共享单车神经网络预测（pytorch )每行代码详细解释 |
您所在的位置：网站首页 › 共享单车模型 › 共享单车神经网络预测（pytorch )每行代码详细解释 |
共享单车神经网络预测（pytorch )每行代码详细解释
|
1.数据来源：本例将会使用一个国外的共享单车公开数据集（Capital Bikeshare）来完成我们的任务，数据集下载链接：www.capitalbikeshare.com/ system-data。（或者也在我上传的资源中也有https://download.csdn.net/download/qq_40840797/20325952） 数据介绍：特征因素（例如：年份，季度，星期几，温度，风速等因素）；目标变量（用户数，临时注册用户数，注册用户数）
2数据处理 import numpy as np import pandas as pd #读取csv文件的库 from matplotlib import pyplot as plt import torch import torch.optim as optim data_path = 'Bike-Sharing-Dataset/hour.csv'#数据位置 rides = pd.read_csv(data_path)#读取数据文件 rides.head()#看看数据长什么样子2.1.原始数据的星期几，天气情况等因素需要编码，这样数据才有意义。 # season=1,2,3,4, weathersi=1,2,3, mnth= 1,2,...,12, hr=0,1, ...,23, weekday=0,1,...,6 # 经过下面的处理后，将会多出若干特征，例如，对于season变量就会有 season_1, season_2, season_3, season_4 dummy_fields = ['season', 'weathersit', 'mnth', 'hr', 'weekday']# 这四种不同的特征,进行编码 for each in dummy_fields: #利用pandas对象，我们可以很方便地将一个类型变量属性进行one-hot编码，变成多个属性 dummies = pd.get_dummies(rides[each], prefix=each, drop_first=False)#prefix是用来生成列名字，drop_first是否把每次生成的第一列去掉 rides = pd.concat([rides, dummies], axis=1)#按照列方向合并2.2.把原来的表格里面被编码原始列与不相关列去掉 # 把原有的类型变量对应的特征去掉，将一些不相关的特征去掉 fields_to_drop = ['instant', 'dteday', 'season', 'weathersit', 'weekday', 'atemp', 'mnth', 'workingday', 'hr']#要去掉的列名字 data = rides.drop(fields_to_drop, axis=1)#从文件中去掉 data.head()2.4.归一化 'cnt', 'temp', 'hum', 'windspeed'这四个列 quant_features = ['cnt', 'temp', 'hum', 'windspeed']#要归一化的四列 #quant_features = ['temp', 'hum', 'windspeed'] # 我们将每一个变量的均值和方差都存储到scaled_features变量中。 scaled_features = {}#空集合 for each in quant_features: mean, std = data[each].mean(), data[each].std()#求均值和方差 scaled_features[each] = [mean, std]#将均值和方差都装进集合 data.loc[:, each] = (data[each] - mean)/std#求归一化结果并装载进data2.5.训练数据与测试数据划分 train_data = data[:-21*24] test_data = data[-21*24:]#最后21天是测试集 print('训练数据：',len(train_data),'测试数据：',len(test_data))2.6生成训练样本与训练目标值 target_fields = ['cnt', 'casual', 'registered']#训目标列【用户数，临时用户数，注册用户数】 features, targets = train_data.drop(target_fields, axis=1), train_data[target_fields] test_features, test_targets = test_data.drop(target_fields, axis=1), test_data[target_fields] # 将数据从pandas dataframe转换为numpy X = features.values#取值 Y = targets['cnt'].values#取值 Y = Y.astype(float)#转化格式 Y = np.reshape(Y, [len(Y),1])#【16875，】转变为【16875，1】 losses = [] features.head()3.两种构建神经网络方式 3.1.手动编写神经网络 input_size = features.shape[1] #输入层单元个数 hidden_size = 10 #隐含层单元个数 output_size = 1 #输出层单元个数 batch_size = 128 #每隔batch的记录数 weights1 = torch.randn([input_size, hidden_size], dtype = torch.double, requires_grad = True) #第一到二层权重 biases1 = torch.randn([hidden_size], dtype = torch.double, requires_grad = True) #隐含层偏置 weights2 = torch.randn([hidden_size, output_size], dtype = torch.double, requires_grad = True) #隐含层到输出层权重 def neu(x): #计算隐含层输出 #x为batch_size * input_size的矩阵，weights1为input_size*hidden_size矩阵， #biases为hidden_size向量，输出为batch_size * hidden_size矩阵 hidden = x.mm(weights1) + biases1.expand(x.size()[0], hidden_size) hidden = torch.sigmoid(hidden) #输入batch_size * hidden_size矩阵，mm上weights2, hidden_size*output_size矩阵， #输出batch_size*output_size矩阵 output = hidden.mm(weights2) return output def cost(x, y): # 计算损失函数 error = torch.mean((x - y)**2) return error def zero_grad(): # 