Day6. 实战案例解析

DataScience

发布于 2020-05-25 15:27:07

4660

发布于 2020-05-25 15:27:07

文章被收录于专栏：A2Data A2DataA2Data

在过去5天的学习中，我们对matplotlib和seaborn都有了一定的了解，并且可以绘制一系列图形。今天我们将讲几个关于pycharts的具体的案例，让大家对可视化有更深的了解。

1.地理坐标图

地理坐标图例类型有'scatter', 'effectScatter', 'heatmap'可选，所以我们分别画一下。

from pyecharts import Geo

data = [
    ("海门", 95), ("鄂尔多斯", 15), ("招远", 12), ("舟山", 12), ("齐齐哈尔", 14), ("盐城", 15),
    ("赤峰", 16), ("青岛", 18), ("乳山", 18), ("金昌", 19), ("泉州", 21), ("莱西", 21),
    ("日照", 21), ("胶南", 22), ("南通", 23), ("拉萨", 24), ("云浮", 24), ("梅州", 25),
    ("文登", 25), ("上海", 25), ("攀枝花", 25), ("威海", 25), ("承德", 25), ("厦门", 26),
    ("汕尾", 26), ("潮州", 26), ("丹东", 27), ("太仓", 27), ("曲靖", 27), ("烟台", 28),
    ("福州", 29), ("瓦房店", 30), ("即墨", 50), ("抚顺", 31), ("玉溪", 31), ("张家口", 31),
    ("阳泉", 31), ("莱州", 42), ("湖州", 32), ("汕头", 32), ("昆山", 33), ("宁波", 33),
    ("湛江", 33), ("揭阳", 44), ("荣成", 54), ("连云港", 35), ("葫芦岛", 35), ("常熟", 36),
    ("东莞", 36), ("河源", 36), ("淮安", 56), ("泰州", 36), ("南宁", 47), ("营口", 37),
    ("惠州", 37), ("江阴", 67), ("蓬莱", 57), ("韶关", 38), ("嘉峪关", 78), ("广州", 38),
    ("延安", 38), ("太原", 69), ("清远", 59), ("中山", 39), ("昆明", 79), ("寿光", 40),
    ("盘锦", 40), ("长治", 61), ("深圳", 51), ("珠海", 42), ("宿迁", 73), ("咸阳", 43),
    ("铜川", 44), ("平度", 64), ("佛山", 54), ("海口", 44), ("江门", 75), ("章丘", 45),
    ("肇庆", 46), ("大连", 67), ("临汾", 57), ("吴江", 47), ("石嘴山", 9), ("沈阳", 50),
    ("苏州", 50), ("茂名", 60), ("嘉兴", 41), ("长春", 51), ("胶州", 52), ("银川", 52),
    ("张家港", 52), ("三门峡", 53), ("锦州", 54), ("南昌", 54), ("柳州", 54), ("三亚", 54),
    ("自贡", 56), ("吉林", 56), ("阳江", 57), ("泸州", 57), ("西宁", 57), ("宜宾", 58),
    ("呼和浩特", 58), ("成都", 58), ("大同", 58), ("镇江", 59), ("桂林", 59), ("张家界", 59),
    ("宜兴", 59), ("北海", 60), ("西安", 61), ("金坛", 62), ("东营", 62), ("牡丹江", 63),
    ("遵义", 63), ("绍兴", 63), ("扬州", 64), ("常州", 64), ("潍坊", 65), ("重庆", 66),
    ("台州", 67), ("南京", 67), ("滨州", 70), ("贵阳", 71), ("无锡", 71), ("本溪", 71),
    ("克拉玛依", 72), ("渭南", 72), ("马鞍山", 72), ("宝鸡", 72), ("焦作", 75), ("句容", 75),
    ("北京", 79), ("徐州", 79), ("衡水", 80), ("包头", 80), ("绵阳", 80), ("乌鲁木齐", 84),
    ("枣庄", 84), ("杭州", 84), ("淄博", 85), ("鞍山", 86), ("溧阳", 86), ("库尔勒", 86),
    ("安阳", 90), ("开封", 90), ("济南", 92), ("德阳", 93), ("温州", 95), ("九江", 96),
    ("邯郸", 98), ("临安", 99), ("兰州", 99), ("沧州", 100), ("临沂", 103), ("南充", 104),
    ("天津", 105), ("富阳", 106), ("泰安", 112), ("诸暨", 112), ("郑州", 113), ("哈尔滨", 114),
    ("聊城", 116), ("芜湖", 117), ("唐山", 119), ("平顶山", 119), ("邢台", 119), ("德州", 120),
    ("济宁", 120), ("荆州", 127), ("宜昌", 130), ("义乌", 132), ("丽水", 133), ("洛阳", 134),
    ("秦皇岛", 136), ("株洲", 143), ("石家庄", 147), ("莱芜", 148), ("常德", 152), ("保定", 153),
    ("湘潭", 154), ("金华", 157), ("岳阳", 169), ("长沙", 175), ("衢州", 177), ("廊坊", 193),
    ("菏泽", 194), ("合肥", 229), ("武汉", 273), ("大庆", 279)]

