python爬虫天猫商品数据及分析（2）

目的

对之前所获取的数据源进行数据分析操作

---

数据分析

---

一：商家地区分布图

通过读取本地数据源，获取其中省份的相关信息，绘制商家地区分布图，以html格式保存在本地，
浏览器打开可随鼠标移动动态显示地区分布商家数量

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
"""

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


import time
import pandas as pd


# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
#n = time.strftime("%Y-%m-%d") + "bak.CSV"
data = pd.read_csv(n)

total_data = {}
for item in data['省份']:
    #print(item)
    if item not in total_data:
        #向字典中更新每个省份默认0病例
        total_data.update({item:1})
    else:
        total_data[item]+=1

province=total_data.keys()
num=total_data.values()

list_data=zip(province,num)


#-------------------------------------------------------------------------------------
# 第二步：绘制全国商家地图
#-------------------------------------------------------------------------------------
def map_cn_disease_dis() -> Map:
    c = (
        Map()
        .add('中国', list_data, 'china')
        .set_global_opts(
            title_opts=opts.TitleOpts(title='全国商家店铺省份分布图'),
            visualmap_opts=opts.VisualMapOpts(is_show=True,
                                              split_number=6,
                                              is_piecewise=True,  # 是否为分段型
                                              pos_top='center',
                                              pieces=[
                                                   {'min': 1000, 'color': '#7f1818'},  #不指定 max
                                                   {'min': 400, 'max': 999},
                                                   {'min': 200, 'max': 399},
                                                   {'min': 100, 'max': 199},
                                                   {'min': 10, 'max': 99},
                                                   {'min': 0, 'max': 5} ],
                                              ),
        )
    )
    return c
#保存html文件
map_cn_disease_dis().render('../file/HTML/全国商家省份分布图.html')
print('文件保存完成')

结果显示

二 商品名称词云图

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import time
import pandas as pd


#----------------------------------------------读取数据----------------------------------------------
# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
#n = time.strftime("%Y-%m-%d") + "bak.CSV"
data = pd.read_csv(n)

#查看数据维度（行，列）
#print(data.shape)

#取出商品标题，区域，价格，销售四个维度的数据
#data=data[['商品名','价格','销售','省份']]



#对每个标题进行分词，使用jieba分词

#----------------------------------------------s商品名称分词处理----------------------------------------------
import jieba

title=data['商品名']

title_s=[]
#商品名分词
for line in title:
    title_cut=jieba.lcut(line)
    for i in title_cut:
        title_s.append(i)
#print(title_s)


# 导入停用此表
stopwords = [line.strip() for line in open('../file/TXT/StopWords.txt', 'r', encoding='utf-8').readlines()]
#print(stopwords)

# 剔除停用词
title_clean = []
for line in title_s:
        if line not in stopwords:
            title_clean.append(line)
#print(title_clean)


# 把列表 allwords_clean_dist 转为数据框
df_allwords_clean_dist = pd.DataFrame({
    'allwords': title_clean
})

#print(df_allwords_clean_dist)
#
# # 对过滤_去重的词语 进行分类汇总
word_count = df_allwords_clean_dist.allwords.value_counts().reset_index()
word_count.columns = ['word', 'count']
#x[0]: x[1] for x in word_count.head(100).values




#----------------------------------------------词云可视化----------------------------------------------

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import imageio as im
#尺寸大小
plt.figure(figsize=(8, 8))

# 读取图片，用于限制大小
pic = im.imread("../file/PNG/猫.PNG")
#print(pic)
w_c = WordCloud(font_path="simhei.ttf", background_color="black",mask=pic,max_font_size=100, margin=1)
wc = w_c.fit_words({
    x[0]: x[1] for x in word_count.head(100).values
})

#显示词云
plt.imshow(wc, interpolation='bilinear')
#坐标刻度隐藏
plt.axis("off")
plt.show()

# 保存到文件
wc.to_file('../file/PNG/01商品名称词云.PNG')

结果展示

三 卖点频率关系图

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/24'
"""
import time
import pandas as pd


#----------------------------------------------读取数据----------------------------------------------
# 读取数据
#n = time.strftime("%Y-%m-%d") + "bak.CSV"
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data_sales=data['销量']
#查看数据维度（行，列）
#print(data.shape)

#取出商品标题，区域，价格，销售四个维度的数据
#data=data[['商品名','价格','销售','省份']]



