sklearn randomSearchCV 中的参数列表，如 GridSearchCV？

Question

我有一个问题，我想测试多个模型，但这些模型并不都具有相同的命名参数。您将如何使用RandomizedSearchCV 中的管道参数列表，就像您可以在此示例中使用GridSearchCV 一样？

示例来自：
https://scikit-learn.org/stable/auto_examples/compose/plot_compare_reduction.html

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.decomposition import PCA, NMF
from sklearn.feature_selection import SelectKBest, chi2

pipe = Pipeline([
    # the reduce_dim stage is populated by the param_grid
    ('reduce_dim', None),
    ('classify', LinearSVC())
])

N_FEATURES_OPTIONS = [2, 4, 8]
C_OPTIONS = [1, 10, 100, 1000]
param_grid = [
    {
        'reduce_dim': [PCA(iterated_power=7), NMF()],
        'reduce_dim__n_components': N_FEATURES_OPTIONS,
        'classify__C': C_OPTIONS
    },
    {
        'reduce_dim': [SelectKBest(chi2)],
        'reduce_dim__k': N_FEATURES_OPTIONS,
        'classify__C': C_OPTIONS
    },
]

grid = GridSearchCV(pipe, cv=3, n_jobs=2, param_grid=param_grid)
digits = load_digits()
grid.fit(digits.data, digits.target)

Answer 1

我找到了一种方法，它依赖于鸭式打字，并且不会受到太多干扰。

它依赖于将完整的估算器作为参数传递给管道。我们首先对模型类型进行采样，然后对其参数进行采样。为此，我们定义了两个可以采样的类：

from sklearn.model_selection import ParameterSampler


class EstimatorSampler:
    """
    Class that holds a model and its parameters distribution.
    When sampled, the parameters are first sampled and set to the model, 
    which is returned.

    # Arguments
    ===========
    model : sklearn.base.BaseEstimator
    param_distributions : dict
        Input to ParameterSampler

    # Returns
    =========
    sampled : sklearn.base.BaseEstimator
    """
    def __init__(self, model, param_distributions):
        self.model = model
        self.param_distributions = param_distributions

    def rvs(self, random_state=None):
        sampled_params = next(iter(
            ParameterSampler(self.param_distributions, 
                             n_iter=1, 
                             random_state=random_state)))
        return self.model.set_params(**sampled_params)


class ListSampler:
    """
    List container that when sampled, returns one of its item, 
    with probabilities defined by `probs`.

    # Arguments
    ===========
    items : 1-D array-like
    probs : 1-D array-like of floats
        If not None, it should be the same length of `items`
        and sum to 1.

    # Returns
    =========
    sampled item
    """
    def __init__(self, items, probs=None):
        self.items = items
        self.probs = probs

    def rvs(self, random_state=None):
        item = np.random.choice(self.items, p=self.probs)
        if hasattr(item, 'rvs'):
            return item.rvs(random_state=random_state)
        return item

其余代码定义如下。

    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.datasets import load_digits
    from sklearn.model_selection import RandomizedSearchCV
    from sklearn.pipeline import Pipeline
    from sklearn.svm import LinearSVC
    from sklearn.decomposition import PCA, NMF
    from sklearn.feature_selection import SelectKBest, chi2

    pipe = Pipeline([
        # the reduce_dim stage is populated by the param_grid
        ('reduce_dim', None),
        ('classify', None)
    ])

    N_FEATURES_OPTIONS = [2, 4, 8]
    dim_reducers = ListSampler([EstimatorSampler(est, {'n_components': N_FEATURES_OPTIONS})
                                for est in [PCA(iterated_power=7), NMF()]] + 
                               [EstimatorSampler(SelectKBest(chi2), {'k': N_FEATURES_OPTIONS})])

    C_OPTIONS = [1, 10, 100, 1000]
    classifiers = EstimatorSampler(LinearSVC(), {'C': C_OPTIONS})

    param_dist = {
        'reduce_dim': dim_reducers, 
        'classify': classifiers
    }

    grid = RandomizedSearchCV(pipe, cv=3, n_jobs=2, scoring='accuracy', param_distributions=param_dist)
    digits = load_digits()
    grid.fit(digits.data, digits.target)

Answer 2

Hyperopt 支持跨多个估计器的超参数调整，查看此wiki 了解更多详细信息（2.2 搜索空间示例：scikit-learn 部分）。

如果您想使用 sklearn 的 GridSearch 来执行此操作，请查看此 post。它建议实现 EstimatorSelectionHelper 估算器，该估算器可以运行不同的估算器，每个估算器都有自己的参数网格。

Answer 3

这是一个老问题，was resolved 有一段时间了（不确定从哪个 scikit-learn 版本开始）。

您现在可以在param_distributions 参数中传递RandomizedSearchCV 的字典列表。您的示例代码将变为：

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import RandomizedSearchCV
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.decomposition import PCA, NMF
from sklearn.feature_selection import SelectKBest, chi2

pipe = Pipeline([
    # the reduce_dim stage is populated by the param_grid
    ('reduce_dim', None),
    ('classify', LinearSVC())
])

N_FEATURES_OPTIONS = [2, 4, 8]
C_OPTIONS = [1, 10, 100, 1000]
param_grid = [
    {
        'reduce_dim': [PCA(iterated_power=7), NMF()],
        'reduce_dim__n_components': N_FEATURES_OPTIONS,
        'classify__C': C_OPTIONS
    },
    {
        'reduce_dim': [SelectKBest(chi2)],
        'reduce_dim__k': N_FEATURES_OPTIONS,
        'classify__C': C_OPTIONS
    },
]

grid = RandomizedSearchCV(pipe, cv=3, n_jobs=2, param_distributions=param_grid)
digits = load_digits()
grid.fit(digits.data, digits.target)

我使用的是 sklearn 0.23.1 版。