quick_reference

# Scikit-learn 快速参考 ## 常用导入模式 python # 核心 scikit-learn import sklearn # 数据拆分与交叉验证 from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV # 预处理 from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder from sklearn.impute import SimpleImputer # 特征选择 from sklearn.feature_selection import SelectKBest, RFE # 监督学习 from sklearn.linear_model import LogisticRegression, Ridge, Lasso from sklearn.ensemble import RandomForestClassifier, GradientBoostingRegressor from sklearn.svm import SVC, SVR from sklearn.tree import DecisionTreeClassifier # 无监督学习 from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering from sklearn.decomposition import PCA, NMF # 指标 from sklearn.metrics import ( accuracy_score, precision_score, recall_score, f1_score, mean_squared_error, r2_score, confusion_matrix, classification_report ) # 管道 from sklearn.pipeline import Pipeline, make_pipeline from sklearn.compose import ColumnTransformer, make_column_transformer # 工具 import numpy as np import pandas as pd import matplotlib.pyplot as plt ## 安装 bash # 使用 uv (推荐) uv pip install scikit-learn # 可选依赖 uv pip install scikit-learn[plots] # 用于绘图工具 uv pip install pandas numpy matplotlib seaborn # 常用配套库 ## 快速工作流模板 ### 分类工作流 python from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import classification_report, confusion_matrix # 拆分数据 X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, stratify=y, random_state=42 ) # 预处理 scaler = StandardScaler() X_train_scaled = scaler.fit_transform(X_train) X_test_scaled = scaler.transform(X_test) # 训练 model = RandomForestClassifier(n_estimators=100, random_state=42) model.fit(X_train_scaled, y_train) # 评估 y_pred = model.predict(X_test_scaled) print(classification_report(y_test, y_pred)) print(confusion_matrix(y_test, y_pred)) ### 回归工作流 python from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.ensemble import GradientBoostingRegressor from sklearn.metrics import mean_squared_error, r2_sco