank_d_1 = replace(data['rank_d_1'])
    score = data['score']
    region = data['region']
    print(country, title, ind_0, ind_1, ind_2, rank_0, rank_d_0, rank_d_1, score, region)

保存数据

    csv_writer.writerow([country, title, ind_0, ind_1, ind_2, rank_0, rank_d_0, rank_d_1, score, region])

详情 / 相对应的安装包/安装教程/激活码/使用教程/学习资料/工具插件可以点击免费领取

数据可视化

from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
from pyecharts.components import Table
import re
import pandas as pd

df = pd.read_csv('rank.csv')

香港，澳门与中国大陆地区等在榜单中是分开的记录的，这边都归为china

df['loc'] = df['country']
df['country'].replace(['China (Mainland)', 'Hong Kong SAR', 'Taiwan', 'Macau SAR'],'China',inplace=True)

tool_js = """
<div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px">
                 {} 
                 </div>
                 排名：{} <br>
                 国家地区：{} <br>
                 加权总分：{} <br>
                 国际学生：{} <br>
                 国际教师：{} <br>
                 师生比例：{} <br>
                 学术声誉：{} <br>
                 雇主声誉：{} <br>
                 教员引用率：{} <br>
"""

t_data = df[(df.year==2021) & (df['rank']<=100)]
t_data = t_data.sort_values(by="total_score" , ascending=True) 

university, score = [], []
for idx, row in t_data.iterrows():
    tjs = tool_js.format(row['university'], row['rank'], row['country'],row['total_score'], 
                         row['score_6'],row['score_5'], row['score_3'],row['score_1'],row['score_2'], row['score_4'])
    if row['country'] == 'China':
        university.append('🇨🇳 {}'.format(re.sub('（.*?）', '',row['university'])))
    else:
        university.append(re.sub('（.*?）', '',row['university']))
    score.append(opts.BarItem(name='', value=row['total_score'], tooltip_opts=opts.TooltipOpts(formatter=tjs)))

bar = (Bar()
       .add_xaxis(university)
       .add_yaxis('', score, category_gap='30%')
       .set_global_opts(title_opts=opts.TitleOpts(title="2021年世界大学排名（QS） TOP 100",
                                                  pos_left="center",
                                                  title_textstyle_opts=opts.TextStyleOpts(font_size=20)),
                        datazoom_opts=opts.DataZoomOpts(range_start=70, range_end=100, orient='vertical'),
                        visualmap_opts=opts.VisualMapOpts(is_show=False, max_=100, min_=60, dimension=0,
                                range_color=['#00FFFF', '#FF7F50']),
                        legend_opts=opts.LegendOpts(is_show=False),
                        xaxis_opts=opts.AxisOpts(is_show=False, is_scale=True),
                        yaxis_opts=opts.AxisOpts(axistick_opts=opts.AxisTickOpts(is_show=False),
                                                 axisline_opts=opts.AxisLineOpts(is_show=False),
                                                 axislabel_opts=opts.LabelOpts(font_size=12)))
       .set_series_opts(label_opts=opts.LabelOpts(is_show=True,
                                                  position='right',
                                                  font_style='italic'),
                        itemstyle_opts={"normal": {
                                                    "barBorderRadius": [30, 30, 30, 30],
                                                    'shadowBlur': 10,
                                                    'shadowColor': 'rgba(120, 36, 50, 0.5)',
                                                    'shadowOffsetY': 5,
                                                }
                                       }
).reversal_axis())

grid = (
        Grid(init_opts=opts.InitOpts(theme='purple-passion', width='1000px', height='1200px'))
        .add(bar, grid_opts=opts.GridOpts(pos_right='10%', pos_left='20%'))
    )
grid.render_notebook()

tool_js = """
<div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px">
                 {} 
                 </div>
                 世界排名：{} <br>
                 国家地区：{} <br>
                 加权总分：{} <br>
                 国际学生：{} <br>
                 国际教师：{} <br>
                 师生比例：{} <br>
                 学术声誉：{} <br>
                 雇主声誉：{} <br>
                 教员引用率：{} <br>
"""

