如何在sklearn類中更新fit方法？

Question

我最近開始使用GridSearchCV，對面向對象的編程不太滿意。

問題：我在一個預測變量中缺少一些數據，並且我要在適當的參數網格中使用一系列算法。 我想知道是否存在一種創建自定義類的方法，該類將在擬合數據之前以不同的方式插補數據中的缺失值，並針對我同時使用的任何算法嘗試不同的屬性組合。 可能嗎？

感謝TON的幫助！

這是我為在房屋價格數據集的SQFT列中估算缺失值而創建的一個類：

class Impute_sqft():

    train_X = houses_dummies_copy.dropna(subset=['sqft']).drop(columns=['sqft', 'final_price'])
    train_Y = houses_dummies_copy.dropna(subset=['sqft'])['sqft']
    test_X = houses_dummies_copy[pd.isna(houses_dummies_copy.sqft)].drop(columns=['sqft', 'final_price'])


    def __init__(self, how='random forest'):
        self.how = how

    def impute(self):

        # replace missing values with the ones predicted by random forest
        if self.how == 'random forest':
            houses_dummies_copy = houses_dummies.copy()
            rf = RandomForestRegressor()
            rf.fit(train_X, train_Y)
            pred_Y = rf.predict(test_X)
            houses_dummies_copy.loc[test_X.index,'sqft'] = pred_Y
            return houses_dummies_copy[predictors]

        # replace missing values with the ones predicted by knn        
        if self.how == 'knn':
            houses_dummies_copy = houses_dummies.copy()
            import sys
            from impyute.imputation.cs import fast_knn
            sys.setrecursionlimit(100000) 
            knn_n = 30
            result = fast_knn(houses_dummies_copy[predictors], k=knn_n)
            result.columns = houses_dummies_copy[predictors].columns
            return result

        # replace missing values with the mean for every type of property     
        if self.how == 'mean':
            houses_dummies_copy = houses_dummies.copy()
            sqft_statistics = []
            for house_type in houses_types:
                statistic = houses_dummies_copy[houses_dummies_copy['type_' + house_type] == 1].sqft.mean(skipna=True)
                indexes = houses_dummies_copy[(houses_dummies_copy['type_' + house_type] == 1) & pd.isna(houses_dummies_copy.sqft)].index
                houses_dummies_copy.loc[indexes, 'sqft'] = statistic
            return houses_dummies_copy[predictors]

我對GridSearchCV有什么網格：

param_grid = [{
    'bootstrap': [True, False],
        'n_estimators': [3, 10],
        'max_features': [2, 3, 4]
    }]

我想要GridSearchCV的什么網格：

param_grid = [{
        'bootstrap': [True, False],
        'n_estimators': [3, 10],
        'max_features': [2, 3, 4],
        'sqft_imputer': ['random forest', 'knn', 'mean']

    }]

Answer 1

您需要創建一個自定義的Transformer ，並在Pipeline的估算器之前使用它。

自定義變壓器：

看一下模板： TemplateTransformer 。

一些評論：

• 您需要從BaseEstimator繼承。
• self.how的選擇必須在類的__init__方法中定義。
• 為正確起見，您需要在fit過程中估計統計量，並在transform過程中應用它們。 （另請參閱為什么sklearn Imputer需要安裝？ ）

管道

要鏈接自定義的估算者和估算器，可以使用scikit-learn Pipeline ：

• 例如 ，請參見本示例 ，該示例在Pipeline鏈接了PCA和LogisticRegression ，然后在GridSearchCV使用了它。
• 您將需要使用管道中使用的名稱來更改參數網格，例如

param_grid = [{
        'estimator__bootstrap': [True, False],
        'estimator__n_estimators': [3, 10],
        'estimator__max_features': [2, 3, 4],
        'imputer__how': ['random forest', 'knn', 'mean']

    }]

Answer 2

按照上面的答案。 現在一切正常。

from sklearn.base import BaseEstimator, TransformerMixin

class Impute_sqft(BaseEstimator, TransformerMixin):
    def __init__(self, how='random forest'):        
        self.how = how

    def fit(self, X, y=None):
        return self

    def transform(self, X):
        import sys
        sys.setrecursionlimit(100000) #Increase the recursion limit of the OS
        from impyute.imputation.cs import fast_knn, mice
        result = X.copy()

        if self.how == 'random forest':
            train_X = houses_dummies.dropna(subset=['sqft']).drop(columns=['sqft', 'final_price'])
            train_Y = houses_dummies.dropna(subset=['sqft'])['sqft']
            test_X = result[pd.isna(result.sqft)].drop(columns=['sqft'])

            rf = RandomForestRegressor()
            rf.fit(train_X, train_Y)
            pred_Y = rf.predict(test_X)
            result.loc[test_X.index,'sqft'] = pred_Y

        if self.how == 'knn':
            knn_n = 30
            result = fast_knn(houses_dummies[predictors], k=knn_n)
            result.columns = houses_dummies[predictors].columns
            result.index = houses_dummies[predictors].index
            result = result.loc[X.index,:]

        if self.how == 'mice':
            result = mice(houses_dummies[predictors])
            result.columns = houses_dummies[predictors].columns
            result.index = houses_dummies[predictors].index
            result = result.loc[X.index,:]

        if self.how == 'mean':
            result['sqft'] = houses_edited.groupby('type')['sqft'].transform(lambda x: x.fillna(x.mean(skipna=True)))

        if self.how == 'median':
            result['sqft'] = houses_edited.groupby('type')['sqft'].transform(lambda x: x.fillna(x.median(skipna=True)))

        if self.how == 'mode':
            result['sqft'] = houses_edited.groupby('type')['sqft'].transform(lambda x: x.fillna(x.mode()[0]))

        return result[predictors]

methods = ['random forest', 'knn', 'mice', 'mean', 'median', 'mode']

imputer = Impute_sqft()
rf = RandomForestRegressor()
pipe = Pipeline(steps=[
    ('imputer', imputer),
    ('rf', rf)
])

param_grid = [{
    'imputer__how':methods,
    'rf__max_depth':[1,2,None],
    'rf__bootstrap':[True, False]    
}]

houses_dummies_copy = houses_dummies.copy()

search = GridSearchCV(pipe, param_grid, iid=False, cv=5, scoring='neg_mean_absolute_error')
search.fit(houses_dummies_copy[predictors], houses_dummies_copy.final_price)