[GitHub]Python Machine Learning Cookbook

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

1. Python Machine Learning Cookbook by Packt Publishing
   
2. 
   
3. ##Instructions and Navigation
   
4. 
   
5. This is the code repository for Python Machine Learning Cookbook, published by Packt. It contains all the supporting project files necessary to work through the book from start to finish. The code files are organized according to the chapters in the book. These code samples will work on any machine running Linux, Mac OS X, or Windows. Even though they are written and tested on Python 2.7, you can easily run them on Python 3.x with minimal changes.
   
6. 
   
7. To run the code samples, you need to install scikit-learn, NumPy, SciPy, and matplotlib. For Chapter 6, you will need to install NLTK and gensim. To run the code in chapter 7, you need to install hmmlearn and python_speech_features. For chapter 8, you need to install Pandas and PyStruct. Chapter 8 also makes use of hmmlearn. For chapters 9 and 10, you need to install OpenCV. For chapter 11, you need to install NeuroLab.
   
8. 
   
9. ##Description Machine learning is becoming increasingly pervasive in the modern data-driven world. It is used extensively across many fields like search engines, robotics, self-driving cars, and so on. During the course of this book, you will learn how to use Python to build a wide variety of machine learning applications to solve real-world problems. You will understand how to deal with different types of data like images, text, audio, and so on.
   
10. 
    
11. We will explore various techniques in supervised and unsupervised learning. We will learn machine learning algorithms like Support Vector Machines, Random Forests, Hidden Markov Models, Conditional Random Fields, Deep Neural Networks, and many more. We will discuss about visualization techniques that can be used to interact with your data. Using these algorithms, we will discuss how to build recommendation engines, perform predictive modeling, build speech recognizers, perform sentiment analysis on text data, develop face recognition systems, and so on.
    
12. 
    
13. You will understand what algorithms to use in a given context with the help of this exciting recipe-based guide. You will learn how to make informed decisions about the type of algorithms you need to use and learn how to implement those algorithms to get the best possible results. Stuck while making sense of images, text, speech, or some other form of data? This guide on applying machine learning techniques to each of these will come to your rescue! The code is well commented, so you will be able to get it up and running easily. The book contains all the relevant explanations of the algorithms that are used to build these applications.
    
14. 
    
15. There is a lot of debate going on between Python 2.x and Python 3.x. While we believe that the world is moving forward with better versions coming out, a lot of developers still enjoy using Python 2.x. A lot of operating systems have Python 2.x built into them. It also helps in maintaining compatibility with Python libraries that haven't been ported to Python 3.x. Keeping that in mind, the code in this book is oriented towards Python 2.x. We have tried to keep all the code as agnostic as possible to the Python versions, so that Python 3.x users won't face too many issues. We are focused on utilizing the machine learning libraries in the best possible way in Python.
    
16. 
    
17. ##Related Python/Machine Learning Products:
    
18. 
    
19. Python Machine Learning
    
20. Mastering Python Machine Learning
    
21. OpenCV with Python By Example

复制代码

本帖隐藏的内容

Python-Machine-Learning-Cookbook-master.zip (13.68 MB)

2017-7-7 22:36:29 上传

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：Learning Cookbook earning machine python

1. import numpy as np
   
2. import matplotlib.pyplot as plt
   
3. from sklearn.naive_bayes import GaussianNB
   
4. 
   
5. from logistic_regression import plot_classifier
   
6. 
   
7. input_file = 'data_multivar.txt'
   
8. 
   
9. X = []
   
10. y = []
    
11. with open(input_file, 'r') as f:
    
12.     for line in f.readlines():
    
13.         data = [float(x) for x in line.split(',')]
    
14.         X.append(data[:-1])
    
15.         y.append(data[-1])
    
16. 
    
17. X = np.array(X)
    
18. y = np.array(y)
    
19. 
    
20. classifier_gaussiannb = GaussianNB()
    
21. classifier_gaussiannb.fit(X, y)
    
22. y_pred = classifier_gaussiannb.predict(X)
    
23. 
    
