knn

KNN算法

看到的一个很简单的例子，用knn算法来实现分类，引用 sklearn 很简单就实现

import numpy as np
from sklearn import neighbors
knn = neighbors.KNeighborsClassifier() #取得knn分类器
data = np.array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]]) # data对应着打斗次数和接吻次数
labels = np.array([1,1,1,2,2,2]) #labels则是对应Romance和Action
knn.fit(data,labels) #导入数据进行训练'''
knn.predict([18,90])
from numpy import *
import operator

然而中间过程细节都被隐藏了，发现一个写内部过程的代码，和模式识别课上一样

# create a dataset which contains 4 samples with 2 classes
def createDataSet():
# create a matrix: each row as a sample
group = array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]])
labels = ['A', 'A','A', 'B', 'B', 'B'] # four samples and two classes
return group, labels

# classify using kNN
def kNNClassify(newInput, dataSet, labels, k):
numSamples = dataSet.shape[0] # shape[0] stands for the num of row

## step 1: calculate Euclidean distance
# tile(A, reps): Construct an array by repeating A reps times
# the following copy numSamples rows for dataSet
diff = tile(newInput, (numSamples, 1)) - dataSet # Subtract element-wise
squaredDiff = diff ** 2 # squared for the subtract
squaredDist = sum(squaredDiff, axis = 1) # sum is performed by row
distance = squaredDist ** 0.5

## step 2: sort the distance
# argsort() returns the indices that would sort an array in a ascending order
sortedDistIndices = argsort(distance)

classCount = {} # define a dictionary (can be append element)
for i in xrange(k):
## step 3: choose the min k distance
voteLabel = labels[sortedDistIndices[i]]

## step 4: count the times labels occur
# when the key voteLabel is not in dictionary classCount, get()
# will return 0
classCount[voteLabel] = classCount.get(voteLabel, 0) + 1

## step 5: the max voted class will return
maxCount = 0
for key, value in classCount.items():
if value > maxCount:
maxCount = value
maxIndex = key

return maxIndex
dataSet, labels = createDataSet()

testX = array([18, 90])
k = 3
outputLabel = kNNClassify(testX, dataSet, labels, 3)
print "Your input is:", testX, "and classified to class: ", outputLabel

用的是同样的参数

这个语言不错