#对每个标题进行分词，使用jieba分词

#----------------------------------------------s商品名称分词处理----------------------------------------------
import jieba

title=data['商品名']

title_s=[]
#商品名分词
for line in title:
    title_cut=jieba.lcut(line)
    for i in title_cut:
        title_s.append(i)
#print(title_s)


# 导入停用此表
stopwords = [line.strip() for line in open('../file/TXT/StopWords.txt', 'r', encoding='utf-8').readlines()]
#print(stopwords)

# 剔除停用词
title_clean = []
for line in title_s:
        if line not in stopwords:
            title_clean.append(line)
#print(title_clean)


# 把列表 allwords_clean_dist 转为数据框
df_allwords_clean_dist = pd.DataFrame({
    'allwords': title_clean
})

#print(df_allwords_clean_dist)
#
# # 对过滤_去重的词语 进行分类汇总
word_count = df_allwords_clean_dist.allwords.value_counts().reset_index()
word_count.columns = ['word', 'count']
#print(word_count)


#------------------------------------------------------------------------------
# 第二步：绘制柱状图
#------------------------------------------------------------------------------
import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#获取数据

nume,sales=[],[]
for shopname,shopsales in word_count.head(30).values:
    nume.append(shopname)
    sales.append(shopsales)
# names = total_data.keys()
# # nums = total_data.values()
# # print(names)
# # print(nums)

# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(nume,sales, width=0.3, color='green')

# 设置标题
plt.xlabel("卖点", fontproperties='SimHei', size=12)
plt.ylabel("频率", fontproperties='SimHei', rotation=90, size=12)
plt.title("卖点频率关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(nume), fontproperties='SimHei', rotation=-40, size=10)
# 显示数字
for a, b in zip(list(nume), list(sales)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)

#保存并显示
plt.savefig('../file/PNG/02卖点频率关系图.png')
plt.show()

结果展示

四 品牌商品关系图

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'

"""
import time
import pandas as pd
import matplotlib.pyplot as plt

# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)

huawei,xioami,sanxing,apple,vivo,oppo,other=0,0,0,0,0,0,0
for item in data['商品名']:
    #print(item)
    if '华为' in item:
        huawei+=1
    elif '小米' in item:
        xioami+=1
    elif '三星' in item:
        sanxing+=1
    elif '苹果' in item:
        apple+=1
    elif 'vivo' in item:
        vivo+=1
    elif 'oppo' in item:
        oppo+=1
    else:
        other+=1

import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#获取数据

names = ['华为','小米','三星','苹果','VIVO','OPPO','其他']
nums = [huawei,xioami,sanxing,apple,vivo,oppo,other]


# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(names,nums, width=0.3, color='green')

# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("商品数量", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌商品关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(names), fontproperties='SimHei', rotation=-40, size=10)
# 显示数字
for a, b in zip(list(names), list(nums)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.savefig('../file/PNG/08品牌商品关系图.png')
plt.show()

结果展示

五 品牌市场占比

import time
import pandas as pd
import matplotlib.pyplot as plt

# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)

huawei,xioami,sanxing,apple,vivo,oppo,other=0,0,0,0,0,0,0
for item in data['商品名']:
    #print(item)
    if '华为' in item:
        huawei+=1
    elif '小米' in item:
        xioami+=1
    elif '三星' in item:
        sanxing+=1
    elif '苹果' in item:
        apple+=1
    elif 'vivo' in item:
        vivo+=1
    elif 'oppo' in item:
        oppo+=1
    else:
        other+=1
#获取数据

names = ['华为','小米','三星','苹果','VIVO','OPPO','其他']
nums = [huawei,xioami,sanxing,apple,vivo,oppo,other]
goods_sum=len(data['商品名'])

import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号


plt.pie(nums,labels=names,autopct='%.2f%%')
plt.title("品牌市场比重", fontproperties='SimHei', size=16)
plt.axis('equal')
plt.legend()

plt.savefig('../file/PNG/09品牌市场比重.png')
plt.show()

结果展示

六 品牌销量关系图

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/24'
"""
import time
import pandas as pd


# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)


huawei,xioami,sanxing,apple,vivo,oppo,other=0,0,0,0,0,0,0
for item,num in zip(data['商品名'],data['销量']):
    if '华为' in item:
        huawei+=num
    elif '小米' in item:
        xioami+=num
    elif '三星' in item:
        sanxing+=num
    elif '苹果' in item:
        apple+=num
    elif 'vivo' in item:
        vivo+=num
    elif 'oppo' in item:
        oppo+=num
    else:
        #print(item)
        other+=num