24. # compute accuracy of the classifier
    
25. accuracy = 100.0 * (y == y_pred).sum() / X.shape[0]
    
26. print "Accuracy of the classifier =", round(accuracy, 2), "%"
    
27. 
    
28. plot_classifier(classifier_gaussiannb, X, y)
    
29. 
    
30. ###############################################
    
31. # Train test split
    
32. from sklearn import cross_validation
    
33. 
    
34. X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=5)
    
35. classifier_gaussiannb_new = GaussianNB()
    
36. classifier_gaussiannb_new.fit(X_train, y_train)
    
37. y_test_pred = classifier_gaussiannb_new.predict(X_test)
    
38. 
    
39. # compute accuracy of the classifier
    
40. accuracy = 100.0 * (y_test == y_test_pred).sum() / X_test.shape[0]
    
41. print "Accuracy of the classifier =", round(accuracy, 2), "%"
    
42. 
    
43. plot_classifier(classifier_gaussiannb_new, X_test, y_test)
    
44. 
    
45. ###############################################
    
46. # Cross validation and scoring functions
    
47. 
    
48. num_validations = 5
    
49. accuracy = cross_validation.cross_val_score(classifier_gaussiannb,
    
50.         X, y, scoring='accuracy', cv=num_validations)
    
51. print "Accuracy: " + str(round(100*accuracy.mean(), 2)) + "%"
    
52. 
    
53. f1 = cross_validation.cross_val_score(classifier_gaussiannb,
    
54.         X, y, scoring='f1_weighted', cv=num_validations)
    
55. print "F1: " + str(round(100*f1.mean(), 2)) + "%"
    
56. 
    
57. precision = cross_validation.cross_val_score(classifier_gaussiannb,
    
58.         X, y, scoring='precision_weighted', cv=num_validations)
    
59. print "Precision: " + str(round(100*precision.mean(), 2)) + "%"
    
60. 
    
61. recall = cross_validation.cross_val_score(classifier_gaussiannb,
    
62.         X, y, scoring='recall_weighted', cv=num_validations)
    
63. print "Recall: " + str(round(100*recall.mean(), 2)) + "%"

复制代码

1. import numpy as np
   
2. import matplotlib.pyplot as plt
   
3. 
   
4. import utilities
   
5. 
   
6. # Load input data
   
7. input_file = 'data_multivar.txt'
   
8. X, y = utilities.load_data(input_file)
   
9. 
   
10. ###############################################
    
11. # Separate the data into classes based on 'y'
    
12. class_0 = np.array([X[i] for i in range(len(X)) if y[i]==0])
    
13. class_1 = np.array([X[i] for i in range(len(X)) if y[i]==1])
    
14. 
    
15. # Plot the input data
    
16. plt.figure()
    
17. plt.scatter(class_0[:,0], class_0[:,1], facecolors='black', edgecolors='black', marker='s')
    
18. plt.scatter(class_1[:,0], class_1[:,1], facecolors='None', edgecolors='black', marker='s')
    
19. plt.title('Input data')
    
20. 
    
21. ###############################################
    
22. # Train test split and SVM training
    
23. from sklearn import cross_validation
    
24. from sklearn.svm import SVC
    
25. 
    
26. X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=5)
    
27. 
    
28. params = {'kernel': 'linear'}
    
29. #params = {'kernel': 'poly', 'degree': 3}
    
30. #params = {'kernel': 'rbf'}
    
31. classifier = SVC(**params)
    
32. classifier.fit(X_train, y_train)
    
33. utilities.plot_classifier(classifier, X_train, y_train, 'Training dataset')
    
34. 
    
35. y_test_pred = classifier.predict(X_test)
    
36. utilities.plot_classifier(classifier, X_test, y_test, 'Test dataset')
    
37. 
    
38. ###############################################
    
39. # Evaluate classifier performance
    
40. 
    
41. from sklearn.metrics import classification_report
    
42. 
    
