深度学习titanic（初学）Kaggle刘二作业第八课

b站刘二视频，地址：

《PyTorch深度学习实践》完结合集_哔哩哔哩_bilibili

代码 （数据可私信或评论获取）

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

#-------------------------------------------step1  prepare data----------------------------------------

class Data(Dataset):
    def __init__(self, filepath):
        xy = pd.read_csv(filepath)
        self.len = xy.shape[0]
        feature = ["Pclass", "Sex", "SibSp", "Parch", "Fare"] #选取用的特征

        self.x_data = torch.from_numpy(np.array(pd.get_dummies(xy[feature])))
        self.y_data = torch.from_numpy(np.array(xy["Survived"]))

    def __getitem__(self, item):
        return self.x_data[item], self.y_data[item]

    def __len__(self):
        return self.len

dataset = Data('train.csv')
dataloder = DataLoader(dataset=dataset, batch_size=32, shuffle=True)

#------------------------------------------setp2 design model--------------------------------------------

class Modle(torch.nn.Module):
    def __init__(self):
        super(Modle, 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):#对test进行预测
        with torch.no_grad():
            x = self.forward(x)
            y = []

            for i in x:
                if i > 0.5:
                    y.append(1)
                else:
                    y.append(0)
            return y

modle = Modle()

#---------------------------------------step3    constuct loss and optimizer-----------------------------

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

#---------------------------------------step4 traning cycle------------------------------------------

if __name__ == '__main__':

    loss_lst = []
    for epoch in range(1000):
        sum = 0
        for i, data in enumerate(dataloder, 0):
            inputs, labels = data
            inputs = inputs.float()
            labels = labels.float()

            y_pred = modle(inputs)
            y_pred = y_pred.squeeze(-1)#前向输出结果是[[12],[34],[35],[23],[11]]这种，需要将这个二维矩阵转换成一行[12,34,35,23,11]
            #print(y_pred.size(), labels.size())
            loss = criteration(y_pred, labels)
            sum += loss.item()

            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        loss_lst.append(sum / dataloder.batch_size)

    #可视化
    num_lst = [i for i in range(len(loss_lst))]
    plt.plot(num_lst, loss_lst)
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.show()

    #测试集
    test_data = pd.read_csv('test.csv')
    feature = ["Pclass", "Sex", "SibSp", "Parch", "Fare"]  # 选取用的特征

    test = torch.from_numpy(np.array(pd.get_dummies(test_data[feature])))
    y = modle.predict(test.float())
    outputs = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': y})
    outputs.to_csv('predict_titanic', index=False)  # index=False 代表不保存索引
    outputs.head()

 

输出结果