Question

我已经学习了如何实现SBS算法，现在尝试在python中实现SFS

class SBS():
    def __init__(self, estimator, k_features, scoring=accuracy_score, test_size=0.25, random_state=1):
        self.scoring = scoring
        self.estimator = clone(estimator)
        self.k_features = k_features
        self.test_size = test_size
        self.random_state = random_state

    def fit(self, X, y):   
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=self.test_size, random_state=self.random_state)
        dim = X_train.shape[1]
        self.indices_ = tuple(range(dim))
        self.subsets_ = [self.indices_]
        score = self._calc_score(X_train, y_train, X_test, y_test, self.indices_)
        self.scores_ = [score]
        while dim > self.k_features:
            scores = []; subsets = []
            for p in combinations(self.indices_, r=dim - 1):
                score = self._calc_score(X_train, y_train, X_test, y_test, p)
                scores.append(score)
                subsets.append(p)
            best = np.argmax(scores)
            self.indices_ = subsets[best]
            self.subsets_.append(self.indices_)
            dim -= 1
            self.scores_.append(scores[best])
        self.k_score_ = self.scores_[-1]
        return self

    def transform(self, X):
        return X[:, self.indices_]

    def _calc_score(self, X_train, y_train, X_test, y_test, indices):
        self.estimator.fit(X_train[:, indices], y_train)
        y_pred = self.estimator.predict(X_test[:, indices])
        score = self.scoring(y_test, y_pred)
        return score

现在，我正在尝试根据上述代码实现SFS算法。

到目前为止：

class SFS():
  def __init__(self, estimator, k_features=0, verbose=0, scoring=accuracy_score, test_size=0.25, random_state=1):
      self.estimator = clone(estimator)
      self.scoring = scoring
      self.test_size = test_size
      self.k_features = k_features
      self.random_state = random_state

  def fit(self, X, y):   
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=self.test_size, random_state=self.random_state)
        dim = X_train.shape[1]
        self.indices_ = 0
        self.subsets_ = []
        score = self._calc_score(X_train, y_train, X_test, y_test, self.indices_)

  def transform(self, X):
        return X[:, self.indices_]

  def _calc_score(self, X_train, y_train, X_test, y_test, indices):
        self.estimator.fit(X_train[1:], y_train)
        y_pred = self.estimator.predict(X_test[1:])
        score = self.scoring(y_test, y_pred)
        return score

我了解SFS算法，

从空子集开始
选择下一个最佳特征（x ^ + = argmax J（Y_k + x）
更新Y_ {k + 1} = Y_k + x ^ +，k + = 1
返回2直到找到最佳功能

但是用代码编写是另一回事。因为我真的是这个主题的初学者。

有人可以在fit()方法上为我提供帮助并解释其工作原理吗？

谢谢！

从头开始实施SFS

0 个答案: