动手学深度学习——实战Kaggle比赛:预测房价

  1. 导入包,建立字典DATA_HUB包含数据集的url和验证文件完整性的sha-1密钥。
  2. 定义download()函数用来下载数据集, 将数据集缓存在本地目录(默认情况下为…/data)中, 并返回下载文件的名称。
  3. 定义download_extract()函数下载并解压缩一个zip或tar文件,定义download_all()将所有数据集从DATA_HUB下载到缓存目录中。
  4. 进行数据标准化得到all_features
  5. 定义损失函数loss和线性模型net
  6. 采用价格预测的对数log_rmse()来衡量差异
  7. 定义训练函数train(),采用Adam优化器
  8. 定义K折交叉验证get_k_fold_data(),并且在K折交叉验证中训练K次k_fold()
  9. 最后进行预测并保存预测文件train_and_pred()
#!/usr/bin/env python
# coding: utf-8


# 导入所需要的包
import hashlib
import os
import tarfile
import zipfile
import requests

#@save
# DATA_HUB为二元组:包含数据集的url和验证文件完整性的sha-1密钥
DATA_HUB = dict()

# 数据集托管在DATA_URL的站点上
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'


"""
    定义download函数:
    1、下载数据集,将数据集缓存在本地目录(../data),并返回下载文件的名称
    2、如果缓存目录中存在此数据集文件,并且与sha-1与存储在DATA_HUB中相匹配,则使用缓存的文件
"""
# download(文件名称,缓存目录)
def download(name, cache_dir=os.path.join('..', 'data')): #@save
    """下载一个DATA_HUB中的文件,返回本地文件名"""
    assert name in DATA_HUB, f"{name} 不存在于 {DATA_HUB}"
    url, sha1_hash = DATA_HUB[name]
    os.makedirs(cache_dir, exist_ok=True)
    fname = os.path.join(cache_dir, url.split('/')[-1])
    if os.path.exists(fname):
        sha1 = hashlib.sha1()
        with open(fname, 'rb') as f:
            while True:
                data = f.read(1048576)
                if not data:
                    break
                sha1.update(data)
        if sha1.hexdigest() == sha1_hash:
            return fname # 命中缓存
    print(f'正在从{url}下载{fname}...')
    r = requests.get(url, stream=True, verify=True)
    with open(fname, 'wb') as f:
        f.write(r.content)
    return fname



"""
    实现两个实用函数:
    1、一个将下载并解压缩一个zip/tar文件
    2、将使用的数据集从DATA_HUB下载到缓存目录
"""
def download_extract(name, folder=None): #@save
    """下载并解压zip/tar文件"""
    fname = dowanload(name)
    base_dir = os.path.dirname(fname)
    data_dir = os.path.splitext(fname)
    if ext == '.zip':
        fp = zipfile.Zipfile(fname, 'r')
    elif ext in ('.tar', '.gz'):
        fp = tarfile.open(fname, 'r')
    else:
        assert False, '只有zip/tar文件可以解压'
    fp.extractall(base_dir)
    return os.path.join(base_dir, folder) if folder else data_dir

def download_all(): #@save
    """下载DATA_HUB中的所有文件"""
    for name in DATA_HUB:
        download(name)




# 如果没有安装pandas,请取消下一行的注释
# !pip install pandas

get_ipython().run_line_magic('matplotlib', 'inline')
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l




# 使用上面定义的脚本下载并缓存Kaggle房屋数据集
DATA_HUB['kaggle_house_train'] = (  #@save
    DATA_URL + 'kaggle_house_pred_train.csv',
    '585e9cc93e70b39160e7921475f9bcd7d31219ce')

DATA_HUB['kaggle_house_test'] = (  #@save
    DATA_URL + 'kaggle_house_pred_test.csv',
    'fa19780a7b011d9b009e8bff8e99922a8ee2eb90')



# 使用pandas分布加载包含训练数据和测试数据的两个csv文件
train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))




# 训练数据集包括1460个样本,每个样本80个特征和1个标签
# 测试数据集包括1459个样本,每个样本80个特征
print(train_data.shape)
print(test_data.shape)



# 前四个和最后两个特征,以及相应标签(房价)
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])



# 对于每个样本:删除第一个特征ID,因为其不携带任何用于预测的信息
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:-1]))



"""
    数据预处理:
    1、将所有缺失的值替换为相应特征的平均值
    2、为了将所有数据放在共同的尺度上,通过特征重新缩放到零均值和单位方差来标准化数据
        (1)方便优化
        (2)不知道哪些特征是相关的,所以不想让惩罚分配给一个特征的系数比分配给其他特征的系数更大
    3、处理离散值,用独热编码来替换。如"MSZoning_RL"为1,"MSZoning_RM"为0
"""
# 若无法获得测试数据,则可根据训练数据计算均值和标准差:x←(x-μ)/σ
# 获取无法获得测试数据的数量
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())) 
# 在标准化数据之后,所有均值消失,因此我们可以将缺失值设置为0
all_features[numeric_features] = all_features[numeric_features].fillna(0)


