111111_Python

import json
import pandas as pd
import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from tkinter import *
plt.rcParams[u’font.sans-serif’] = [‘simhei’]

def click1():
with open(‘D:ECommerce源代码staticcountryCustomer.json’, ‘r’, encoding=‘utf8’) as fp:
json_data = json.load(fp)
print(json_data)
print(type(json_data))
# print(json_data[0][1])
x1 = []
y1 = []
for data in json_data:
x1.append(data[0])
y1.append(data[1])
plt.figure(figsize=(15,12))
plt.title(‘概览’)
plt.subplot(321)
plt.title(‘客户数最多的10个国家’)
plt.xticks(rotation=70)
plt.bar(x1, y1)
#plt.show()

with open('D:ECommerce源代码staticcountryQuantity.json', 'r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    x2 = []
    y2 = []
    for data in json_data:
        x2.append(data[0])
        y2.append(data[1])
    plt.xticks(rotation=70)
    plt.subplot(322)
    plt.title('销量最高的10个国家')
    plt.xticks(rotation=70)
    plt.bar(x2, y2)
    #plt.show()

with open('D:ECommerce源代码staticcountrySumOfPrice.json', 'r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    labels = []
    nums = []
    for i in range(0, len(json_data)):
        labels.append(json_data[i][0])
        nums.append(json_data[i][1])
    #plt.figure(figsize=(20,6.5))
    plt.subplot(325)
    plt.title('总销售额最高的10个国家分布情况')
    plt.pie(x=nums, labels=labels, pctdistance=0.5,explode=(0,0.1,0.1,0.1,0.1,0.1,0.3,0.5,0.9,1.0))
    # plt.legend(labels)
    # plt.legend(loc='upper right')
    #plt.show()

with open('D:ECommerce源代码staticstockQuantity.json', 'r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    x4 = []
    y4 = []
    for data in json_data:
        x4.append(data[0])
        y4.append(data[1])
    plt.xticks(rotation=70)
    plt.subplot(326)
    plt.title('销量最高的10个商品')
    plt.bar(x4, y4)
    plt.show()

def click2():
with open(‘D:ECommerce源代码staticwordCount.json’, ‘r’, encoding=‘utf8’) as fp:
json_data = json.load(fp)
print(json_data)
print(type(json_data))
wc=WordCloud(background_color=‘white’,max_words=100)
x5 = []
y5 = []
for data in json_data:
x5.append(data[0])
y5.append(data[1])
dic=dict(zip(x5,y5))
wc.generate_from_frequencies(dic)
plt.figure(figsize=(8, 5))
plt.title(‘热门关键词’)
plt.imshow(wc)
plt.axis(“off”)
plt.show()

def click3():
with open(‘D:ECommerce源代码staticcountryReturnInvoice.json’, ‘r’, encoding=‘utf8’) as fp:
json_data = json.load(fp)
print(json_data)
print(type(json_data))
# print(json_data[0][1])
x6 = []
y6 = []
for data in json_data:
x6.append(data[0])
y6.append(data[1])
plt.figure(figsize=(15, 12))
plt.title(‘关系’)
plt.subplot(231)
plt.title(‘退货订单数最多的10个国家’)
plt.xticks(rotation=70)
plt.bar(x6, y6)
#plt.show()

with open('D:ECommerce源代码static\tradePrice.json', 'r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    x7 = []
    y7 = []
    for data in json_data:
        x7.append(data[0])
        y7.append(data[1])
    plt.subplot(233)
    plt.title('月销售额随时间的变化趋势')
    plt.xticks(rotation=70)
    plt.plot(x7, y7)
    #plt.show()

with open('D:ECommerce源代码staticsaleQuantity.json', 'r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    x8 = []
    y8 = []
    for data in json_data:
        x8.append(data[0])
        y8.append(data[1])
    plt.subplot(235)
    plt.title('日销量随时间的变化趋势')
    plt.xticks(rotation=70)
    plt.plot(x8, y8)
    plt.xticks(range(0, 365, 30))
    plt.show()

