Question

我创建了一个自定义手工编码分类器，它实现了标准的sklearn分类器函数（fit()，predict()和predict_proba()）。这可以直接与sklearn实用程序GridSearchCV()一起使用，还是应该添加任何内容？

编辑1：根据cel的建议，我尝试直接应用

第一步是按照here的说明添加get_params和set_params。确实完整的交叉验证程序确实运行但最终出现以下错误

return self._fit(X, y, ParameterGrid(self.param_grid))
best_estimator.fit(X, y, **self.fit_params)
AttributeError: 'NoneType' object has no attribute 'fit'

编辑2：添加分类器代码（基于theano的Logistic回归分类器）

class LogisticRegression:
    """ Apply minibatch logistic regression

    :type n_in: int
    :param n_in: number of input units, the dimension of the space in
                 which the datapoints lie

    :type n_out: int
    :param n_out: number of output units, the dimension of the space in
                  which the labels lie

    """

    def __init__(self,n_in,n_out,batch_size=600,learning_rate=0.13,iters=500,verbose=0):
        self.n_in = n_in
        self.n_out = n_out
        self.batch_size = batch_size
        self.learning_rate = learning_rate
        self.iters = iters
        self.verbose = verbose
        self.single_layer = Layer(self.n_in,self.n_out,T.nnet.softmax)
        self.minibatch_count = 0

    def get_params(self,deep=True):
        return {"n_in" : self.n_in,"n_out" : self.n_out,"batch_size" : self.batch_size,
                "learning_rate" : self.learning_rate,"iters" : self.iters,
                "verbose" : self.verbose}

    def set_params(self, **parameters):
        for parameter, value in parameters.items():
            setattr(self, parameter, value)

    def minibatch_trainer(self,data_x,data_y):
        n_batches = data_x.get_value(borrow=True).shape[0]/self.batch_size
        tensor_x = T.matrix('x')
        tensor_y = T.ivector('y')
        index = T.lscalar('index')
        cost = self.single_layer.negative_log_likelihood(tensor_x, tensor_y)
        g_W = T.grad(cost,self.single_layer.W)
        g_b = T.grad(cost,self.single_layer.b)
        updates = [(self.single_layer.W,self.single_layer.W - g_W*self.learning_rate),
                    (self.single_layer.b,self.single_layer.b - g_b*self.learning_rate)]
        train_batch = theano.function([index],[cost],
                                      updates=updates,
                                      givens={tensor_x : data_x[index*self.batch_size : (index + 1)*self.batch_size],
                                              tensor_y : data_y[index*self.batch_size : (index + 1)*self.batch_size]})
        return np.mean([train_batch(i) for i in xrange(n_batches)])

    def fit(self,data_x,data_y):
        data_x,data_y = shared_dataset(data_x,data_y)
        start = time.clock()
        for iter in xrange(self.iters):
            train_err = self.minibatch_trainer(data_x,data_y)
            if self.verbose==1: print "Iter %d --> %f" % (iter,train_err)
        end = time.clock()
        print "Finished Training Logistic Regression Model\n" \
              "Iterations %d\n" \
              "Time Taken : %d secs" % (self.iters,end - start)
        return self

    def partial_fit(self,data_x,data_y):
        data_x,data_y = shared_dataset(data_x,data_y)
        self.minibatch_count += 1
        err = self.minibatch_trainer(data_x, data_y)
        print "MiniBatch %d --> %f" % (self.minibatch_count,err)

    def predict(self,data_x):
        data_x = shared_dataset(data_x)
        n_batches = data_x.get_value(borrow=True).shape[0]/self.batch_size
        tensor_x = T.matrix('x')
        index = T.lscalar('index')
        tensor_ypred = self.prediction_tensor(tensor_x)
        predictor = theano.function([index],tensor_ypred,
                                    givens={tensor_x : data_x[index*self.batch_size:(index + 1)*self.batch_size]})
        ypred = [predictor(i) for i in xrange(n_batches)]
        return np.hstack(ypred)

    def predict_proba(self,data_x):
        data_x = shared_dataset(data_x)
        tensor_x = T.matrix('x')
        tensor_ypredproba = self.single_layer.decision_function_tensor(tensor_x)
        predproba_func = theano.function([],tensor_ypredproba,
                                           givens={tensor_x : data_x})
        return predproba_func()

    def prediction_tensor(self,tensor_x):
        """
        Returns the predicted y value as a tensor variable
        :param tensor_x: TensorType matrix on input data
        :return: TensorType tensor_ypred output
        """
        return T.argmax(self.single_layer.decision_function_tensor(tensor_x),axis=1)

编辑3：添加GridSearchCV的确切用法

clf_cv = GridSearchCV(LogisticRegression(n_in=200,n_out=2),{"iters" : [3]},cv=4,scoring="roc_auc",n_jobs=-1,verbose=1)

我也尝试过添加BaseEstimator和ClassifierMixin; sklearn.base.clone不输出任何错误

Answer 1

几分钟前有同样的问题。 documentation不正确。您必须更改set_params才能返回self：

def set_params(self, **parameters):
  for parameter, value in parameters.items():
    setattr(self, parameter, value)
  return self

GridSearchCV可以与自定义分类器一起使用吗？

1 个答案: