Python ELM模型预测美国10个商店3049个商品销售量 ANN人工神经网络

106 阅读 0 评论 70 点赞

我是靠谱客的博主冷艳日记本，这篇文章主要介绍Python ELM模型预测美国10个商店3049个商品销售量 ANN人工神经网络，现在分享给大家，希望可以做个参考。

问题描述
美国有10个商店，每个商店有3049个商品，统计了1914天内各个商品的价格和销售数量，以及每天的属性(节日，打折活动等)，通过构建非时序模型预测1914天-1941天各个商品销售数量，使用均方误差作为评价标准。
实验数据
① 30490个商品在1941天内的价格
②30490个商品在1914天的销量(标签)
③1941天所对应的属性（节日，打折等）
其中①和③是我们需要使用的特征，③中对应很多的节日，如Purim Enc，StPatricksl，Memoriall，Mother’s day等等，使用pandas包中的dummies进行onehot编码。
②是我们需要预测的lable，这个问题是一个大规模的回归问题
实验环境
pycharm平台，python语言
实验结果
预测了1914-1941天的销量数据并写入了excel。

源码：

复制代码

# -*- coding: utf-8 -*-
from sklearn.metrics import mean_squared_error
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd
from sklearn.utils import shuffle
import tensorflow as tf
class RELM_HiddenLayer:
"""
正则化的极限学习机
:param x: 初始化学习机时的训练集属性X
:param num: 学习机隐层节点数
:param C: 正则化系数的倒数
"""
def __init__(self, x, num, C=10):
row = x.shape[0]
columns = x.shape[1]
rnd = np.random.RandomState()
# 权重w
self.w = rnd.uniform(-1, 1, (columns, num))
# 偏置b
self.b = np.zeros([row, num], dtype=float)
for i in range(num):
rand_b = rnd.uniform(-0.4, 0.4)
for j in range(row):
self.b[j, i] = rand_b
self.H0 = np.matrix(self.sigmoid(np.dot(x, self.w) + self.b))
self.C = C
self.P = (self.H0.H * self.H0 + len(x) / self.C).I
# .T:共轭矩阵,.H:共轭转置,.I:逆矩阵
@staticmethod
def sigmoid(x):
"""
激活函数sigmoid
:param x: 训练集中的X
:return: 激活值
"""
return 1.0 / (1 + np.exp(-x))
@staticmethod
def softplus(x):
"""
激活函数 softplus
:param x: 训练集中的X
:return: 激活值
"""
return np.log(1 + np.exp(x))
@staticmethod
def tanh(x):
"""
激活函数tanh
:param x: 训练集中的X
:return: 激活值
"""
return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))
# 回归问题 训练
def regressor_train(self, T):
"""
初始化了学习机后需要传入对应标签T
:param T: 对应属性X的标签T
:return: 隐层输出权值beta
"""
#
all_m = np.dot(self.P, self.H0.H)
#
self.beta = np.dot(all_m, T)
#
return self.beta
all_m = np.dot(self.P, self.H0.H)
self.beta = np.dot(all_m, T)
return self.beta
# 回归问题 测试
def regressor_test(self, test_x):
"""
传入待预测的属性X并进行预测获得预测值
:param test_x:被预测标签的属性X
:return: 被预测标签的预测值T
"""
b_row = test_x.shape[0]
h = self.sigmoid(np.dot(test_x, self.w) + self.b[:b_row, :])
#
h = self.sigmoid(np.dot(test_x, self.w) + self.b[:b_row, :])
result = np.dot(h, self.beta)
#
result =np.argmax(result,axis=1)
return result
if __name__ == '__main__':
with tf.device("/gpu:0"):
# 项目所在路径
ProjectPath = 'D:/Python/RecSysProject/'
# 数据读取及划分
url1 = ProjectPath+'20210612/train/traincalendar.csv'
url2 = ProjectPath+'20210612/train/trainsaleslable.csv'
url3 = ProjectPath+'20210612/test/testcalendar.csv'
url4 = ProjectPath+'20210612/test/testsaleslable.csv'
url5 = ProjectPath + '20210612/FinalPrediction/precalendar.csv'
saveurl = ProjectPath+'20210612/test/testsaleslable.csv'
data1 = pd.read_csv(url1, sep=',', header=None)
data2 = pd.read_csv(url2, sep=',', header=None)
data3 = pd.read_csv(url3, sep=',', header=None)
data4 = pd.read_csv(url4, sep=',', header=None)
data5 = pd.read_csv(url5, sep=',', header=None)
data1 = np.array(data1)
data2 = np.array(data2)
data3 = np.array(data3)
data4 = np.array(data4)
data5 = np.array(data5)
data1 = shuffle(data1)
data2 = shuffle(data2)
data3 = shuffle(data3)
data4 = shuffle(data4)
data5 = np.array(data5)
X_data = np.vstack((data1,data3))
Y = np.vstack((data2,data4))
# print(Y)
# 下面3行代码就是将数据集随即按照num_train分成训练集和测试集，数据量大，就分了两部分
num_train = 0.1
X_train, X_, Y_train, Y_ = train_test_split(X_data, Y, test_size=num_train, random_state=20)
X_test, X_vld, Y_test, Y_vld = train_test_split(X_, Y_, test_size=0.1, random_state=20)
# 数据标准化处理
stdsc = StandardScaler()
X_train = stdsc.fit_transform(X_train)
X_test = stdsc.fit_transform(X_test)
X_vld = stdsc.fit_transform(X_vld)
Y_true = Y_test
# 不同隐藏层结果对比
bestHiddenLayer = 1
minMSE = 100
for j in range(1, 10, 1):
a = RELM_HiddenLayer(X_train, j)
a.regressor_train(Y_train)
predict = a.regressor_test(X_test)
#预测结果
# print(predict)
#预测均方误差
MSE = mean_squared_error(predict,Y_true)
print('hidden- %d,MSE:%f'%(j,MSE))
if MSE< minMSE:
minMSE = MSE
bestHiddenLayer = j
result = predict
print('训练结束，训练数据中最佳隐含层网络节点数量为:%d,MSE=%f' %(bestHiddenLayer,minMSE))
print('开始计算1914-1941结果！')
result = []
a = RELM_HiddenLayer(X_train, bestHiddenLayer)
a.regressor_train(Y_train)
predict = a.regressor_test(data5)
predict = np.round(abs(predict))
calendar = pd.read_csv(ProjectPath+'20210612/sales_train.csv')
# print(calendar.iloc[0:27967, 1919:1947].shape)
# print(predict.T.shape)
calendar.iloc[0:27967, 1919:1947] = predict.T
calendar.to_csv(ProjectPath+'20210612/pre_result_sales_train.csv', header=True, index=False)
print('写入完毕！')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
# -*- coding: utf-8 -*-
from sklearn.metrics import mean_squared_error
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd
from sklearn.utils import shuffle
import tensorflow as tf
class RELM_HiddenLayer:
"""
正则化的极限学习机
:param x: 初始化学习机时的训练集属性X
:param num: 学习机隐层节点数
:param C: 正则化系数的倒数
"""
def __init__(self, x, num, C=10):
row = x.shape[0]
columns = x.shape[1]
rnd = np.random.RandomState()
# 权重w
self.w = rnd.uniform(-1, 1, (columns, num))
# 偏置b
self.b = np.zeros([row, num], dtype=float)
for i in range(num):
rand_b = rnd.uniform(-0.4, 0.4)
for j in range(row):
self.b[j, i] = rand_b
self.H0 = np.matrix(self.sigmoid(np.dot(x, self.w) + self.b))
self.C = C
self.P = (self.H0.H * self.H0 + len(x) / self.C).I
# .T:共轭矩阵,.H:共轭转置,.I:逆矩阵
@staticmethod
def sigmoid(x):
"""
激活函数sigmoid
:param x: 训练集中的X
:return: 激活值
"""
return 1.0 / (1 + np.exp(-x))
@staticmethod
def softplus(x):
"""
激活函数 softplus
:param x: 训练集中的X
:return: 激活值
"""
return np.log(1 + np.exp(x))
@staticmethod
def tanh(x):
"""
激活函数tanh
:param x: 训练集中的X
:return: 激活值
"""
return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))
# 回归问题 训练
def regressor_train(self, T):
