目錄

目錄

前言?

1.檢查GPU

2.查看數據

?編輯?3.劃分數據集

?4.創建模型與編譯訓練

5.編譯及訓練模型

6.結果可視化

7.總結?

前言?

?🍨 本文為🔗365天深度學習訓練營中的學習記錄博客
🍖 原作者：K同學啊

1.檢查GPU

import torch.nn as nn
import torch.nn.functional as F
import torchvision,torch# 設置硬件設備，如果有GPU則使用，沒有則使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2.查看數據

import numpy             as np
import pandas            as pd
import seaborn           as sns
from sklearn.model_selection   import train_test_split
import matplotlib.pyplot as plt
plt.rcParams['savefig.dpi'] = 500 #圖片像素
plt.rcParams['figure.dpi']  = 500 #分辨率plt.rcParams['font.sans-serif'] = ['SimHei']  # 用來正常顯示中文標簽import warnings 
warnings.filterwarnings("ignore")DataFrame=pd.read_excel('data/dia.xls')
DataFrame.head()# 查看數據是否有缺失值
print('數據缺失值---------------------------------')
print(DataFrame.isnull().sum())feature_map = {'年齡': '年齡','高密度脂蛋白膽固醇': '高密度脂蛋白膽固醇','低密度脂蛋白膽固醇': '低密度脂蛋白膽固醇','極低密度脂蛋白膽固醇': '極低密度脂蛋白膽固醇','甘油三酯': '甘油三酯','總膽固醇': '總膽固醇','脈搏': '脈搏','舒張壓':'舒張壓','高血壓史':'高血壓史','尿素氮':'尿素氮','尿酸':'尿酸','肌酐':'肌酐','體重檢查結果':'體重檢查結果'
}
plt.figure(figsize=(15, 10))import matplotlib.pyplot as plt
import seaborn as sns# 刪除列 '卡號'
DataFrame.drop(columns=['卡號'], inplace=True)# 計算各列之間的相關系數
df_corr = DataFrame.corr()# 相關矩陣生成函數
def corr_generate(df):plt.figure(figsize=(10, 8))sns.heatmap(df, annot=True,          # 顯示數值fmt=".2f",           # 保留兩位小數cmap='RdBu_r',       # 使用相同顏色方案annot_kws={"size": 8}, # 調整注釋字號linewidths=0.5)      # 單元格間線 寬plt.xticks(rotation=45, ha='right')  # 調整x軸標簽角度plt.yticks(rotation=0)           # 保持y軸標簽水平plt.tight_layout()               # 自動調整布局plt.show()# 生成相關矩陣
corr_generate(df_corr)for i, (col, col_name) in enumerate(feature_map.items(), 1):plt.subplot(3, 5, i)sns.boxplot(x=DataFrame['是否糖尿病'], y=DataFrame[col])plt.title(f'{col_name}的箱線圖', fontsize=14)plt.ylabel('數值', fontsize=12)plt.grid(axis='y', linestyle='--', alpha=0.7)plt.tight_layout()
plt.show()

?

?3.劃分數據集

from sklearn.preprocessing import StandardScaler
X = DataFrame.drop(['是否糖尿病','高密度脂蛋白膽固醇'],axis=1)
y = DataFrame['是否糖尿病']# 數據集標準化處理
sc_X = StandardScaler()
X = sc_X.fit_transform(X)
X = torch.tensor(np.array(X), dtype=torch.float32)
y = torch.tensor(np.array(y), dtype=torch.int64)
train_X, test_X, train_y, test_y = train_test_split(X, y,test_size=0.2,random_state=1)
# 維度擴增使其符合LSTM模型可接受shape
train_X = train_X.unsqueeze(1)
test_X = test_X.unsqueeze(1)
train_X.shape, train_y.shapefrom torch.utils.data import TensorDataset, DataLoadertrain_dl = DataLoader(TensorDataset(train_X, train_y),
batch_size=64, 
shuffle=False)test_dl = DataLoader(TensorDataset(test_X, test_y),
batch_size=64, 
shuffle=False)

?4.創建模型與編譯訓練

class model_lstm(nn.Module):def __init__(self):super(model_lstm, self).__init__()self.lstm0 = nn.LSTM(input_size=13 ,hidden_size=200, num_layers=1, batch_first=True)self.lstm1 = nn.LSTM(input_size=200 ,hidden_size=200, num_layers=1, batch_first=True)self.fc0 = nn.Linear(200, 2)def forward(self, x):out, hidden1 = self.lstm0(x) out, _ = self.lstm1(out, hidden1) out = out[:, -1, :] # 只取最后一個時間步的輸出out = self.fc0(out) return out model = model_lstm().to(device)
model

5.編譯及訓練模型

# 訓練循環
def train(dataloader, model, loss_fn, optimizer):size = len(dataloader.dataset) # 訓練集的大小num_batches = len(dataloader) # 批次數目, (size/batch_size，向上取整)train_loss, train_acc = 0, 0 # 初始化訓練損失和正確率for X, y in dataloader: # 獲取圖片及其標簽X, y = X.to(device), y.to(device)# 計算預測誤差pred = model(X) # 網絡輸出loss = loss_fn(pred, y) # 計算網絡輸出和真實值之間的差距，targets為真實值，計算二者差值即為損失# 反向傳播optimizer.zero_grad() # grad屬性歸零loss.backward() # 反向傳播optimizer.step() # 每一步自動更新# 記錄acc與losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_lossdef test (dataloader, model, loss_fn):size = len(dataloader.dataset) # 測試集的大小num_batches = len(dataloader) # 批次數目, (size/batch_size，向上取整)test_loss, test_acc = 0, 0# 當不進行訓練時，停止梯度更新，節省計算內存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target = imgs.to(device), target.to(device)# 計算losstarget_pred = model(imgs)loss = loss_fn(target_pred, target)test_loss += loss.item()test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()test_acc /= sizetest_loss /= num_batchesreturn test_acc, test_lossloss_fn = nn.CrossEntropyLoss() # 創建損失函數
learn_rate = 1e-4 # 學習率
opt = torch.optim.Adam(model.parameters(),lr=learn_rate)
epochs = 30train_loss = []
train_acc = []
test_loss = []
test_acc = []for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)# 獲取當前的學習率lr = opt.state_dict()['param_groups'][0]['lr']template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr))
print("="*20, 'Done', "="*20)

6.結果可視化

import matplotlib.pyplot as plt
#隱藏警告
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用來正常顯示中文標簽
plt.rcParams['axes.unicode_minus'] = False # 用來正常顯示負號
plt.rcParams['figure.dpi'] = 100 #分辨率from datetime import datetime
current_time = datetime.now() # 獲取當前時間epochs_range = range(epochs)plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.xlabel(current_time) # 打卡請帶上時間戳，否則代碼截圖無效plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

7.總結?

? ? ? ?由于 LSTM 的細胞結構和門控機制相對復雜，相比于簡單的神經網絡模型，其計算復雜度較高。在處理大規模數據或構建深度 LSTM 網絡時，訓練時間和計算資源的需求可能會成為瓶頸，需要強大的計算硬件支持。

? ? ? ? 在數據量較小或模型參數過多的情況下，LSTM 模型也可能出現過擬合現象，即模型過于適應訓練數據，而對新的數據泛化能力較差。

下一步探索：嘗試減少參數，擬合效果會更好，剔除掉相關性較弱的數據。