PyTorch 深度学习实践 第8讲 加载数据集

数据来源：diabetes.csv

批量梯度下降要并行处理，所以要加上 if __name__ == '__main__':

import torch
import numpy as np
from torch.utils.data import Dataset, DataLoader

class DiabetesDataset(Dataset):
    def __init__(self, datapath):
        xy = np.loadtxt(datapath, delimiter = ',',dtype =  np.float32)
        self.x = torch.from_numpy(xy[:, : -1])
        self.y = torch.from_numpy(xy[:, [-1]])
        self.len = xy.shape[0]
        
    def __len__(self):
        return self.len
    
    def __getitem__(self, index):
        return self.x[index], self.y[index]
    
dataset = DiabetesDataset('diabetes.csv')
train_loader = DataLoader(dataset = dataset,
                         batch_size = 32,
                         shuffle = True,
                         num_workers = 2)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()
        
    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))        
        x = self.sigmoid(self.linear3(x))     
        return x
    
model = Model()

criterion = torch.nn.BCELoss(reduction = 'mean')
optimizer = torch.optim.SGD(model.parameters(), lr = 0.1)

if __name__ == '__main__':
    for epoch in range(100):
        for i, data in enumerate(train_loader, 0):
            x, y = data
            y_pred = model(x)
            loss = criterion(y_pred, y)
            
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
        print('epoch:', epoch, 'loss', loss.item())

作业
数据集：Titanic - Machine Learning from Disaster

import torch
import numpy as np
import pandas as pd
from torch.utils.data import Dataset, DataLoader

class TitanicDataset(Dataset):
    def __init__(self, filepath):
        xy = pd.read_csv(filepath)
        self.len = xy.shape[0]
        
        features = ["Pclass", "Sex", "SibSp", "Parch", "Fare"]
        self.x_data = torch.from_numpy(np.array(pd.get_dummies(xy[features])))
        self.y_data = torch.from_numpy(np.array(xy[["Survived"]]))
        
    def __len__(self):
        return self.len
    
    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]
    
dataset = TitanicDataset('train.csv')
dataloader = DataLoader(dataset = dataset,
                       batch_size = 32,
                       shuffle = True,
                       num_workers = 2)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(6, 3)
        self.linear2 = torch.nn.Linear(3, 1)
        self.sigmoid = torch.nn.Sigmoid()
        
    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))     
        return x
    
    def predict(self, x):
        with torch.no_grad():
            x = self.sigmoid(self.linear1(x))
            x = self.sigmoid(self.linear2(x))
            y = []
            for i in x:
                if i > 0.5:
                    y.append(1)
                else:
                    y.append(0)
            return y
        
model = Model()

criterion = torch.nn.BCELoss(reduction = 'mean')
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)

if __name__ == '__main__':
    for epoch in range(10):
        for i, data in enumerate(dataloader, 0):
            x, y = data
            y_pred = model(x.float())
            loss = criterion(y_pred, y.float())            
            
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
        
        print("epoch:", epoch, "loss", loss.item())

    test_data = pd.read_csv('test.csv')
    features = ["Pclass", "Sex", "SibSp", "Parch", "Fare"]
    x_test = torch.from_numpy(np.array(pd.get_dummies(test_data[features])))

    y_test = model.predict(x_test.float())
    outputs = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': y_test})
    outputs.to_csv('predict_titantic.csv', index=False) 

作业参考：PyTorch深度学习（B站刘二大爷）第八讲作业——Kaggle网站泰坦尼克号Titanic