#“Dummy_na=True”将“na”(缺失值)视为有效的特征值,并为其创建指示符特征
# all_features是删除ID那一列之后,将每个样本中所有的特征连接起来
all_features = pd.get_dummies(all_features, dummy_na=True)
all_features.shape



# 通过values属性将数据从pandas格式提取numpy格式,并将其转为张量用于训练
n_train = train_data.shape[0]
train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float32)
test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float32)
train_labels = torch.tensor(
    train_data.SalePrice.values.reshape(-1, 1), dtype=torch.float32)



"""
    训练一个带有损失平方的线性模型:
    1、损失函数为损失平方
    2、线性模型作为基线模型
"""
loss = nn.MSELoss()
in_features = train_features.shape[1]

def get_net():
    net = nn.Sequential(nn.Linear(in_features,1))
    return net


# 采用价格预测的对数来衡量差异:√ ̄(1/n*(∑(logy - logy')^2))
def log_rmse(net, features, labels):
    # 为了在取对数时进一步稳定该值,将小于1的值设置为1
    clipped_preds = torch.clamp(net(features), 1, float('inf'))
    rmse = torch.sqrt(loss(torch.log(clipped_preds),
                          torch.log(labels)))
    return rmse.item()



# 优化器借助Adam优化器
"""
    定义训练函数:
    1、加载训练数据集
    2、使用Adam优化器(对初始学习率不那么敏感)
    3、进行训练:计算损失,进行梯度优化,返回训练损失和测试损失
"""
def train(net, train_features, train_labels, test_features, test_labels,
         num_epochs, learning_rate, weight_decay, batch_size):
    train_ls, test_ls = [], []
    train_iter = d2l.load_array((train_features, train_labels), batch_size)
    # 这里使用的是Adam优化算法
    optimizer = torch.optim.Adam(net.parameters(),
                                lr = learning_rate,
                                weight_decay = weight_decay)
    for epoch in range(num_epochs):
        for X,y in train_iter:
            optimizer.zero_grad()
            l = loss(net(X), y)
            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



"""
    定义K折交叉验证:
    1、当k > 1时,进行K折交叉验证,将数据集分为K份
    2、选择第i个切片作为验证集,其余部分作为训练数据
    3、第一片的训练数据直接填进去,之后的使用cat进行相连接
""" 
def get_k_fold_data(k, i, X, y):
    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], 0) 
            y_train = torch.cat([y_train, y_part], 0)
    return X_train, y_train, X_valid, y_valid



"""
    在K折交叉验证中训练K次:
    1、返回训练和验证误差的平均值
    2、可视化训练误差和验证误差
"""
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()
        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.plot(list(range(1, num_epochs + 1)), [train_ls, valid_ls],
                     xlabel='epoch', ylabel='rmse', xlim=[1, num_epochs],
                     legend=['train', 'valid'], yscale='log')
        print(f'折{i + 1}, 训练log rmse{float(train_ls[-1]):f},'
             f'验证log rmse{float(valid_ls[-1]):f}')
    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(f'{k}-折验证:平均训练log rmse:{float(train_l):f},'
     f'平均验证log rmse:{float(valid_l):f}')



"""
    提交Kaggle预测:
    1、使用所有数据进行训练,得到模型
    2、该模型可以应用到测试集上,将预测保存在csv文件
"""
def train_and_pred(train_features, test_features, train_labels, test_data,
                  num_epochs, lr, weight_decay, batch_size):
    net = get_net()
    train_ls, _ = train(net, train_features, train_labels, None, None,
         num_epochs, lr, weight_decay, batch_size)
    d2l.plot(np.arange(1, num_epochs + 1), [train_ls], xlabel='epoch',
            ylabel='log rmse', xlim=[1, num_epochs], yscale='log')
    print(f'训练log rmse:{float(train_ls[-1]):f}')
    # 将网络应用与测试集。
    preds = net(test_features).detach().numpy()
    # 将其重新格式化以导出到Kaggle
    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)



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

你可能感兴趣的:(深度学习,深度学习,人工智能)