t_data = df[(df.country=='China') & (df['rank']<=500)]
t_data = t_data.sort_values(by="total_score" , ascending=True) 

university, score = [], []
for idx, row in t_data.iterrows():
    tjs = tool_js.format(row['university'], row['rank'], row['country'],row['total_score'], 
                         row['score_6'],row['score_5'], row['score_3'],row['score_1'],row['score_2'], row['score_4'])
    if row['country'] == 'China':
        university.append('🇨🇳 {}'.format(re.sub('（.*?）', '',row['university'])))
    else:
        university.append(re.sub('（.*?）', '',row['university']))
    score.append(opts.BarItem(name='', value=row['total_score'], tooltip_opts=opts.TooltipOpts(formatter=tjs)))

bar = (Bar()
       .add_xaxis(university)
       .add_yaxis('', score, category_gap='30%')
       .set_global_opts(title_opts=opts.TitleOpts(title="TOP 500中的中国大学",
                                                  pos_left="center",
                                                  title_textstyle_opts=opts.TextStyleOpts(font_size=20)),
                        datazoom_opts=opts.DataZoomOpts(range_start=50, range_end=100, orient='vertical'),
                        visualmap_opts=opts.VisualMapOpts(is_show=False, max_=90, min_=20, dimension=0,
                                range_color=['#00FFFF', '#FF7F50']),
                        legend_opts=opts.LegendOpts(is_show=False),
                        xaxis_opts=opts.AxisOpts(is_show=False, is_scale=True),
                        yaxis_opts=opts.AxisOpts(axistick_opts=opts.AxisTickOpts(is_show=False),
                                                 axisline_opts=opts.AxisLineOpts(is_show=False),
                                                 axislabel_opts=opts.LabelOpts(font_size=12)))
       .set_series_opts(label_opts=opts.LabelOpts(is_show=True,
                                                  position='right',
                                                  font_style='italic'),
                        itemstyle_opts={"normal": {
                                                    "barBorderRadius": [30, 30, 30, 30],
                                                    'shadowBlur': 10,
                                                    'shadowColor': 'rgba(120, 36, 50, 0.5)',
                                                    'shadowOffsetY': 5,
                                                }
                                       }
).reversal_axis())

grid = (
        Grid(init_opts=opts.InitOpts(theme='purple-passion', width='1000px', height='1200px'))
        .add(bar, grid_opts=opts.GridOpts(pos_right='10%', pos_left='20%'))
    )
grid.render_notebook()

t_data = df[(df.year==2021) & (df['rank']<=1000)]
t_data = t_data.groupby(['region'])['university'].count().reset_index()
t_data.columns = ['region', 'num']
t_data = t_data.sort_values(by="num" , ascending=False) 


bar = (Bar(init_opts=opts.InitOpts(theme='purple-passion', width='1000px', height='600px'))
       .add_xaxis(t_data['region'].tolist())
       .add_yaxis('出现次数', t_data['num'].tolist(), category_gap='50%')
       .set_global_opts(title_opts=opts.TitleOpts(title="TOP 1000高校按大洲分布",
                                                  pos_left="center",
                                                  title_textstyle_opts=opts.TextStyleOpts(font_size=20)),
                        visualmap_opts=opts.VisualMapOpts(is_show=False, max_=300, min_=0, dimension=1,
                                range_color=['#00FFFF', '#FF7F50']),
                        legend_opts=opts.LegendOpts(is_show=False),
                        xaxis_opts=opts.AxisOpts(axistick_opts=opts.AxisTickOpts(is_show=False),
                                                 axisline_opts=opts.AxisLineOpts(is_show=False),
                                                 axislabel_opts=opts.LabelOpts(font_size=15)),
                        yaxis_opts=opts.AxisOpts(is_show=False))
       .set_series_opts(label_opts=opts.LabelOpts(is_show=True,
                                                  position='top',
                                                  font_size=15,
                                                  font_style='italic'),
                        itemstyle_opts={"normal": {
                                                    "barBorderRadius": [30, 30, 30, 30],
                                                    'shadowBlur': 10,
                                                    'shadowColor': 'rgba(120, 36, 50, 0.5)',
                                                    'shadowOffsetY': 5,
                                                }
                                       }
))

bar.render_notebook()

