Modernize Python 2 code to get ready for Python 3

Author: cclauss

AnomalyDetection/AnomalyDetection.py

@@ -1,6 +1,7 @@
 #-*- coding: utf-8 -*-
 # Author: Bob
 # Date:   2016.12.22
+from __future__ import print_function
 import numpy as np
 from matplotlib import pyplot as plt
 from scipy import io as spio
@@ -25,8 +26,8 @@ def anomalyDetection_example():
     yval = data['yval']   # y=1代表异常
     pval = multivariateGaussian(Xval, mu, sigma2) # 计算CV上的概率密度值
     epsilon,F1 = selectThreshold(yval,pval)       # 选择最优的epsilon临界值
-    print u'在CV上得到的最好的epsilon是：%e'%epsilon
-    print u'对应的F1Score值为：%f'%F1
+    print(u'在CV上得到的最好的epsilon是：%e'%epsilon)
+    print(u'对应的F1Score值为：%f'%F1)
     outliers = np.where(p<epsilon)  # 找到小于临界值的异常点，并作图
     plt.plot(X[outliers,0],X[outliers,1],'o',markeredgecolor='r',markerfacecolor='w',markersize=10.)
     plt = display_2d_data(X, 'bx')

K-Means/K-Menas.py

@@ -1,4 +1,5 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 import numpy as np
 from matplotlib import pyplot as plt
 from matplotlib import colors
@@ -11,7 +12,7 @@
 
 def KMeans():
     '''二维数据聚类过程演示'''
-    print u'聚类过程展示...\n'
+    print(u'聚类过程展示...\n')
     data = spio.loadmat("data.mat")
     X = data['X']
     K = 3   # 总类数
@@ -21,7 +22,7 @@ def KMeans():
     '''
     图片压缩
     '''
-    print u'K-Means压缩图片\n'
+    print(u'K-Means压缩图片\n')
     img_data = misc.imread("bird.png")  # 读取图片像素数据
     img_data = img_data/255.0             # 像素值映射到0-1
     img_size = img_data.shape
@@ -31,21 +32,21 @@ def KMeans():
     max_iters = 5
     initial_centroids = kMeansInitCentroids(X,K)
     centroids,idx = runKMeans(X, initial_centroids, max_iters, False)
-    print u'\nK-Means运行结束\n'
-    print u'\n压缩图片...\n'
+    print(u'\nK-Means运行结束\n')
+    print(u'\n压缩图片...\n')
     idx = findClosestCentroids(X, centroids)
     X_recovered = centroids[idx,:]
     X_recovered = X_recovered.reshape(img_size[0],img_size[1],3)
 
-    print u'绘制图片...\n'
+    print(u'绘制图片...\n')
     plt.subplot(1,2,1)
     plt.imshow(img_data)
     plt.title(u"原先图片",fontproperties=font)
     plt.subplot(1,2,2)
     plt.imshow(X_recovered)
     plt.title(u"压缩图像",fontproperties=font)
     plt.show()
-    print u'运行结束！'
+    print(u'运行结束！')
 
 
 # 找到每条数据距离哪个类中心最近    
@@ -86,7 +87,7 @@ def runKMeans(X,initial_centroids,max_iters,plot_process):
     idx = np.zeros((m,1))           # 每条数据属于哪个类
 
     for i in range(max_iters):      # 迭代次数
-        print u'迭代计算次数：%d'%(i+1)
+        print(u'迭代计算次数：%d'%(i+1))
         idx = findClosestCentroids(X, centroids)
         if plot_process:    # 如果绘制图像
             plt = plotProcessKMeans(X,centroids,previous_centroids) # 画聚类中心的移动过程

LinearRegression/LinearRegression.py

@@ -1,12 +1,13 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 import numpy as np
 from matplotlib import pyplot as plt
 from matplotlib.font_manager import FontProperties
 font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)    # 解决windows环境下画图汉字乱码问题
 
 
 def linearRegression(alpha=0.01,num_iters=400):
-    print u"加载数据...\n"
+    print(u"加载数据...\n")
 
     data = loadtxtAndcsv_data("data.txt",",",np.float64)  #读取数据
     X = data[:,0:-1]      # X对应0到倒数第2列                  
@@ -19,7 +20,7 @@ def linearRegression(alpha=0.01,num_iters=400):
 
     X = np.hstack((np.ones((m,1)),X))    # 在X前加一列1
 
-    print u"\n执行梯度下降算法....\n"
+    print(u"\n执行梯度下降算法....\n")
 
     theta = np.zeros((col,1))
     y = y.reshape(-1,1)   #将行向量转化为列
@@ -73,7 +74,7 @@ def gradientDescent(X,y,theta,alpha,num_iters):
         temp[:,i] = theta - ((alpha/m)*(np.dot(np.transpose(X),h-y)))   #梯度的计算
         theta = temp[:,i]
         J_history[i] = computerCost(X,y,theta)      #调用计算代价函数
-        print '.',      
+        print('.', end=' ')      
     return theta,J_history  
 
 # 计算代价函数

LinearRegression/LinearRegression_scikit-learn.py

@@ -1,10 +1,11 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 import numpy as np
 from sklearn import linear_model
 from sklearn.preprocessing import StandardScaler    #引入归一化的包
 
 def linearRegression():
-    print u"加载数据...\n"
+    print(u"加载数据...\n")
     data = loadtxtAndcsv_data("data.txt",",",np.float64)  #读取数据
     X = np.array(data[:,0:-1],dtype=np.float64)      # X对应0到倒数第2列                  
     y = np.array(data[:,-1],dtype=np.float64)        # y对应最后一列  
@@ -21,9 +22,9 @@ def linearRegression():
 
