监督学习

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import pandas as pd

# 加载数据
df = pd.read_csv('labeled_data.csv')
X = df.drop('target', axis=1)
y = df['target']

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

# 训练模型
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# 评估
y_pred = model.predict(X_test)
print(f'Accuracy: {accuracy_score(y_test, y_pred):.3f}')

最短闭环：加载标注数据 → 划分集合 → 训练随机森林 → 评估准确率

{
  "model": "RandomForestClassifier",
  "metrics": {
    "accuracy": 0.873,
    "precision": 0.865,
    "recall": 0.881,
    "f1_score": 0.873
  },
  "confusion_matrix": [
    [
      45,
      5
    ],
    [
      8,
      42
    ]
  ],
  "feature_importance": {
    "age": 0.32,
    "income": 0.28,
    "education": 0.18,
    "experience": 0.22
  }
}