打卡第37天：信贷神经网络训练

仔细回顾一下神经网络到目前的内容，没跟上进度的同学补一下进度。

●作业：对之前的信贷项目，利用神经网络训练下，尝试用到目前的知识点让代码更加规范和美观。

●探索性作业（随意完成）：尝试进入nn.Module中，查看他的方法

import torch
import pandas as pd
import torch.nn as nn
import torch.optim as optim
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import time
import matplotlib.pyplot as plt
 # 替换import numpy as np     #用于数值计算，提供了高效的数组操作。
import matplotlib.pyplot as plt    #用于绘制各种类型的图表
import seaborn as sns   #基于matplotlib的高级绘图库，能绘制更美观的统计图形。
from tqdm import tqdm 
 # 设置GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"使用设备: {device}")

 # 设置中文字体（解决中文显示问题）
plt.rcParams['font.sans-serif'] = ['SimHei']  # Windows系统常用黑体字体
plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号
data = pd.read_csv(r'C:\Users\许兰\Desktop\打卡文件\python60-days-challenge-master\data.csv')    #读取数据

# 先筛选字符串变量 
discrete_features = data.select_dtypes(include=['object']).columns.tolist()
# Home Ownership 标签编码
home_ownership_mapping = {
    'Own Home': 1,
    'Rent': 2,
    'Have Mortgage': 3,
    'Home Mortgage': 4
}
data['Home Ownership'] = data['Home Ownership'].map(home_ownership_mapping)

# Years in current job 标签编码
years_in_job_mapping = {
    '< 1 year': 1,
    '1 year': 2,
    '2 years': 3,
    '3 years': 4,
    '4 years': 5,
    '5 years': 6,
    '6 years': 7,
    '7 years': 8,
    '8 years': 9,
    '9 years': 10,
    '10+ years': 11
}
data['Years in current job'] = data['Years in current job'].map(years_in_job_mapping)

# Purpose 独热编码，记得需要将bool类型转换为数值
data = pd.get_dummies(data, columns=['Purpose'])
data2 = pd.read_csv(r'C:\Users\许兰\Desktop\打卡文件\python60-days-challenge-master\data.csv') # 重新读取数据，用来做列名对比
list_final = [] # 新建一个空列表，用于存放独热编码后新增的特征名
for i in data.columns:
    if i not in data2.columns:
       list_final.append(i) # 这里打印出来的就是独热编码后的特征名
for i in list_final:
    data[i] = data[i].astype(int) # 这里的i就是独热编码后的特征名



# Term 0 - 1 映射
term_mapping = {
    'Short Term': 0,
    'Long Term': 1
}
data['Term'] = data['Term'].map(term_mapping)
data.rename(columns={'Term': 'Long Term'}, inplace=True) # 重命名列
continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()  #把筛选出来的列名转换成列表
 
 # 连续特征用中位数补全
for feature in continuous_features:     
    mode_value = data[feature].mode()[0]            #获取该列的众数。
    data[feature].fillna(mode_value, inplace=True)          #用众数填充该列的缺失值，inplace=True表示直接在原数据上


# 划分训练集、验证集和测试集，因为需要考2次
# 这里演示一下如何2次划分数据集，因为这个函数只能划分一次，所以需要调用两次才能划分出训练集、验证集和测试集。
from sklearn.model_selection import train_test_split
X = data.drop(['Credit Default'], axis=1)  # 特征，axis=1表示按列删除
y = data['Credit Default']  # 标签
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # 80%训练集，20%临时集

# 归一化数据
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

X_train = torch.FloatTensor(X_train).to(device)
y_train = torch.LongTensor(y_train.to_numpy()).to(device)
X_test = torch.FloatTensor(X_test).to(device)
y_test = torch.LongTensor(y_test).to(device)


class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.fc1 = nn.Linear(31, 18)  # 输入层到隐藏层
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(18, 2)  # 隐藏层到输出层

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

# 实例化模型并移至GPU
model = MLP()

# 分类问题使用交叉熵损失函数
criterion = nn.CrossEntropyLoss()

# 使用随机梯度下降优化器
optimizer = optim.SGD(model.parameters(), lr=0.01)

# 训练模型
num_epochs = 20000  # 训练的轮数

# 用于存储每100个epoch的损失值和对应的epoch数
losses = []
epochs = []
start_time = time.time()  # 记录开始时间

# 创建tqdm进度条
with tqdm(total=num_epochs, desc="训练进度", unit="epoch") as pbar:
    # 训练模型
    for epoch in range(num_epochs):
        # 前向传播
        outputs = model(X_train)  # 隐式调用forward函数
        loss = criterion(outputs, y_train)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 记录损失值并更新进度条
        if (epoch + 1) % 200 == 0:
            losses.append(loss.item())
            epochs.append(epoch + 1)
            # 更新进度条的描述信息
            pbar.set_postfix({'Loss': f'{loss.item():.4f}'})

        # 每1000个epoch更新一次进度条
        if (epoch + 1) % 1000 == 0:
            pbar.update(1000)  # 更新进度条

    # 确保进度条达到100%
    if pbar.n < num_epochs:
        pbar.update(num_epochs - pbar.n)  # 计算剩余的进度并更新

time_all = time.time() - start_time  # 计算训练时间
print(f'Training time: {time_all:.2f} seconds')

model.eval() # 设置模型为评估模式
with torch.no_grad(): # torch.no_grad()的作用是禁用梯度计算，可以提高模型推理速度
    outputs = model(X_test)  # 对测试数据进行前向传播，获得预测结果
    _, predicted = torch.max(outputs, 1) # torch.max(outputs, 1)返回每行的最大值和对应的索引

    correct = (predicted == y_test).sum().item() # 计算预测正确的样本数
    accuracy = correct / y_test.size(0)
    print(f'测试集准确率: {accuracy * 100:.2f}%')

损失曲线：

模型评估：

@浙大疏锦行