Merge pull request apachecn#389 from cclauss/patch-2

有心了，谢谢小哥哥 | print() is a function in Python 3
DallasAutumn · Jun 7, 2018 · d5379f8 · d5379f8
2 parents 62593ed + 736778f
commit d5379f8
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 31 deletions.
diff --git a/src/py3.x/ML/13.PCA/pca.py b/src/py3.x/ML/13.PCA/pca.py
@@ -33,11 +33,11 @@ def pca(dataMat, topNfeat=9999999):
 
     # 计算每一列的均值
     meanVals = mean(dataMat, axis=0)
-    # print ('meanVals', meanVals)
+    # print('meanVals', meanVals)
 
     # 每个向量同时都减去 均值
     meanRemoved = dataMat - meanVals
-    # print ('meanRemoved=', meanRemoved)
+    # print('meanRemoved=', meanRemoved)
 
     # cov协方差=[(x1-x均值)*(y1-y均值)+(x2-x均值)*(y2-y均值)+...+(xn-x均值)*(yn-y均值)+]/(n-1)
     '''
@@ -53,8 +53,8 @@ def pca(dataMat, topNfeat=9999999):
 
     # eigVals为特征值， eigVects为特征向量
     eigVals, eigVects = linalg.eig(mat(covMat))
-    # print ('eigVals=', eigVals)
-    # print( 'eigVects=', eigVects)
+    # print('eigVals=', eigVals)
+    # print('eigVects=', eigVects)
     # 对特征值，进行从小到大的排序，返回从小到大的index序号
     # 特征值的逆序就可以得到topNfeat个最大的特征向量
     '''
@@ -70,20 +70,20 @@ def pca(dataMat, topNfeat=9999999):
     array([0, 2, 1])
     '''
     eigValInd = argsort(eigVals)
-    # print ('eigValInd1=', eigValInd)
+    # print('eigValInd1=', eigValInd)
 
     # -1表示倒序，返回topN的特征值[-1 到 -(topNfeat+1) 但是不包括-(topNfeat+1)本身的倒叙]
     eigValInd = eigValInd[:-(topNfeat+1):-1]
-    # print ('eigValInd2=', eigValInd)
+    # print('eigValInd2=', eigValInd)
     # 重组 eigVects 最大到最小
     redEigVects = eigVects[:, eigValInd]
-    # print ('redEigVects=', redEigVects.T)
+    # print('redEigVects=', redEigVects.T)
     # 将数据转换到新空间
     # print( "---", shape(meanRemoved), shape(redEigVects))
     lowDDataMat = meanRemoved * redEigVects
     reconMat = (lowDDataMat * redEigVects.T) + meanVals
-    # print ('lowDDataMat=', lowDDataMat)
-    # print ('reconMat=', reconMat)
+    # print('lowDDataMat=', lowDDataMat)
+    # print('reconMat=', reconMat)
     return lowDDataMat, reconMat
 
 
@@ -130,7 +130,7 @@ def analyse_data(dataMat):
 
         最后，我们可能会注意到有一些小的负值，他们主要源自数值误差应该四舍五入成0.
         '''
-        print '主成分：%s, 方差占比：%s%%, 累积方差占比：%s%%' % (format(i+1, '2.0f'), format(line_cov_score/cov_all_score*100, '4.2f'), format(sum_cov_score/cov_all_score*100, '4.1f'))
+        print('主成分：%s, 方差占比：%s%%, 累积方差占比：%s%%' % (format(i+1, '2.0f'), format(line_cov_score/cov_all_score*100, '4.2f'), format(sum_cov_score/cov_all_score*100, '4.1f')))
 
 
 if __name__ == "__main__":
@@ -140,14 +140,14 @@ def analyse_data(dataMat):
     # lowDmat, reconMat = pca(dataMat, 1)
     # # 只需要2个特征向量，和原始数据一致，没任何变化
     # # lowDmat, reconMat = pca(dataMat, 2)
-    # # print (shape(lowDmat))
+    # # print(shape(lowDmat))
     # show_picture(dataMat, reconMat)
 
     # 利用PCA对半导体制造数据降维
     dataMat = replaceNanWithMean()
-    print (shape(dataMat))
+    print(shape(dataMat))
     # 分析数据
     analyse_data(dataMat)
     # lowDmat, reconMat = pca(dataMat, 20)
-    # print (shape(lowDmat))
+    # print(shape(lowDmat))
     # show_picture(dataMat, reconMat)
diff --git a/src/py3.x/ML/7.AdaBoost/sklearn-adaboost-demo.py b/src/py3.x/ML/7.AdaBoost/sklearn-adaboost-demo.py
@@ -47,15 +47,15 @@
 plt.legend()
 plt.show()
 
-print 'y---', type(y[0]), len(y), y[:4]
-print 'y_1---', type(y_1[0]), len(y_1), y_1[:4]
-print 'y_2---', type(y_2[0]), len(y_2), y_2[:4]
+print('y---', type(y[0]), len(y), y[:4])
+print('y_1---', type(y_1[0]), len(y_1), y_1[:4])
+print('y_2---', type(y_2[0]), len(y_2), y_2[:4])
 
