Pytorch Daily Practice - Predicting Surviving Passengers on the Titanic

训练数据：
Survived是输出标签,other age、性别、Names, etc. are treated as input.Of course there will be missing data,It needs to be cleaned in advance.
The purpose of the test is to input the sample features,Whether the output can survive(0或1)

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

class DiabetesDataset(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 __getitem__(self, index):
        return self.x_data[index], self.y_data[index]
    
    def __len__(self):
        return self.len
    
dataset = DiabetesDataset('Dataset\\titanic\\train.csv')
train_loader = DataLoader(dataset = dataset,
                          batch_size = 32,
                          shuffle = True,
                         num_workers = 0)
batch_size = 32
batch = np.round(dataset.__len__() / batch_size)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(6, 4)
        self.linear2 = torch.nn.Linear(4, 2)
        self.linear3 = torch.nn.Linear(2, 1)
        self.relu = torch.nn.ReLU()
        self.sigmoid = torch.nn.Sigmoid()
        
    def forward(self, x):
        x = self.relu(self.linear1(x))
        x = self.relu(self.linear2(x))
        x = self.sigmoid(self.linear3(x))#注意最后一步不能使用relu,避免无法计算梯度
        return x

mymodel = Model() 

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

epoch_list = []
loss_list = []
sum_loss = 0
if __name__ == '__main__':
    for epoch in range(500):
        for index, data in enumerate(train_loader, 0):  #train_loaderWhat is stored is the split and combined mini-batch training samples and the corresponding labels
            inputs, labels = data #inputs labels都是张量
            inputs = inputs.float()
            labels = labels.float()
            y_pred = mymodel(inputs)
            y_pred = y_pred.squeeze(-1)
            loss = criterion(y_pred, labels)

            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            sum_loss += loss.item()

            print('epoch = ', epoch + 1,'index = ', index+1, 'loss = ', loss.item())
        epoch_list.append(epoch)
        loss_list.append(sum_loss/batch)
        print(sum_loss/batch)
        sum_loss = 0

test_x = pd.read_csv('Dataset\\titanic\\test.csv')
features = ["Pclass", "Sex", "SibSp", "Parch", "Fare"]
test_x_data = torch.from_numpy(np.array(pd.get_dummies(test_x[features])))
test_x_data = test_x_data.float()
y_test_pred = mymodel(test_x_data)
len_y = y_test_pred.shape[0]
y = []
for i in range(len_y):
    if(y_test_pred[i].item()<0.5):
        y.append(0)
    else:
        y.append(1)
for i in range(len(y)):
    print(y[i])

Finally put the outputy保存到gender_submission.csv中,提交kaggle即可.

Just started practicing the basics,Improve slowly later…