Python 通过应用RFE选择提供最佳调整R平方值的特征子集

我有两个目标。我想：

通过特征值1-10循环，然后

比较调整后的R平方值 我知道如何只为下面代码中显示的一个固定功能执行此操作。我曾尝试循环使用

selector=RFE（regr，n\u features\u to\u select，step=1）

，但我认为我遗漏了谜题的关键部分。谢谢大家!

from sklearn.feature_selection import RFE
regr = LinearRegression()
#parameters: estimator, n_features_to_select=None, step=1

selector = RFE(regr, 5, step=1)
selector.fit(x_train, y_train)
selector.support_

def show_best_model(support_array, columns, model):
    y_pred = model.predict(X_test.iloc[:, support_array])
    r2 = r2_score(y_test, y_pred)
    n = len(y_pred) #size of test set
    p = len(model.coef_) #number of features
    adjusted_r2 = 1-(1-r2)*(n-1)/(n-p-1)
    print('Adjusted R-squared: %.2f' % adjusted_r2)
    j = 0;
        for i in range(len(support_array)):
        if support_array[i] == True:
            print(columns[i], model.coef_[j])
            j +=1


show_best_model(selector.support_, x_train.columns, selector.estimator_)

---

您可以创建一个自定义的

GridSearchCV

，它对估计器的指定参数值执行穷举搜索

您还可以选择任何可用的评分功能，例如在Scikit learn中。但是，您可以使用给定的简单公式从R2分数计算调整后的R2，然后在自定义

GridSearchCV

中实现它

from collections import OrderedDict
from itertools import product
from sklearn.feature_selection import RFE
from sklearn.linear_model import LinearRegression
from sklearn.datasets import load_iris
from sklearn.metrics import r2_score
from sklearn.model_selection import StratifiedKFold


def customR2Score(y_true, y_pred, n, p):
    """
    Workaround for the adjusted R^2 score
    :param y_true: Ground Truth during iterations
    :param y_pred: Y predicted during iterations
    :param n: the sample size
    :param p: the total number of explanatory variables in the model
    :return: float, adjusted R^2 score
    """
    r2 = r2_score(y_true, y_pred)
    return 1 - (1 - r2) * (n - 1) / (n - p - 1)


def CustomGridSearchCV(X, Y, param_grid, n_splits=10, n_repeats=3):
    """
    Perform GridSearchCV using adjusted R^2 as Scoring.
    Note here we are performing GridSearchCV MANUALLY because adjusted R^2
    cannot be used directly in the GridSearchCV function builtin in Scikit-learn
    :param X: array_like, shape (n_samples, n_features), Samples.
    :param Y: array_like, shape (n_samples, ), Target values.
    :param param_grid: Dictionary with parameters names (string) as keys and lists
                       of parameter settings to try as values, or a list of such
                       dictionaries, in which case the grids spanned by each dictionary
                       in the list are explored. This enables searching over any
                       sequence of parameter settings.
    :param n_splits: Number of folds. Must be at least 2. default=10
    :param n_repeats: Number of times cross-validator needs to be repeated. default=3
    :return: an Ordered Dictionary of the model object and information and best parameters
    """
    best_model = OrderedDict()
    best_model['best_params'] = {}
    best_model['best_train_AdjR2'], best_model['best_cross_AdjR2'] = 0, 0
    best_model['best_model'] = None

    allParams = OrderedDict()
    for key, value in param_grid.items():
        allParams[key] = value

    for items in product(*allParams.values()):
        params = {}
        i = 0
        for k in allParams.keys():
            params[k] = items[i]
            i += 1
        # at this point, we get different combination of parameters
        model_ = RFE(**params)
        avg_AdjR2_train = 0.
        avg_AdjR2_cross = 0.
        for rep in range(n_repeats):
            skf = StratifiedKFold(n_splits=n_splits, shuffle=True)
            AdjR2_train = 0.
            AdjR2_cross = 0.
            for train_index, cross_index in skf.split(X, Y):
                x_train, x_cross = X[train_index], X[cross_index]
                y_train, y_cross = Y[train_index], Y[cross_index]
                model_.fit(x_train, y_train)
                # find Adjusted R2 of train and cross
                y_pred_train = model_.predict(x_train)
                y_pred_cross = model_.predict(x_cross)
                AdjR2_train += customR2Score(y_train, y_pred_train, len(y_train), model_.n_features_)
                AdjR2_cross += customR2Score(y_cross, y_pred_cross, len(y_cross), model_.n_features_)
            AdjR2_train /= n_splits
            AdjR2_cross /= n_splits
            avg_AdjR2_train += AdjR2_train
            avg_AdjR2_cross += AdjR2_cross
        avg_AdjR2_train /= n_repeats
        avg_AdjR2_cross /= n_repeats
        # store the results of the first set of parameters combination
        if abs(avg_AdjR2_cross) >= abs(best_model['best_cross_AdjR2']):
            best_model['best_params'] = params
            best_model['best_train_AdjR2'] = avg_AdjR2_train
            best_model['best_cross_AdjR2'] = avg_AdjR2_cross
            best_model['best_model'] = model_

    return best_model



# Dataset for testing
iris = load_iris()
X = iris.data
Y = iris.target


regr = LinearRegression()

param_grid = {'estimator': [regr],  # you can try different estimator
              'n_features_to_select': range(1, X.shape[1] + 1)}

best_model = CustomGridSearchCV(X, Y, param_grid, n_splits=5, n_repeats=2)

print(best_model)
print(best_model['best_model'].ranking_)
print(best_model['best_model'].support_)

