前提代码：
import numpy as np
class KNearestNeighbor(object):
""" a kNN classifier with L2 distance """
def __init__(self):
pass
def train(self, X, y):
"""
Train the classifier. For k-nearest neighbors this is just
memorizing the training data.
Inputs:
- X: A numpy array of shape (num_train, D) containing the training data
consisting of num_train samples each of dimension D.
- y: A numpy array of shape (N,) containing the training labels, where
y[i] is the label for X[i].
"""
self.X_train = X
self.y_train = y
def predict(self, X, k=1, num_loops=0):
"""
Predict labels for test data using this classifier.
Inputs:
- X: A numpy array of shape (num_test, D) containing test data consisting
of num_test samples each of dimension D.
- k: The number of nearest neighbors that vote for the predicted labels.
- num_loops: Determines which implementation to use to compute distances
between training points and testing points.
Returns:
- y: A numpy array of shape (num_test,) containing predicted labels for the
test data, where y[i] is the predicted label for the test point X[i].
"""
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)
二重循环计算l2距离
def compute_distances_two_loops(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using a nested loop over both the training data and the
test data.
Inputs:
- X: A numpy array of shape (num_test, D) containing test data.
Returns:
- dists: A numpy array of shape (num_test, num_train) where dists[i, j]
is the Euclidean distance between the ith test point and the jth training
point.
"""
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):
#####################################################################
# TODO: #
# Compute the l2 distance between the ith test point and the jth #
# training point, and store the result in dists[i, j]. You should #
# not use a loop over dimension. #
#####################################################################
dists[i][j] = np.sqrt(np.sum(np.square(self.X_train[j, :] - X[i, :])))
#####################################################################
# END OF YOUR CODE #
#####################################################################
return dists
- dists的第n行代表第n个测试集分别与不同训练集的l2距离
- dists[i][j] = np.sqrt(np.sum(np.square(self.X_train[j, :] - X[i, :])))：
求第i个测试集与第j个训练集之间的l2距离
一重循环计算l2距离
def compute_distances_one_loop(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using a single loop over the test data.
Input / Output: Same as compute_distances_two_loops
"""
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):
#######################################################################
# TODO: #
# Compute the l2 distance between the ith test point and all training #
# points, and store the result in dists[i, :]. #
#######################################################################
dists[i,] = np.sqrt(np.sum(np.square(self.X_train- X[i, :]),axis=1))
#######################################################################
# END OF YOUR CODE #
#######################################################################
return dists
- np.square(self.X_train- X[i, :])利用了python的广播特性，直接求出第i个测试集与其他训练集之间的l2距离
- np.sum(np.square(self.X_train- X[i, :]),axis=1)中axis=1指定了求的是行的和，返回一个一维向量，否则np.sum函数会直接求整个数组的和，返回一个整数
无循环计算l2距离
def compute_distances_no_loops(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using no explicit loops.
Input / Output: Same as compute_distances_two_loops
"""
#########################################################################
# TODO: #
# Compute the l2 distance between all test points and all training #
# points without using any explicit loops, and store the result in #
# dists. #
# #
# You should implement this function using only basic array operations; #
# in particular you should not use functions from scipy. #
# #
# HINT: Try to formulate the l2 distance using matrix multiplication #
# and two broadcast sums. #
#########################################################################
num_test = X.shape[0]
num_train = self.X_train.shape[0]
dists = np.zeros((num_test, num_train))
d1 = np.multiply(np.dot(X, self.X_train.T), -2) # shape (num_test, num_train)
d2 = np.sum(np.square(X), axis=1, keepdims=True) # shape (num_test, 1)
d3 = np.sum(np.square(self.X_train), axis=1) # shape (1, num_train)
dists = np.sqrt(d1 + d2 + d3)
#########################################################################
# END OF YOUR CODE #
#########################################################################
return dists
图源点击跳转
- 根据上图公式将距离拆为三个矩阵的和，利用广播机制，(m,1)自动拓展为n列m，(1,n)自动拓展为m行n
- keepdims主要用于保持矩阵的二维特性 更多关于keepdims
图源点击跳转
预测标签
def predict_labels(self, dists, k=1):
"""
Given a matrix of distances between test points and training points,
predict a label for each test point.
Inputs:
- dists: A numpy array of shape (num_test, num_train) where dists[i, j]
gives the distance betwen the ith test point and the jth training point.
Returns:
- y: A numpy array of shape (num_test,) containing predicted labels for the
test data, where y[i] is the predicted label for the test point X[i].
"""
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 = []
#########################################################################
# TODO: #
# Use the distance matrix to find the k nearest neighbors of the ith #
# testing point, and use self.y_train to find the labels of these #
# neighbors. Store these labels in closest_y. #
# Hint: Look up the function numpy.argsort. #
#########################################################################
a = np.argsort(dists[i])[:k]
closet_y = self.y_train[a]
#########################################################################
# TODO: #
# Now that you have found the labels of the k nearest neighbors, you #
# need to find the most common label in the list closest_y of labels. #
# Store this label in y_pred[i]. Break ties by choosing the smaller #
# label. #
#########################################################################
np.sort(closet_y)
num_same = 0
num_temp = 0
for j in range(k):
if (j == 0):
num_same = num_temp = 1
y_pred[i] = closet_y[0]
else:
if (closet_y[j] == closet_y[j - 1]):
num_temp = num_temp + 1
elif (closet_y[j] != closet_y[j - 1]):
num_temp = 1
if num_temp > num_same:
num_same = num_temp
y_pred[i] = closet_y[j]
#########################################################################
# END OF YOUR CODE #
#########################################################################
return y_pred
以上代码是参考链接2中的，还可以使用numpy中的bincount和argmax简化第二段操作
m = np.bincount(closet_y)
y_pred[i] = np.argmax(m)
-
argsort函数：将x中的元素从小到大排列，提取其对应的index(索引)，然后输出到y更多关于argsort
-
故而a = np.argsort(dists[i])[:k]求出了前k个距离最小的索引，closet_y = self.y_train[a]求出他们对应的标签
-
sort函数：从小到大排序
-
bincount函数：统计输入数组各元素的频次更多关于bincount函数
例如输入[1,1,1,2,5]，输出[0,3,1,0,0,1] (0出现0次，1出现3次，2出现1次……) -
argmax函数：获得numpy数组中最大元素的索引
总结
最简单的第一次作业的第一道题，也还是花了一些时间，主要是对于python的numpy函数不熟悉，广播机制和相关函数还需要好好学习，漫漫长路~
扫一扫
370
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
