models.py 文件源码

def fit(self, X, Y):
        if len(Y.shape)==1: 
            Y = np.array([Y]).transpose() # Transform vector into column matrix
            # This is NOT what we want: Y = Y.reshape( -1, 1 ), because Y.shape[1] out of range
        self.n_target = Y.shape[1]                 # Num target values = num col of Y
        self.n_label = len(set(Y.ravel()))         # Num labels = num classes (categories of categorical var if n_target=1 or n_target if labels are binary )
        # Create the right number of copies of the predictor instance
        if len(self.predictors)!=self.n_target:
            predictorInstance = self.predictors[0]
            self.predictors = [predictorInstance]
            for i in range(1,self.n_target):
                self.predictors.append(copy.copy(predictorInstance))
        # Fit all predictors
        for i in range(self.n_target):
            # Update the number of desired prodictos
            if hasattr(self.predictors[i], 'n_estimators'):
                self.predictors[i].n_estimators=self.n_estimators
            # Subsample if desired
            if self.balance:
                pos = Y[:,i]>0
                neg = Y[:,i]<=0
                if sum(pos)<sum(neg): 
                    chosen = pos
                    not_chosen = neg
                else: 
                    chosen = neg
                    not_chosen = pos
                num = sum(chosen)
                idx=filter(lambda(x): x[1]==True, enumerate(not_chosen))
                idx=np.array(zip(*idx)[0])
                np.random.shuffle(idx)
                chosen[idx[0:min(num, len(idx))]]=True
                # Train with chosen samples            
                self.predictors[i].fit(X[chosen,:],Y[chosen,i])
            else:
                self.predictors[i].fit(X,Y[:,i])
        return