PyTorch基础——预测共享单车的使用量

预处理实验数据

读取数据

# 下载并解压数据集

!wget http://labfile.oss.aliyuncs.com/courses/1073/bike-sharing-dataset.zip
!unzip bike-sharing-dataset.zip

#导入需要使用的库
import numpy as np
import pandas as pd #读取csv文件的库
import matplotlib.pyplot as plt
import torch
from torch.autograd import Variable
import torch.optim as optim

# 让输出的图形直接在Notebook中显示
%matplotlib inline

#首先，让我们再来看看数据长什么样子
#读取数据到内存中，rides为一个dataframe对象
data_path = 'hour.csv'
rides = pd.read_csv(data_path)
rides.head()

对于类型变量的处理

#对于类型变量的特殊处理
# 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
# 这四种不同的特征。
dummy_fields = ['season', 'weathersit', 'mnth', 'hr', 'weekday']
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)
    rides = pd.concat([rides, dummies], axis=1)

# 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']
data = rides.drop(fields_to_drop, axis=1)
data.head()

对于数值类型变量进行标准化

# 调整所有的特征，标准化处理
quant_features = ['cnt', 'temp', 'hum', 'windspeed']
#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 = {}
for each in quant_features:
    mean, std = data[each].mean(), data[each].std()
    scaled_features[each] = [mean, std]
    data.loc[:, each] = (data[each] - mean)/std

将数据集进行分割

# 将所有的数据集分为测试集和训练集，我们以后21天数据一共21*24个数据点作为测试集，其它是训练集
test_data = data[-21*24:]
train_data = data[:-21*24]
print('训练数据：',len(train_data),'测试数据：',len(test_data))

# 将我们的数据列分为特征列和目标列

#目标列
target_fields = ['cnt', 'casual', 'registered']
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
Y = targets['cnt'].values
Y = Y.astype(float)

Y = np.reshape(Y, [len(Y),1])
losses = []

features.head()

构建神经网络模型

手动编写用 Tensor 运算的人工神经网络

# 定义神经网络架构，features.shape[1]个输入层单元，10个隐含层，1个输出层
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 = Variable(torch.randn([input_size, hidden_size]), requires_grad = True) #第一到二层权重
biases1 = Variable(torch.randn([hidden_size]), requires_grad = True) #隐含层偏置
weights2 = Variable(torch.randn([hidden_size, output_size]), 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)

调用PyTorch现成的函数，构建序列化的神经网络

# 定义神经网络架构，features.shape[1]个输入层单元，10个隐含层，1个输出层
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)

数据的分批次处理

# 神经网络训练循环
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 = Variable(torch.FloatTensor(X[start:end]))
        yy = Variable(torch.FloatTensor(Y[start:end]))
        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))

# 打印输出损失值
fig = plt.figure(figsize=(10, 7))
plt.plot(np.arange(len(losses))*100,losses, 'o-')
plt.xlabel('epoch')
plt.ylabel('MSE')

测试网络

使用测试数据集测试网络

# 用训练好的神经网络在测试集上进行预测
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

# 将属性和预测变量包裹在Variable型变量中
x = Variable(torch.FloatTensor(test_features.values))
y = Variable(torch.FloatTensor(targets))

# 用神经网络进行预测
predict = neu(x)
predict = predict.data.numpy()


# 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)