我想从头开始编写自己的kNN算法,原因是我需要加权特征。问题是,尽管删除了for循环并使用内置的numpy功能,但我的程序仍然非常慢。
有人能建议一种加速的方法吗?我不使用np.sqrt
来计算L2距离,因为这是不必要的,实际上会使速度变慢。
class GlobalWeightedKNN:
"""
A k-NN classifier with feature weights
Returns: predictions of k-NN.
"""
def __init__(self):
self.X_train = None
self.y_train = None
self.k = None
self.weights = None
self.predictions = list()
def fit(self, X_train, y_train, k, weights):
self.X_train = X_train
self.y_train = y_train
self.k = k
self.weights = weights
def predict(self, testing_data):
"""
Takes a 2d array of query cases.
Returns a list of predictions for k-NN classifier
"""
np.fromiter((self.__helper(qc) for qc in testing_data), float)
return self.predictions
def __helper(self, qc):
neighbours = np.fromiter((self.__weighted_euclidean(qc, x) for x in self.X_train), float)
neighbours = np.array([neighbours]).T
indexes = np.array([range(len(self.X_train))]).T
neighbours = np.append(indexes, neighbours, axis=1)
# Sort by second column - distances
neighbours = neighbours[neighbours[:,1].argsort()]
k_cases = neighbours[ :self.k]
indexes = [x[0] for x in k_cases]
y_answers = [self.y_train[int(x)] for x in indexes]
answer = max(set(y_answers), key=y_answers.count) # get most common value
self.predictions.append(answer)
def __weighted_euclidean(self, qc, other):
"""
Custom weighted euclidean distance
returns: floating point number
"""
return np.sum( ((qc - other)**2) * self.weights )
heapq
模块),并仅在其中存储当前最接近的邻居。 - carrdelling