更新文件目录到 db 目录下面

Author: jiangzhonglian

blog/ml/13.利用PCA来简化数据.md

@@ -115,7 +115,7 @@
 
 ```python
 def replaceNanWithMean():
-    datMat = loadDataSet('input/13.PCA/secom.data', ' ')
+    datMat = loadDataSet('db/13.PCA/secom.data', ' ')
     numFeat = shape(datMat)[1]
     for i in range(numFeat):
         # 对value不为NaN的求均值

blog/ml/14.利用SVD简化数据.md

@@ -402,7 +402,7 @@ def imgCompress(numSV=3, thresh=0.8):
         thresh      判断的阈值
     """
     # 构建一个列表
-    myMat = imgLoadData('input/14.SVD/0_5.txt')
+    myMat = imgLoadData('db/14.SVD/0_5.txt')
 
     print "****original matrix****"
     # 对原始图像进行SVD分解并重构图像e

blog/ml/15.大数据与MapReduce.md

@@ -64,15 +64,15 @@ cat inputFile.txt | python mapper.py | sort | python reducer.py > outputFile.txt
 ```
 # 测试 Mapper
 # Linux
-cat input/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanMapper.py
+cat db/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanMapper.py
 # Window
-# python src/python/15.BigData_MapReduce/mrMeanMapper.py < input/15.BigData_MapReduce/inputFile.txt
+# python src/python/15.BigData_MapReduce/mrMeanMapper.py < db/15.BigData_MapReduce/inputFile.txt
 
 # 测试 Reducer
 # Linux
-cat input/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanMapper.py | python src/python/15.BigData_MapReduce/mrMeanReducer.py
+cat db/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanMapper.py | python src/python/15.BigData_MapReduce/mrMeanReducer.py
 # Window
-# python src/python/15.BigData_MapReduce/mrMeanMapper.py < input/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanReducer.py
+# python src/python/15.BigData_MapReduce/mrMeanMapper.py < db/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapReduce/mrMeanReducer.py
 ```
 
 ### MapReduce 机器学习
@@ -93,17 +93,17 @@ cat input/15.BigData_MapReduce/inputFile.txt | python src/python/15.BigData_MapR
 * mrjob 是一个不错的学习工具，与2010年底实现了开源，来之于 Yelp(一个餐厅点评网站).
 
 ```Shell
-python src/python/15.BigData_MapReduce/mrMean.py < input/15.BigData_MapReduce/inputFile.txt > input/15.BigData_MapReduce/myOut.txt
+python src/python/15.BigData_MapReduce/mrMean.py < db/15.BigData_MapReduce/inputFile.txt > db/15.BigData_MapReduce/myOut.txt
 ```
 
 > 实战脚本
 