"""
初始化了学习机后需要传入对应标签T
:param T: 对应属性X的标签T
:return: 隐层输出权值beta
"""
#
all_m = np.dot(self.P, self.H0.H)
#
self.beta = np.dot(all_m, T)
#
return self.beta
all_m = np.dot(self.P, self.H0.H)
self.beta = np.dot(all_m, T)
return self.beta
# 回归问题 测试
def regressor_test(self, test_x):
"""
传入待预测的属性X并进行预测获得预测值
:param test_x:被预测标签的属性X
:return: 被预测标签的预测值T
"""
b_row = test_x.shape[0]
h = self.sigmoid(np.dot(test_x, self.w) + self.b[:b_row, :])
#
h = self.sigmoid(np.dot(test_x, self.w) + self.b[:b_row, :])
result = np.dot(h, self.beta)
#
result =np.argmax(result,axis=1)
return result
if __name__ == '__main__':
with tf.device("/gpu:0"):
# 项目所在路径
ProjectPath = 'D:/Python/RecSysProject/'
# 数据读取及划分
url1 = ProjectPath+'20210612/train/traincalendar.csv'
url2 = ProjectPath+'20210612/train/trainsaleslable.csv'
url3 = ProjectPath+'20210612/test/testcalendar.csv'
url4 = ProjectPath+'20210612/test/testsaleslable.csv'
url5 = ProjectPath + '20210612/FinalPrediction/precalendar.csv'
saveurl = ProjectPath+'20210612/test/testsaleslable.csv'
data1 = pd.read_csv(url1, sep=',', header=None)
data2 = pd.read_csv(url2, sep=',', header=None)
data3 = pd.read_csv(url3, sep=',', header=None)
data4 = pd.read_csv(url4, sep=',', header=None)
data5 = pd.read_csv(url5, sep=',', header=None)
data1 = np.array(data1)
data2 = np.array(data2)
data3 = np.array(data3)
data4 = np.array(data4)
data5 = np.array(data5)
data1 = shuffle(data1)
data2 = shuffle(data2)
data3 = shuffle(data3)
data4 = shuffle(data4)
data5 = np.array(data5)
X_data = np.vstack((data1,data3))
Y = np.vstack((data2,data4))
# print(Y)
# 下面3行代码就是将数据集随即按照num_train分成训练集和测试集，数据量大，就分了两部分
num_train = 0.1
X_train, X_, Y_train, Y_ = train_test_split(X_data, Y, test_size=num_train, random_state=20)
X_test, X_vld, Y_test, Y_vld = train_test_split(X_, Y_, test_size=0.1, random_state=20)
# 数据标准化处理
stdsc = StandardScaler()
X_train = stdsc.fit_transform(X_train)
X_test = stdsc.fit_transform(X_test)
X_vld = stdsc.fit_transform(X_vld)
Y_true = Y_test
# 不同隐藏层结果对比
bestHiddenLayer = 1
minMSE = 100
for j in range(1, 10, 1):
a = RELM_HiddenLayer(X_train, j)
a.regressor_train(Y_train)
predict = a.regressor_test(X_test)
#预测结果
# print(predict)
#预测均方误差
MSE = mean_squared_error(predict,Y_true)
print('hidden- %d,MSE:%f'%(j,MSE))
if MSE< minMSE:
minMSE = MSE
bestHiddenLayer = j
result = predict
print('训练结束，训练数据中最佳隐含层网络节点数量为:%d,MSE=%f' %(bestHiddenLayer,minMSE))
print('开始计算1914-1941结果！')
result = []
a = RELM_HiddenLayer(X_train, bestHiddenLayer)
a.regressor_train(Y_train)
predict = a.regressor_test(data5)
predict = np.round(abs(predict))
calendar = pd.read_csv(ProjectPath+'20210612/sales_train.csv')
# print(calendar.iloc[0:27967, 1919:1947].shape)
# print(predict.T.shape)
calendar.iloc[0:27967, 1919:1947] = predict.T
calendar.to_csv(ProjectPath+'20210612/pre_result_sales_train.csv', header=True, index=False)
print('写入完毕！')