练习：Kaggle房价预测

注册kaggle发生不出现验证码的情况，参考了：https://www.cnblogs.com/liuxiaomin/p/11785645.html

这份经典的练习里有很多需要揣摩的，我看的一些问题如下：

K折交叉验证：https://www.cnblogs.com/zymei/p/10832582.html

epochs,batch_size,iteratios概念详解：https://blog.csdn.net/u013041398/article/details/72841854

代码是按照沐神的文档跑了一遍，将num_epochs改成了200，如下：

import d2lzh as d2l
from mxnet import autograd, gluon, init, nd
from mxnet.gluon import data as gdata, loss as gloss, nn
import numpy as np
import pandas as pd

train_data = pd.read_csv('data/train.csv')
test_data = pd.read_csv('data/test.csv')

#除去训练集和测试集的第一列ID，因为他们并没有特别的作用。然后将训练集和测试集放在一起
#这样就有79个特征
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

#连续数值标准化
numeric_features = all_features.dtypes[all_features.dtypes!='object'].index
#object是dataframe的字符类型，这里选出不是数值类型的特征
all_features[numeric_features] = all_features[numeric_features].apply(
    lambda x: (x - x.mean()) / (x.std()))
#这个部分的处理需要再琢磨一下,用了匿名函数
all_features[numeric_features] = all_features[numeric_features].fillna(0)

#离散数值转成指示特征，d.get_dummies很好用
all_features = pd.get_dummies(all_features, dummy_na=True)

#最后，通过values属性得到NumPy格式的数据，并转成NDArray方便后面的训练。
n_train = train_data.shape[0]
train_features = nd.array(all_features[:n_train].values)
test_features = nd.array(all_features[n_train:].values)
train_labels = nd.array(train_data.SalePrice.values).reshape((-1,1))

#训练模型：使用一个基本的线性回归模型和平方损失函数来训练模型。
loss = gloss.L2Loss()

def get_net():
    net = nn.Sequential()
    net.add(nn.Dense(1))
    net.initialize()
    return net

#使用对数均方根误差
def log_rmse(net,features,labels):
    #将小于1的值设成1，使得取对数时数值更稳定
    clipped_preds = nd.clip(net(features),1,float('inf'))
    rmse = nd.sqrt(2*loss(clipped_preds.log(),labels.log()).mean())
    return rmse.asscalar()

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 = gdata.DataLoader(gdata.ArrayDataset(
        train_features, train_labels), batch_size, shuffle=True)
    # 这里使用了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
    trainer = gluon.Trainer(net.collect_params(), 'adam', {
        'learning_rate': learning_rate, 'wd': weight_decay})
    for epoch in range(num_epochs):
        for X, y in train_iter:
            with autograd.record():
                l = loss(net(X), y)
            l.backward()
            trainer.step(batch_size)
        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

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 = nd.concat(X_train, X_part, dim=0)
            y_train = nd.concat(y_train, y_part, dim=0)
    return X_train, y_train, X_valid, y_valid

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.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

k, num_epochs, lr, weight_decay, batch_size = 5, 200, 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))

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.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse')
    print('train rmse %f' % train_ls[-1])
    preds = net(test_features).asnumpy()
    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)

结果如下：

这是kaggle上提交的结果，排名在50%左右（汗）：

总结：由于训练次数太少，效果并不好。用来学习一下数据处理和训练方法还是可以的。