import hashlib
import os
import tarfile
import zipfile
import requests
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l

# 下载和缓存数据集
DATA_HUB = dict()  # 创建一个字典
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'


def download(name, cache_dir=os.path.join('..', 'data')):
    """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}"  # 检查name是否作为值在DATA_HUB中
    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:  # 以二进制只读模式打开文件
            while True:
                data = f.read(1048576)  # 每次读1MB的数据
                if not data:
                    break
                sha1.update(data)
            if sha1.hexdigest() == sha1_hash:  # 比较两个哈希值是否相等
                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


def download_extract(name, folder=None):
    """下载并解压zip/tar文件"""
    fname = download(name)
    base_dir = os.path.dirname(fname)
    data_dir, ext = os.path.splitext(fname)  # 文件名与拓展名
    if ext == '.zip':
        fp = zipfile.ZipFile(fname, 'r')
    elif ext == '.tar':
        fp = tarfile.open(fname, 'r')
    else:
        assert False, '只有zip/tar文件可以被解压缩'
    fp.extractall(base_dir)
    return os.path.join(base_dir, folder) if folder else data_dir


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


# 访问和读取数据集
DATA_HUB['kaggle_house_train'] = (DATA_URL + 'kaggle_house_pred_train.csv',
                                  '585e9cc9370b9160e7921475fbcd7d31219ce')

DATA_HUB['kaggle_house_test'] = (DATA_URL + 'kaggle_house_pred_test.csv',
                                 'fal9780a7b011d9b009e8bff8e99922a8ee2eb90')

train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))

# 看一下数据集长什么样子
'''
print(train_data.shape)
print(test_data.shape)

print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])
'''

# 看到第一个特征是ID,不带有任何预测信息，所以移除
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))  # 沿着行连接训练集和测试集的特征

# 数据预处理

# 若无法获得测试数据，可以根据训练数据计算均值和标准差
numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index  # 获得all_features中的数值的索引
all_features[numeric_features] = all_features[numeric_features].apply(
    lambda x: (x - x.mean()) / x.std())  # 将数值转为均值为0，标准差为1的数
# 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)

# 处理离散值
# dummy_na=True将na(缺失值)视为有效的特征值
all_features = pd.get_dummies(all_features, dummy_na=True)
# print(all_features.shape)

n_train = train_data.shape[0]
# 预处理完后要将训练集和测试集分隔开
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)  # 还需要将售价提取出来

# 训练
loss = nn.MSELoss()
in_features = train_features.shape[1]


def get_net():
    net = nn.Sequential(nn.Linear(in_features, 64),
                        nn.ReLU(),
                        nn.Linear(64, 64),
                        nn.ReLU(),
                        nn.Linear(64,1))
    return net


def log_rmse(net, features, labels):
    # 为了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'))
    """
    torch.clamp(input, min, max)：这个函数将 input 张量中的每个元素的值限制在 [min, max] 的范围内。如果某个元素的值小于 min，则将其
    设置为 min；如果大于 max，则将其设置为 max；如果已经在 [min, max] 范围内，则保持不变。
    """
    rmse = torch.sqrt(loss(torch.log(clipped_preds), torch.log(labels)))
    return rmse.item()


def train(net, train_features, train_labels, test_features, test_labels, num_epochs, lr, 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优化器
    optimizer = torch.optim.Adam(net.parameters(), lr=lr, 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


# K折交叉验证
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)  # 返回一个对象切片器 从j * fold_size 到 (j + 1) * fold_size
        X_part, y_part = X[idx, :], y[idx]
        if j == 1:
            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


def k_fold(k, X_train, y_train, num_epochs, lr, 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, lr, 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


k, num_epochs, lr, weight_decay, batch_size = 5, 200, 0.03, 0.5, 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}')

d2l.plt.show()


def train_and_pred(train_features, test_feature, 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'train log rmse {float(train_ls[-1]):f}')
    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)