机器学习入门（scikit-learn）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report

# 1. 加载数据集（鸢尾花，经典入门数据集）
iris = load_iris()
X, y = iris.data, iris.target
print(f"特征形状: {X.shape}, 类别数: {len(set(y))}")

# 2. 切分数据集
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# 3. 特征标准化（零均值，单位方差）
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)   # 在训练集上 fit
X_test  = scaler.transform(X_test)         # 测试集只用 transform！

# 4. 训练模型
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)   # 两行搞定训练

# 5. 评估
y_pred = model.predict(X_test)
print(f"准确率: {accuracy_score(y_test, y_pred):.4f}")
print(classification_report(y_test, y_pred))

from sklearn.linear_model    import LogisticRegression, LinearRegression
from sklearn.tree             import DecisionTreeClassifier
from sklearn.ensemble         import RandomForestClassifier, GradientBoostingClassifier
from sklearn.svm              import SVC
from sklearn.neighbors        import KNeighborsClassifier

# 所有算法接口完全一样！
models = {
    "逻辑回归":   LogisticRegression(),
    "决策树":     DecisionTreeClassifier(max_depth=5),
    "随机森林":   RandomForestClassifier(n_estimators=100),
    "梯度提升":   GradientBoostingClassifier(),
    "SVM":       SVC(kernel="rbf"),
    "KNN":       KNeighborsClassifier(n_neighbors=5),
}

# 快速对比所有算法的效果
for name, clf in models.items():
    clf.fit(X_train, y_train)
    acc = clf.score(X_test, y_test)
    print(f"{name:10s}: {acc:.4f}")

from sklearn.model_selection import cross_val_score, StratifiedKFold
from sklearn.metrics import (
    accuracy_score, precision_score,
    recall_score, f1_score, roc_auc_score,
    confusion_matrix
)

model = RandomForestClassifier(n_estimators=100, random_state=42)

# 5折交叉验证
cv_scores = cross_val_score(model, X, y, cv=5, scoring="accuracy")
print(f"CV 准确率: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")

# 评估各指标（在测试集上）
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

print(f"准确率 (Accuracy):  {accuracy_score(y_test, y_pred):.4f}")
print(f"精确率 (Precision): {precision_score(y_test, y_pred, average='macro'):.4f}")
print(f"召回率 (Recall):    {recall_score(y_test, y_pred, average='macro'):.4f}")
print(f"F1 Score:          {f1_score(y_test, y_pred, average='macro'):.4f}")

# 混淆矩阵：可视化预测错误的分布
cm = confusion_matrix(y_test, y_pred)
print("混淆矩阵:\n", cm)

from sklearn.model_selection import GridSearchCV

model = RandomForestClassifier(random_state=42)

# 定义要搜索的参数范围
param_grid = {
    "n_estimators": [50, 100, 200],
    "max_depth":    [None, 5, 10],
    "min_samples_split": [2, 5],
}

# 5折交叉验证 + 网格搜索
grid_search = GridSearchCV(
    model, param_grid,
    cv=5, scoring="f1_macro",
    n_jobs=-1  # 用所有 CPU 核心并行
)
grid_search.fit(X_train, y_train)

print(f"最佳参数: {grid_search.best_params_}")
print(f"最佳得分: {grid_search.best_score_:.4f}")

# 用最佳参数的模型进行预测
best_model = grid_search.best_estimator_
final_score = best_model.score(X_test, y_test)
print(f"测试集得分: {final_score:.4f}")

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score

# Pipeline 确保每次交叉验证折叠中，
# scaler 只在训练折上 fit，不会泄露验证折数据
pipeline = Pipeline([
    ("scaler",  StandardScaler()),         # 步骤1：标准化
    ("model",   RandomForestClassifier(      # 步骤2：分类器
        n_estimators=100,
        random_state=42
    ))
])

# 交叉验证时 Pipeline 自动处理数据泄露问题
cv_scores = cross_val_score(pipeline, X, y, cv=5)
print(f"CV 准确率: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")

# 训练完整管道并预测
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)

# 用 GridSearchCV 优化 Pipeline 参数
from sklearn.model_selection import GridSearchCV
param_grid = {
    # Pipeline 参数格式：步骤名__参数名
    "model__n_estimators": [50, 100, 200],
    "model__max_depth":    [None, 5, 10],
}
grid_search = GridSearchCV(pipeline, param_grid, cv=5)
grid_search.fit(X_train, y_train)