classifier.py 文件源码

def train_classifier(self, trainvectors, labels, alpha='', iterations=50, jobs=10):
        iterations = int(iterations)
        jobs = int(jobs)
        if alpha == '':
            paramsearch = GridSearchCV(estimator=Perceptron(), param_grid=dict(alpha=numpy.linspace(0,2,20)[1:],n_iter=[iterations]), n_jobs=jobs)
            paramsearch.fit(trainvectors,self.label_encoder.transform(labels))
            selected_alpha = paramsearch.best_estimator_.alpha
        elif alpha == 'default':
            selected_alpha = 1.0
        else:
            selected_alpha = alpha
        # train a perceptron with the settings that led to the best performance
        self.model = Perceptron(alpha=selected_alpha,n_iter=iterations,n_jobs=jobs)
        self.model.fit(trainvectors, self.label_encoder.transform(labels))