geo = Geo("全国主要城市空气质量", "data from pm2.5", title_color="b",
          title_pos = "center", width = 1200,
          height = 600, background_color = '#404a59')

attr, value = geo.cast(data)

geo.add("", attr, value, visual_range=[0, 200], visual_text_color="#fff",
        symbol_size = 15, is_visualmap = True)
        
geo.render()

上面为默认的“scatter”类型，下面我们画一下'effectScatter'类型

attr, value = geo.cast(data)
geo.add("", attr, value, type="effectScatter", is_random=True, effect_scale=5)
geo.render("effect.html")

下面画一下 'headmap'类型，这是非常常用的一种类型。

geo.add("", attr, value, type="heatmap", is_visualmap=True, visual_range=[0, 300],
        visual_text_color='#fff')
geo.render("headmap.html")

2.地理坐标系线图

适用于分析数据出行

from pyecharts import GeoLines, Style
style = Style(title_top="#fff",title_pos = "center",width=1200,height=600,background_color="#404a59")
style_geo = style.add(is_label_show=True,line_curve=0.2,line_opacity=0.6,legend_text_color="#eee",
    legend_pos="right",geo_effect_symbol="plane",geo_effect_symbolsize=15,label_color=['#a6c84c', '#ffa022', '#46bee9'],
    label_pos="right",label_formatter="{b}",label_text_color="#eee",)
data_guangzhou = [
    ["广州", "上海"],
    ["广州", "北京"],
    ["广州", "呼和浩特"],
    ["广州", "太原"],
    ["广州", "长沙"],
    ["广州", "吐鲁番"]
]
geolines = GeoLines("GeoLines 示例", **style.init_style)
geolines.add("从广州出发", data_guangzhou, **style_geo)
geolines.render()

3.关系图

关系图是用于展现节点以及节点之间的关系的一种图，顾名思义，它用以分析关系最为适合，比如微博转发关系，文章引用关系等。

from pyecharts import Graph

nodes = [{"name": "a", "symbolSize": 10},
         {"name": "b", "symbolSize": 20},
         {"name": "c", "symbolSize": 30},
         {"name": "d", "symbolSize": 40},
         {"name": "e", "symbolSize": 50},
         {"name": "f", "symbolSize": 40},
         {"name": "g", "symbolSize": 30},
         {"name": "h", "symbolSize": 20}]
links = []
for i in nodes:
    for j in nodes:
        links.append({"source": i.get('name'), "target": j.get('name')})
graph = Graph("关系图-环形布局示例")
graph.add("", nodes, links, is_label_show=True,
          graph_repulsion=8000, graph_layout='circular',
          label_text_color=None)
graph.render("graph.html")

4.词云

from pyecharts import WordCloud

name = [
    '上善若水', '醉梦浮生', '映琴', '拾年', 'Kelley',
    'B Mn', '梁鹏飞', '阿牛哥', '少年风', '花酱学姐', '大枫学姐',
    '助教Shon', '困而弥坚', '不疯魔不成活', '练十七', 'Kylon',
    '十二', '哈喽哈喽～', '归途', 'wt']
value = [
    10000, 6181, 4386, 4055, 2467, 2244, 1898, 1484, 1112,
    965, 847, 582, 555, 550, 462, 366, 360, 282, 273, 265]
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("", name, value, word_size_range=[20, 100])
wordcloud.render("wordcloud.html")

5.关于pyecharts的更多案例

#coding=utf-8
from __future__ import unicode_literals

#首先来我的绘制第一个图表

from pyecharts import Bar

bar = Bar("我的第一个图表","这里是一个副标题")
bar.add("服装",["A","B","C","D","E","F"],[15,18,35,66,6,88])
#bar.print_echarts_options() # 该行只为了打印配置项，方便调试时使用
bar.render() #生成本地 HTML 文件
bar

·add()

主要方法，用于添加图表的数据和设置各种配置项

·print_echarts_options()

打印输出图表的所有配置项

·render()

默认将会在根目录下生成一个render.html的文件,

支持path参数，设置文件保存位置。

例如：render(r"e:\my_first_chart.html"),文件用浏览器打开

·Note：

可以按右边的下载按钮将图片下载到本地，如果想要提供更多实用工具按钮，请在add()中设置is_more_utils 为True

图形绘制过程

步骤描述代码示例备注

1 实例一个具体类型图表的对象 chart = FooChart()

2 为图表添加通用的配置，如主题 chart.use_theme()

3 为图表添加特定的配置 geo.add_coordinate()

4 添加数据及配置项 chart.add()5 生成本地文件(html/svg/jpeg/png/pdf/gif）chart.render() 参考数据解析与导入篇

# note ：使用Pandas & Numpy 时，整数类型请确保为int， 而不是 numpy.int32

#当然你可以采用更加酷炫的方式，使用jupyter notebook 来展示图表，matplotib有的，
# pyecharts 也会有的

#Note :从v0.1.9.2版本开始，废弃 render_notebook() 方法，现在已采用更加pythonic的做法。
#直接调用本身实例就可以了。

#EG 案例
from pyecharts import Bar

attr = ["{}月".format(i) for i in range(1,13)]
v1 = [2.0,4.9,7.0,23.2,25.6,76.7,135.6,162.2,32.6,20.0,6.4,3.3]
v2 = [2.6,5.9,9.0,26.4,28.7,70.7,175.6,182.2,48.7,18.8,6.0,2.3]

bar = Bar("柱状图示例")
bar.add("蒸发量",attr,v1,mark_line=["average"],mark_point=["max","min"])
bar.add("降水量",attr,v2,mark_line=["average"],mark_point=["max","min"])
bar

# 还有这样
from pyecharts import Pie

attr = ["衬衫","羊毛衫","雪纺衫","裤子","高跟鞋","袜子"]
v1 = [11,12,13,10,10,10]
v2 = [19,21,32,20,20,33]

pie= Pie("饼图-玫瑰图示例",title_pos='center',width=900)
pie.add("商品A",attr,v1,center=[25,50],is_random=True,redius=[30,75],rosetype='redius')
pie.add("商品B",attr,v2,center=[75,50],is_random=True,redius=[30,75],rosetype='area',is_legend_show=False,is_label_show=True)

pie

# 如果使用的是 自定义类，直接调用自定义类示例即可

from pyecharts import Bar,Line,Overlap

attr = ["A","B","C","D","E","F"]
v1 = [10,20,30,40,50,60]
v2 = [38,28,58,48,88,68]
bar =Bar("Line-Bar 示例")
bar.add("bar",attr,v1)
line = Line()
line.add("line",attr,v2)

overlap = Overlap()
overlap.add(bar)
overlap.add(line)

overlap