如何从 Sklearn 管道中提取特征重要性

Posted 2023-02-23

【中文标题】如何从 Sklearn 管道中提取特征重要性

【英文标题】：How to extract feature importances from an Sklearn pipeline

【发布时间】：2016-12-11 18:33:49

【问题描述】：

我在 Scikit-Learn 中构建了一个管道，分两个步骤：一个是构建特征，第二个是 RandomForestClassifier。

虽然我可以保存该管道，但查看各个步骤和步骤中设置的各种参数，我希望能够从生成的模型中检查特征重要性。

这可能吗？

【参考方案1】：

啊，是的。

您列出了要检查估算器的步骤：

例如：

pipeline.steps[1]

返回：

('predictor',
 RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
             max_depth=None, max_features='auto', max_leaf_nodes=None,
             min_samples_leaf=1, min_samples_split=2,
             min_weight_fraction_leaf=0.0, n_estimators=50, n_jobs=2,
             oob_score=False, random_state=None, verbose=0,
             warm_start=False))

然后您可以直接访问模型步骤：

pipeline.steps[1][1].feature_importances_

【讨论】：

要获取功能的名称，您可以查看 pipe.steps[0][1].get_feature_names()

这是一个不完整的答案。预处理和特征工程通常是管道的一部分。因此，您需要考虑到这一点。

如果有超过 1 个步骤，那么一种方法是 use the name of the step to retrieve the estimator。对于 OP 而言，这可能是 pipeline.named_steps['predictor'].feature_importances_。

如何更改特征重要性类型？

【参考方案2】：

我写了一篇关于这样做的文章，你可以找到here。

通常对于管道，您可以访问named_steps 参数。这将为您提供管道中的每个变压器。以这条管道为例：

model = Pipeline(
[
    ("vectorizer", CountVectorizer()),
    ("transformer", TfidfTransformer()),
    ("classifier", classifier),
])

我们可以通过model.named_steps["transformer"].get_feature_names() 访问各个功能步骤，这将返回来自TfidfTransformer 的功能名称列表。这一切都很好，但并没有真正涵盖很多用例，因为我们通常想要组合一些功能。以这个模型为例：

model = Pipeline([
("union", FeatureUnion(transformer_list=[
    ("h1", TfidfVectorizer(vocabulary="worst": 0)),
    ("h2", TfidfVectorizer(vocabulary="best": 0)),
    ("h3", TfidfVectorizer(vocabulary="awful": 0)),
    ("tfidf_cls", Pipeline([
        ("vectorizer", CountVectorizer()),
        ("transformer", TfidfTransformer())
    ]
    ))
])
 ),
("classifier", classifier)])

在这里，我们使用功能联合和子管道组合了一些功能。要访问这些功能，我们需要按顺序显式调用每个命名步骤。例如，我们必须从内部管道中获取 TF-IDF 功能：

model.named_steps["union"].tranformer_list[3][1].named_steps["transformer"].get_feature_names()

这有点令人头疼，但它是可行的。通常我所做的是使用以下 sn-p 的变体来获取它。下面的代码只是将管道/特征联合集视为一棵树，并在执行过程中结合特征名称执行 DFS。

from sklearn.pipeline import FeatureUnion, Pipeline

def get_feature_names(model, names: List[str], name: str) -> List[str]:
    """Thie method extracts the feature names in order from a Sklearn Pipeline
    
    This method only works with composed Pipelines and FeatureUnions.  It will
    pull out all names using DFS from a model.

    Args:
        model: The model we are interested in
        names: The list of names of final featurizaiton steps
        name: The current name of the step we want to evaluate.

    Returns:
        feature_names: The list of feature names extracted from the pipeline.
    """
    
    # Check if the name is one of our feature steps.  This is the base case.
    if name in names:
        # If it has the named_steps atribute it's a pipeline and we need to access the features
        if hasattr(model, "named_steps"):
            return extract_feature_names(model.named_steps[name], name)
        # Otherwise get the feature directly
        else:
            return extract_feature_names(model, name)
    elif type(model) is Pipeline:
        feature_names = []
        for name in model.named_steps.keys():
            feature_names += get_feature_names(model.named_steps[name], names, name)
        return feature_names
    elif type(model) is FeatureUnion:
        feature_names= []
        for name, new_model in model.transformer_list:
            feature_names += get_feature_names(new_model, names, name)
        return feature_names
    # If it is none of the above do not add it.
    else:
        return []

您还需要此方法。它对单个转换（例如 TfidfVectorizer）进行操作以获取名称。在 SciKit-Learn 中没有通用的get_feature_names，因此您必须针对每种不同的情况对其进行捏造。这是我尝试为大多数用例做一些合理的事情。

def extract_feature_names(model, name) -> List[str]:
  """Extracts the feature names from arbitrary sklearn models
  
  Args:
    model: The Sklearn model, transformer, clustering algorithm, etc. which we want to get named features for.
    name: The name of the current step in the pipeline we are at.

  Returns:
    The list of feature names.  If the model does not have named features it constructs feature names
by appending an index to the provided name.
  """
    if hasattr(model, "get_feature_names"):
        return model.get_feature_names()
    elif hasattr(model, "n_clusters"):
        return [f"name_x" for x in range(model.n_clusters)]
    elif hasattr(model, "n_components"):
        return [f"name_x" for x in range(model.n_components)]
    elif hasattr(model, "components_"):
        n_components = model.components_.shape[0]
        return [f"name_x" for x in range(n_components)]
    elif hasattr(model, "classes_"):
        return classes_
    else:
        return [name]