实战Kaggle比赛:房价预测

简述

  • 读取数据
  • 数据预处理
  • 定义模型:线性函数
  • 定义损失函数:对数均方根误差
  • 选择验证方法:k-折交叉验证
  • 选择优化算法:Adam优化算法
  • 训练与预测

代码

import torch
import torch.nn as nn
import numpy as np
import pandas as pd
import sys
sys.path.append("..")
import d2lzh_pytorch as d2l

print(torch.__version__)
torch.set_default_tensor_type(torch.FloatTensor)

# 获取和读取数据集
'''下面使用pandas读取数据'''
train_data = pd.read_csv('data/kaggle_house/train.csv')
test_data = pd.read_csv('data/kaggle_house/test.csv')

print(train_data.shape)  # 输出 (1460, 81)
print(test_data.shape)   # 输出 (1459, 80)

'''查看前4个样本的前4个特征、后2个特征和标签(SalePrice)'''
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])

'''可以看到第一个特征是Id,它能帮助模型记住每个训练样本,但难以推广到测试样本,
所以我们不使用它来训练。我们将所有的训练数据和测试数据的79个特征按样本连结。'''
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

# 数据预处理
'''我们对连续数值的特征做标准化(standardization):
设该特征在整个数据集上的均值为μ,标准差为σ。
那么,我们可以将该特征的每个值先减去μ再除以σ得到标准化后的每个特征值。
对于缺失的特征值,我们将其替换成该特征的均值。'''
numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index
all_features[numeric_features] = all_features[numeric_features].apply(
    lambda x: (x - x.mean()) / (x.std()))
# 标准化后,每个数值特征的均值变为0,所以可以直接用0来替换缺失值
all_features[numeric_features] = all_features[numeric_features].fillna(0)

'''接下来将离散数值转成指示特征。举个例子,假设特征MSZoning里面有两个不同的离散值RL和RM,
那么这一步转换将去掉MSZoning特征,并新加两个特征MSZoning_RL和MSZoning_RM,其值为0或1。
如果一个样本原来在MSZoning里的值为RL,那么有MSZoning_RL=1且MSZoning_RM=0。'''
# dummy_na=True将缺失值也当作合法的特征值并为其创建指示特征
all_features = pd.get_dummies(all_features, dummy_na=True)
print(all_features.shape) # (2919, 331)

'''最后,通过values属性得到NumPy格式的数据,并转成Tensor方便后面的训练。'''
n_train = train_data.shape[0]
train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float)
test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float)
train_labels = torch.tensor(train_data.SalePrice.values, dtype=torch.float).view(-1, 1)

# 训练模型
loss = torch.nn.MSELoss()

def get_net(feature_num):
    net = nn.Linear(feature_num, 1)
    for param in net.parameters():
        nn.init.normal_(param, mean=0, std=0.01)
    return net

'''对数均方根误差'''
def log_rmse(net, features, labels):
    with torch.no_grad():
        # 将小于1的值设成1,使得取对数时数值更稳定
        clipped_preds = torch.max(net(features), torch.tensor(1.0))
        rmse = torch.sqrt(loss(clipped_preds.log(), labels.log()))
    return rmse.item()

'''下面的训练函数使用了Adam优化算法。
相对之前使用的小批量随机梯度下降,它对学习率相对不那么敏感。'''
def train(net, train_features, train_labels, test_features, test_labels,
          num_epochs, learning_rate, weight_decay, batch_size):
    train_ls, test_ls = [], []
    dataset = torch.utils.data.TensorDataset(train_features, train_labels)
    train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True)
    # 这里使用了Adam优化算法
    optimizer = torch.optim.Adam(params=net.parameters(), lr=learning_rate, weight_decay=weight_decay)
    net = net.float()
    for epoch in range(num_epochs):
        for X, y in train_iter:
            l = loss(net(X.float()), y.float())
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
        train_ls.append(log_rmse(net, train_features, train_labels))
        if test_labels is not None:
            test_ls.append(log_rmse(net, test_features, test_labels))
    return train_ls, test_ls

# K折交叉验证
def get_k_fold_data(k, i, X, y):
    # 返回第i折交叉验证时所需要的训练和验证数据
    assert k > 1
    fold_size = X.shape[0] // k
    X_train, y_train = None, None
    for j in range(k):
        idx = slice(j * fold_size, (j + 1) * fold_size)
        X_part, y_part = X[idx, :], y[idx]
        if j == i:
            X_valid, y_valid = X_part, y_part
        elif X_train is None:
            X_train, y_train = X_part, y_part
        else:
            X_train = torch.cat((X_train, X_part), dim=0)
            y_train = torch.cat((y_train, y_part), dim=0)
    return X_train, y_train, X_valid, y_valid
'''在K折交叉验证中我们训练K次并返回训练和验证的平均误差。'''
def k_fold(k, X_train, y_train, num_epochs,
           learning_rate, weight_decay, batch_size):
    train_l_sum, valid_l_sum = 0, 0
    for i in range(k):
        data = get_k_fold_data(k, i, X_train, y_train)
        net = get_net(X_train.shape[1])
        train_ls, valid_ls = train(net, *data, num_epochs, learning_rate,
                                   weight_decay, batch_size)
        train_l_sum += train_ls[-1]
        valid_l_sum += valid_ls[-1]
        if i == 0:
            d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse',
                         range(1, num_epochs + 1), valid_ls,
                         ['train', 'valid'])
        print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1]))
    return train_l_sum / k, valid_l_sum / k

# 模型选择
k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64
train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, lr, weight_decay, batch_size)
print('%d-fold validation: avg train rmse %f, avg valid rmse %f' % (k, train_l, valid_l))

# 预测
def train_and_pred(train_features, test_features, train_labels, test_data,
                   num_epochs, lr, weight_decay, batch_size):
    net = get_net(train_features.shape[1])
    train_ls, _ = train(net, train_features, train_labels, None, None,
                        num_epochs, lr, weight_decay, batch_size)
    d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse')
    print('train rmse %f' % train_ls[-1])
    preds = net(test_features).detach().numpy()
    test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0])
    submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis=1)
    submission.to_csv('./submission.csv', index=False)

train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)

  • 0
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值