class sklearn.tree.DecisionTreeClassifier(*, criterion='gini', splitter='best', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features=None, random_state=None, max_leaf_nodes=None, min_impurity_decrease=0.0, class_weight=None, ccp_alpha=0.0, monotonic_cst=None)[source]

class sklearn.tree.DecisionTreeRegressor(*, criterion='squared_error', splitter='best', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features=None, random_state=None, max_leaf_nodes=None, min_impurity_decrease=0.0, ccp_alpha=0.0, monotonic_cst=None)

class sklearn.tree.ExtraTreeClassifier(*, criterion='gini', splitter='random', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='sqrt', random_state=None, max_leaf_nodes=None, min_impurity_decrease=0.0, class_weight=None, ccp_alpha=0.0, monotonic_cst=None)

property feature_importances_

返回标准化后的特征的重要性，又被称为基尼重要性，即通过计算每个特征在决策树的各个节点上对Gini不纯度的减少量来评估特征的重要性。

具体来说，Gini重要性计算步骤如下：

1. 在构建决策树的过程中，每次选择一个特征进行节点分裂时，计算该特征在该节点上的Gini不纯度减少量。
2. 将该特征在所有节点上的Gini不纯度减少量累加，得到该特征的总Gini不纯度减少量。
3. 对所有特征的总Gini不纯度减少量进行归一化处理，使其总和为1。

最终，Gini重要性值越高，表示该特征对分类结果的贡献越大。Gini重要性常用于特征选择和特征工程中，以识别和保留对模型性能影响较大的特征。

class sklearn.ensemble.RandomForestClassifier(n_estimators=100, *, criterion='gini', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='sqrt', max_leaf_nodes=None, min_impurity_decrease=0.0, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None, ccp_alpha=0.0, max_samples=None, monotonic_cst=None)

class sklearn.ensemble.RandomForestRegressor(n_estimators=100, *, criterion='squared_error', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features=1.0, max_leaf_nodes=None, min_impurity_decrease=0.0, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, ccp_alpha=0.0, max_samples=None, monotonic_cst=None)

class sklearn.ensemble.GradientBoostingClassifier(*, loss='log_loss', learning_rate=0.1, n_estimators=100, subsample=1.0, criterion='friedman_mse', min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_depth=3, min_impurity_decrease=0.0, init=None, random_state=None, max_features=None, verbose=0, max_leaf_nodes=None, warm_start=False, validation_fraction=0.1, n_iter_no_change=None, tol=0.0001, ccp_alpha=0.0)

class sklearn.ensemble.GradientBoostingRegressor(*, loss='squared_error', learning_rate=0.1, n_estimators=100, subsample=1.0, criterion='friedman_mse', min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_depth=3, min_impurity_decrease=0.0, init=None, random_state=None, max_features=None, alpha=0.9, verbose=0, max_leaf_nodes=None, warm_start=False, validation_fraction=0.1, n_iter_no_change=None, tol=0.0001, ccp_alpha=0.0)

property feature_importances_

返回总和为1的特征重要性，除非所有树只有一个根节点。

class sklearn.ensemble.AdaBoostClassifier(estimator=None, *, n_estimators=50, learning_rate=1.0, algorithm='deprecated', random_state=None)

property feature_importances_

返回值:
feature_importances_：一维数组 (n_features,)，The feature importances.

class sklearn.ensemble.AdaBoostRegressor(estimator=None, *, n_estimators=50, learning_rate=1.0, loss='linear', random_state=None)

property feature_importances_

返回值:
feature_importances_：一维数组 (n_features,)，The feature importances.

classxgboost.XGBClassifier(*, importance_type='total_gain', objective='binary:logistic', **kwargs)

参数：

• importance_type: 特征重要性的类型，关系到 feature_importances_属性:
  - 树模型：可选 “gain”, “weight”, “cover”, “total_gain” 或 “total_cover”.
  - 线性模型：进可选 “weight” .

属性：propertyfeature_importances_

• 返回值取决于importance_type参数:
  - 一维数组[n_features]，代表每个特征的重要性
  - 线性模型：二维数组(n_features, n_classes)，代表每个特征在每个类别上的重要性

classxgboost.XGBRegressor(*,  importance_type='total_gain', objective='reg:squarederror', **kwargs)

参数与属性相关内容同上

classlightgbm.LGBMClassifier(boosting_type='gbdt', num_leaves=31, max_depth=-1, learning_rate=0.1, n_estimators=100, subsample_for_bin=200000, objective=None, class_weight=None, min_split_gain=0.0, min_child_weight=0.001, min_child_samples=20, subsample=1.0, subsample_freq=0, colsample_bytree=1.0, reg_alpha=0.0, reg_lambda=0.0, random_state=None, n_jobs=None, importance_type='split', **kwargs)

参数：

• importance_type(str, optional (default=‘split’)): 关系到 feature_importances_属性的输出:
  - ‘split’：返回结果包含特征使用的次数
  - ‘gain’：返回结果包含特征分裂时的总增益

属性：property feature_importances_

• 返回特征重要性，值越高，特征越重要:
  - 一维数组[n_features]，代表每个特征的重要性

classlightgbm.LGBMRegressor(boosting_type='gbdt', num_leaves=31, max_depth=-1, learning_rate=0.1, n_estimators=100, subsample_for_bin=200000, objective=None, class_weight=None, min_split_gain=0.0, min_child_weight=0.001, min_child_samples=20, subsample=1.0, subsample_freq=0, colsample_bytree=1.0, reg_alpha=0.0, reg_lambda=0.0, random_state=None, n_jobs=None, importance_type='split', **kwargs)

参数与属性相关内容同上

-评估特征的重要性，且模型已经过训练，即模型已调用fit(X, y)。
-由参数scoring指定评估度量方式；打乱特征列的值，打乱次数由参数n_repeats指定；评估特征值打乱前后的scoring度量结果的差异，即表示该特征的重要程度。

sklearn.inspection.permutation_importance(estimator, X, y, *, scoring=None, n_repeats=5, n_jobs=None, random_state=None, sample_weight=None, max_samples=1.0)

参数：

• estimator：已经训练好的模型
• X：用于计算特征重要性的输入数据。
• y：目标值。
• scoring：评估指标，默认为 None，使用模型的默认评分方法。
• n_repeats：打乱特征的次数，默认为 5。

返回值：

• importances_mean：每个特征基于n_repeats的重要性均值。
• importances_std：每个特征基于n_repeats的的重要性标准差。
• importances：每次打乱后特征的重要性。为二维数组，表示每个特征每次打乱后的重要性。