fcitx | xargs kill
sogou-qimpanel | xargs kill

#!/bin/sh
pidof fcitx | xargs kill
pidof sogou-qimpanel | xargs kill
nohup fcitx  1>/dev/null 2>/dev/null &
nohup sogou-qimpanel  1>/dev/null 2>/dev/null &

def loadDataSet():
    dataMat = []; labelMat = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])	#加上第0维特征值
        labelMat.append(int(lineArr[2]))
    return dataMat,labelMat	#返回数据矩阵和标签向量

def sigmoid(inX):
    return 1.0/(1+exp(-inX))

def gradAscent(dataMatIn, classLabels):		#Logistic回归梯度上升优化算法
    dataMatrix = mat(dataMatIn)             	#由列表转换成NumPy矩阵数据类型，dataMatrix是一个100×3的矩阵
    labelMat = mat(classLabels).transpose() 	#由列表转换成NumPy矩阵数据类型，labelMat是一个100×1的矩阵
    m,n = shape(dataMatrix)		    	#shape函数取得矩阵的行数和列数，m=100,n=3
    alpha = 0.001				#向目标移动的步长
    maxCycles = 500				#迭代次数
    weights = ones((n,1))			#3行1列的矩阵，这个矩阵为最佳的回归系数，和原来的100×3相乘，可以得到100×1的结果
    for k in range(maxCycles):              
        h = sigmoid(dataMatrix*weights)     	#矩阵相乘，得到100×1的矩阵，即把dataMat的每一行的所有元素相加
        error = (labelMat - h)              	#求出和目标向量之间的误差
	#梯度下降算法
        weights = weights + alpha * dataMatrix.transpose()* error #3×100的矩阵乘以100×1的矩阵，weights是梯度算子，总是指向函数值增长最快的方向
    return weights				#返回一组回归系数，确定了不同类别数据之间的分割线

dataMat,labelMat = loadDataSet()
print gradAscent(dataMat,labelMat)	#输出回归系数

-Dzookeeper.DigestAuthenticationProvider.superDigest=super:xQJmxLMiHGwaqBvst5y6rkB6HQs=

[zk: localhost:2181(CONNECTED) 15] addauth digest super:admin
[zk: localhost:2181(CONNECTED) 16] get /hbase

cZxid = 0x155e7a
ctime = Wed Oct 20 21:35:34 CST 2021
mZxid = 0x155e7a
mtime = Wed Oct 20 21:35:34 CST 2021
pZxid = 0x15639a
cversion = 40
dataVersion = 0
aclVersion = 0
ephemeralOwner = 0x0
dataLength = 0
numChildren = 12
[zk: localhost:2181(CONNECTED) 17] rmr /hbase

def loadDataSet():
    postingList=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
                 ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
                 ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
                 ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
                 ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
                 ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    classVec = [0,1,0,1,0,1]    #1 is abusive, 0 not
    return postingList,classVec		#第一个变量是词条切分后的文档集合，取出标点，第二个变量是类别标签的集合
                 
def createVocabList(dataSet):		#创建一个包含在所有文档中出现的不重复词的列表
    vocabSet = set([])  		#生成一个空的集合
    for document in dataSet:
        vocabSet = vocabSet | set(document) #求两个集合的并集
    return list(vocabSet)

def setOfWords2Vec(vocabList, inputSet):#输入参数为词汇表vocabList及某个文档inputSet，输出的是文档向量，即文档中的每个词在词汇表中出现的次数
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else: print "the word: %s is not in my Vocabulary!" % word
    return returnVec

listOPosts,listClasses = loadDataSet()
print "某个文档："
print listOPosts[0]
myVocabList = createVocabList(listOPosts)	#由词表生成向量
print "词汇表："
print myVocabList
print "文档向量："
print setOfWords2Vec(myVocabList,listOPosts[0])

某个文档：
['my', 'dog', 'has', 'flea', 'problems', 'help', 'please']
词汇表：
['cute', 'love', 'help', 'garbage', 'quit', 'I', 'problems', 'is', 'park', 'stop', 'flea', 'dalmation', 'licks', 'food', 'not', 'him', 'buying', 'posting', 'has', 'worthless', 'ate', 'to', 'maybe', 'please', 'dog', 'how', 'stupid', 'so', 'take', 'mr', 'steak', 'my']
文档向量：
[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1]