数据预处理及模型预测笔记——简单搭建架构

数据预处理及模型预测——简单搭建架构

数据预处理操作

导包

import numpy as np
import pandas as pd

import warnings
warnings.filterwarnings('ignore') # 隐藏警告

读取数据集

df = pd.read_excel(r'D:\Mycode\JupyterWork\MyWork\AN\Standard.xlsx')

数据选取

del df["level_0"]
df.sort_values(by='label',ascending=False,inplace=True)
df["index"].value_counts() # 得出共1642家企业，每个企业有四年的观测数据
# loc()、iloc()方法的使用
df.loc[df["label"] ==0]
df.iloc[:600,:]
df = df.reset_index()  # 重设索引
df.shape

数据预处理

缺失值填充

np.all(pd.notnull(df))  # 判断是否有空值
# 若有空值

划分数据集

from sklearn.model_selection import train_test_split
train_features, test_features, train_labels, test_labels = train_test_split(numdf,label,test_size = 0.1, random_state = 0)

# 通过values属性，我们可以 从pandas格式中提取NumPy格式，并将其转换为张量表示用于训练。
n_train = train_features.shape[0]
train_features = torch.tensor(np.array(train_features), dtype=torch.float32)
test_features = torch.tensor(np.array(test_features), dtype=torch.float32)
train_labels = torch.tensor(train_labels.reshape(-1, 1), dtype=torch.float32)

训练

import torch
from torch import nn
from d2l import torch as d2l


# 训练一个带有损失平方的线性模型
loss = nn.MSELoss()
in_features = train_features.shape[1]    # 特征数
def get_net():
    net = nn.Sequential(nn.Linear(in_features,1))
    return net

MLP构建分析数据（对回归问题）

# 稳定不同样本误差
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
    #  clamp()将输入input张量每个元素的值压缩到区间 [min,max]，并返回结果到一个新张量。
    clipped_preds = torch.clamp(net(features), 1, float('inf'))  # 正负无穷 float('inf')
    
    rmse = torch.sqrt(loss(torch.log(clipped_preds),  torch.log(labels)))
    return rmse.item()

设置优化器

深度学习的目标是通过不断改变网络参数，使得参数能够对输入做各种非线性变换拟合输出，本质上就是一个函数去寻找最优解，所以如何去更新参数是深度学习研究的重点。
通常将更新参数的算法称为优化器，字面理解就是通过什么算法去优化网络模型的参数。常用的优化器就是梯度下降。接下来讲的就是梯度下降和进一步优化梯度下降的各种算法。
优化器或者优化算法，是通过训练优化参数，来最小化（最大化）损失函数。损失函数是用来计算测试集中目标值Y的真实值和预测值的偏差程度。
为了使模型输出逼近或达到最优值，我们需要用各种优化策略和算法，来更新和计算影响模型训练和模型输出的网络参数。
按吴恩达老师所说的，梯度下降（Gradient Descent）就好比一个人想从高山上奔跑到山谷最低点，用最快的方式（steepest）奔向最低的位置（minimum）

# 借助Adam优化器
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

设置k折交叉验证

使用(K)折交叉验证来选择模型并调整超参数

# \(K\)折交叉验证
def get_k_fold_data(k, i, X, y):
    assert k > 1    # 设置断言确保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

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

# 定义超参数
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

# 提交你的Kaggle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_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}')
    # 将网络应用于测试集。
    preds = net(test_features).detach().numpy() # detach()返回一个new Tensor，只不过不再有梯度。
    # 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)
    
# 执行提交函数  
train_and_pred(train_features, test_features, train_labels, test_data,
        num_epochs, lr, weight_decay, batch_size)

submission.to_csv(‘submission.csv’, index=False)

执行提交函数

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