【spider】Yohobuy数据处理

对Yohobuy鞋靴类别商品的数据爬取见Yohobuy数据爬取

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['KaiTi']

df = pd.DataFrame(pd.read_csv('D:\shoes.csv',header = 0))
df.sort_values(["deal"],ascending = False)
dft10 = df[:10]
ts = pd.Series(dft10['deal'].values,index = dft10['title'])
plt.figure(figsize = (12,8))
ts.plot.bar(edgecolor='black', color='pink',fontsize=12)
plt.title('Yohobuy 价格最贵的鞋靴top10',size=15)
plt.xlabel('鞋靴型号',size=15)
plt.ylabel('商品标价',size=15)
plt.savefig('Yohobuy 价格最贵的鞋靴top10.png')

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['KaiTi']

df = pd.DataFrame(pd.read_csv('D:\shoes.csv',header = 0))
df_converse = df[df['brand']=='converse']
df_VANS = df[df['brand']=='VANS']
df_PUMA = df[df['brand']=='PUMA']
df_adidas = df[df['brand']=='adidas Originals']
df_NBA = df[df['brand']=='NBA']
df_Nike = df[df['brand']=='Nike']
df_UGG = df[df['brand']=='UGG']
df_Reebok = df[df['brand']=='Reebok']
ts0 = pd.Series(df['deal'].values)
ts1 = pd.Series(df_converse['deal'].values)
ts2 = pd.Series(df_VANS['deal'].values)
ts3 = pd.Series(df_PUMA['deal'].values)
ts4 = pd.Series(df_adidas['deal'].values)
ts5 = pd.Series(df_NBA['deal'].values)
ts6 = pd.Series(df_Nike['deal'].values)
ts7 = pd.Series(df_UGG['deal'].values)
ts8 = pd.Series(df_Reebok['deal'].values)
plt.figure(figsize = (12,8))
ts0.plot.kde(legend=True,label='全品类',xlim=(0,2500),ylim=(0,0.01),fontsize=15)
ts1.plot.kde(legend=True,label='converse')
ts2.plot.kde(legend=True,label='VANS')
ts3.plot.kde(legend=True,label='PUMA')
ts4.plot.kde(legend=True,label='adidas Originals')
ts5.plot.kde(legend=True,label='NBA')
ts6.plot.kde(legend=True,label='Nike')
ts7.plot.kde(legend=True,label='UGG')
ts8.plot.kde(legend=True,label='Reebok')
plt.legend(prop={'size':15})
plt.title('主流品牌价格区间kde比对图',size=15)
plt.xlabel('鞋靴价格',size=15)
plt.ylabel('density',size=15)
plt.savefig('主流品牌价格区间kde比对图.png')

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import math

plt.rcParams['font.sans-serif'] = ['KaiTi']

df = pd.DataFrame(pd.read_csv('D:\shoes.csv',header = 0))
counts = (df['deal']).value_counts()
counts1 = counts[:20].sort_values(ascending = True)
print(counts1)
plt.figure(figsize = (12,8))
counts1.plot.barh(edgecolor='#E6E6E6', color='#EE6666',fontsize=15)
plt.xlabel('商品数量',size=15)
plt.ylabel('商品标价',size=15)
plt.title('Yohobuy 商家最爱给出的商品标价top20',size=15)
plt.savefig('Yohobuy 商家最爱给出的商品标价top20.png')

1280     53
539      55
1299     56
680      57
469      65
1190     65
569      65
790      75
339      81
1199     97
299      98
369     105
899     115
999     116
1099    123
499     136
699     166
399     179
799     182
599     183
Name: deal, dtype: int64

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['KaiTi']

df = pd.DataFrame(pd.read_csv('D:\shoes.csv',header = 0))
counts = df['brand'].value_counts()
plt.figure(figsize = (12,8))
counts.T.plot.pie(fontsize=12)
plt.xlabel('品牌名称',size=15)
plt.title('Yohobuy 鞋靴品牌商品数量比例图',size=15)
plt.savefig('Yohobuy 鞋靴品牌商品数量比例图.png')