-
Pyecharts | 历年全国各地民政局登记数据分析+可视化
数据集下载：数据集
运行工具：jupyter notebook1. 导入模块
升级 pyecharts 包
可视化部分需要用到 pyecharts==1.9.0
已安装其他低版本的需要升级，如果未安装过pyecharts，直接pip安装就是最新版本!pip install --upgrade pyecharts- 1
import pandas as pd from pyecharts.charts import * from pyecharts import options as opts from pyecharts.globals import ThemeType from pyecharts.globals import SymbolType from pyecharts.commons.utils import JsCode from pyecharts.charts import Line,Bar,Page,Map- 1
- 2
- 3
- 4
- 5
- 6
- 7
2. 读取数据
2.1 结婚登记数据
df_marry = pd.read_csv('/home/mw/input/202108196091/结婚登记(万对).csv', encoding='gb2312') df_marry.head()- 1
- 2
2.2 离婚登记数据
df_divorce = pd.read_csv('/home/mw/input/202108196091/离婚登记(万对).csv', encoding='gb2312') df_divorce.head()- 1
- 2
2.3 查看是否有缺失值
df_marry.isnull().any()- 1
结婚登记数据没有缺失值。df_divorce.isnull().any()- 1
离婚登记数据没有缺失值。2.4 新增列：结婚占比、离婚占比、离结率
# 2019年各地区离结率 df_tmp = pd.DataFrame() df_tmp['地区'] = df_marry['地区'] df_tmp['结婚'] = df_marry['2019年'] df_tmp['离婚'] = df_divorce['2019年'] df_tmp['结婚占比'] = round(df_marry['2019年']*100 /(df_marry['2019年'] + df_divorce['2019年']), 2) df_tmp['离婚占比'] = round(df_divorce['2019年']*100 /(df_marry['2019年'] + df_divorce['2019年']), 2) df_tmp['离结率'] = round(df_tmp['离婚占比'] /(df_tmp['结婚占比']), 2) df_tmp.head()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
3. 可视化
3.1 2019年各地区结婚离婚占比
# 阴影样式 itemstyle={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 阴影颜色 'shadowBlur': 5, # 阴影大小 'shadowOffsetY': 2, # Y轴方向阴影偏移 'shadowOffsetX': 2, # x轴方向阴影偏移 'borderColor': '#fff' } } area = df_tmp['地区'].values.tolist() marry_count = df_tmp['结婚占比'].values.tolist() divorce_count = df_tmp['离婚占比'].values.tolist() b1 = ( Bar( init_opts=opts.InitOpts( width='800px', height='600px', ) ) .add_xaxis(area) .add_yaxis('结婚占比', marry_count, stack='stack1',itemstyle_opts=opts.ItemStyleOpts(color='#ed1941')) .add_yaxis('离婚占比', divorce_count, stack='stack1',itemstyle_opts=opts.ItemStyleOpts(color='#009ad6')) .set_series_opts( label_opts=opts.LabelOpts( is_show=True, position='inside' ) ) .set_global_opts( legend_opts=opts.LegendOpts( pos_right='10%', pos_top='2%', orient='horizontal', ), title_opts=opts.TitleOpts( title='2019年各地区结婚离婚占比', pos_top='2%' ), ) .reversal_axis() ) b1.render_notebook()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
3.2 列数据逆序高亮
df_tmp = df_tmp.sort_values('离结率', ascending=False) df_tmp.style.bar(subset=['离结率'],color='#ed1941')- 1
- 2
3.3 离结率柱状图
sort_info = df_tmp.sort_values('离结率', ascending=True) b1 = ( Bar(init_opts=opts.InitOpts( width='800px', height='600px',)) .add_xaxis(list(sort_info['地区'])[-20:]) .add_yaxis('', sort_info['离结率'].values.tolist()[-20:], category_gap='30%', itemstyle_opts={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 阴影颜色 'shadowBlur': 5, # 阴影大小 'shadowOffsetY': 2, # Y轴方向阴影偏移 'shadowOffsetX': 2, # x轴方向阴影偏移 'borderColor': '#fff' } } ) .reversal_axis() .set_global_opts( xaxis_opts=opts.AxisOpts(is_show=False), yaxis_opts=opts.AxisOpts(is_show=False, axisline_opts=opts.AxisLineOpts(is_show=False), axistick_opts=opts.AxisTickOpts(is_show=False) ), title_opts=opts.TitleOpts( title='离结率 TOP20', pos_left='9%', pos_top='4%', title_textstyle_opts=opts.TextStyleOpts( color='#ed1941', font_size=16) ), visualmap_opts=opts.VisualMapOpts( is_show=False, max_=20, series_index=0, ), ) .set_series_opts( itemstyle_opts={ "normal": { "color": JsCode( """new echarts.graphic.LinearGradient(0, 0, 0, 1, [{ offset: 0, color: '#ed1941' }, { offset: 1, color: '#009ad6' }], false)""" ), "barBorderRadius": [30, 30, 30, 30], "shadowColor": "rgb(0, 160, 221)", } }, label_opts=opts.LabelOpts(position="insideLeft", font_size=10, vertical_align='middle', horizontal_align='left', font_weight='bold', formatter='{b}: {c}')) ) b1.render_notebook()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
print('全国共有{}个省市地区离结率超过50%，这已经是相当高了'.format(len(df_tmp[df_tmp['离结率'] > 0.5])))- 1
全国共有15个省市地区离结率超过50%，这已经是相当高了
离结率超过50%的城市：df_tmp[df_tmp['离结率'] > 0.5]['地区']- 1
3.4 天津历年结婚/离婚登记数据
可以自行查看自己所在城市数据，这里我用了离结率第一的天津市
# 线性渐变 color_js0 = """new echarts.graphic.LinearGradient(0, 1, 0, 0, [{offset: 0, color: '#FFFFFF'}, {offset: 1, color: '#ed1941'}], false)""" color_js1 = """new echarts.graphic.LinearGradient(0, 1, 0, 0, [{offset: 0, color: '#FFFFFF'}, {offset: 1, color: '#009ad6'}], false)""" city = '天津市' b2 = ( Bar() .add_xaxis(df_divorce.columns[1:].values.tolist()) .add_yaxis( series_name="结婚登记", y_axis=df_marry[df_marry['地区']==city].values[0][1:].tolist(), markpoint_opts=opts.MarkPointOpts( data=[ opts.MarkPointItem(type_="max", name="最大值"), opts.MarkPointItem(type_="min", name="最小值"), ] ), itemstyle_opts=opts.ItemStyleOpts(color=JsCode(color_js0)) ) .add_yaxis( series_name="离婚登记", y_axis=df_divorce[df_divorce['地区']=='北京市'].values[0][1:].tolist(), markpoint_opts=opts.MarkPointOpts( data=[ opts.MarkPointItem(type_="max", name="最大值"), opts.MarkPointItem(type_="min", name="最小值"), ] ), itemstyle_opts=opts.ItemStyleOpts(color=JsCode(color_js1)) ) .set_global_opts( title_opts=opts.TitleOpts(title=""), tooltip_opts=opts.TooltipOpts(trigger="axis"), xaxis_opts=opts.AxisOpts(name="年份",type_="category", boundary_gap=True, axisline_opts=opts.AxisLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(width=4, color='#DB7093')), axislabel_opts=opts.LabelOpts(rotate=45)), yaxis_opts=opts.AxisOpts( axislabel_opts=opts.LabelOpts(formatter="{value} /万对"), name=f'{city}历年结婚/离婚登记', is_scale=True, name_textstyle_opts=opts.TextStyleOpts(font_size=14,font_weight='bold',color='#FF1493'), splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(type_='dashed')), axisline_opts=opts.AxisLineOpts(is_show=False, linestyle_opts=opts.LineStyleOpts(width=2, color='#DB7093')) ), legend_opts=opts.LegendOpts(is_show=True, pos_top='2%', legend_icon='roundRect'), ) ) b2.render_notebook()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
3.5 2019年各地区离结率数据热力图
# 线性渐变 color_js = """new echarts.graphic.LinearGradient(0, 0, 1, 0, [{offset: 0, color: '#009ad6'}, {offset: 1, color: '#ed1941'}], false)""" df_tmp = df_tmp.replace('省', '', regex=True).replace('市', '', regex=True).replace('自治区', '', regex=True).replace('壮族', '', regex=True).replace('维吾尔', '', regex=True).replace('回族', '', regex=True) map_chart = Map(init_opts=opts.InitOpts(theme='light', width='800px', height='600px')) map_chart.add('离婚/结婚', [list(z) for z in zip(df_tmp['地区'].values.tolist(), df_tmp['离结率'].values.tolist())], maptype='china', is_map_symbol_show=False, itemstyle_opts={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 阴影颜色 'shadowBlur': 5, # 阴影大小 'shadowOffsetY': 0, # Y轴方向阴影偏移 'shadowOffsetX': 0, # x轴方向阴影偏移 'borderColor': '#fff' } } ) map_chart.set_global_opts( visualmap_opts=opts.VisualMapOpts( is_show=True, is_piecewise=True, min_ = 0, max_ = 1, split_number = 5, series_index=0, pos_top='70%', pos_left='10%', range_text=['离结率', ''], pieces=[ {'max':1.0, 'min':0.8, 'label':'0.8-1.0', 'color': '#990000'}, {'max':0.8, 'min':0.6, 