run_model_fit.py 文件源码

def sample_pipelines(pca_kernels=None, svr_kernels=None):
    """
    Pipelines that can't be fit in a reasonable amount of time on the whole
    dataset
    """
    # Model instances
    model_steps = []
    if pca_kernels is None:
        pca_kernels = ['poly', 'rbf', 'sigmoid', 'cosine']
    for pca_kernel in pca_kernels:
        model_steps.append([
            KernelPCA(n_components=2, kernel=pca_kernel),
            LinearRegression(),
        ])
    if svr_kernels is None:
        svr_kernels = ['poly', 'rbf', 'sigmoid']
    for svr_kernel in svr_kernels:
        model_steps.append(SVR(kernel=svr_kernel, verbose=True, cache_size=1000))

    # Pipelines
    pipelines = []
    for m in model_steps:
        # Steps
        common_steps = [
            StandardScaler(),
        ]
        model_steps = m if isinstance(m, list) else [m]
        steps = common_steps + model_steps
        pipelines.append(make_pipeline(*steps))
    return pipelines