利用pytorch两层线性网络对titanic数据集进行分类（kaggle)

本文主要是介绍利用pytorch两层线性网络对titanic数据集进行分类（kaggle)，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

利用pytorch两层线性网络对titanic数据集进行分类

最近在看pytorch的入门课程，做了一下在kaggle网站上的作业，用的是titanic数据集，因为想搭一下神经网络，所以数据加载部分简单的把训练集和测试集中有缺失值的列还有含有字符串的列去除了，加入了DataLoader模块，其实这个数据集很小，用不到，本人还没入门，小白一枚。

import torch 
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
import numpy as np
from torchvision import datasets
from torchvision import transforms
import pandas as pdclass titanicDataset(Dataset):def __init__(self,filepath):xy=np.loadtxt(filepath,delimiter=',',skiprows=1,usecols=[1,2,7,8],dtype=np.float32)self.len=xy.shape[0]# print(self.len)self.y_data=torch.from_numpy(xy[:,[0]])self.x_data=torch.from_numpy(xy[:,1:])def __getitem__(self,index):#获取索引元素 return self.x_data[index],self.y_data[index]def __len__(self):return self.len
dataset=titanicDataset('./pytorch/dataset/titanic/train.csv')
train_loader=DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=0)# print(dataset.x_data,dataset.y_data)
test_loader=DataLoader(dataset=np.loadtxt('./pytorch/dataset/titanic/test.csv',delimiter=',',skiprows=1,usecols=[1,6,7],dtype=np.float32),batch_size=32,shuffle=False,num_workers=0)
print(next(iter(test_loader)))class Model(torch.nn.Module):def __init__(self):super(Model,self).__init__()# self.linear1=torch.nn.Linear(4,3)self.linear2=torch.nn.Linear(3,2)self.linear3=torch.nn.Linear(2,1)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(size_average=True)
optimizer=torch.optim.SGD(model.parameters(),lr=0.1,momentum=0.9)
for epoch in range(10000):acc_num=0for i,data in enumerate(train_loader,0):#1.Prepare datainputs,labels=data# print(inputs.shape[0])#2.Forwardy_pred=model(inputs)loss=criterion(y_pred,labels)# print(epoch,i,loss.item())#3.Backwardoptimizer.zero_grad()loss.backward()#4.Updateoptimizer.step()y_pred_label=torch.where(y_pred>0.5,torch.tensor([1.0]),torch.tensor([0.0]))acc_num+=torch.eq(y_pred_label,labels).sum().item()# print(acc_num,len(dataset),len(train_loader.dataset))acc=acc_num/len(dataset)
print(acc)
# print(test_loader)
# print(test_loader.dataset.shape)
out = model(torch.tensor(test_loader.dataset))
y_pred = torch.where(out>0.5,torch.tensor([1.0]),torch.tensor([0.0]))[:,0]
print(y_pred)
print(pd.Series(y_pred))
id=pd.read_csv('./pytorch/dataset/titanic/test.csv',usecols=['PassengerId']).iloc[:,0]
# print(type(id))pd.DataFrame({'PassengerId':id,'Survived':pd.Series(y_pred,dtype=int)}).to_csv('pred.csv',index=None)
a=pd.DataFrame([id,pd.Series(y_pred)])
print(a)
# print(y_pred[-10:])# for x in test_loader:
#     print(x.shape)
#     out = model(x)
#     y_pred = torch.where(out>0.5,torch.tensor([1.0]),torch.tensor([0.0]))
# print(y_pred)

这篇关于利用pytorch两层线性网络对titanic数据集进行分类（kaggle)的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---