# 導(dǎo)包
import pandas as pd
import numpy as np
import re

# author：Dragon少年
# 導(dǎo)入爬取得到的數(shù)據(jù)
df = pd.read_csv("月餅.csv", encoding='utf-8-sig', header=None)
df.columns = ["商品名", "價格", "購買人數(shù)", "店鋪", "地址"]
# 去除重復(fù)的數(shù)據(jù)
df.drop_duplicates(inplace=True)
print(df.shape)
# 刪除購買人數(shù)0的記錄
df['購買人數(shù)'] = df['購買人數(shù)'].replace(np.nan,'0人付款')

df['num'] = [re.findall(r'(\d+\.{0,1}\d*)', i)[0] for i in df['購買人數(shù)']]  # 提取數(shù)值
df['num'] = df['num'].astype('float')  # 轉(zhuǎn)化數(shù)值型
# 提取單位（萬）
df['unit'] = [''.join(re.findall(r'(萬)', i)) for i in df['購買人數(shù)']]  # 提取單位（萬）
df['unit'] = df['unit'].apply(lambda x:10000 if x=='萬' else 1)
# 計算銷量
df['銷量'] = df['num'] * df['unit']

# 刪除沒有發(fā)貨地址的店鋪數(shù)據(jù) 獲取省份
df = df[df['地址'].notna()]
df['省份'] = df['地址'].str.split(' ').apply(lambda x:x[0])
# 刪除多余的列
df.drop(['購買人數(shù)', '地址', 'num', 'unit'], axis=1, inplace=True)
# 重置索引
df = df.reset_index(drop=True)
df.to_csv('月餅清洗數(shù)據(jù).csv')

# 導(dǎo)入包
from pyecharts.charts import Bar
from pyecharts import options as opts 

# 計算月餅總銷量Top10的店鋪
shop_top10 = df.groupby('店鋪')['銷量'].sum().sort_values(ascending=False).head(10)

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

# 導(dǎo)入包
from pyecharts.charts import Bar
from pyecharts import options as opts 

# 計算銷量top10月餅
shop_top10 = df.groupby('商品名')['銷量'].sum().sort_values(ascending=False).head(10)

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

from pyecharts.charts import Pie

def price_range(x): #按照淘寶推薦劃分價格區(qū)間
    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['價格'].apply(lambda x: price_range(x)) 
price_cut_num = df.groupby('price_range')['銷量'].sum() 
data_pair = [list(z) for z in zip(price_cut_num.index, price_cut_num.values)]
print(data_pair)


# 餅圖
pie1 = Pie(init_opts=opts.InitOpts(width='750px', height='350px'))
# 內(nèi)置富文本
pie1.add( 
        series_name="銷量",
        radius=["35%", "55%"],
        data_pair=data_pair,
        label_opts=opts.LabelOpts(formatter='—占比vvxyksv9kd%'),
)

pie1.set_global_opts(legend_opts=opts.LegendOpts(pos_left="left", pos_top='30%', orient="vertical"), 
                     title_opts=opts.TitleOpts(title='不同價格月餅銷量占比-Dragon少年'))

pie1.render("不同價格月餅銷量占比-Dragon少年.html")
pie1.render_notebook()

from pyecharts.charts import Map 

# 計算銷量
province_num = df.groupby('省份')['銷量'].sum().sort_values(ascending=False) 

# 繪制地圖
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='各省月餅銷量分布-Dragon少年'),
                     visualmap_opts=opts.VisualMapOpts(max_=1500000)
                    )
map1.render("各省月餅銷量分布-Dragon少年.html")
map1.render_notebook()