'label':'0.6-0.8', 'color': '#CD5C5C'}, {'max':0.6, 'min':0.4, 'label':'0.4-0.6', 'color': '#F08080'}, {'max':0.4, 'min':0.2, 'label':'0.2-0.4', 'color': '#FFCC99'}, {'max':0.2, 'min':0.0, 'label':'0.0-0.2', 'color': '#FFE4E1'}, ], ), legend_opts=opts.LegendOpts(is_show=False), tooltip_opts=opts.TooltipOpts( is_show=True, trigger='item', formatter='{b}:{c}' ), title_opts=dict( text='2001-2019年各地区离结率', left='center', top='5%', textStyle=dict( color='#DC143C')) ) map_chart.render_notebook()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
3.6 历年全国结婚离婚登记趋势
df_marry.loc["总计"] =df_marry.apply(lambda x:x.sum()) df_divorce.loc["总计"] =df_divorce.apply(lambda x:x.sum()) df_marry.loc['总计','地区'] = '全国' df_divorce.loc['总计','地区'] = '全国' df_marry[df_marry['地区'] == '全国']- 1
- 2
- 3
- 4
- 5
df_divorce[df_marry['地区'] == '全国']- 1
# 背景色 background_color_js = """ new echarts.graphic.RadialGradient(0.3, 0.3, 0.8, [{offset: 0,color: '#f7f8fa'}, {offset: 1,color: '#cdd0d5'}]) """ # 线条样式 linestyle_dic = { 'normal': { 'width': 4, 'shadowColor': '#696969', 'shadowBlur': 10, 'shadowOffsetY': 10, 'shadowOffsetX': 10, } } l1 = ( Line(init_opts=opts.InitOpts(bg_color=JsCode(background_color_js))) .add_xaxis(xaxis_data=df_divorce.columns[1:][::-1]) .add_yaxis( series_name="结婚登记", y_axis=[round(i,2) for i in df_marry.loc["总计"].values.tolist()[1:]], symbol_size=8, is_smooth=True, color="#009ad6", ) .add_yaxis( series_name="离婚登记", y_axis=[round(i,2) for i in df_divorce.loc["总计"].values.tolist()[1:]], symbol_size=8, is_smooth=True, color="#ed1941", ) # 系列配置项 .set_series_opts(linestyle_opts=linestyle_dic, areastyle_opts=opts.AreaStyleOpts(opacity=0.6), label_opts=opts.LabelOpts(is_show=False), markline_opts=opts.MarkLineOpts(data=[opts.MarkLineItem(type_="average")]), markpoint_opts=opts.MarkPointOpts( data=[opts.MarkPointItem(type_="max"), opts.MarkPointItem(type_="min")], symbol_size=[65, 50], label_opts=opts.LabelOpts(position="inside", color="#fff", font_size=10) ), ) # 通用配置项 .set_global_opts( title_opts=opts.TitleOpts( title='历年全国结/离婚登记趋势', pos_top='2%', title_textstyle_opts=opts.TextStyleOpts(color='#4169E1', font_size=20)), tooltip_opts=opts.TooltipOpts(trigger="axis"), xaxis_opts=opts.AxisOpts(name="",type_="category", boundary_gap=True, axisline_opts=opts.AxisLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(width=2, color='#DB7093')), axislabel_opts=opts.LabelOpts(rotate=45)), yaxis_opts=opts.AxisOpts( axislabel_opts=opts.LabelOpts(formatter="{value} /万对"), is_scale=True, name_textstyle_opts=opts.TextStyleOpts(font_size=12,font_weight='bold',color='#FF1493'), splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(type_='dashed')), axisline_opts=opts.AxisLineOpts(is_show=False, linestyle_opts=opts.LineStyleOpts(width=2, color='#DB7093')) ), # 图例样式 legend_opts=opts.LegendOpts(is_show=True, pos_right='1%', pos_top='2%',legend_icon='roundRect'), ) ) l1.render_notebook()- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
总结
1.结婚登记数量前五地区：河南、广东、四川、江苏、安徽
2.离婚登记数量前五地区：河南、四川、江苏、山东、河北
3.全国结婚登记数量从2007年开始出现持续下降趋势
4.北方地区离结率较南方地区高出不少
待续。。 -
相关阅读:
Matplotlib格式化轴
cf1693C. Keshi in Search of AmShZ（div1）【最短路，反向建图】
基于javaweb的社区养老服务管理系统
关于android studio 新建项目 是否勾选 use legacy android.support libraries
CTFhub-RCE-综合过滤练习
软件架构设计(三) B/S架构风格-层次架构（一）
【微服务】SpringCloud中Ribbon的轮询(RoundRobinRule)与重试(RetryRule)策略
枚举
ssm基于微信小程序的学习资料销售平台+ssm+uinapp+Mysql+计算机毕业设计
Linux的目录管理
- 原文地址：https://blog.csdn.net/weixin_46043195/article/details/125438527