cat /etc/os-release

python3 -m venv ml_env

source ml_env/bin/activate

pip install torch==1.13.1+cpu torchvision==0.14.1+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# 加載數據集
iris = load_iris()
X = iris.data  # 特徵數據
y = iris.target  # 標籤數據# 轉換為DataFrame便於查看
df = pd.DataFrame(X, columns=iris.feature_names)
df['label'] = y
print("數據集前5行：")print(df.head())# 數據劃分（訓練集80%，測試集20%）
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42)# 特徵標準化
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)# 保存預處理後的數據import numpy as np
np.savez('iris_processed.npz', 
         X_train=X_train_scaled, 
         X_test=X_test_scaled, 
         y_train=y_train, 
         y_test=y_test)print("\n預處理完成，數據已保存為iris_processed.npz")

import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.metrics import accuracy_score, classification_report

# 加載預處理數據
data = np.load('iris_processed.npz')
X_train, X_test = data['X_train'], data['X_test']
y_train, y_test = data['y_train'], data['y_test']# 轉換為Tensor
X_train = torch.FloatTensor(X_train)
X_test = torch.FloatTensor(X_test)
y_train = torch.LongTensor(y_train)
y_test = torch.LongTensor(y_test)# 定義神經網絡模型class IrisClassifier(nn.Module):def __init__(self):super(IrisClassifier, self).__init__()
        self.fc1 = nn.Linear(4, 16)  # 輸入層到隱藏層
        self.fc2 = nn.Linear(16, 3)  # 隱藏層到輸出層
        self.relu = nn.ReLU()def forward(self, x):
        x = self.relu(self.fc1(x))
        x = self.fc2(x)return x

# 初始化模型、損失函數和優化器
model = IrisClassifier()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)# 訓練模型
epochs = 100for epoch in range(epochs):
    model.train()
    optimizer.zero_grad()
    outputs = model(X_train)
    loss = criterion(outputs, y_train)
    loss.backward()
    optimizer.step()if (epoch+1) % 20 == 0:print(f'Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}')# 模型評估
model.eval（)with torch.no_grad():
    y_pred = model(X_test).argmax(dim=1)
    acc = accuracy_score(y_test.numpy(), y_pred.numpy())print(f'\n測試集準確率: {acc:.4f}')print("\n分類報告:")print(classification_report(y_test.numpy(), y_pred.numpy()))