# 以下国家单独在地图上显示出来
country_list = ['China', 'United States', 'Brazil', 'United Kingdom', 'Canada', 'Russia', 'India']

# 对应国家的经纬度
loc = {
    'Brazil': [-51.92528, -14.235004],
    'Canada': [-106.346771, 56.130366],
    'China': [104.195397, 35.86166],
    'India': [78.96288, 20.593684],
    'United Kingdom': [-3.435973, 55.378051],
    'United States': [-95.712891, 37.09024],
    'Russia': [116.8564, 65.067703],
}

t_data = df[(df.year==2021) & (df['rank']<=1000)]
t_data = t_data.groupby(['country'])['university'].count().reset_index()
t_data.columns = ['country', 'num']
t_data = t_data.sort_values(by="num" , ascending=True) 

data_pair = []
for idx, row in t_data.iterrows():
    if row['country'] in ['China (Mainland)', 'Hong Kong SAR', 'Taiwan', 'Macau SAR']:
        data_pair.append(['China', row['num']])
    else:
        data_pair.append([row['country'], row['num']])

fmt_js = """function (params) {return params.name+': '+Number(params.value[2]);}"""

mp = Map()
mp.add(
        "高校数量",
        data_pair,
        "world",
        is_map_symbol_show=False,
        is_roam=False)

mp.set_series_opts(label_opts=opts.LabelOpts(is_show=False),
                          itemstyle_opts={'normal': {
                                                'areaColor': '#191970',
                                                'borderColor': '#1773c3',
                                                'shadowColor': '#1773c3',
                                                'shadowBlur': 20,
                                                'opacity': 0.8
                                                    }
                                        })
    
mp.set_global_opts(
        title_opts=opts.TitleOpts(title="TOP 1000高校按国家分布", pos_left='center',
                                  title_textstyle_opts=opts.TextStyleOpts(font_size=18)),
        legend_opts=opts.LegendOpts(is_show=False),
        visualmap_opts=opts.VisualMapOpts(is_show=False, 
                                          max_=100,
                                          is_piecewise=False,
                                          dimension=0,
                                          range_color=['rgba(255,228,225,0.6)', 'rgba(255,0,0,0.9)', 'rgba(255,0,0,1)'])
    )

data_pair = [[x, y] for x, y in data_pair if x in country_list]    
geo = Geo()
    
# 需要先将几个国家的经纬度信息加入到geo中
for k, v in loc.items():
    geo.add_coordinate(k, v[0], v[1])
# 这里将geo的地图透明度配置为0
geo.add_schema(maptype="world", is_roam=False, itemstyle_opts={'normal': {'opacity': 0}})
    
geo.add("", data_pair, symbol_size=1)
# 显示标签配置
geo.set_series_opts(
    label_opts=opts.LabelOpts(
            is_show=True,
            position='right',
            color='white',
            font_size=12,
            font_weight='bold',
            formatter=JsCode(fmt_js)),
    )
    
grid = (
        Grid(init_opts=opts.InitOpts(theme='chalk', width='1000px', height='600px'))
        .add(mp, grid_opts=opts.GridOpts(pos_top="12%"))
        .add(geo, grid_opts=opts.GridOpts(pos_bottom="12%"))
    )

grid.render_notebook()

t_data = df[(df.year==2021) & (df['rank']<=1000)]
t_data = t_data.groupby(['region', 'country'])['university'].count().reset_index()
t_data.columns = ['region', 'country', 'num']
#t_data.num = round(t_data.num.div(t_data.num.sum(axis=0), axis=0) * 100, 1)

data_pair = [
            {"name": 'Europe',
              "label":{"show": True},
              "children": []},
            {"name": 'Asia',
              "label":{"show": True},
              "children": []},
            {"name": 'North America',
              "label":{"show": True},
              'shadowBlur': 10,
              'shadowColor': 'rgba(120, 36, 50, 0.5)',
              'shadowOffsetY': 5,
              "children": []},
            {"name": 'Latin America',
              "label":{"show": True},
              "children": []},
            {"name": 'Oceania',
              "label":{"show": True},
              "children": []},
            {"name": 'Africa',
              "label":{"show": False},
              "children": []}
    ]