#------------------------------------------------------------------------------
# 第二步：绘制柱状图
#------------------------------------------------------------------------------
import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#获取数据

names = ['华为','小米','三星','苹果','VIVO','OPPO','其他']
nums = [huawei,xioami,sanxing,apple,vivo,oppo,other]


# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(names,nums, width=0.3, color='green')

# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("销量", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌-销量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(names), fontproperties='SimHei', rotation=-0, size=10)
# 显示数字
for a, b in zip(list(names), list(nums)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)

plt.grid(linestyle='-.')
plt.savefig('../file/PNG/10品牌销量关系图.png')
plt.show()

结果展示

七 品牌销售额对比

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/24'
"""
import time
import pandas as pd
import matplotlib.pyplot as plt

# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)

huawei,xioami,sanxing,apple,vivo,oppo,other=0,0,0,0,0,0,0
for item,price,num in zip(data['商品名'],data['价格'],data['销量']):
    #print(item,price)
    price=int(price)
    if '华为' in item:
        huawei+=price*num
    elif '小米' in item:
        xioami+=price*num
    elif '三星' in item:
        sanxing+=price*num
    elif '苹果' in item:
        apple+=price*num
    elif 'vivo' in item:
        vivo+=price*num
    elif 'oppo' in item:
        oppo+=price*num
    else:
        other+=price*num



#------------------------------------------------------------------------------
# 第二步：绘制柱状图
#------------------------------------------------------------------------------
import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#获取数据

names = ['华为','小米','三星','苹果','VIVO','OPPO','其他']
nums = [huawei,xioami,sanxing,apple,vivo,oppo,other]


# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(names,nums, width=0.3, color='green')

# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("销售额", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌销售额关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(names), fontproperties='SimHei', rotation=-0, size=10)
# 显示数字
for a, b in zip(list(names), list(nums)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.savefig('../file/PNG/11品牌销售额关系图.png')
plt.show()

结果展示

八 价格销量

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/24'
"""
import time
import matplotlib
import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt

# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)
print(len(data['销量']))
#data=list()

price_1000,price_2000,price_3000,price_4000,price_5000,price_6000,price_more =0,0,0,0,0,0,0

for i,sale in zip(data['价格'],data['销量']):
    i=int(i)
    sale=int(sale)
    if i<1000:
        price_1000+=sale
    elif i<2000:
        #print(sale)
        price_2000+=sale
        #print(price_2000)
    elif i<3000:
        price_3000+=sale
    elif i<4000:
        price_4000+=sale
    elif i<5000:
        price_5000+=sale
    elif i<6000:
        price_6000+=sale
    else:
        price_more+=sale

print(price_2000)


#------------------------------------------------------------------------------
# 第二步：绘制柱状图
#------------------------------------------------------------------------------

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号


nume=['0_1000','1000_2000','2000_3000','3000_4000','4000_5000','5000_6000','6000+']
sales=[price_1000,price_2000,price_3000,price_4000,price_5000,price_6000,price_more ]
# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(nume,sales, width=0.3, color='green')

# 设置标题
plt.xlabel("价格", fontproperties='SimHei', size=12)
plt.ylabel("销量", fontproperties='SimHei', rotation=90, size=12)
plt.title("价格销量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(nume), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(nume), list(sales)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.savefig('../file/PNG/04价格销量关系图.png')
plt.show()

九 价格销售额

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/24'
"""
import time
import matplotlib
import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt

# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)
print(len(data['销量']))
#data=list()

price_1000,price_2000,price_3000,price_4000,price_5000,price_6000,price_more =0,0,0,0,0,0,0

for i,sale in zip(data['价格'],data['销量']):
    i=int(i)
    sale=i*sale

    if i<1000:
        price_1000+=sale
    elif i<2000:
        #print(sale)
        price_2000+=sale
        #print(price_2000)
    elif i<3000:
        price_3000+=sale
    elif i<4000:
        price_4000+=sale
    elif i<5000:
        price_5000+=sale
    elif i<6000:
        price_6000+=sale
    else:
        price_more+=sale

print(price_2000)


#------------------------------------------------------------------------------
# 第二步：绘制柱状图
#------------------------------------------------------------------------------

