交叉验证、超参数调优与模型持久化

import pandas as pd

results = pd.DataFrame(search.cv_results_)
print(results[[
    "params", "mean_test_score", "std_test_score", "mean_fit_time",
]].sort_values("mean_test_score", ascending=False).head())

import json
from pathlib import Path

import joblib
import sklearn
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

X, y = make_classification(n_samples=600, n_features=7, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, stratify=y, random_state=42,
)
pipeline = make_pipeline(
    StandardScaler(), LogisticRegression(max_iter=1000, random_state=42)
)
search = GridSearchCV(
    pipeline,
    {"logisticregression__C": [0.1, 1.0, 10.0]},
    scoring="f1", cv=5, n_jobs=-1,
)
search.fit(X_train, y_train)
print("best:", search.best_params_)
print("test score:", round(search.score(X_test, y_test), 3))

output = Path("model_output")
output.mkdir(exist_ok=True)
joblib.dump(search.best_estimator_, output / "pipeline.joblib")
(output / "metadata.json").write_text(json.dumps({
    "sklearn_version": sklearn.__version__,
    "feature_count": X.shape[1],
    "metric": "f1",
}, indent=2), encoding="utf-8")

loaded = joblib.load(output / "pipeline.joblib")
print("loaded prediction:", loaded.predict(X_test[:2]).tolist())

before = search.best_estimator_.predict_proba(X_test[:10])
reloaded = joblib.load(output / "pipeline.joblib")
after = reloaded.predict_proba(X_test[:10])

import numpy as np
np.testing.assert_allclose(before, after, rtol=1e-10, atol=1e-12)