数据可视化（pyecharts 1.7.1）学习笔记——系列笔记（8）

八、多元变量及数据分布可视化

1、多元变量及数据分布常用图形

• 少数变量

  • 相关性——因果性，相似但不一定相同

• 多元变量

  • 多个变量直接存在正相关行、负相关行和弱相关性
  • 正相关：线条呈现平行
  • 负相关：线条一直交叉（顶端与底端相连）
  • 弱相关：方向不清晰

• 数据分布

  • 通过不同的图表(例如：散点图、柱状图)来观察数据分布

  • 箱线图

    

    • 上四分位数于下四分位数之间的范围称为四分位间距

    • 上/下边界
      $$上/下边界=上/下四分位数\pm 1\frac{1}{2}四分位间距$$

2、多元变量案例

• 导入可视化所需的模块

  import pandas as pd
  from pyecharts.globals import CurrentConfig, NotebookType
  CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
  
  import pyecharts.options as opts
  from pyecharts.globals import ThemeType
  

• 平行折线图

  from pyecharts.charts import Parallel
  # 导入数据
  df_final = pd.read_csv('data/beijing_AQI_2018.csv')
  df_final = df_final[['AQI', 'AQI_rank', 'PM', 'Quality_grade']].values.tolist()
  
  parallel = (
      Parallel(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_schema(
          [
              opts.ParallelAxisOpts(dim=0, name="AQI"),
              opts.ParallelAxisOpts(dim=1, name="AQI_rank"),
              opts.ParallelAxisOpts(dim=2, name="PM"),
              opts.ParallelAxisOpts(
                  dim=3,
                  name="Quality_grade",
                  type_="category",
                  data=["优", "良", "轻度污染", "中度污染", "重度污染", "严重污染"],
              ),
          ]
      )
      .add("parallel", df_final[:50])
      .set_global_opts(title_opts=opts.TitleOpts(title="北京空气质量平行折线图"))
  )
  parallel.load_javascript()
  parallel.render_notebook()
  

  

• 散点矩阵图

  import matplotlib.pyplot as plt
  import seaborn as sns
  # 数据准备
  iris = pd.read_csv('data/iris.csv')
  # 用Seabron画成对关系
  sns.pairplot(iris, hue='species')
  plt.show()
  

  

3、数据分布案例

• 直方图
• 箱线图
• 多个时间序列图

4、分类数据可视化实验

• 实验环境

  • python=3.7.6
  • pyecharts=1.7.1
  • jupyterlab=1.2.6

• 2018北京AQI全年走势图

  from pyecharts.charts import Line
  df = pd.read_csv('data/beijing_AQI_2018.csv')
  attr = df['Date'].values.tolist()
  v1 = df['AQI'].values.tolist()
  
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(attr)
      .add_yaxis("AQI值", v1,
                 markline_opts=opts.MarkLineOpts(data=[opts.MarkLineItem(type_='average')]),
                 markpoint_opts=opts.MarkPointOpts(data=[opts.MarkPointItem(type_='max'),
                                                        opts.MarkPointItem(type_='min')])
                 )
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京AQI全年走势图'))
  )
  line.render_notebook()
  

  

• 2018北京PM2.5全年走势图

  v1 = df['PM'].values.tolist()
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(attr)
      .add_yaxis("PM2.5值", v1,
                 markline_opts=opts.MarkLineOpts(data=[opts.MarkLineItem(type_='average')]),
                 markpoint_opts=opts.MarkPointOpts(data=[opts.MarkPointItem(type_='max'),
                                                        opts.MarkPointItem(type_='min')])
                 )
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京PM2.5全年走势图'))
  )
  line.render_notebook()
  

  

• 2018年北京月均AQI走势图

  import numpy as np
  
  dom = df[['Date', 'AQI']]
  list1 = []
  for j in dom['Date']:
      time = j.split('/')[1]
      list1.append(time)
  df['month'] = list1
  
  month_message = df.groupby(['month'])
  month_com = month_message['AQI'].agg(['mean'])
  month_com.reset_index(inplace=True)
  month_com_last = month_com.sort_index()
  
  attr = ['{}'.format(str(i) + '月') for i in range(1, 13)]
  v1 = np.array(month_com_last['mean'])
  v1 = [int(i) for i in v1]
  
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(attr)
      .add_yaxis("AQI月均值", v1,
                 markpoint_opts=opts.MarkPointOpts(data=[opts.MarkPointItem(type_='max'),
                                                        opts.MarkPointItem(type_='min')])
                 )
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京月均AQI走势图'))
  )
  line.render_notebook()
  

  

• 2018年北京月均PM2.5走势图

  dom = df[['Date', 'PM']]
  list1 = []
  for j in dom['Date']:
      time = j.split('/')[1]
      list1.append(time)
  df['month'] = list1
  
  month_message = df.groupby(['month'])
  month_com = month_message['PM'].agg(['mean'])
  month_com.reset_index(inplace=True)
  month_com_last = month_com.sort_index()
  
  attr = ['{}'.format(str(i) + '月') for i in range(1, 13)]
  v1 = np.array(month_com_last['mean'])
  v1 = [int(i) for i in v1]
  
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(attr)
      .add_yaxis("PM2.5月均值", v1,
                 markpoint_opts=opts.MarkPointOpts(data=[opts.MarkPointItem(type_='max'),
                                                        opts.MarkPointItem(type_='min')])
                 )
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京月均PM2.5走势图'))
  )
  line.render_notebook()
  

  

• 2018年北京季度AQI箱型图

  from pyecharts.charts import Boxplot
  
  dom = df[['Date', 'AQI']]
  data = [[], [], [], []]
  dom1, dom2, dom3, dom4 = data
  for i, j in zip(dom['Date'], dom['AQI']):
      time = i.split('/')[1]
      if time in ['1', '2', '3']:
          dom1.append(j)
      elif time in ['4', '5', '6']:
          dom2.append(j)
      elif time in ['7', '8', '9']:
          dom3.append(j)
      else:
          dom4.append(j)
  
  boxplot = Boxplot(init_opts=opts.InitOpts(theme=ThemeType.DARK))
  boxplot = (
      boxplot.add_xaxis(['第一季度', '第二季度', '第三季度', '第四季度'])
      .add_yaxis("", boxplot.prepare_data([dom1, dom2, dom3, dom4]))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京季度AQI箱型图'))
  )
  boxplot.render_notebook()
  

  

• 2018年北京季度PM2.5箱型图

  dom = df[['Date', 'PM']]
  data = [[], [], [], []]
  dom1, dom2, dom3, dom4 = data
  for i, j in zip(dom['Date'], dom['PM']):
      time = i.split('/')[1]
      if time in ['1', '2', '3']:
          dom1.append(j)
      elif time in ['4', '5', '6']:
          dom2.append(j)
      elif time in ['7', '8', '9']:
          dom3.append(j)
      else:
          dom4.append(j)
  
  boxplot = Boxplot(init_opts=opts.InitOpts(theme=ThemeType.DARK))
  boxplot = (
      boxplot.add_xaxis(['第一季度', '第二季度', '第三季度', '第四季度'])
      .add_yaxis("", boxplot.prepare_data([dom1, dom2, dom3, dom4]))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京季度PM2.5箱型图'))
  )
  boxplot.render_notebook()
  

  

• 2018年北京全年空气质量情况

  from pyecharts.charts import Pie
  
  rank_message = df.groupby(['Quality_grade'])
  rank_com = rank_message['Quality_grade'].agg(['count'])
  rank_com.reset_index(inplace=True)
  rank_com_last = rank_com.sort_values('count', ascending=False)
  
  attr = rank_com_last['Quality_grade']
  v1 = rank_com_last['count']
  
  pie = (
      Pie(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add("空气质量", [list(z) for z in zip(attr, v1)], radius=[130, 180], 
           tooltip_opts=opts.TooltipOpts(textstyle_opts=opts.TextStyleOpts(align='center'),
                                         formatter='{a}'+'
  '+'{b}: {c} ({d}%)'))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北京全年空气质量情况', pos_left='center'),
                       legend_opts=opts.LegendOpts(orient='vertical', pos_top='5%', pos_left='2%')
                      )
  )
  pie.render_notebook()
  

  

• 2018年北京PM2.5指数日历图

  import datetime
  import random
  from pyecharts.charts import Calendar
  
  dom = df[['Date', 'PM']]
  list1 = []
  for i, j in zip(dom['Date'], dom['PM']):
      time_list = i.split('/')
      time = datetime.date(int(time_list[0]), int(time_list[1]), int(time_list[2]))
      PM = int(j)
      list1.append([str(time), int(PM)])
  
  calendar=(
      Calendar(init_opts=opts.InitOpts(bg_color='white', height='300px'))
      .add("PM2.5", list1, calendar_opts=opts.CalendarOpts(range_="2018"))
      .set_global_opts(
          title_opts=opts.TitleOpts(title="2018年北京PM2.5指数日历图"),
          visualmap_opts=opts.VisualMapOpts(
              max_=max(dom['PM']),
              min_=min(dom['PM']),
              orient="horizontal",
              is_piecewise=True,
              pos_top="230px",
              pos_left="100px",
          )
      )
  )
  calendar.render_notebook()
  

  