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号


nume=['0_1000','1000_2000','2000_3000','3000_4000','4000_5000','5000_6000','6000+']
sales=[price_1000,price_2000,price_3000,price_4000,price_5000,price_6000,price_more ]
# 绘图
plt.figure(figsize=[10,6])
#plt.bar(names, nums, width=0.3, color='green')
plt.bar(nume,sales, width=0.3, color='green')

# 设置标题
plt.xlabel("价格", fontproperties='SimHei', size=12)
plt.ylabel("销售额", fontproperties='SimHei', rotation=90, size=12)
plt.title("价格销售额关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(nume), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(nume), list(sales)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.savefig('../file/PNG/05价格销售额关系图.png')
plt.show()

十 价格影响图

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/25'
"""
import time
import pandas as pd


# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)
#数据定义
count_1000,count_2000,count_3000,count_4000,count_5000,count_6000,count_more =0,0,0,0,0,0,0
sale_1000,sale_2000,sale_3000,sale_4000,sale_5000,sale_6000,sale_more =0,0,0,0,0,0,0
money_1000,money_2000,money_3000,money_4000,money_5000,money_6000,money_more =0,0,0,0,0,0,0
#数据处理
for i,j in zip(data['价格'],data['销量']):
    i=int(i)
    #print(i)
    if i<1000:
        count_1000+=1
        sale_1000+=j
        money_1000+=i*j
    elif i<2000:
        count_2000 += 1
        sale_2000 += j
        money_2000 += i * j
    elif i<3000:
        count_3000 += 1
        sale_3000 += j
        money_3000 += i * j
    elif i<4000:
        count_4000 += 1
        sale_4000 += j
        money_4000 += i * j
    elif i<5000:
        count_5000 += 1
        sale_5000 += j
        money_5000 += i * j
    elif i<6000:
        count_6000 += 1
        sale_6000 += j
        money_6000 += i * j
    else:
        count_more += 1
        sale_more += j
        money_more += i * j
#print(count_2000)
#------------------------------------------------------------------------------
# 初始化
#------------------------------------------------------------------------------

import matplotlib.pyplot as plt

plt.figure(figsize=[18,18])
plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#------------------------------------------------------------------------------
# 数据获取
#------------------------------------------------------------------------------
index=['0_1000','1000_2000','2000_3000','3000_4000','4000_5000','5000_6000','6000+']
count=[count_1000,count_2000,count_3000,count_4000,count_5000,count_6000,count_more ]
sale=[sale_1000,sale_2000,sale_3000,sale_4000,sale_5000,sale_6000,sale_more]
money=[money_1000,money_2000,money_3000,money_4000,money_5000,money_6000,money_more]


#------------------------------------------------------------------------------
# p1价格商品关系条形图
#------------------------------------------------------------------------------
p1=plt.subplot(221)
plt.bar(index,count, width=0.3, color='green')
# 设置标题
plt.xlabel("价格", fontproperties='SimHei', size=12)
plt.ylabel("商品数量", fontproperties='SimHei', rotation=90, size=12)
plt.title("价格商品数量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(index), list(count)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.sca(p1)
#------------------------------------------------------------------------------
# 价格商品数量饼图
#------------------------------------------------------------------------------
p2=plt.subplot(222)

plt.pie(count,labels=index,autopct='%.2f%%')
plt.title("价格商品总量占比", fontproperties='SimHei', size=16)
plt.axis('equal')
plt.legend()
plt.sca(p2)
#------------------------------------------------------------------------------
# 价格销量关系
#------------------------------------------------------------------------------
p3=plt.subplot(223)
plt.bar(index,sale, width=0.3, color='black')

# 设置标题
plt.xlabel("价格", fontproperties='SimHei', size=12)
plt.ylabel("销量", fontproperties='SimHei', rotation=90, size=12)
plt.title("价格销量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)

plt.grid(linestyle='-.')
# 显示数字
for a, b in zip(list(index), list(sale)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.sca(p3)


#------------------------------------------------------------------------------
# 价格销售额
#------------------------------------------------------------------------------
p4=plt.subplot(224)
plt.bar(index,money, width=0.3, color='red')

# 设置标题
plt.xlabel("价格", fontproperties='SimHei', size=12)
plt.ylabel("销售额", fontproperties='SimHei', rotation=90, size=12)
plt.title("价格销售额关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(index), list(money)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.sca(p4)

