文章目录
1.准备数据
爬取高考网的大学高校数据，利用pyecharts库绘图
代码数据放在Github
2.数据展示
3.可视化展示
3.1 各城市高校数量 bar
bar = Bar()
bar.add_xaxis(data['name'].values.tolist())
bar.add_yaxis("", data['counts'].values.tolist())
bar.set_global_opts(
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=50)),
title_opts=opts.TitleOpts(title="各城市高校数量", subtitle="仅仅统计数量"),
datazoom_opts=opts.DataZoomOpts(),
)
bar.set_series_opts(itemstyle_opts={
"normal": {
"color": JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1, [{
offset: 0,
color: 'rgba(0, 244, 255, 1)'
}, {
offset: 1,
color: 'rgba(0, 77, 167, 1)'
}], false)"""),
"barBorderRadius": [30, 30, 30, 30],
"shadowColor": 'rgb(0, 160, 221)',
}})
bar.render_notebook()
bar.render('各城市高校数量.html')
3.2 高校数量前十名 pie
# 高校数量前十名
pie = Pie()
pie.add("", [list(z) for z in zip(data['name'].values.tolist()[:10], data['counts'].values.tolist()[:10])],
radius=["30%", "75%"],
center=["40%", "50%"],
rosetype="radius")
pie.set_global_opts(
title_opts=opts.TitleOpts(title="高校数量前十名"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.render_notebook()
pie.render('高校数量前十名.html')
3.3 高校数量后十名 pie
# 高校数量后十名
pie = Pie()
pie.add("", [list(z) for z in zip(data['name'].values.tolist()[-10:], data['counts'].values.tolist()[-10:])],
radius=["30%", "75%"],
center=["40%", "50%"],
rosetype="radius")
pie.set_global_opts(
title_opts=opts.TitleOpts(title="高校数量后十名"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.render_notebook()
pie.render('高校数量后十名.html')
3.4 高校分布热力图 geo
# 高校分布热力图
geo = Geo()
geo.add_schema(maptype="china")
geo.add("高校分布热力图", [list(z) for z in zip(data['name'].values.tolist(), data['counts'].values.tolist())],
type_=ChartType.HEATMAP)
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="全国高校热力图"),
)
geo.render_notebook()
geo.render('高校分布热力图.html')
3.5 各地区高校数量段位图 geo
# 各地区高校数量段位图
geo = Geo()
geo.add_schema(maptype="china")
geo.add("各地区高校数量段位图", [list(z) for z in zip(data['name'].values.tolist(), data['counts'].values.tolist())],
type_=ChartType.EFFECT_SCATTER)
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_piecewise=True, max_=150),
title_opts=opts.TitleOpts(title="各地区高校数量段位图"),
)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.render_notebook()
geo.render('各地区高校数量段位图.html')
3.6 高校质量分析985_211 pie bar
- 985
df_title = df_new[df_new['title'] != '——']
print(df_title['title'].value_counts())
df_985 = df_title[df_title['title'] == '211985']
site_counts_985 = df_985['site'].value_counts()
dict_site_985 = {'name': site_counts_985.index, 'counts': site_counts_985.values}
data_985 = pd.DataFrame(dict_site_985)
# 985高校排行
pie = Pie()
pie.add("", [list(z) for z in zip(data_985['name'].values.tolist(), data_985['counts'].values.tolist())],
radius=["30%", "75%"],
center=["40%", "50%"],
rosetype="radius")
pie.set_global_opts(
title_opts=opts.TitleOpts(title="985高校排行"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.render_notebook()
pie.render('985高校排行.html')
- 211
df_211 = df_title[df_title['title'] == '211']
site_counts_211 = df_211['site'].value_counts()
dict_site_211 = {'name': site_counts_211.index, 'counts': site_counts_211.values}
data_211 = pd.DataFrame(dict_site_211)
# 211高校排行
pie = Pie()
pie.add("", [list(z) for z in zip(data_211['name'].values.tolist(), data_211['counts'].values.tolist())],
radius=["30%", "75%"],
center=["40%", "50%"],
rosetype="radius")
pie.set_global_opts(
title_opts=opts.TitleOpts(title="211高校排行"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.render_notebook()
pie.render('211高校排行.html')
- 985 211
# 211 985 综合
df_985_211 = pd.concat([df_211, df_985], ignore_index=True)
site_counts_985_211 = df_985_211['site'].value_counts()
dict_site_985_211 = {'name': site_counts_985_211.index, 'counts': site_counts_985_211.values}
data_985_211 = pd.DataFrame(dict_site_985_211)
# 各城市高质量高校数量
bar = Bar()
bar.add_xaxis(data_985_211['name'].values.tolist())
bar.add_yaxis("", data_985_211['counts'].values.tolist())
bar.set_global_opts(
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-45)),
title_opts=opts.TitleOpts(title="各城市高质量高校数量", subtitle="统计高质量高校数量"),
datazoom_opts=opts.DataZoomOpts(),
)
bar.set_series_opts(itemstyle_opts={
"normal": {
"color": JsCode("""new echarts.graphic.LinearGradient(0, 0, 0, 1, [{
offset: 0,
color: 'rgba(0, 244, 255, 1)'
}, {
offset: 1,
color: 'rgba(0, 77, 167, 1)'
}], false)"""),
"barBorderRadius": [30, 30, 30, 30],
"shadowColor": 'rgb(0, 160, 221)',
}})
bar.render_notebook()
bar.render('各城市高质量高校数量.html')
3.7 高质量高校分布热力图 geo map
# 高质量高校分布热力图
geo = Geo()
geo.add_schema(maptype="china")
geo.add("高质量高校分布热力图", [list(z) for z in zip(data_985_211['name'].values.tolist(), data_985_211['counts'].values.tolist())],
type_=ChartType.HEATMAP)
#['北京', 30], ['上海', 12], ['江苏', 11],...]