 ```
 # 测试 mrjob的案例
 # 先测试一下mapper方法
-# python src/python/15.BigData_MapReduce/mrMean.py --mapper < input/15.BigData_MapReduce/inputFile.txt
+# python src/python/15.BigData_MapReduce/mrMean.py --mapper < db/15.BigData_MapReduce/inputFile.txt
 # 运行整个程序，移除 --mapper 就行
-python src/python/15.BigData_MapReduce/mrMean.py < input/15.BigData_MapReduce/inputFile.txt
+python src/python/15.BigData_MapReduce/mrMean.py < db/15.BigData_MapReduce/inputFile.txt
 ```
 
 ### 项目案例：分布式 SVM 的 Pegasos 算法
@@ -213,7 +213,7 @@ def batchPegasos(dataSet, labels, lam, T, k):
 
 [完整代码地址](https://github.com/apachecn/AiLearning/blob/master/src/py2.x/ml/15.BigData_MapReduce/pegasos.py): <https://github.com/apachecn/AiLearning/blob/master/src/py2.x/ml/15.BigData_MapReduce/pegasos.py>
 
-运行方式：`python /opt/git/MachineLearning/src/python/15.BigData_MapReduce/mrSVM.py < input/15.BigData_MapReduce/inputFile.txt`
+运行方式：`python /opt/git/MachineLearning/src/python/15.BigData_MapReduce/mrSVM.py < db/15.BigData_MapReduce/inputFile.txt`
 [MR版本的代码地址](https://github.com/apachecn/AiLearning/blob/master/src/py2.x/ml/15.BigData_MapReduce/mrSVM.py): <https://github.com/apachecn/AiLearning/blob/master/src/py2.x/ml/15.BigData_MapReduce/mrSVM.py>
 
 * * *

blog/ml/2.k-近邻算法.md

@@ -98,7 +98,7 @@ knn 算法按照距离最近的三部电影的类型，决定未知电影的类
 
 > 收集数据：提供文本文件
 
-海伦把这些约会对象的数据存放在文本文件 [datingTestSet2.txt](https://github.com/apachecn/AiLearning/tree/dev/input/2.KNN/datingTestSet2.txt) 中，总共有 1000 行。海伦约会的对象主要包含以下 3 种特征：
+海伦把这些约会对象的数据存放在文本文件 [datingTestSet2.txt](https://github.com/apachecn/AiLearning/tree/ddb/2.KNN/datingTestSet2.txt) 中，总共有 1000 行。海伦约会的对象主要包含以下 3 种特征：
 
 * 每年获得的飞行常客里程数
 * 玩视频游戏所耗时间百分比
@@ -288,7 +288,7 @@ def datingClassTest():
     # 设置测试数据的的一个比例（训练数据集比例=1-hoRatio）
     hoRatio = 0.1  # 测试范围,一部分测试一部分作为样本
     # 从文件中加载数据
-    datingDataMat, datingLabels = file2matrix('input/2.KNN/datingTestSet2.txt')  # load data setfrom file
+    datingDataMat, datingLabels = file2matrix('db/2.KNN/datingTestSet2.txt')  # load data setfrom file
     # 归一化数据
     normMat, ranges, minVals = autoNorm(datingDataMat)
     # m 表示数据的行数，即矩阵的第一维
@@ -361,7 +361,7 @@ You will probably like this person: in small doses
 
 > 收集数据: 提供文本文件
 
-目录 [trainingDigits](../input/2.KNN/trainingDigits) 中包含了大约 2000 个例子，每个例子内容如下图所示，每个数字大约有 200 个样本；目录 [testDigits](../input/2.KNN/testDigits) 中包含了大约 900 个测试数据。
+目录 [trainingDigits](db/2.KNN/trainingDigits) 中包含了大约 2000 个例子，每个例子内容如下图所示，每个数字大约有 200 个样本；目录 [testDigits](db/2.KNN/testDigits) 中包含了大约 900 个测试数据。
 
 ![手写数字数据集的例子](/img/ml/2.KNN/knn_2_handWriting.png)
 
@@ -402,7 +402,7 @@ array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1
 def handwritingClassTest():
     # 1. 导入训练数据
     hwLabels = []
-    trainingFileList = listdir('input/2.KNN/trainingDigits')  # load the training set
+    trainingFileList = listdir('db/2.KNN/trainingDigits')  # load the training set
     m = len(trainingFileList)
     trainingMat = zeros((m, 1024))
     # hwLabels存储0～9对应的index位置， trainingMat存放的每个位置对应的图片向量
@@ -412,17 +412,17 @@ def handwritingClassTest():
         classNumStr = int(fileStr.split('_')[0])
         hwLabels.append(classNumStr)
         # 将 32*32的矩阵->1*1024的矩阵
-        trainingMat[i, :] = img2vector('input/2.KNN/trainingDigits/%s' % fileNameStr)
+        trainingMat[i, :] = img2vector('db/2.KNN/trainingDigits/%s' % fileNameStr)
 
     # 2. 导入测试数据
-    testFileList = listdir('input/2.KNN/testDigits')  # iterate through the test set
+    testFileList = listdir('db/2.KNN/testDigits')  # iterate through the test set
     errorCount = 0.0
     mTest = len(testFileList)
     for i in range(mTest):
         fileNameStr = testFileList[i]
         fileStr = fileNameStr.split('.')[0]  # take off .txt
         classNumStr = int(fileStr.split('_')[0])
-        vectorUnderTest = img2vector('input/2.KNN/testDigits/%s' % fileNameStr)
+        vectorUnderTest = img2vector('db/2.KNN/testDigits/%s' % fileNameStr)
         classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
         print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
         if (classifierResult != classNumStr): errorCount += 1.0

blog/ml/4.朴素贝叶斯.md

@@ -502,11 +502,11 @@ def spamTest():
     fullText = []
     for i in range(1, 26):
         # 切分，解析数据，并归类为 1 类别
-        wordList = textParse(open('input/4.NaiveBayes/email/spam/%d.txt' % i).read())
+        wordList = textParse(open('db/4.NaiveBayes/email/spam/%d.txt' % i).read())
         docList.append(wordList)
         classList.append(1)
         # 切分，解析数据，并归类为 0 类别
-        wordList = textParse(open('input/4.NaiveBayes/email/ham/%d.txt' % i).read())
+        wordList = textParse(open('db/4.NaiveBayes/email/ham/%d.txt' % i).read())
         docList.append(wordList)
         fullText.extend(wordList)
         classList.append(0)

blog/ml/5.Logistic回归.md

@@ -297,7 +297,7 @@ def plotBestFit(dataArr, labelMat, weights):
 ```python
 def testLR():
     # 1.收集并准备数据
-    dataMat, labelMat = loadDataSet("input/5.Logistic/TestSet.txt")
+    dataMat, labelMat = loadDataSet("db/5.Logistic/TestSet.txt")
 