43. target_names = ['Class-' + str(int(i)) for i in set(y)]
    
44. print "\n" + "#"*30
    
45. print "\nClassifier performance on training dataset\n"
    
46. print classification_report(y_train, classifier.predict(X_train), target_names=target_names)
    
47. print "#"*30 + "\n"
    
48. 
    
49. print "#"*30
    
50. print "\nClassification report on test dataset\n"
    
51. print classification_report(y_test, y_test_pred, target_names=target_names)
    
52. print "#"*30 + "\n"
    
53. 
    
54. plt.show()

复制代码

1. import numpy as np
   
2. import matplotlib.pyplot as plt
   
3. from sklearn import metrics
   
4. from sklearn.cluster import KMeans
   
5. 
   
6. import utilities
   
7. 
   
8. # Load data
   
9. data = utilities.load_data('data_multivar.txt')
   
10. num_clusters = 4
    
11. 
    
12. # Plot data
    
13. plt.figure()
    
14. plt.scatter(data[:,0], data[:,1], marker='o',
    
15.         facecolors='none', edgecolors='k', s=30)
    
16. x_min, x_max = min(data[:, 0]) - 1, max(data[:, 0]) + 1
    
17. y_min, y_max = min(data[:, 1]) - 1, max(data[:, 1]) + 1
    
18. plt.title('Input data')
    
19. plt.xlim(x_min, x_max)
    
20. plt.ylim(y_min, y_max)
    
21. plt.xticks(())
    
22. plt.yticks(())
    
23. 
    
24. # Train the model
    
25. kmeans = KMeans(init='k-means++', n_clusters=num_clusters, n_init=10)
    
26. kmeans.fit(data)
    
27. 
    
28. # Step size of the mesh
    
29. step_size = 0.01
    
30. 
    
31. # Plot the boundaries
    
32. x_min, x_max = min(data[:, 0]) - 1, max(data[:, 0]) + 1
    
33. y_min, y_max = min(data[:, 1]) - 1, max(data[:, 1]) + 1
    
34. x_values, y_values = np.meshgrid(np.arange(x_min, x_max, step_size), np.arange(y_min, y_max, step_size))
    
35. 
    
36. # Predict labels for all points in the mesh
    
37. predicted_labels = kmeans.predict(np.c_[x_values.ravel(), y_values.ravel()])
    
38. 
    
39. # Plot the results
    
40. predicted_labels = predicted_labels.reshape(x_values.shape)
    
41. plt.figure()
    
42. plt.clf()
    
43. plt.imshow(predicted_labels, interpolation='nearest',
    
44.            extent=(x_values.min(), x_values.max(), y_values.min(), y_values.max()),
    
45.            cmap=plt.cm.Paired,
    
46.            aspect='auto', origin='lower')
    
47. 
    
48. plt.scatter(data[:,0], data[:,1], marker='o',
    
49.         facecolors='none', edgecolors='k', s=30)
    
50. 
    
51. centroids = kmeans.cluster_centers_
    
52. plt.scatter(centroids[:,0], centroids[:,1], marker='o', s=200, linewidths=3,
    
53.         color='k', zorder=10, facecolors='black')
    
54. x_min, x_max = min(data[:, 0]) - 1, max(data[:, 0]) + 1
    
55. y_min, y_max = min(data[:, 1]) - 1, max(data[:, 1]) + 1
    
56. plt.title('Centoids and boundaries obtained using KMeans')
    
57. plt.xlim(x_min, x_max)
    
58. plt.ylim(y_min, y_max)
    
59. plt.xticks(())
    
60. plt.yticks(())
    
61. plt.show()

复制代码

1. import csv
   
2. 
   
3. import numpy as np
   
4. from sklearn import cluster, covariance, manifold
   
5. from sklearn.cluster import MeanShift, estimate_bandwidth
   
6. import matplotlib.pyplot as plt
   
7. 
   
8. # Load data from input file
   
9. input_file = 'wholesale.csv'
   
10. file_reader = csv.reader(open(input_file, 'rb'), delimiter=',')
    
11. X = []
    
12. for count, row in enumerate(file_reader):
    
13.     if not count:
    
14.         names = row[2:]
    
15.         continue
    
16. 
    
17.     X.append([float(x) for x in row[2:]])
    
18. 
    
19. # Input data as numpy array
    
20. X = np.array(X)
    
21. 
    
22. # Estimating the bandwidth
    
23. bandwidth = estimate_bandwidth(X, quantile=0.8, n_samples=len(X))
    
24. 
    
25. # Compute clustering with MeanShift
    
26. meanshift_estimator = MeanShift(bandwidth=bandwidth, bin_seeding=True)
    
27. meanshift_estimator.fit(X)
    
28. labels = meanshift_estimator.labels_
    
29. centroids = meanshift_estimator.cluster_centers_
    
30. num_clusters = len(np.unique(labels))
    
31. 
    
32. print "\nNumber of clusters in input data =", num_clusters
    
33. 
    
34. print "\nCentroids of clusters:"
    
35. print '\t'.join([name[:3] for name in names])
    
36. for centroid in centroids:
    
37.     print '\t'.join([str(int(x)) for x in centroid])
    
38. 
    
39. ################
    
40. # Visualizing data
    
41. 
    
42. centroids_milk_groceries = centroids[:, 1:3]
    
43. 
    
44. # Plot the nodes using the coordinates of our centroids_milk_groceries
    
45. plt.figure()
    
46. plt.scatter(centroids_milk_groceries[:,0], centroids_milk_groceries[:,1],
    
47.         s=100, edgecolors='k', facecolors='none')
    
48. 
    
49. offset = 0.2
    
50. plt.xlim(centroids_milk_groceries[:,0].min() - offset * centroids_milk_groceries[:,0].ptp(),
    
51.         centroids_milk_groceries[:,0].max() + offset * centroids_milk_groceries[:,0].ptp(),)
    
52. plt.ylim(centroids_milk_groceries[:,1].min() - offset * centroids_milk_groceries[:,1].ptp(),
    
53.         centroids_milk_groceries[:,1].max() + offset * centroids_milk_groceries[:,1].ptp())
    
54. 
    
55. plt.title('Centroids of clusters for milk and groceries')
    
56. plt.show()

复制代码

1. import numpy as np
   
2. from sklearn import preprocessing
   
3. from sklearn.ensemble import RandomForestClassifier
   
4. import matplotlib.pyplot as plt
   
5. 
   
6. input_file = 'car.data.txt'
   
7. 
   
8. # Reading the data
   
9. X = []
   
10. y = []
    
11. count = 0
    
12. with open(input_file, 'r') as f:
    
13.     for line in f.readlines():
    
14.         data = line[:-1].split(',')
    
15.         X.append(data)
    
16. 
    
17. X = np.array(X)
    
18. 
    
19. # Convert string data to numerical data
    
20. label_encoder = []
    
21. X_encoded = np.empty(X.shape)
    
22. for i,item in enumerate(X[0]):
    
23.     label_encoder.append(preprocessing.LabelEncoder())
    
24.     X_encoded[:, i] = label_encoder[-1].fit_transform(X[:, i])
    
25. 
    
26. X = X_encoded[:, :-1].astype(int)
    
27. y = X_encoded[:, -1].astype(int)
    
28. 
    
29. # Build a Random Forest classifier
    
30. params = {'n_estimators': 200, 'max_depth': 8, 'random_state': 7}
    
31. classifier = RandomForestClassifier(**params)
    
32. classifier.fit(X, y)
    
33. 
    
34. # Cross validation
    
35. from sklearn import cross_validation
    
36. 
    
37. accuracy = cross_validation.cross_val_score(classifier,
    
38.         X, y, scoring='accuracy', cv=3)
    
39. print "Accuracy of the classifier: " + str(round(100*accuracy.mean(), 2)) + "%"
    
40. 
    
41. # Testing encoding on single data instance
    
42. input_data = ['vhigh', 'vhigh', '2', '2', 'small', 'low']
    
43. input_data_encoded = [-1] * len(input_data)
    
44. for i,item in enumerate(input_data):
    
45.     input_data_encoded[i] = int(label_encoder[i].transform(input_data[i]))
    
46. 
    
47. input_data_encoded = np.array(input_data_encoded)
    
48. 
    
49. # Predict and print output for a particular datapoint
    
50. output_class = classifier.predict(input_data_encoded)
    
51. print "Output class:", label_encoder[-1].inverse_transform(output_class)[0]
    
52. 
    
53. ########################
    
54. # Validation curves
    
55. 
    
56. from sklearn.learning_curve import validation_curve
    
57. 
    
58. classifier = RandomForestClassifier(max_depth=4, random_state=7)
    
59. 
    
60. parameter_grid = np.linspace(25, 200, 8).astype(int)
    
61. train_scores, validation_scores = validation_curve(classifier, X, y,
    
62.         "n_estimators", parameter_grid, cv=5)
    
63. print "\n##### VALIDATION CURVES #####"
    
64. print "\nParam: n_estimators\nTraining scores:\n", train_scores
    
65. print "\nParam: n_estimators\nValidation scores:\n", validation_scores
    
66. 
    
67. # Plot the curve
    
68. plt.figure()
    
69. plt.plot(parameter_grid, 100*np.average(train_scores, axis=1), color='black')
    
70. plt.title('Training curve')
    
71. plt.xlabel('Number of estimators')
    
72. plt.ylabel('Accuracy')
    
73. plt.show()
    
74. 
    
75. classifier = RandomForestClassifier(n_estimators=20, random_state=7)
    
76. parameter_grid = np.linspace(2, 10, 5).astype(int)
    
77. train_scores, valid_scores = validation_curve(classifier, X, y,
    
78.         "max_depth", parameter_grid, cv=5)
    
79. print "\nParam: max_depth\nTraining scores:\n", train_scores
    
80. print "\nParam: max_depth\nValidation scores:\n", validation_scores
    
81. 
    
82. # Plot the curve
    
83. plt.figure()
    
84. plt.plot(parameter_grid, 100*np.average(train_scores, axis=1), color='black')
    
85. plt.title('Validation curve')
    
86. plt.xlabel('Maximum depth of the tree')
    
87. plt.ylabel('Accuracy')
    
88. plt.show()
    
89. 
    
90. ########################
    
91. # Learning curves
    
92. 
    
93. from sklearn.learning_curve import learning_curve
    
94. 
    
95. classifier = RandomForestClassifier(random_state=7)
    
96. 
    
97. parameter_grid = np.array([200, 500, 800, 1100])
    
98. train_sizes, train_scores, validation_scores = learning_curve(classifier,
    
99.         X, y, train_sizes=parameter_grid, cv=5)
    
100. print "\n##### LEARNING CURVES #####"
     
101. print "\nTraining scores:\n", train_scores
     
102. print "\nValidation scores:\n", validation_scores
     
103. 
     
104. # Plot the curve
     
105. plt.figure()
     
106. plt.plot(parameter_grid, 100*np.average(train_scores, axis=1), color='black')
     
107. plt.title('Learning curve')
     
108. plt.xlabel('Number of training samples')
     
109. plt.ylabel('Accuracy')
     
110. plt.show()

复制代码

1. import numpy as np
   
2. from sklearn import linear_model
   
3. import matplotlib.pyplot as plt
   
4. 
   
5. def plot_classifier(classifier, X, y):
   
6.     # define ranges to plot the figure
   
7.     x_min, x_max = min(X[:, 0]) - 1.0, max(X[:, 0]) + 1.0
   
8.     y_min, y_max = min(X[:, 1]) - 1.0, max(X[:, 1]) + 1.0
   
9. 
   
10.     # denotes the step size that will be used in the mesh grid
    
11.     step_size = 0.01
    
12. 
    