 # 适合2分类
 y_true = np.array([0, 0, 1, 1])
 y_scores = np.array([0.1, 0.4, 0.35, 0.8])
-print 'y_scores---', type(y_scores[0]), len(y_scores), y_scores
-print metrics.roc_auc_score(y_true, y_scores)
+print('y_scores---', type(y_scores[0]), len(y_scores), y_scores)
+print(metrics.roc_auc_score(y_true, y_scores))
 
-# print "-" * 100
-# print metrics.roc_auc_score(y[:1], y_2[:1])
+# print("-" * 100)
+# print(metrics.roc_auc_score(y[:1], y_2[:1]))
diff --git a/src/py3.x/ML/7.RandomForest/randomForest.py b/src/py3.x/ML/7.RandomForest/randomForest.py
@@ -102,7 +102,7 @@ def get_split(dataset, n_features):
             # 左右两边的数量越一样，说明数据区分度不高，gini系数越大
             if gini < b_score:
                 b_index, b_value, b_score, b_groups = index, row[index], gini, groups  # 最后得到最优的分类特征 b_index,分类特征值 b_value,分类结果 b_groups。b_value 为分错的代价成本
-    # print b_score
+    # print(b_score)
     return {'index': b_index, 'value': b_value, 'groups': b_groups}
 
 
@@ -303,7 +303,7 @@ def evaluate_algorithm(dataset, algorithm, n_folds, *args):
 
     # 加载数据
     dataset = loadDataSet('input/7.RandomForest/sonar-all-data.txt')
-    # print dataset
+    # print(dataset)
 
     n_folds = 5        # 分成5份数据，进行交叉验证
     max_depth = 20     # 调参（自己修改） #决策树深度不能太深，不然容易导致过拟合
@@ -315,7 +315,7 @@ def evaluate_algorithm(dataset, algorithm, n_folds, *args):
         scores = evaluate_algorithm(dataset, random_forest, n_folds, max_depth, min_size, sample_size, n_trees, n_features)
         # 每一次执行本文件时都能产生同一个随机数
         seed(1)
-        print 'random=', random()
-        print 'Trees: %d' % n_trees
-        print 'Scores: %s' % scores
-        print 'Mean Accuracy: %.3f%%' % (sum(scores)/float(len(scores)))
+        print('random=', random())
+        print('Trees: %d' % n_trees)
+        print('Scores: %s' % scores)
+        print('Mean Accuracy: %.3f%%' % (sum(scores)/float(len(scores))))
diff --git a/tools/DecisionTree_getInfoGain.py b/tools/DecisionTree_getInfoGain.py
@@ -16,7 +16,7 @@ def calcShannonEnt(dataSet):
     """
     # 求list的长度，表示计算参与训练的数据量
     numEntries = len(dataSet)
-    # print type(dataSet), 'numEntries: ', numEntries
+    # print(type(dataSet), 'numEntries: ', numEntries)
 
     # 计算分类标签label出现的次数
     labelCounts = {}
@@ -26,15 +26,15 @@ def calcShannonEnt(dataSet):
         if currentLabel not in labelCounts.keys():
             labelCounts[currentLabel] = 0
         labelCounts[currentLabel] += 1
-        # print '-----', featVec, labelCounts
+        # print('-----', featVec, labelCounts)
 
     # 对于label标签的占比，求出label标签的香农熵
     shannonEnt = 0.0
     for key in labelCounts:
         prob = float(labelCounts[key])/numEntries
         # log base 2
         shannonEnt -= prob * log(prob, 2)
-        # print '---', prob, prob * log(prob, 2), shannonEnt
+        # print('---', prob, prob * log(prob, 2), shannonEnt)
     return shannonEnt
 
 
@@ -100,7 +100,7 @@ def getFeatureShannonEnt(dataSet, labels):
         # gain[信息增益]=0, 表示与类别相同，无需其他的分类
         # gain[信息增益]=baseEntropy, 表示分类和没分类没有区别
         infoGain = baseEntropy - newEntropy
-        # print infoGain
+        # print(infoGain)
         if (infoGain > bestInfoGain):
             endEntropy = newEntropy
             bestInfoGain = infoGain
@@ -120,5 +120,5 @@ def getFeatureShannonEnt(dataSet, labels):
     infoGain1 = getFeatureShannonEnt(dataSet1, labels)
     infoGain2 = getFeatureShannonEnt(dataSet2, labels)
     infoGain3 = getFeatureShannonEnt(dataSet3, labels)
-    print '信息增益: \n\t%s, \n\t%s, \n\t%s' % (infoGain1, infoGain2, infoGain3)
+    print('信息增益: \n\t%s, \n\t%s, \n\t%s' % (infoGain1, infoGain2, infoGain3))