【python】kNN基礎算法--推薦系統

  雖然把text轉成所有量化是能夠的，可是仍是須要把text轉成numpy的形式（這個是必須掌握的）

  在將數據輸入到分類器以前，必須將待處理數據的格式改變爲分類器能夠接受的格式。

  數據規範化、數據歸一化、數據算法化、輸出偏差分析

代碼：

 

# -*- coding:utf-8 -*-
from numpy import *


def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector
#結果所有量化，把喜歡不喜歡排名一、二、3
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')

import matplotlib
import matplotlib.pyplot as plt
# matplotlib 是python最著名的繪圖庫，它提供了一整套和matlab類似的命令API，十分適合交互式地行製圖。並且也能夠方便地將它做爲繪圖控件，嵌入GUI應用程序中。
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
plt.show()

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))  #建立新的返回矩陣
    m = dataSet.shape[0]   #獲得數據集的行數  shape方法用來獲得矩陣或數組的維數
    normDataSet = dataSet - tile(minVals,(m,1))  #tile:numpy中的函數。tile將原來的一個數組minVals，擴充成了m行1列的數組
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals

normMat,ranges,minVals = autoNorm((datingDataMat))

import operator
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()     
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


    def datingClassTest():
        hoRatio = 0.10
        ErrorCount = 0.0
        datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
        normMat, ranges, minVals = autoNorm(datingDataMat)
        m = normMat.shape[0]
        count = int(m*hoRatio)    #這裏須要整型化
        for i in range(count):
            #算法裏使用的數據是count（總數）仍是i（當前數）,
            #逐漸被測試的數據inX使用[i,:],可是數據集使用count
            # 輸入參數:normMat[i,:]爲測試樣例，表示歸一化後的第i行數據
            #       normMat[numTestVecs:m,:]爲訓練樣本數據，樣本數量爲(m-numTestVecs)個
            #       datingLabels[numTestVecs:m]爲訓練樣本對應的類型標籤
            #       k爲k-近鄰的取值
            classifierResult = classify0(normMat[i,:],normMat[count:m,:],datingLabels[count:m],4)
            print "the classifier came back with:%d,the real answer is :%d"\
                   % (classifierResult,datingLabels[i])
            if (classifierResult != datingLabels[i]) : ErrorCount += 1.0
        print "the total error rate is :%f" % (ErrorCount/float(count))

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    #float定義了輸入的類型
    percentTats = float(raw_input(
        "percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels = file2matrix(("datingTestSet2.txt"))
    normMat,ranges,minVals = autoNorm(datingDataMat)
    #將輸入的數據數組化
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print "You will probably like this person:",resultList[classifierResult - 1]