cs231n assignment1 knn作业

import numpy as np

class KNearestNeighbor(object):
  """ a kNN classifier with L2 distance """

  def __init__(self):
    pass

  def train(self, X, y):
   
    self.X_train = X
    self.y_train = y
    
  def predict(self, X, k=1, num_loops=0):

    if num_loops == 0:
      dists = self.compute_distances_no_loops(X)
    elif num_loops == 1:
      dists = self.compute_distances_one_loop(X)
    elif num_loops == 2:
      dists = self.compute_distances_two_loops(X)
    else:
      raise ValueError('Invalid value %d for num_loops' % num_loops)

    return self.predict_labels(dists, k=k)

  def compute_distances_two_loops(self, X):

    num_test = X.shape[0]
    num_train = self.X_train.shape[0]
    dists = np.zeros((num_test, num_train))
    for i in range(num_test):
      for j in range(num_train):


        dist = np.sqrt(np.sum(np.square(self.X_train[j] - X[i])))    #l2 distance
        # dist = np.sum(abs(self.X_train[j]-X[i]))                   #l1 distance
        dists[i][j] = dist

    return dists

  def compute_distances_one_loop(self, X):


    num_test = X.shape[0]
    num_train = self.X_train.shape[0]
    dists = np.zeros((num_test, num_train))
    # print(self.X_train.T.shape)
    # print(X.shape)
    for i in range(num_test):

      dists[i] = np.sqrt(np.sum(np.square(self.X_train-X[i]),axis = 1))

    return dists

  def compute_distances_no_loops(self, X):
    
    num_test = X.shape[0]
    num_train = self.X_train.shape[0]
    dists = np.zeros((num_test, num_train)) 

    a2 = np.sum(np.square(self.X_train),axis=1)
    b2 = np.sum(np.square(X),axis=1,keepdims=True)
    f2ab = np.multiply(np.dot(X,self.X_train.T),-2)
    dists = np.add(np.add(a2,f2ab),b2)
    
    dists = np.sqrt(dists)

    return dists

  def predict_labels(self, dists, k=1):

    num_test = dists.shape[0]
    y_pred = np.zeros(num_test)
    for i in range(num_test):
      # A list of length k storing the labels of the k nearest neighbors to
      # the ith test point.
      closest_y = []   
    
      closest_y = self.y_train[np.argsort(dists[i])[:k]]
      y_pred[i] = np.argmax(np.bincount(closest_y))


    return y_pred