for idx, row in t_data.iterrows():
    t_dict = {"name": row.country,
              "label":{"show": True},
              "children": []}
    if row.num > 15:
        child_data = {"name": row.country, "value":row.num, "label":{"show": True}}
    else:
        child_data = {"name": row.country, "value":row.num, "label":{"show": False}}
    if row.region == "Europe":
        data_pair[0]['children'].append(child_data)   
    elif row.region == "Asia":
        data_pair[1]['children'].append(child_data)   
    elif row.region == "North America":
        data_pair[2]['children'].append(child_data)  
    elif row.region == "Latin America":
        data_pair[3]['children'].append(child_data)  
    elif row.region == "Oceania":
        data_pair[4]['children'].append(child_data)  
    elif row.region == "Africa":
        data_pair[5]['children'].append(child_data)

c = (Sunburst(
        init_opts=opts.InitOpts(
            theme='purple-passion',
            width="1000px",
            height="1000px"))
    .add(
        "",
        data_pair=data_pair,
        highlight_policy="ancestor",
        radius=[0, "100%"],
        sort_='null',
        levels=[
            {},
            {
                "r0": "20%",
                "r": "48%",
                "itemStyle": {"borderColor": 'rgb(220,220,220)', "borderWidth": 2}
            },
            {"r0": "50%", "r": "80%", "label": {"align": "right"},
                "itemStyle": {"borderColor": 'rgb(220,220,220)', "borderWidth": 1}}
        ],
    )
    .set_global_opts(
        visualmap_opts=opts.VisualMapOpts(is_show=False, max_=300, min_=0, is_piecewise=False,
                                range_color=['#4285f4', '#34a853', '#fbbc05', '#ea4335', '#ea4335']),
        title_opts=opts.TitleOpts(title="TOP 1000\n\n大学地理分布",
                                               pos_left="center",
                                               pos_top="center",
                                               title_textstyle_opts=opts.TextStyleOpts(font_style='oblique', font_size=20),))
    .set_series_opts(label_opts=opts.LabelOpts(font_size=14, formatter="{b}: {c}"))
)

c.render_notebook()

cn_data_x, cn_data_y = [], []
for idx, row in df[(df.country=='China') & (df['rank']<=1000)].iterrows():
    cn_data_y.append([row['score_4'], row['score_1'], row['rank'], row['university']])
    cn_data_x.append(row['score_3'])
    
un_data_x, un_data_y = [], []
for idx, row in df[(df.country=='United States') & (df['rank']<=1000)].iterrows():
    un_data_y.append([row['score_4'], row['score_1'], row['rank'], row['university']])
    un_data_x.append(row['score_3'])
    
uk_data_x, uk_data_y = [], []
for idx, row in df[(df.country=='United Kingdom') & (df['rank']<=1000)].iterrows():
    uk_data_y.append([row['score_4'], row['score_1'], row['rank'], row['university']])
    uk_data_x.append(row['score_3'])

tool_js = """
function (obj) {
            var value = obj.value;
            var schema = [{name: 'rank', index: 0, text: '总体排名'},
                            {name: 'score_1', index: 1, text: '学术声誉'},
                            {name: 'score_4', index: 2, text: '教员引用率'},
                            {name: 'score_3', index: 3, text: '师生比例'}];
            return '<div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px">'
                + value[4] 
                + '</div>'
                + schema[0].text + '：' + value[3] + '<br>'
                + schema[1].text + '：' + value[2] + '<br>'
                + schema[2].text + '：' + value[1] + '<br>'
                + schema[3].text + '：' + value[0] + '<br>';
        }
"""