     # print dataMat, '---\n', labelMat
     # 2.训练模型，  f(x)=a1*x1+b2*x2+..+nn*xn中 (a1,b2, .., nn).T的矩阵值
@@ -576,8 +576,8 @@ def colicTest():
     Returns:
         errorRate -- 分类错误率
     '''
-    frTrain = open('input/5.Logistic/horseColicTraining.txt')
-    frTest = open('input/5.Logistic/horseColicTest.txt')
+    frTrain = open('db/5.Logistic/horseColicTraining.txt')
+    frTest = open('db/5.Logistic/horseColicTest.txt')
     trainingSet = []
     trainingLabels = []
     # 解析训练数据集中的数据特征和Labels

blog/ml/6.支持向量机.md

@@ -526,7 +526,7 @@ def smoP(dataMatIn, classLabels, C, toler, maxIter, kTup=('lin', 0)):
 def testDigits(kTup=('rbf', 10)):
 
     # 1. 导入训练数据
-    dataArr, labelArr = loadImages('input/6.SVM/trainingDigits')
+    dataArr, labelArr = loadImages('db/6.SVM/trainingDigits')
     b, alphas = smoP(dataArr, labelArr, 200, 0.0001, 10000, kTup)
     datMat = mat(dataArr)
     labelMat = mat(labelArr).transpose()
@@ -544,7 +544,7 @@ def testDigits(kTup=('rbf', 10)):
     print("the training error rate is: %f" % (float(errorCount) / m))
 
     # 2. 导入测试数据
-    dataArr, labelArr = loadImages('input/6.SVM/testDigits')
+    dataArr, labelArr = loadImages('db/6.SVM/testDigits')
     errorCount = 0
     datMat = mat(dataArr)
     labelMat = mat(labelArr).transpose()

