机器学习基础

from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

# 生成数据
X, y = make_classification(n_samples=1000, n_features=20, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# 训练模型
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)

# 预测
accuracy = model.score(X_test, y_test)
print(f"准确率: {accuracy:.4f}")

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(
    n_estimators=100,    # 树的数量
    max_depth=10,        # 最大深度
    min_samples_split=5, # 最小分裂样本数
    random_state=42
)
rf.fit(X_train, y_train)
print(f"特征重要性: {rf.feature_importances_}")

from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

kmeans = KMeans(n_clusters=3, random_state=42)
labels = kmeans.fit_predict(X)
centers = kmeans.cluster_centers_

# 可视化
plt.scatter(X[:, 0], X[:, 1], c=labels)
plt.scatter(centers[:, 0], centers[:, 1], marker='x', s=200, c='red')
plt.show()

from sklearn.cluster import DBSCAN

dbscan = DBSCAN(eps=0.5, min_samples=5)
labels = dbscan.fit_predict(X)

from sklearn.decomposition import PCA

pca = PCA(n_components=2)
X_reduced = pca.fit_transform(X)
print(f"解释方差比: {pca.explained_variance_ratio_}")

from sklearn.manifold import TSNE

tsne = TSNE(n_components=2, perplexity=30, random_state=42)
X_embedded = tsne.fit_transform(X)

from sklearn.metrics import classification_report, roc_auc_score, confusion_matrix

y_pred = model.predict(X_test)
y_prob = model.predict_proba(X_test)[:, 1]

print(classification_report(y_test, y_pred))
print(f"AUC: {roc_auc_score(y_test, y_prob):.4f}")
print(f"混淆矩阵:\n{confusion_matrix(y_test, y_pred)}")

from sklearn.linear_model import Lasso
model = Lasso(alpha=0.1)  # alpha控制正则化强度

from sklearn.linear_model import Ridge
model = Ridge(alpha=1.0)

import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(100, 50)
        self.dropout = nn.Dropout(0.5)  # 50%的神经元随机失活
        self.fc2 = nn.Linear(50, 10)

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

from sklearn.model_selection import train_test_split

X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2)

best_score = 0
patience = 10
counter = 0

for epoch in range(100):
    model.fit(X_train, y_train)
    val_score = model.score(X_val, y_val)

    if val_score > best_score:
        best_score = val_score
        counter = 0
    else:
        counter += 1

    if counter >= patience:
        print(f"Early stopping at epoch {epoch}")
        break

from sklearn.linear_model import Lasso, Ridge

# L1正则化 - 部分系数为0
lasso = Lasso(alpha=0.1)
lasso.fit(X_train, y_train)
print(f"非零系数数量: {np.sum(lasso.coef_ != 0)}")

# L2正则化 - 系数接近0但不为0
ridge = Ridge(alpha=0.1)
ridge.fit(X_train, y_train)
print(f"系数范围: [{ridge.coef_.min():.4f}, {ridge.coef_.max():.4f}]")

from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

inertias = []
K_range = range(1, 11)

for k in K_range:
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans.fit(X)
    inertias.append(kmeans.inertia_)

plt.plot(K_range, inertias, 'bo-')
plt.xlabel('K值')
plt.ylabel('簇内误差平方和')
plt.title('肘部法则')
plt.show()

from sklearn.metrics import silhouette_score

for k in range(2, 11):
    kmeans = KMeans(n_clusters=k, random_state=42)
    labels = kmeans.fit_predict(X)
    score = silhouette_score(X, labels)
    print(f"K={k}, Silhouette Score={score:.4f}")

# ReLU梯度: x>0时为1, x≤0时为0
nn.ReLU()

nn.BatchNorm1d(num_features)

class ResidualBlock(nn.Module):
    def forward(self, x):
        return x + self.conv_block(x)  # 跳跃连接

torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)

from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.datasets import load_digits
import matplotlib.pyplot as plt

# 加载手写数字数据集
digits = load_digits()
X, y = digits.data, digits.target

# PCA降维
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)

# t-SNE降维
tsne = TSNE(n_components=2, random_state=42)
X_tsne = tsne.fit_transform(X)

# 可视化对比
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 5))

ax1.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='tab10')
ax1.set_title('PCA')

ax2.scatter(X_tsne[:, 0], X_tsne[:, 1], c=y, cmap='tab10')
ax2.set_title('t-SNE')

plt.show()