itemStyle_1 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#80F1BE'
}

itemStyle_2 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#fec42c'
}

itemStyle_3 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#dd4444'
}


visualMap = [
        {
            'left': 'right',
            'top': '10%',
            'dimension': 2,
            'min': 20,
            'max': 100,
            'itemWidth': 30,
            'itemHeight': 120,
            'calculable': True,
            'precision': 0.1,
            'text': ['圆形大小：学术声誉'],
            'textGap': 30,
            'textStyle': {
                'color': '#fff'
            },
            'inRange': {
                'symbolSize': [10, 50]
            },
            'outOfRange': {
                'symbolSize': [10, 50],
                'color': ['rgba(255,255,255,.2)']
            },
            'controller': {
                'inRange': {
                    'color': ['#c23531']
                },
                'outOfRange': {
                    'color': ['#444']
                }
            }
        },
        {
            'left': 'right',
            'bottom': '15%',
            'dimension': 3,
            'min': 1,
            'max': 500,
            'itemHeight': 120,

            'precision': 0.1,
            'text': ['明暗：总体排名'],
            'textGap': 30,
            'textStyle': {
                'color': '#fff'
            },
            'inRange': {
                'colorLightness': [0.5, 1]
            },
            'outOfRange': {
                'color': ['rgba(255,255,255,.2)']
            },
            'controller': {
                'inRange': {
                    'color': ['#c23531']
                },
                'outOfRange': {
                    'color': ['#444']
                }
            }
        }
    ]

scatter1 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(cn_data_x)
            .add_yaxis("中国", cn_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_3
                       )
            .set_global_opts(yaxis_opts=opts.AxisOpts(name='教员引用率', type_="value", is_scale=True, 
                                                      name_textstyle_opts={'color': '#fff', 'fontSize': 16},
                                                      axisline_opts=opts.AxisLineOpts(linestyle_opts=opts.LineStyleOpts(color='#eee'))),
                             xaxis_opts=opts.AxisOpts(name='师生比', type_="value", is_scale=True, 
                                                      name_textstyle_opts={'color': '#fff', 'fontSize': 16},
                                                      axisline_opts=opts.AxisLineOpts(linestyle_opts=opts.LineStyleOpts(color='#eee'))),
                             tooltip_opts=opts.TooltipOpts(is_show=True, background_color='#222', border_color='#777', border_width=1, formatter=JsCode(tool_js)),
                             legend_opts=opts.LegendOpts(is_show=True, pos_right=10,
                                                         textstyle_opts=opts.TextStyleOpts(color='#fff',font_size=16)),
                             visualmap_opts=visualMap
                             )
            )

scatter2 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(un_data_x)
            .add_yaxis("美国", un_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_2
                       )
            )
            
scatter3 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(uk_data_x)
            .add_yaxis("英国", uk_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_1
                       )
            )
            
scatter1.overlap(scatter2)
scatter1.overlap(scatter3)
scatter1.render_notebook()

cn_data_x, cn_data_y = [], []
for idx, row in df[(df.country=='China') & (df['rank']<=1000)].iterrows():
    cn_data_y.append([row['score_6'], row['total_score'], row['rank'], row['university']])
    cn_data_x.append(row['score_5'])
    
un_data_x, un_data_y = [], []
for idx, row in df[(df.country=='United States') & (df['rank']<=1000)].iterrows():
    un_data_y.append([row['score_6'], row['total_score'], row['rank'], row['university']])
    un_data_x.append(row['score_5'])
    
uk_data_x, uk_data_y = [], []
for idx, row in df[(df.country=='United Kingdom') & (df['rank']<=1000)].iterrows():
    uk_data_y.append([row['score_6'], row['total_score'], row['rank'], row['university']])
    uk_data_x.append(row['score_5'])

tool_js = """
function (obj) {
            var value = obj.value;
            var schema = [{name: 'rank', index: 0, text: '总体排名'},
                            {name: 'score_1', index: 1, text: '国际学生'},
                            {name: 'score_4', index: 2, text: '国际教师'},
                            {name: 'score_3', index: 3, text: '总体分数'}];
            return '<div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px">'
                + value[4] 
                + '</div>'
                + schema[0].text + '：' + value[3] + '<br>'
                + schema[1].text + '：' + value[1] + '<br>'
                + schema[2].text + '：' + value[0] + '<br>'
                + schema[3].text + '：' + value[2] + '<br>';
        }
"""

