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：
# -*- coding: utf-8 -*-from sklearn.metrics import mean_squared_errorimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerimport pandas as pdfrom sklearn.utils import shuffleimport tensorflow as tfclass 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wself.w = rnd.uniform(-1, 1, (columns, num))# 偏置bself.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_bself.H0 = np.matrix(self.sigmoid(np.dot(x, self.w) + self.b))self.C = Cself.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@staticmethoddef 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))@staticmethoddef 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))@staticmethoddef 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.betaall_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 resultif __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+'0612/train/traincalendar.csv'url2 = ProjectPath+'0612/train/trainsaleslable.csv'url3 = ProjectPath+'0612/test/testcalendar.csv'url4 = ProjectPath+'0612/test/testsaleslable.csv'url5 = ProjectPath + '0612/FinalPrediction/precalendar.csv'saveurl = ProjectPath+'0612/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 = 0.1X_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 = 1minMSE = 100for 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 = MSEbestHiddenLayer = jresult = predictprint('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+'0612/sales_train.csv')# print(calendar.iloc[0:27967, 1919:1947].shape)# print(predict.T.shape)calendar.iloc[0:27967, 1919:1947] = predict.Tcalendar.to_csv(ProjectPath+'0612/pre_result_sales_train.csv', header=True, index=False)print('写入完毕！')
需要帮助联系VX vx_xuxx