清空每个参数的梯度信息 if weights1.grad is not None and biases1.grad is not None and weights2.grad is not None: weights1.grad.data.zero_() weights2.grad.data.zero_() biases1.grad.data.zero_() def optimizer_step(learning_rate): # 梯度下降算法 weights1.data.add_(- learning_rate * weights1.grad.data) weights2.data.add_(- learning_rate * weights2.grad.data) biases1.data.add_(- learning_rate * biases1.grad.data) losses = [] for i in range(1000): # 每128个样本点被划分为一个撮，在循环的时候一批一批地读取 batch_loss = []#每一批次的损失 # start和end分别是提取一个batch数据的起始和终止下标 for start in range(0, len(X), batch_size):#每128个点作为一个批次 end = start + batch_size if start + batch_size < len(X) else len(X)#取截止点位 xx = torch.tensor(X[start:end], dtype = torch.double, requires_grad = True)#生成特征批次 yy = torch.tensor(Y[start:end], dtype = torch.double, requires_grad = True)#生成目标批次 predict = neu(xx)#预测 loss = cost(predict, yy)#损失 zero_grad()#梯度清零 loss.backward()#损失反向传播 optimizer_step(0.01)#学习率设置 batch_loss.append(loss.data.numpy())#每个批次损失装载在列表 # 每隔100步输出一下损失值（loss） if i % 100==0: losses.append(np.mean(batch_loss))#每一百次迭代的损失均值装载在losses print(i, np.mean(batch_loss)) # 打印输出损失值 fig = plt.figure(figsize=(10, 7)) plt.plot(np.arange(len(losses))*100,losses, 'o-')#绘制损失曲线 plt.xlabel('epoch') plt.ylabel('MSE')3.2.使用pytorch已有网络框架 input_size = features.shape[1] hidden_size = 10 output_size = 1 batch_size = 128 neu = torch.nn.Sequential( torch.nn.Linear(input_size, hidden_size), torch.nn.Sigmoid(), torch.nn.Linear(hidden_size, output_size), ) cost = torch.nn.MSELoss() optimizer = torch.optim.SGD(neu.parameters(), lr = 0.01) losses = [] for i in range(1000): # 每128个样本点被划分为一个撮，在循环的时候一批一批地读取 batch_loss = [] # start和end分别是提取一个batch数据的起始和终止下标 for start in range(0, len(X), batch_size): end = start + batch_size if start + batch_size < len(X) else len(X) xx = torch.tensor(X[start:end], dtype = torch.float, requires_grad = True) yy = torch.tensor(Y[start:end], dtype = torch.float, requires_grad = True) predict = neu(xx) loss = cost(predict, yy) optimizer.zero_grad() loss.backward() optimizer.step() batch_loss.append(loss.data.numpy()) # 每隔100步输出一下损失值（loss） if i % 100==0: losses.append(np.mean(batch_loss)) print(i, np.mean(batch_loss))4.测试 targets = test_targets['cnt'] #读取测试集的cnt数值 targets = targets.values.reshape([len(targets),1]) #将数据转换成合适的tensor形式 targets = targets.astype(float) #保证数据为实数 x = torch.tensor(test_features.values, dtype = torch.double, requires_grad = True)#使用3.1搭建网络，则dtype= torch.double；使用3.2搭建3.2搭建网络，则dtype = torch.float y = torch.tensor(targets, dtype = torch.float, requires_grad = True) print(x[:10]) # 用神经网络进行预测 predict = neu(x) predict = predict.data.numpy() print((predict * std + mean)[:10]) # 将后21天的预测数据与真实数据画在一起并比较 # 横坐标轴是不同的日期，纵坐标轴是预测或者真实数据的值 fig, ax = plt.subplots(figsize = (10, 7)) mean, std = scaled_features['cnt'] ax.plot(predict * std + mean, label='Prediction', linestyle = '--') ax.plot(targets * std + mean, label='Data', linestyle = '-') ax.legend() ax.set_xlabel('Date-time') ax.set_ylabel('Counts') # 对横坐标轴进行标注 dates = pd.to_datetime(rides.loc[test_data.index]['dteday']) dates = dates.apply(lambda d: d.strftime('%b %d')) ax.set_xticks(np.arange(len(dates))[12::24]) _ = ax.set_xticklabels(dates[12::24], rotation=45)5.结果图
|
【本文地址】
今日新闻 |
推荐新闻 |