     #预测结果
     result = model.predict(x_test)
-    print model.coef_       # Coefficient of the features 决策函数中的特征系数
-    print model.intercept_  # 又名bias偏置,若设置为False，则为0
-    print result            # 预测结果
+    print(model.coef_)       # Coefficient of the features 决策函数中的特征系数
+    print(model.intercept_)  # 又名bias偏置,若设置为False，则为0
+    print(result)            # 预测结果
 
 
 # 加载txt和csv文件

LogisticRegression/LogisticRegression.py

@@ -1,4 +1,5 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 import numpy as np
 import matplotlib.pyplot as plt
 from scipy import optimize
@@ -19,7 +20,7 @@ def LogisticRegression():
 
     J = costFunction(initial_theta,X,y,initial_lambda)  #计算一下给定初始化的theta和lambda求出的代价J
 
-    print J  #输出一下计算的值，应该为0.693147
+    print(J)  #输出一下计算的值，应该为0.693147
     #result = optimize.fmin(costFunction, initial_theta, args=(X,y,initial_lambda))    #直接使用最小化的方法，效果不好
     '''调用scipy中的优化算法fmin_bfgs（拟牛顿法Broyden-Fletcher-Goldfarb-Shanno）
     - costFunction是自己实现的一个求代价的函数，
@@ -29,7 +30,7 @@ def LogisticRegression():
     '''
     result = optimize.fmin_bfgs(costFunction, initial_theta, fprime=gradient, args=(X,y,initial_lambda))    
     p = predict(X, result)   #预测
-    print u'在训练集上的准确度为%f%%'%np.mean(np.float64(p==y)*100)   # 与真实值比较，p==y返回True，转化为float   
+    print(u'在训练集上的准确度为%f%%'%np.mean(np.float64(p==y)*100))   # 与真实值比较，p==y返回True，转化为float   
 
     X = data[:,0:-1]
     y = data[:,-1]    

LogisticRegression/LogisticRegression_OneVsAll.py

@@ -1,4 +1,5 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 import numpy as np
 import matplotlib.pyplot as plt
 import scipy.io as spio
@@ -27,7 +28,7 @@ def logisticRegression_OneVsAll():
     #res = np.hstack((p,y.reshape(-1,1)))
     #np.savetxt("predict.csv", res, delimiter=',')
 
-    print u"预测准确度为：%f%%"%np.mean(np.float64(p == y.reshape(-1,1))*100)
+    print(u"预测准确度为：%f%%"%np.mean(np.float64(p == y.reshape(-1,1))*100))
 
 # 加载mat文件
 def loadmat_data(fileName):

LogisticRegression/LogisticRegression_OneVsAll_scikit-learn.py

@@ -1,4 +1,5 @@
 #-*- coding: utf-8 -*-
+from __future__ import print_function
 from scipy import io as spio
 import numpy as np
 from sklearn import svm
@@ -17,7 +18,7 @@ def logisticRegression_oneVsAll():
 
     predict = model.predict(X) #预测
 
-    print u"预测准确度为：%f%%"%np.mean(np.float64(predict == y)*100)
+    print(u"预测准确度为：%f%%"%np.mean(np.float64(predict == y)*100))
 
 # 加载mat文件
 def loadmat_data(fileName):

LogisticRegression/LogisticRegression_scikit-learn.py

@@ -4,40 +4,39 @@
 import numpy as np
 
 def logisticRegression():
-    data = loadtxtAndcsv_data("data1.txt", ",", np.float64) 
+    data = loadtxtAndcsv_data("data1.txt", ",", np.float64)
     X = data[:,0:-1]
     y = data[:,-1]
-    
-    # 划分为训练集和测试集
+
+    # ����Ϊѵ�����Ͳ��Լ�
     x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2)
-    
-    # 归一化
+
+    # ��һ��
     scaler = StandardScaler()
     scaler.fit(x_train)
     x_train = scaler.fit_transform(x_train)
     x_test = scaler.fit_transform(x_test)
-    
-    #逻辑回归
+
+    #�߼��ع�
     model = LogisticRegression()
     model.fit(x_train,y_train)
-    
-    # 预测
+
+    # Ԥ��
     predict = model.predict(x_test)
     right = sum(predict == y_test)
-    
-    predict = np.hstack((predict.reshape(-1,1),y_test.reshape(-1,1)))   # 将预测值和真实值放在一块，好观察
-    print predict
-    print ('测试集准确率：%f%%'%(right*100.0/predict.shape[0]))          #计算在测试集上的准确度
 
-# 加载txt和csv文件
+    predict = np.hstack((predict.reshape(-1,1),y_test.reshape(-1,1)))   # ��Ԥ��ֵ����ʵֵ����һ�飬�ù۲�
+    print(predict)
+    print('���Լ�׼ȷ�ʣ�%f%%'%(right*100.0/predict.shape[0]))          #�����ڲ��Լ��ϵ�׼ȷ��
+
+# ����txt��csv�ļ�
 def loadtxtAndcsv_data(fileName,split,dataType):
     return np.loadtxt(fileName,delimiter=split,dtype=dataType)
 
-# 加载npy文件
+# ����npy�ļ�
 def loadnpy_data(fileName):
     return np.load(fileName)
 
 
-
 if __name__ == "__main__":
-    logisticRegression()
+    logisticRegression()