blog/ml/7.集成方法-随机森林和AdaBoost.md

@@ -498,13 +498,13 @@ def adaClassify(datToClass, classifierArr):
 ```python
 # 马疝病数据集
 # 训练集合
-dataArr, labelArr = loadDataSet("input/7.AdaBoost/horseColicTraining2.txt")
+dataArr, labelArr = loadDataSet("db/7.AdaBoost/horseColicTraining2.txt")
 weakClassArr, aggClassEst = adaBoostTrainDS(dataArr, labelArr, 40)
 print weakClassArr, '\n-----\n', aggClassEst.T
 # 计算ROC下面的AUC的面积大小
 plotROC(aggClassEst.T, labelArr)
 # 测试集合
-dataArrTest, labelArrTest = loadDataSet("input/7.AdaBoost/horseColicTest2.txt")
+dataArrTest, labelArrTest = loadDataSet("db/7.AdaBoost/horseColicTest2.txt")
 m = shape(dataArrTest)[0]
 predicting10 = adaClassify(dataArrTest, weakClassArr)
 errArr = mat(ones((m, 1)))

blog/ml/8.回归.md

@@ -161,7 +161,7 @@ def standRegres(xArr,yArr):
 
 
 def regression1():
-    xArr, yArr = loadDataSet("input/8.Regression/data.txt")
+    xArr, yArr = loadDataSet("db/8.Regression/data.txt")
     xMat = mat(xArr)
     yMat = mat(yArr)
     ws = standRegres(xArr, yArr)
@@ -325,7 +325,7 @@ def lwlrTestPlot(xArr,yArr,k=1.0):
 
 #test for LWLR
 def regression2():
-    xArr, yArr = loadDataSet("input/8.Regression/data.txt")
+    xArr, yArr = loadDataSet("db/8.Regression/data.txt")
     yHat = lwlrTest(xArr, xArr, yArr, 0.003)
     xMat = mat(xArr)
     srtInd = xMat[:,1].argsort(0)           # argsort()函数是将x中的元素从小到大排列，提取其对应的index(索引)，然后输出
@@ -418,7 +418,7 @@ def abaloneTest():
         None
     '''
     # 加载数据
-    abX, abY = loadDataSet("input/8.Regression/abalone.txt")
+    abX, abY = loadDataSet("db/8.Regression/abalone.txt")
     # 使用不同的核进行预测
     oldyHat01 = lwlrTest(abX[0:99], abX[0:99], abY[0:99], 0.1)
     oldyHat1 = lwlrTest(abX[0:99], abX[0:99], abY[0:99], 1)
@@ -540,7 +540,7 @@ def ridgeTest(xArr,yArr):
 
 #test for ridgeRegression
 def regression3():
-    abX,abY = loadDataSet("input/8.Regression/abalone.txt")
+    abX,abY = loadDataSet("db/8.Regression/abalone.txt")
     ridgeWeights = ridgeTest(abX, abY)
     fig = plt.figure()
     ax = fig.add_subplot(111)
@@ -619,7 +619,7 @@ def stageWise(xArr,yArr,eps=0.01,numIt=100):
 
 #test for stageWise
 def regression4():
-    xArr,yArr=loadDataSet("input/8.Regression/abalone.txt")
+    xArr,yArr=loadDataSet("db/8.Regression/abalone.txt")
     print(stageWise(xArr,yArr,0.01,200))
     xMat = mat(xArr)
     yMat = mat(yArr).T
@@ -745,12 +745,12 @@ def scrapePage(retX, retY, inFile, yr, numPce, origPrc):
 
 # 依次读取六种乐高套装的数据，并生成数据矩阵        
 def setDataCollect(retX, retY):
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego8288.html', 2006, 800, 49.99)
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego10030.html', 2002, 3096, 269.99)
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego10179.html', 2007, 5195, 499.99)
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego10181.html', 2007, 3428, 199.99)
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego10189.html', 2008, 5922, 299.99)
-    scrapePage(retX, retY, 'input/8.Regression/setHtml/lego10196.html', 2009, 3263, 249.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego8288.html', 2006, 800, 49.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego10030.html', 2002, 3096, 269.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego10179.html', 2007, 5195, 499.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego10181.html', 2007, 3428, 199.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego10189.html', 2008, 5922, 299.99)
+    scrapePage(retX, retY, 'db/8.Regression/setHtml/lego10196.html', 2009, 3263, 249.99)
 ```
 
 > 测试算法：使用交叉验证来测试不同的模型，分析哪个效果最好