• 2018年北上广深AQI全年走势图

  city_name = ['beijing', 'shanghai', 'guangzhou', 'shenzhen']
  cityes_AQI = []
  for i in range(4):
      filename = 'data/' + city_name[i] + '_AQI' + '_2018.csv'
      aqi_data = pd.read_csv(filename)
      
      get_data = aqi_data[['Date', 'AQI']]
      month_for_data = []
      for j in get_data['Date']:
          time = j.split('/')[1]
          month_for_data.append(time)
  #   获取每行数据的月份
      aqi_data['Month'] = month_for_data
  #   求每个月AQI平均值
      month_data = aqi_data.groupby(['Month'])
      month_AQI = month_data['AQI'].agg(['mean'])
      month_AQI.reset_index(inplace = True)
      month_AQI_average = month_AQI.sort_index()
  #   获取每个城市月均AQI的数据，转化为int数据类型
      month_AQI_data = np.array(month_AQI_average['mean'])
      month_AQI_data_int = [int(i) for i in month_AQI_data]
      cityes_AQI.append(month_AQI_data_int)
  months = ['{}'.format(str(i) + '月') for i in range(1, 13)]
  
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(months)
      .add_yaxis("北京", cityes_AQI[0])
      .add_yaxis("上海", cityes_AQI[1])
      .add_yaxis("广州", cityes_AQI[2])
      .add_yaxis("深圳", cityes_AQI[3])
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北上广深AQI全年走势图'), 
                       legend_opts=opts.LegendOpts(pos_top='8%')
                      )
  )
  line.render_notebook()
  

  

• 2018年北上广深PM2.5全年走势图

  cityes_PM = []
  for i in range(4):
      filename = 'data/' + city_name[i] + '_AQI' + '_2018.csv'
      pm_data = pd.read_csv(filename)
      
      get_data = pm_data[['Date', 'PM']]
      month_for_data = []
      for j in get_data['Date']:
          time = j.split('/')[1]
          month_for_data.append(time)
  #   获取每行数据的月份
      pm_data['Month'] = month_for_data
  #   求每个月PM平均值
      month_data = pm_data.groupby(['Month'])
      month_PM = month_data['PM'].agg(['mean'])
      month_PM.reset_index(inplace = True)
      month_PM_average = month_PM.sort_index()
  #   获取每个城市月均PM的数据，转化为int数据类型
      month_PM_data = np.array(month_PM_average['mean'])
      month_PM_data_int = [int(i) for i in month_PM_data]
      cityes_PM.append(month_PM_data_int)
  months = ['{}'.format(str(i) + '月') for i in range(1, 13)]
  
  line = (
      Line(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add_xaxis(months)
      .add_yaxis("北京", cityes_PM[0])
      .add_yaxis("上海", cityes_PM[1])
      .add_yaxis("广州", cityes_PM[2])
      .add_yaxis("深圳", cityes_PM[3])
      .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北上广深PM2.5全年走势图'), 
                       legend_opts=opts.LegendOpts(pos_top='8%')
                      )
  )
  line.render_notebook()
  

  

• 2018年北上广深全年空气质量情况

  v = []
  attrs = []
  for i in range(4):
      filename = 'data/' + city_name[i] + '_AQI' + '_2018.csv'
      df = pd.read_csv(filename)
      
      Quality_grade_message = df.groupby(['Quality_grade'])
      Quality_grade_com = Quality_grade_message['Quality_grade'].agg(['count'])
      Quality_grade_com.reset_index(inplace = True)
      Quality_grade_com_list = Quality_grade_com.sort_values('count', ascending=False)
  
      Quality_grade_array = np.array(Quality_grade_com_list['Quality_grade'])
      attrs.append(Quality_grade_array)
      Quality_grade_count = np.array(Quality_grade_com_list['count'])
      v.append(Quality_grade_count)
  months = ['{}'.format(str(i) + '月') for i in range(1, 13)]
  
  
  pie = (
      Pie(init_opts=opts.InitOpts(theme=ThemeType.DARK))
      .add("北京", [list(z) for z in zip(attrs[0].tolist(), v[0].tolist())], radius=[60,80], center=['20%', '30%'],
           label_opts=opts.LabelOpts(formatter="北京", position="center", font_size='25')
          )
      .add("上海", [list(z) for z in zip(attrs[1].tolist(), v[1].tolist())], radius=[60,80], center=['55%', '30%'],
           label_opts=opts.LabelOpts(formatter="上海", position="center", font_size='25')
          )
      .add("广州", [list(z) for z in zip(attrs[2].tolist(), v[2].tolist())], radius=[60,80], center=['20%', '70%'],
           label_opts=opts.LabelOpts(formatter="广州", position="center", font_size='25')
          )
      .add("深圳", [list(z) for z in zip(attrs[3].tolist(), v[3].tolist())], radius=[60,80], center=['55%', '70%'],
           label_opts=opts.LabelOpts(formatter="深圳", position="center", font_size='25')
          )
      .set_global_opts(title_opts=opts.TitleOpts(title='2018年北上广深全年空气质量情况'),
                       legend_opts=opts.LegendOpts(type_="scroll", pos_top="20%", pos_left="80%", orient="vertical")
                      )
  )
  pie.render_notebook()