**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。
python
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
import time
from tqdm import tqdm
import warnings
warnings.filterwarnings("ignore")
# 使用设备
device = torch.device("mps")
# 读取数据
data = pd.read_csv('data.csv')
# 筛选连续型特征
continuous_features = data.select_dtypes(include=['float64', 'int64']).columns.to_list()
# 筛选离散型特征
discrete_features = data.select_dtypes(include=['object']).columns.to_list()
# 缺失值补全
for feature in continuous_features:
data[feature].fillna(data[feature].mode()[0], inplace=True)
# 标签编码
mapping = {
'Home Ownership': {
'Own Home': 1,
'Rent': 2,
'Have Mortgage': 3,
'Home Mortgage': 4
},
'Years in current job': {
'< 1 year': 0,
'1 year': 1,
'2 years': 2,
'3 years': 3,
'4 years': 4,
'5 years': 5,
'6 years': 6,
'7 years': 7,
'8 years': 8,
'9 years': 9,
'10+ years': 10
},
'Term': {
'Short Term': 0,
'Long Term': 1
}
}
data['Home Ownership'] = data['Home Ownership'].map(mapping['Home Ownership'])
data['Years in current job'] = data['Years in current job'].map(mapping['Years in current job'])
data['Term'] = data['Term'].map(mapping['Term'])
data.rename(columns={'Term': 'Long Term'}, inplace=True)
# 独热编码
data = pd.get_dummies(data, columns=['Purpose'])
data2 = pd.read_csv('data.csv')
list = []
for i in data.columns:
if i not in data2.columns:
list.append(i)
for i in list:
data[i] = data[i].astype(int)
# 特征和标签的分离
X = data.drop(['Credit Default'], axis=1)
y = data['Credit Default']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 归一化
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# 转换为张量
X_train = torch.FloatTensor(X_train).to(device)
X_test = torch.FloatTensor(X_test).to(device)
y_train = torch.LongTensor(y_train.values).to(device)
y_test = torch.LongTensor(y_test.values).to(device)
# 定义MLP
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.fc1 = nn.Linear(31, 64) # 输入层到第一个隐藏层
self.relu = nn.ReLU()
self.fc2 = nn.Linear(64, 32) # 第一个隐藏层到第二个隐藏层
self.fc3 = nn.Linear(32, 2) # 第二个隐藏层到输出层
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.fc2(out)
out = self.relu(out)
out = self.fc3(out)
return out
model = MLP().to(device)
# 损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.01)
# 模型训练
num_epochs = 100
losses = []
epoches = []
start_time = time.time()
with tqdm(total=num_epochs, desc='训练进度', unit='epoch') as pbar:
for epoch in range(num_epochs):
# 前向传播
outputs = model(X_train)
loss = criterion(outputs, y_train)
# 反向传播和优化
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 记录损失并更新进度条
losses.append(loss.item())
epoches.append(epoch+1)
# 更新进度条的描述信息
pbar.set_postfix({'Loss':f'{loss.item():.4f}'})
# 每10个epoch更新一次进度条
if (epoch + 1) % 10 == 0:
pbar.update(10)
# 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
print(f'Training time: {time_all:.2f} seconds')
# 模型推理
model.eval()
with torch.no_grad():
outputs = model(X_test)
_, predicted = torch.max(outputs, 1)
accuracy = (predicted == y_test).sum().item() / len(y_test)
print(f'Accuracy: {accuracy*100:.2f}%')
# 可视化曲线
plt.figure(figsize=(10, 6))
plt.plot(epoches, losses, label='Training Loss')
plt.title('Training Loss Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.grid(True)
plt.show() 训练进度: 100%|██████████| 100/100 00:00\<00:00, 201.31epoch/s, Loss=0.5917
Training time: 0.50 seconds
Accuracy: 70.60%
