Domine rapidamente os gráficos da ferramenta de visualização de dados

Introdução aos gráficos da biblioteca de visualização de dados Python

Artigo Diretório

Ferramentas de desenho:

Use a biblioteca de pyecharts de código aberto do Baidu

Você pode consultar seu documento
oficial pyecharts documento oficial

Pré-processamento de dados

Instalação do módulo

pip install pyecharts

Módulo de importação

import pandas as pd
df = pd.read_excel('taobao.xlsx')

Deduplicação

# 删除行完全一样的值
df.drop_duplicates(inplace=True)
# 删除列重复的值
df.drop_duplicates(subset=['列名','列名'])

Processando localização geográfica

location_list = []
for location in df['location']:
    location = location.split(' ')[0]
    location_list.append(location)
df['location'] = location_list

Vendas de processo

sales_list = []
for sale in df['sales']:
    sale = sale[:-3].replace('+', '')
    if '万' in sale:
        sale = int(float(sale.replace('万', '')) * 10000)
    sales_list.append(sale)

df['sales'] = sales_list

Faça um gráfico

### Importar módulos

import jieba
import pandas as pd
from pyecharts import options as opts
from pyecharts.globals import ThemeType
from pyecharts.globals import SymbolType
from pyecharts.charts import Pie, Bar, Map, WordCloud, Page

2.1 Word Cloud

Dois métodos:

pyechartsNuvem de palavras integrada
wordcloud Módulo gera nuvem de palavras (recomendado

método um:

stop_words_txt = 'stop_words.txt'
# 载入停用词,即过滤词
jieba.analyse.set_stop_words(stop_words_txt)
# TextRank 关键词抽取，只获取固定词性
# topK为返回权重最大的关键词，默认值为20
# withWeight为返回权重值，默认为False
keywords_count_list = jieba.analyse.textrank(' '.join(df1.comment), topK=100, withWeight=True)
print(keywords_count_list)

word_cloud = (
    WordCloud()
        .add("", keywords_count_list, word_size_range=[5, 50], 
             shape=SymbolType.TRIANGLE,
            )
        .set_global_opts(title_opts=opts.TitleOpts(title="这里输入标题"))
)
# 这句话是渲染成一个html文件到当前文件夹下面
#     word_cloud.render('WordCloud.html')

Método 2: (recomendado, pode ser personalizado

pip install wordcloud

import jieba
import numpy as np
import matplotlib.pyplot as plt

from PIL import Image
from wordcloud import WordCloud


# 打开文本
# text = open('1.txt',encoding='utf-8').read()
 
# 中文分词
text = ' '.join(jieba.cut(text))
 
# 生成对象
mask = np.array(Image.open("input_picture"))
wc = WordCloud(mask=mask,font_path='C:\Windows\Fonts\SimHei.ttf',mode='RGBA').generate(text)
 
# 显示词云
# plt.imshow(wc, interpolation='bilinear')
# plt.axis("off")
# plt.show()
 
# 保存到文件
wc.to_file('output_picture')

2.2 Histograma

Histograma geral:

bar = (
    Bar()
    .add_xaxis(Faker.days_attrs)
    .add_yaxis("商家A", Faker.days_values)
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Bar-DataZoom（slider+inside）"),
    )
#     .render("bar_datazoom_both.html")
)

Histograma horizontal:

.reversal_axis()
.set_series_opts(label_opts=opts.LabelOpts(position="right"))

Histograma do controle deslizante:

datazoom_opts=[opts.DataZoomOpts()]

2.3 Gráfico de pizza

Os dados vêm de:standard_goods_comments.xlsx

Use o copo para exibir aqui

[('B', 1909), ('C', 810), ('A', 696), ('D', 259)]

Copo de exibição de várias imagens:

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.commons.utils import JsCode


fn = """
    function(params) {
        if(params.name == 'other')
            return '\\n\\n\\n' + params.name + ' : ' + params.value + '%';
        return params.name + ' : ' + params.value + '%';
    }
    """


def new_label_opts():
    return opts.LabelOpts(formatter=JsCode(fn), position="center")


pie = (
    Pie()
    .add(
        "",
        [['A_cup', round(696/total_cup, 2)*100],['other',round(1 - 696/total_cup, 2)*100]],
        center=["20%", "30%"],
        radius=[60, 80],
        label_opts=new_label_opts(),
    )
    .add(
        "",
        [['B_cup', round(1909/total_cup, 2)*100],['other',round(1 - 1909/total_cup, 2)*100]],
        center=["55%", "30%"],
        radius=[60, 80],
        label_opts=new_label_opts(),
    )
    .add(
        "",
        [['C_cup', round(810/total_cup, 2)*100],['other',round(1 - 810/total_cup, 2)*100]],
        center=["20%", "70%"],
        radius=[60, 80],
        label_opts=new_label_opts(),
    )
    .add(
        "",
        [['D_cup', round(259/total_cup * 100, 1)],['other',round(1 - 259/total_cup, 2)*100]],
        center=["55%", "70%"],
        radius=[60, 80],
        label_opts=new_label_opts(),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Cup-多饼图"),
        legend_opts=opts.LegendOpts(
            type_="scroll", pos_top="20%", pos_left="80%", orient="vertical"
        ),
    )
#     .render("mutiple_pie.html")
)

2.3.1 Diagrama de rosa

Exibição da epidemia:

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker


v = Faker.choose()
pie = (
    Pie()
    .add(
        "",
        [list(z) for z in zip(v, list(range(10,80,10)))],
        radius=["30%", "75%"],
        center=["25%", "50%"],
        rosetype="radius",
        label_opts=opts.LabelOpts(is_show=False),
    )
    .add(
        "",
        [list(z) for z in zip(v,list(range(10,80,10))[::-1])],
        radius=["30%", "75%"],
        center=["75%", "50%"],
        rosetype="area",
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="Pie-玫瑰图示例"))
)

2.4 Mapa

from pyecharts import options as opts
from pyecharts.charts import Map
from pyecharts.faker import Faker

map = (
    Map()
    .add("店铺数量",[['广东',100],['广西',100],['湖南',19,]], "china")
    .set_global_opts(
        title_opts=opts.TitleOpts(title="商家店铺地址分布图"),
        visualmap_opts=opts.VisualMapOpts(max_=200),
    )
)

2.5 Diagrama de pólo aquático

o clima:

from pyecharts import options as opts
from pyecharts.charts import Liquid

liquid = (
    Liquid()
    .add("lq", [0.45,0.5])	
 	# 第一个值为显示的值，第二个值为水的分量
    .set_global_opts(title_opts=opts.TitleOpts(title="今日湿度"))
    .render("liquid_base.html")
)

Gráfico integrado

Integração de vários gráficos

Page.save_resize_html('page_draggable_layout.html',cfg_file= 'chart_config.json')

Documentos de referência:

Leitura recomendada: