future

Author: GuangxiaoSong

0000_preparing_data.py

@@ -5,7 +5,7 @@
 @name: 0000_preparing_data.py
 @time: 2016/11/27 12:20
 """
-
+from __future__ import print_function
 import data.load_raw_data_to_file as loader
 import os
 
@@ -29,4 +29,4 @@
     for file in files:
         ld.merge_cvt_files("data/converted/"+file, "data/merge/allRawData.txt")
 
-print "Finished."
+print ("Finished.")

0001_merge_file_line_num.py

@@ -1,13 +1,15 @@
 # -*- coding:utf-8 -*-
 
+from __future__ import print_function
+
 f = open("data/merge/allRawData.txt", "r")
 line_num = 0
 line = f.readline()
 str = line.split(" ")
-print len(str)
-print str[-1]
+print (len(str))
+print (str[-1])
 for line in f:
 	line_num += 1
-print "File has %i lines" % (line_num)
+print ("File has %i lines" % (line_num))
 
 # 本机win7中有1000行数据

0100_rawdata_svm.py

@@ -6,6 +6,7 @@
 @time: 2016/11/25 12:43
 """
 
+from __future__ import print_function
 import data.load_raw_data_file_to_array as f2a
 import numpy as np
 from sklearn.cross_validation import train_test_split
@@ -26,15 +27,15 @@
 t1 = time.time()
 data = f2a.LoadRawDataFileToArray().load("data/merge/allRawData.txt")
 t2 = time.time()
-print "Time cost: %f s." %(t2-t1)
-print "start training"
+print ("Time cost: %f s." %(t2-t1))
+print ("start training")
 t3 = time.time()
 data_train, data_test, label_train, label_test = train_test_split(data, labels, test_size=0.2)
 
 clf = SVC(C=16, cache_size=200, class_weight=None, coef0=0.0, degree=3,
     gamma=0.00024, kernel='rbf', max_iter=-1, probability=False,
     random_state=None, shrinking=True, tol=0.001, verbose=False)
 clf.fit(data_train, label_train)
-print clf.score(data_test, label_test)
+print (clf.score(data_test, label_test))
 t4 = time.time()
-print "Time cost: %f s." %(t4-t3)
+print ("Time cost: %f s." %(t4-t3))

0200_svm.py

@@ -6,6 +6,7 @@
 @time: 2016/11/24 18:06
 """
 
+from __future__ import print_function
 import numpy as np
 from sklearn.cross_validation import train_test_split
 from sklearn.svm import SVC
@@ -31,4 +32,4 @@
     gamma=0.00024, kernel='rbf', max_iter=-1, probability=False,
     random_state=None, shrinking=True, tol=0.001, verbose=False)
 clf.fit(data_train, label_train)
-print clf.score(data_test, label_test)
+print (clf.score(data_test, label_test))

0300_multi-layer_perceptron.py

@@ -5,6 +5,8 @@
 @name: 0300_multi-layer_perceptron.py
 @time: 2016/11/24 20:35
 """
+
+from __future__ import print_function
 import numpy as np
 from sklearn.neural_network import MLPClassifier
 from sklearn.cross_validation import train_test_split
@@ -28,4 +30,4 @@
                    solver='sgd', tol=0.0001, validation_fraction=0.1, verbose=False,
                    warm_start=False)
 clf.fit(data_train, label_train)
-print clf.score(data_test, label_test)
+print (clf.score(data_test, label_test))

0400_nearest_centroid.py

@@ -23,4 +23,4 @@
 
 clf = NearestCentroid(metric='euclidean', shrink_threshold=None)
 clf.fit(data_train, label_train)
-print clf.score(data_test, label_test)
+print (clf.score(data_test, label_test))

0500_tensorflow_hw.py

@@ -1,8 +1,10 @@
 # -*- coding:utf-8 -*-
+
 import tensorflow as tf
+from __future__ import print_function
 
 a = tf.constant(2)
 b = tf.constant(3)
 
 with tf.Session() as sess:
-    print sess.run(a+b)
+    print (sess.run(a+b))

0503_0_tf_csv_example.py

@@ -6,6 +6,7 @@
 @time: 11/30/16 5:45 PM
 """
 
+from __future__ import print_function
 import tensorflow as tf
 import numpy as np
 
@@ -40,9 +41,9 @@ def inputPipeLine(fileNames=["data/file0.csv", "data/file1.csv"], batchSize=4, n
         # while not coord.should_stop():
         while True:
             example, label = sess.run([featureBatch, labelBatch])
-            print example
+            print (example)
     except tf.errors.OutOfRangeError:
-        print 'Done reading'
+        print ('Done reading')
     finally:
         coord.request_stop()
 

data/0102_test_cross_validation.py

@@ -6,6 +6,7 @@
 @time: 2016/11/23 20:03
 """
 
+from __future__ import print_function
 from sklearn import cross_validation
 from sklearn import datasets, svm   #导入所需要的库
 
@@ -19,7 +20,7 @@
 svc = svm.SVC(C=1, kernel='linear')  #初始化svm分类器
 kfold = cross_validation.KFold(len(X_digits), n_folds=3) #初始化交叉验证对象，len(X_digits)指明有多少个样本；n_folds指代kfolds中的参数k,表示把训练集分成k份（n_folds份），本例中为3份
 for train, test in kfold:
-    print svc.fit(X_digits[train], y_digits[train]).score(X_digits[test], y_digits[test])
+    print (svc.fit(X_digits[train], y_digits[train]).score(X_digits[test], y_digits[test]))
     #此处train、test里有交叉验证对象中已经初始化好的3组训练样本和测试样本所需的位置标号
 ##其实cross_validation库将上述for循环也集成进来了
 #cross_validation.cross_val_score(svc, X_digits, y_digits, n_jobs=-1)  #n_jobs=-1代表将受用计算机上的所有cpu计算,参数cv（此例中为默认值）除了kfold选项，还可以选择StratifiedKFold等,如果cv是一个int数字的话，并且如果提供了raw target参数，那么就代表使用StratifiedKFold分类方式，如果没有提供raw target参数，那么就代表使用KFold分类方式。

data/0103_test_cv_single_file.py

@@ -5,12 +5,15 @@
 @name: 0103_test_cv_single_file.py
 @time: 2016/11/23 20:11
 """
+
+
+from __future__ import print_function
 import numpy as np
 
 data = np.loadtxt('data/testFeatureDataSingleFile.txt')
-print data
-print data.shape
+print (data)
+print (data.shape)
 
 data1 = data.reshape((1,-1))
-print data1
-print data1.shape
+print (data1)
+print (data1.shape)

data/0104_trans_test_data.py

@@ -5,6 +5,8 @@
 @name: 0104_trans_test_data.py
 @time: 2016/11/23 20:11
 """
+
+from __future__ import print_function
 import numpy as np
 
 data = np.loadtxt('data/testFeatureData.txt')
@@ -40,7 +42,7 @@
         for i in range(data.shape[0]):  # 行 433
             tempArray.append(np.float32(data[i][j]))
 
-print result.shape
+print (result.shape)
 
 np.savetxt('data/transTestData.txt',result,fmt='%s',newline='\n')
 

data/0105_trans_all_data.py

@@ -6,6 +6,7 @@
 @time: 2016/11/23 20:11
 """
 import numpy as np
+from __future__ import print_function
 
 data = np.loadtxt('data/allFeatureData.txt')
 # print data
@@ -40,7 +41,7 @@
         for i in range(data.shape[0]):  # 行 433
             tempArray.append(np.float32(data[i][j]))
 
-print result.shape
+print (result.shape)
 
 np.savetxt('data/transAllData.txt',result,fmt='%s',newline='\n')
 

data/0106_label_the_data.py

@@ -9,7 +9,7 @@
 打散数据
 http://friskit.me/2014/10/22/shuffle-train-data-in-numpy/
 """
-
+from __future__ import print_function
 import numpy as np
 
 data = np.loadtxt('transAllData.txt')
@@ -20,6 +20,6 @@
     for i in range(num):
         y.append(genre)
 labels = np.array(y)
-print labels
+print (labels)
 
 

data/0109_train_test_spilt_test.py

@@ -5,19 +5,19 @@
 @name: 0109_train_test_spilt_test.py
 @time: 2016/11/24 17:23
 """
-
+from __future__ import print_function
 from sklearn.cross_validation import train_test_split
 import numpy as np
 data = np.reshape(np.random.randn(20),(10,2)) # 10 training examples
 labels = np.random.randint(2, size=10) # 10 labels
 x1, x2, y1, y2 = train_test_split(data, labels, test_size=0.2)
 
-print data
-print labels
+print (data)
+print (labels)
 
-print "#################"
+print ("#################")
 
-print x1
-print x2
-print y1
-print y2
+print (x1)
+print (x2)
+print (y1)
+print (y2)

data/add_class_in_each_row.py data/0200_add_class_in_each_row.py

@@ -2,10 +2,12 @@
 
 """
 @author: Songgx
-@file: add_class_in_each_row.py
+@file: 0200_add_class_in_each_row.py
 @time: 11/28/16 7:20 PM
 """
 
+from __future__ import print_function
+
 TOTAL_ROW_NUM = 1000
 
 # line 0-999
@@ -30,11 +32,11 @@
     line_num += 1
     if line_num % 100 == 0:
         class_num += 1
-        print "%i / 1000 lines finished." % (line_num)
+        print ("%i / 1000 lines finished." % (line_num))
 fr.close()
 fw.close()
 
-print "Verify new file:"
+print ("Verify new file:")
 
 '''
 fr1 = open("merge/raw_data.txt", "r")
@@ -44,9 +46,9 @@
     line_num1 = i + 1
     l = fr1.readline()[-10:]
     if (line_num1+1) % 100 == 0 or (line_num1-1) % 100 == 0 or line_num1 % 100 == 0:
-        print "line-" + str(line_num1) + ":" + l.strip()
+        print ("line-" + str(line_num1) + ":" + l.strip())
 fr1.close()
-print "Finished."
+print ("Finished.")
 
 
 

data/convert_to_TFrecords.py data/0201_convert_to_TFrecords.py

@@ -2,7 +2,7 @@
 
 """
 @author: Songgx
-@file: convert_to_TFrecords.py
+@file: 0201_convert_to_TFrecords.py
 @time: 12/1/16 5:07 PM
 """
 

data/load_raw_data_file_to_array.py

@@ -6,6 +6,7 @@
 @time: 2016/11/27 15:54
 """
 
+from __future__ import print_function
 import numpy as np
 import re
 
@@ -23,7 +24,7 @@ def load(self, path):
             r = []
             counter += 1
             if counter % 50 == 0:
-                print "line %i finished." % (counter)
+                print ("line %i finished." % (counter))
             for v in line.strip().split(' '):
                 try:
                     r.append(np.float32(v))
@@ -35,5 +36,5 @@ def load(self, path):
             result.append(r)
         f.close()
         del result[0]
-        print "data shape: %i,%i" %(len(result), len(result[0]))
+        print ("data shape: %i,%i" %(len(result), len(result[0])))
         return result