run_model_fit.py 文件源码

def scaled_pipelines():
    # Model parameters
    # RANSAC parameters
    # 500 max trials takes 90s
    ransac_kwargs = {
        'max_trials': 1000,
        'min_samples': 5000,
        'loss': 'absolute_loss',
        'residual_threshold': 2.0,
        'random_state': _RANDOM_STATE,
    }
    # Ridge CV parameters
    alphas = [.01, .1, 1, 10]
    # Model instances
    model_steps = [
        LinearRegression(),
        # [PolynomialFeatures(degree=2), LinearRegression()],
        # [PolynomialFeatures(degree=3), LinearRegression()],
        # RANSACRegressor(base_estimator=LinearRegression(), **ransac_kwargs),
        # RANSACRegressor with polynomial regression?
        # RidgeCV(alphas=alphas),
        # LassoCV(),  # Alphas set automatically by default
        # ElasticNetCV(l1_ratio=0.5),  # Same as default
        # [PolynomialFeatures(degree=2), ElasticNetCV(l1_ratio=0.5)],
        # SGDRegressor(),
    ]
    # Pipelines
    pipelines = []
    for m in model_steps:
        # Steps
        common_steps = [
            StandardScaler(),
            PCA(**_PCA_KWARGS)
        ]
        model_steps = m if isinstance(m, list) else [m]
        steps = common_steps + model_steps
        pipelines.append(make_pipeline(*steps))
    return pipelines