测试结果

---

谢谢Yahya的回复。我还没有机会测试它。我对python相当陌生，因此我将尝试从您的回答中学习

尽管如此，我还是找到了解决问题的办法。这是给未来的学习者的

def show_best_model(support_array, columns, model):
    y_pred = model.predict(X_test.iloc[:, support_array])
    r2 = r2_score(y_test, y_pred)
    n = len(y_pred) #size of test set
    p = len(model.coef_) #number of features
    adjusted_r2 = 1-(1-r2)*(n-1)/(n-p-1)
    print('Adjusted R-squared: %.2f' % adjusted_r2)
    j = 0;
    for i in range(len(support_array)):
        if support_array[i] == True:
            print(columns[i], model.coef_[j])
            j +=1

from sklearn.feature_selection import RFE
regr = LinearRegression()

for m in range(1,11):
    selector = RFE(regr, m, step=1) 
    selector.fit(x_train, y_train)
    if m<11:
        show_best_model(selector.support_, x_train.columns, selector.estimator_)

X = df.loc[:,['Age_08_04', 'KM', 'HP', 'Weight', 'Automatic_airco']]
x_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    test_size =.4,
                                                    random_state = 20)
regr = LinearRegression()
regr.fit(x_train, y_train)
y_pred = regr.predict(X_test)
print('Average error: %.2f' %mean(y_test - y_pred))
print('Mean absolute error: %.2f' %mean_absolute_error(y_test, y_pred))
print('Mean absolute error: %.2f' %(mean(abs(y_test - y_pred))))
print("Root mean squared error: %.2f"
      % math.sqrt(mean_squared_error(y_test, y_pred)))
print('percentage absolute error: %.2f' %mean(abs((y_test - y_pred)/y_test)))
print('percentage absolute error: %.2f' %(mean(abs(y_test - y_pred))/mean(y_test)))
print('R-squared: %.2f' % r2_score(y_test, y_pred))

x_train = x_train.loc[:,
                      ['Age_08_04', 'KM' , 'HP',
                       'Weight', 'Automatic_airco']]
X_test = X_test.loc[:,
                    ['Age_08_04', 'KM' , 'HP',
                     'Weight', 'Automatic_airco']]
selector = RFE(regr, 5, step=1)
selector.fit(x_train, y_train)
show_best_model(selector.support_, x_train.columns, selector.estimator_)

def显示最佳模型（支持数组、列、模型）：
y_pred=model.predict（X_test.iloc[：，support_数组]）
r2=r2_分数（y_测试，y_预测）
n=长度（y_pred）#测试集的大小
p=len（model.coef）#特征数量
调整后的r2=1-（1-r2）*（n-1）/（n-p-1）
打印（'调整后的R平方：%.2f'%Adjusted\u r2）
j=0；
对于范围内的i（len（支持_数组））：
如果支持_数组[i]==True：
打印（第[i]列，model.coef_j]列）
j+=1
从sklearn.feature_选择导入RFE
regr=线性回归（）
对于范围（1,11）内的m：
选择器=RFE（重新，m，步骤=1）
选择器。安装（x_系列、y_系列）
如果mI建议将您的一个标记更改为
scikit，请学习
，因为您将有更多具有该专业知识的人看到您的问题。唯一缺少的是它不会为您比较值。您必须比较r平方的值，然后使用该数量的特性。亲爱的@ron，我的方法是标准的，它会比较值并选择最好的，正如您所说，一旦您熟悉Python，您就会理解我的简单解决方案：）顺便说一句，如果您是指比较，您希望看到元数据，
print（）
是你的朋友：）@ron如果这个答案对你有帮助，请接受它：）
def show_best_model(support_array, columns, model):
    y_pred = model.predict(X_test.iloc[:, support_array])
    r2 = r2_score(y_test, y_pred)
    n = len(y_pred) #size of test set
    p = len(model.coef_) #number of features
    adjusted_r2 = 1-(1-r2)*(n-1)/(n-p-1)
    print('Adjusted R-squared: %.2f' % adjusted_r2)
    j = 0;
    for i in range(len(support_array)):
        if support_array[i] == True:
            print(columns[i], model.coef_[j])
            j +=1

from sklearn.feature_selection import RFE
regr = LinearRegression()

for m in range(1,11):
    selector = RFE(regr, m, step=1) 
    selector.fit(x_train, y_train)
    if m<11:
        show_best_model(selector.support_, x_train.columns, selector.estimator_)

X = df.loc[:,['Age_08_04', 'KM', 'HP', 'Weight', 'Automatic_airco']]
x_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    test_size =.4,
                                                    random_state = 20)
regr = LinearRegression()
regr.fit(x_train, y_train)
y_pred = regr.predict(X_test)
print('Average error: %.2f' %mean(y_test - y_pred))
print('Mean absolute error: %.2f' %mean_absolute_error(y_test, y_pred))
print('Mean absolute error: %.2f' %(mean(abs(y_test - y_pred))))
print("Root mean squared error: %.2f"
      % math.sqrt(mean_squared_error(y_test, y_pred)))
print('percentage absolute error: %.2f' %mean(abs((y_test - y_pred)/y_test)))
print('percentage absolute error: %.2f' %(mean(abs(y_test - y_pred))/mean(y_test)))
print('R-squared: %.2f' % r2_score(y_test, y_pred))

x_train = x_train.loc[:,
                      ['Age_08_04', 'KM' , 'HP',
                       'Weight', 'Automatic_airco']]
X_test = X_test.loc[:,
                    ['Age_08_04', 'KM' , 'HP',
                     'Weight', 'Automatic_airco']]
selector = RFE(regr, 5, step=1)
selector.fit(x_train, y_train)
show_best_model(selector.support_, x_train.columns, selector.estimator_)