Method predict

DecisionTree/id3_c45.py:196–231

(self,X)

    

    def predict(self,X):
        if self._tree==None:
            raise NotFittedError("Estimator not fitted, call `fit` first")
        
        #类型检查
        if isinstance(X,np.ndarray): 
            pass
        else: 
            try:
                X = np.array(X)
            except:
                raise TypeError("numpy.ndarray required for X")
        
        def _classify(tree,sample):
            """
            用训练好的决策树对输入数据分类 
            决策树的构建是一个递归的过程，用决策树分类也是一个递归的过程
            _classify()一次只能对一个样本（sample）分类
            To Do: 多个sample的预测怎样并行化？
            """
            featIndex = tree.keys()[0]
            secondDict = tree[featIndex]
            key = sample[int(featIndex[1:])]
            valueOfkey = secondDict[key]
            if isinstance(valueOfkey, dict): 
                label = _classify(valueOfkey,sample)
            else: label = valueOfkey
            return label
            
        if len(X.shape)==1:
            return _classify(self._tree,X)
        else:   
            results = []
            for i in range(X.shape[0]):
                results.append(_classify(self._tree,X[i]))
            return np.array(results)
        
    def show(self):
        if self._tree==None: