python对月饼数据可视化

# 导包
import pandas as pd
import numpy as np
import re

# author：Dragon少年
# 导入爬取得到的数据
df = pd.read_csv("月饼.csv", encoding='utf-8-sig', header=None)
df.columns = ["商品名", "价格", "购买人数", "店铺", "地址"]
# 去除重复的数据
df.drop_duplicates(inplace=True)
print(df.shape)
# 删除购买人数0的记录
df['购买人数'] = df['购买人数'].replace(np.nan,'0人付款')

df['num'] = [re.findall(r'(\d+\.{0,1}\d*)', i)[0] for i in df['购买人数']]  # 提取数值
df['num'] = df['num'].astype('float')  # 转化数值型
# 提取单位（万）
df['unit'] = [''.join(re.findall(r'(万)', i)) for i in df['购买人数']]  # 提取单位（万）
df['unit'] = df['unit'].apply(lambda x:10000 if x=='万' else 1)
# 计算销量
df['销量'] = df['num'] * df['unit']

# 删除没有发货地址的店铺数据 获取省份
df = df[df['地址'].notna()]
df['省份'] = df['地址'].str.split(' ').apply(lambda x:x[0])
# 删除多余的列
df.drop(['购买人数', '地址', 'num', 'unit'], axis=1, inplace=True)
# 重置索引
df = df.reset_index(drop=True)
df.to_csv('月饼清洗数据.csv')

# 导入包
from pyecharts.charts import Bar
from pyecharts import options as opts 

# 计算月饼总销量Top10的店铺
shop_top10 = df.groupby('店铺')['销量'].sum().sort_values(ascending=False).head(10)

# 绘制柱形图
bar1 = Bar(init_opts=opts.InitOpts(width='600px', height='450px')) 
bar1.add_xaxis(shop_top10.index.tolist())
bar1.add_yaxis('销量', shop_top10.values.tolist()) 
bar1.set_global_opts(title_opts=opts.TitleOpts(title='销量Top10店铺-Dragon少年'),
                     xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-30))) 
bar1.render("销量Top10店铺-Dragon少年.html")
bar1.render_notebook()

# 导入包
from pyecharts.charts import Bar
from pyecharts import options as opts 

# 计算销量top10月饼
shop_top10 = df.groupby('商品名')['销量'].sum().sort_values(ascending=False).head(10)

# 绘制柱形图
bar0 = Bar(init_opts=opts.InitOpts(width='750px', height='450px')) 
bar0.add_xaxis(shop_top10.index.tolist())
bar0.add_yaxis('销量', shop_top10.values.tolist()) 
bar0.set_global_opts(title_opts=opts.TitleOpts(title='销量Top10月饼-Dragon少年'),
                     xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-30))) 
bar0.render("销量Top10月饼-Dragon少年.html")
bar0.render_notebook()

from pyecharts.charts import Pie

def price_range(x): #按照淘宝推荐划分价格区间
    if x <= 50:
        return '50元以下'
    elif x <= 150:
        return '50-150元'
    elif x <= 500:
        return '150-500元'
    else:
        return '500元以上'

df['price_range'] = df['价格'].apply(lambda x: price_range(x)) 
price_cut_num = df.groupby('price_range')['销量'].sum() 
data_pair = [list(z) for z in zip(price_cut_num.index, price_cut_num.values)]
print(data_pair)


# 饼图
pie1 = Pie(init_opts=opts.InitOpts(width='750px', height='350px'))
# 内置富文本
pie1.add( 
        series_name="销量",
        radius=["35%", "55%"],
        data_pair=data_pair,
        label_opts=opts.LabelOpts(formatter='{b}—占比{d}%'),
)

pie1.set_global_opts(legend_opts=opts.LegendOpts(pos_left="left", pos_top='30%', orient="vertical"), 
                     title_opts=opts.TitleOpts(title='不同价格月饼销量占比-Dragon少年'))

pie1.render("不同价格月饼销量占比-Dragon少年.html")
pie1.render_notebook()

from pyecharts.charts import Map 

# 计算销量
province_num = df.groupby('省份')['销量'].sum().sort_values(ascending=False) 

# 绘制地图
map1 = Map(init_opts=opts.InitOpts(width='950px', height='600px'))
map1.add("", [list(z) for z in zip(province_num.index.tolist(), province_num.values.tolist())],
         maptype='china'
        ) 
map1.set_global_opts(title_opts=opts.TitleOpts(title='各省月饼销量分布-Dragon少年'),
                     visualmap_opts=opts.VisualMapOpts(max_=1500000)
                    )
map1.render("各省月饼销量分布-Dragon少年.html")
map1.render_notebook()