def click4():
with open(‘D:ECommerce源代码staticbuyReturn.json’, ‘r’, encoding=‘utf8’) as fp:
json_data = json.load(fp)
print(json_data)
print(type(json_data))
# print(json_data[0][1])
x9 = []
y9 = []
for data in json_data:
x9.append(data[1])
y9.append(data[2])
del x9[x9.index(max(x9))]
del y9[y9.index(max(y9))]
plt.figure(figsize=(15, 12))
plt.subplot(121)
plt.title(‘各国的购买订单量和退货订单量的关系’)
plt.scatter(x9, y9, marker=’*’)
#plt.show()

with open('D:ECommerce源代码static\unitPriceSales.json','r', encoding='utf8') as fp:
    json_data = json.load(fp)
    print(json_data)
    print(type(json_data))
    # print(json_data[0][1])
    x10 = []
    y10 = []
    for data in json_data:
        x10.append(data[1])
        y10.append(data[2])
    # del x9[x9.index(max(x9))]
    # del y9[y9.index(max(y9))]
    newx10=[]
    newy10=[]
    for x in x10:
        if x<=50:
            newx10.append(x)
            newy10.append(y10[x10.index(x)])
    plt.subplot(122)
    plt.title('商品的平均单价与销量的关系')
    plt.scatter(newx10, newy10,marker='*')
    plt.show()

def click5():
# plt.rcParams[‘font.sans-serif’] = [‘SimHei’]
plt.rcParams[‘axes.unicode_minus’] = False
filepath = “D:ECommerce数据集E_Commerce_Data_Clean.csv”
dataset = pd.read_csv(filepath, decimal=’,’)

data_Q = np.array(dataset["Quantity"])
data_P = np.array(dataset["UnitPrice"])

data_quantity = []

data_price = []

for i in range(len(data_Q)):
    if data_Q[i] < 0 and data_Q[i] > -100:
        data_quantity.append(data_Q[i] * (-1))
        data_price.append(float(data_P[i]))

data_quantity = np.array(data_quantity)
data_price = np.array(data_price)

# plt.figure(figsize=(120, 8), dpi=80)
# plt.title('退货数量与价格关系', size=15)
# plt.xlabel('价格',fontsize=15)
# plt.ylabel('退货数量',fontsize=15)
# plt.xticks(rotation=60)
# plt.bar(range(len(data_price)), data_quantity, tick_label=data_price)
# plt.savefig('kpi_time.png', bbox_inches='tight')

# Pearson相关系数
data1 = pd.Series(data_quantity).sort_values()
data2 = pd.Series(data_price).sort_values()
print(data1)
data = pd.Dataframe({'value1': data1.values,
                     'value2': data2.values})
print(data)
print('------')

# 正态性检验
u1, u2 = data['value1'].mean(), data['value2'].mean()  # 计算均值
std1, std2 = data['value1'].std(), data['value2'].std()  # 计算标准差
print('value1正态性检验：n', stats.kstest(data['value1'], 'norm', (u1, std1)))
print('value2正态性检验：n', stats.kstest(data['value2'], 'norm', (u2, std2)))
print('------')

# 制作Pearson相关系数求值表
data['(x-u1)*(y-u2)'] = (data['value1'] - u1) * (data['value2'] - u2)
data['(x-u1)**2'] = (data['value1'] - u1) ** 2
data['(y-u2)**2'] = (data['value2'] - u2) ** 2
print(data.head())
print('------')

# 求出r
# |r| > 0.8 → 高度线性相关
r = data['(x-u1)*(y-u2)'].sum() / (np.sqrt(data['(x-u1)**2'].sum() * data['(y-u2)**2'].sum()))
print('Pearson相关系数为：%.4f' % r)

window = Tk()
window.minsize(85, 60)
window.title(‘数据可视化分析’)
lbl = Label(window, text=‘销量分析’)
lbl.grid(column=0, row=0)

txt = Entry(window, width=20) txt.grid(column=2, row=0)

btn1=Button(window,text=‘概览’,bg=‘yellow’,fg=‘red’,command=click1)
btn1.grid(column=0,row=1)
btn2=Button(window,text=‘热门关键词’,bg=‘orange’,fg=‘white’,command=click2)
btn2.grid(column=0,row=2)
btn3 = Button(window, text=‘关系1’, command=click3)
btn3.grid(column=1, row=1)
btn4 = Button(window, text=‘关系2’, command=click4)
btn4.grid(column=1, row=2)
window.mainloop()

window.mainloop()

111111

Python相关栏目本月热门文章