itemStyle_1 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#80F1BE'
}

itemStyle_2 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#fec42c'
}

itemStyle_3 = {
    'opacity': 0.8,
    'shadowBlur': 10,
    'shadowOffsetX': 0,
    'shadowOffsetY': 0,
    'shadowColor': 'rgba(0, 0, 0, 0.5)',
    'color': '#dd4444'
}


visualMap = [
        {
            'left': 'right',
            'top': '10%',
            'dimension': 2,
            'min': 20,
            'max': 100,
            'itemWidth': 30,
            'itemHeight': 120,
            'calculable': True,
            'precision': 0.1,
            'text': ['圆形大小：总体分数'],
            'textGap': 30,
            'textStyle': {
                'color': '#fff'
            },
            'inRange': {
                'symbolSize': [10, 50]
            },
            'outOfRange': {
                'symbolSize': [10, 50],
                'color': ['rgba(255,255,255,.2)']
            },
            'controller': {
                'inRange': {
                    'color': ['#c23531']
                },
                'outOfRange': {
                    'color': ['#444']
                }
            }
        },
        {
            'left': 'right',
            'bottom': '15%',
            'dimension': 3,
            'min': 1,
            'max': 500,
            'itemHeight': 120,

            'precision': 0.1,
            'text': ['明暗：总体排名'],
            'textGap': 30,
            'textStyle': {
                'color': '#fff'
            },
            'inRange': {
                'colorLightness': [0.5, 1]
            },
            'outOfRange': {
                'color': ['rgba(255,255,255,.2)']
            },
            'controller': {
                'inRange': {
                    'color': ['#c23531']
                },
                'outOfRange': {
                    'color': ['#444']
                }
            }
        }
    ]

scatter1 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(cn_data_x)
            .add_yaxis("中国", cn_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_3
                       )
            .set_global_opts(yaxis_opts=opts.AxisOpts(name='国际学生', type_="value", is_scale=True, 
                                                      name_textstyle_opts={'color': '#fff', 'fontSize': 16},
                                                      axisline_opts=opts.AxisLineOpts(linestyle_opts=opts.LineStyleOpts(color='#eee'))),
                             xaxis_opts=opts.AxisOpts(name='国际教师', type_="value", is_scale=True, 
                                                      name_textstyle_opts={'color': '#fff', 'fontSize': 16},
                                                      axisline_opts=opts.AxisLineOpts(linestyle_opts=opts.LineStyleOpts(color='#eee'))),
                             tooltip_opts=opts.TooltipOpts(is_show=True, background_color='#222', border_color='#777', border_width=1, formatter=JsCode(tool_js)),
                             legend_opts=opts.LegendOpts(is_show=True, pos_right=10,
                                                         textstyle_opts=opts.TextStyleOpts(color='#fff',font_size=16)),
                             visualmap_opts=visualMap
                             )
            )

scatter2 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(un_data_x)
            .add_yaxis("美国", un_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_2
                       )
            )
            
scatter3 = (Scatter(init_opts=opts.InitOpts(bg_color='#404a59',width='1000px', height='800px'))
            .add_xaxis(uk_data_x)
            .add_yaxis("英国", uk_data_y,
                       label_opts=opts.LabelOpts(is_show=False),
                       itemstyle_opts=itemStyle_1
                       )
            )
            
scatter1.overlap(scatter2)
scatter1.overlap(scatter3)
scatter1.render_notebook()

t_data = df[(df['loc'] == 'China (Mainland)') & (df['rank'] <= 100)]

data_cn = []
for idx, row in t_data.iterrows():
    data_cn.append([row['score_1'], row['score_2'], row['score_3'],
                    row['score_4'], row['score_5'], row['score_6'], row['university']])


t_data = df[(df['loc'] == 'United States') & (df['rank'] <= 100)]

data_un = []
for idx, row in t_data.iterrows():
    data_un.append([row['score_1'], row['score_2'], row['score_3'],
                    row['score_4'], row['score_5'], row['score_6'], row['university']])
                    
t_data = df[(df['loc'] == 'United Kingdom') & (df['rank'] <= 100)]

data_uk = []
for idx, row in t_data.iterrows():
    data_uk.append([row['score_1'], row['score_2'], row['score_3'],
                    row['score_4'], row['score_5'], row['score_6'], row['university']
                    