#------------------------------------------------------------------------------
# 数据显示
#------------------------------------------------------------------------------
plt.grid(linestyle='-.')
plt.savefig('../file/PNG/06价格影响关系图.png')
plt.show()

十一 品牌影响关系图

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
__title__ = ''
__author__ = 'jia666666'
__time__ = '2020/3/25'
"""

import time
import pandas as pd


# 读取数据
n = '../file/CSV/智能手机'  + '-all.csv'
data = pd.read_csv(n)
data.fillna(value=0,inplace=True)
#数据定义
count_1000,count_2000,count_3000,count_4000,count_5000,count_6000,count_more =0,0,0,0,0,0,0
sale_1000,sale_2000,sale_3000,sale_4000,sale_5000,sale_6000,sale_more =0,0,0,0,0,0,0
money_1000,money_2000,money_3000,money_4000,money_5000,money_6000,money_more =0,0,0,0,0,0,0
#数据处理
for item,i,j in zip(data['商品名'],data['价格'],data['销量']):
    i=int(i)
    #print(i)
    if '华为' in item:
        count_1000+=1
        sale_1000+=j
        money_1000+=i*j
    elif '小米' in item:
        count_2000 += 1
        sale_2000 += j
        money_2000 += i * j
    elif '三星' in item:
        count_3000 += 1
        sale_3000 += j
        money_3000 += i * j
    elif '苹果' in item:
        count_4000 += 1
        sale_4000 += j
        money_4000 += i * j
    elif 'vivo' in item or 'VIVO' in item :
        count_5000 += 1
        sale_5000 += j
        money_5000 += i * j
    elif 'oppo' in item or 'OPPO' in item:
        count_6000 += 1
        sale_6000 += j
        money_6000 += i * j
    else:
        count_more += 1
        sale_more += j
        money_more += i * j
#print(count_2000)
#------------------------------------------------------------------------------
# 初始化
#------------------------------------------------------------------------------

import matplotlib.pyplot as plt

plt.figure(figsize=[20,18])
plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False    #用来正常显示负号

#------------------------------------------------------------------------------
# 数据获取
#------------------------------------------------------------------------------
index=['华为','小米','三星','苹果','VIVO','OPPO','其他']
count=[count_1000,count_2000,count_3000,count_4000,count_5000,count_6000,count_more ]
sale=[sale_1000,sale_2000,sale_3000,sale_4000,sale_5000,sale_6000,sale_more]
money=[money_1000,money_2000,money_3000,money_4000,money_5000,money_6000,money_more]


#------------------------------------------------------------------------------
# p1价格商品关系条形图
#------------------------------------------------------------------------------
p1=plt.subplot(221)
plt.bar(index,count, width=0.3, color='green')
# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("商品数量", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌商品数量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(index), list(count)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.sca(p1)
#------------------------------------------------------------------------------
# 品牌商品数量饼图
#------------------------------------------------------------------------------
p2=plt.subplot(222)

plt.pie(count,labels=index,autopct='%.2f%%')
plt.title("品牌商品总量占比", fontproperties='SimHei', size=16)
plt.axis('equal')
plt.legend()
plt.sca(p2)
#------------------------------------------------------------------------------
# 品牌销量关系
#------------------------------------------------------------------------------
p3=plt.subplot(223)
plt.bar(index,sale, width=0.3, color='black')

# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("销量", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌销量关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(index), list(sale)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.sca(p3)


#------------------------------------------------------------------------------
# 品牌销售额
#------------------------------------------------------------------------------
p4=plt.subplot(224)
plt.bar(index,money, width=0.3, color='red')

# 设置标题
plt.xlabel("品牌", fontproperties='SimHei', size=12)
plt.ylabel("销售额", fontproperties='SimHei', rotation=90, size=12)
plt.title("品牌销售额关系图", fontproperties='SimHei', size=16)
#倾斜度角
plt.xticks(list(index), fontproperties='SimHei', rotation=0, size=10)
# 显示数字
for a, b in zip(list(index), list(money)):
    #x轴，y轴，显示数值，水平居中，垂直底部，字体大小
    plt.text(a,b,b, ha='center', va='bottom', size=10)
plt.grid(linestyle='-.')
plt.sca(p4)

#------------------------------------------------------------------------------
# 数据显示
#------------------------------------------------------------------------------


plt.savefig('../file/PNG/12品牌影响关系图.png')
plt.show()