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(max_=20),
title_opts=opts.TitleOpts(title="高质量高校分布热力图"),
)
geo.render_notebook()
geo.render('高质量高校分布热力图.html')
# 高质量高校分布热力图
map = Map()
map.add("高质量高校分布热力图", [list(z) for z in zip(data_985_211['name'].values.tolist(), data_985_211['counts'].values.tolist())],
)
map.set_global_opts(
visualmap_opts=opts.VisualMapOpts(max_=20),
title_opts=opts.TitleOpts(title="高质量高校分布热力图"),
)
map.render_notebook()
map.render('高质量高校分布热力图map.html')
3.8 地区高质量高校占比 liquid
北京高质量高校占比
data_985_211['rate']=data_985_211['counts'].values/data_985_211['counts'].sum()
# 北京高质量高校占比
liquid = Liquid()
liquid.add('', [data_985_211['rate'].values[0]])
liquid.set_global_opts(title_opts=opts.TitleOpts(title="北京高质量高校占比"))
liquid.render_notebook()
liquid.render('北京高质量高校占比.html')
北京上海江苏高质量高校占比
# 北京上海江苏高质量高校占比
liquid = Liquid()
liquid.add('', [sum(data_985_211['rate'].values[:3])])
liquid.set_global_opts(title_opts=opts.TitleOpts(title="北京上海江苏高质量高校占比"))
liquid.render_notebook()
liquid.render('北京上海江苏高质量高校占比.html')
占比前十城市高质量高校占比
# 占比前十城市高质量高校占比
liquid = Liquid()
liquid.add('', [sum(data_985_211['rate'].values[:11])])
liquid.set_global_opts(title_opts=opts.TitleOpts(title="占比前十城市高质量高校占比"))
liquid.render_notebook()
liquid.render('占比前十城市高质量高校占比.html')
3.9 高校类型、属性分析 pie
# 高校类型分析
df_type = df_new[df_new['type'] != '——']
df_type = df_type[df_type['type'] != '------']
df_type_counts = df_type['type'].value_counts()
dict_type_counts = {'name': df_type_counts.index, 'counts': df_type_counts.values}
data_type_counts = pd.DataFrame(dict_type_counts)
pie = Pie()
pie.add("", [list(z) for z in zip(data_type_counts['name'].values.tolist(), data_type_counts['counts'].values.tolist())],
radius=["30%", "75%"],
center=["40%", "50%"],
rosetype="radius")
pie.set_global_opts(
title_opts=opts.TitleOpts(title="高校类型排行"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.render_notebook()
pie.render('高校类型分析pie.html')
# 高校属性分析
df_nature = df_new[df_new['nature'] != '——']
df_nature = df_nature[df_nature['nature'] != '------']
df_nature_counts = df_nature['nature'].value_counts()
dict_nature_counts = {'name': df_nature_counts.index, 'counts': df_nature_counts.values}
data_nature_counts = pd.DataFrame(dict_nature_counts)
pie = Pie()
pie.add("", [list(z) for z in zip(data_nature_counts['name'].values.tolist(), data_nature_counts['counts'].values.tolist())],
)
pie.set_global_opts(
title_opts=opts.TitleOpts(title="高校属性排行"),
legend_opts=opts.LegendOpts(
type_="scroll", pos_left="80%", orient="vertical"
),
)
pie.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}: {d}%"))
pie.render_notebook()
pie.render('高校属性分析pie.html')
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