                     ])

split_line_style = {'color': [
                    'rgba(238, 197, 102, 0.1)', 'rgba(238, 197, 102, 0.2)',
                    'rgba(238, 197, 102, 0.4)', 'rgba(238, 197, 102, 0.6)',
                    'rgba(238, 197, 102, 0.8)', 'rgba(238, 197, 102, 1)'
                    ][::-1]
}

tool_js = """
function (obj) {
            var value = obj.value;
            var schema = [{name: 'score_1', index: 1, text: '学术声誉'},
                            {name: 'score_4', index: 2, text: '雇主声誉'},
                            {name: 'score_3', index: 3, text: '师生比'},
                            {name: 'score_3', index: 3, text: '教员引用率'},
                            {name: 'score_4', index: 2, text: '国际教师'},
                            {name: 'score_3', index: 3, text: '国际学生'}];
            return '<div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px">'
                + value[6] 
                + '</div>'
                + schema[0].text + '：' + value[0] + '<br>'
                + schema[1].text + '：' + value[1] + '<br>'
                + schema[2].text + '：' + value[2] + '<br>'
                + schema[3].text + '：' + value[3] + '<br>'
                + schema[4].text + '：' + value[4] + '<br>'
                + schema[5].text + '：' + value[5] + '<br>';
        }
"""

radar = Radar(init_opts=opts.InitOpts(theme='dark', bg_color='#161627', height='800px', width='1000px'))
radar.add_schema(shape='circle',
                 textstyle_opts=opts.TextStyleOpts(color='rgb(238, 197, 102)'),
                 axisline_opt=opts.LineStyleOpts(is_show=True, color='rgba(238, 197, 102, 1)'),
                 splitline_opt=opts.SplitLineOpts(is_show=True, linestyle_opts=split_line_style),
                 schema=[opts.RadarIndicatorItem(name='学术声誉', max_=100),
                         opts.RadarIndicatorItem(name='雇主声誉', max_=100),
                         opts.RadarIndicatorItem(name='师生比', max_=100),
                         opts.RadarIndicatorItem(name="教员引用率", max_=100),
                         opts.RadarIndicatorItem(name="国际教师", max_=100),
                         opts.RadarIndicatorItem(name="国际学生", max_=100)])

radar.add('中国', data_cn, symbol='none', is_selected=True,
          label_opts=opts.LabelOpts(is_show=False),
          linestyle_opts=opts.LineStyleOpts(color='#dd4444', width=1, opacity=0.5),
          areastyle_opts=opts.AreaStyleOpts(color='#dd4444', opacity=0.05))

radar.add('美国', data_un, symbol='none', is_selected=False,
          label_opts=opts.LabelOpts(is_show=False),
          linestyle_opts=opts.LineStyleOpts(color='#fec42c', width=1, opacity=0.5),
          areastyle_opts=opts.AreaStyleOpts(color='#fec42c', opacity=0.05))

radar.add('英国', data_uk, symbol='none', is_selected=False,
          label_opts=opts.LabelOpts(is_show=False),
          linestyle_opts=opts.LineStyleOpts(color='#80F1BE', width=1, opacity=0.5),
          areastyle_opts=opts.AreaStyleOpts(color='#80F1BE',opacity=0.05))

radar.set_global_opts(legend_opts=opts.LegendOpts(is_show=True, selected_mode='multiple', pos_bottom=5),
                      tooltip_opts=opts.TooltipOpts(is_show=True, background_color='#222', 
                          border_color='#777', border_width=1, formatter=JsCode(tool_js)),
                      title_opts=opts.TitleOpts(title="中英美——TOP100大学对比", pos_left='center',
                                                title_textstyle_opts=opts.TextStyleOpts(font_size=20)))


radar.render_notebook()