13.     # define the mesh grid
    
14.     x_values, y_values = np.meshgrid(np.arange(x_min, x_max, step_size), np.arange(y_min, y_max, step_size))
    
15. 
    
16.     # compute the classifier output
    
17.     mesh_output = classifier.predict(np.c_[x_values.ravel(), y_values.ravel()])
    
18. 
    
19.     # reshape the array
    
20.     mesh_output = mesh_output.reshape(x_values.shape)
    
21. 
    
22.     # Plot the output using a colored plot
    
23.     plt.figure()
    
24. 
    
25.     # choose a color scheme you can find all the options
    
26.     # here: http://matplotlib.org/examples/color/colormaps_reference.html
    
27.     plt.pcolormesh(x_values, y_values, mesh_output, cmap=plt.cm.gray)
    
28. 
    
29.     # Overlay the training points on the plot
    
30.     plt.scatter(X[:, 0], X[:, 1], c=y, s=80, edgecolors='black', linewidth=1, cmap=plt.cm.Paired)
    
31. 
    
32.     # specify the boundaries of the figure
    
33.     plt.xlim(x_values.min(), x_values.max())
    
34.     plt.ylim(y_values.min(), y_values.max())
    
35. 
    
36.     # specify the ticks on the X and Y axes
    
37.     plt.xticks((np.arange(int(min(X[:, 0])-1), int(max(X[:, 0])+1), 1.0)))
    
38.     plt.yticks((np.arange(int(min(X[:, 1])-1), int(max(X[:, 1])+1), 1.0)))
    
39. 
    
40.     plt.show()
    
41. 
    
42. if __name__=='__main__':
    
43.     # input data
    
44.     X = np.array([[4, 7], [3.5, 8], [3.1, 6.2], [0.5, 1], [1, 2], [1.2, 1.9], [6, 2], [5.7, 1.5], [5.4, 2.2]])
    
45.     y = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2])
    
46. 
    
47.     # initialize the logistic regression classifier
    
48.     classifier = linear_model.LogisticRegression(solver='liblinear', C=100)
    
49. 
    
50.     # train the classifier
    
51.     classifier.fit(X, y)
    
52. 
    
53.     # draw datapoints and boundaries
    
54.     plot_classifier(classifier, X, y)

复制代码

1. import numpy as np
   
2. import matplotlib.pyplot as plt
   
3. from sklearn.naive_bayes import GaussianNB
   
4. 
   
5. from logistic_regression import plot_classifier
   
6. 
   
7. input_file = 'data_multivar.txt'
   
8. 
   
9. X = []
   
10. y = []
    
11. with open(input_file, 'r') as f:
    
12.     for line in f.readlines():
    
13.         data = [float(x) for x in line.split(',')]
    
14.         X.append(data[:-1])
    
15.         y.append(data[-1])
    
16. 
    
17. X = np.array(X)
    
18. y = np.array(y)
    
19. 
    
20. classifier_gaussiannb = GaussianNB()
    
21. classifier_gaussiannb.fit(X, y)
    
22. y_pred = classifier_gaussiannb.predict(X)
    
23. 
    
24. # compute accuracy of the classifier
    
25. accuracy = 100.0 * (y == y_pred).sum() / X.shape[0]
    
26. print "Accuracy of the classifier =", round(accuracy, 2), "%"
    
27. 
    
28. plot_classifier(classifier_gaussiannb, X, y)
    
29. 
    
30. ###############################################
    
31. # Train test split
    
32. from sklearn import cross_validation
    
33. 
    
34. X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=5)
    
35. classifier_gaussiannb_new = GaussianNB()
    
36. classifier_gaussiannb_new.fit(X_train, y_train)
    
37. y_test_pred = classifier_gaussiannb_new.predict(X_test)
    
38. 
    
39. # compute accuracy of the classifier
    
40. accuracy = 100.0 * (y_test == y_test_pred).sum() / X_test.shape[0]
    
41. print "Accuracy of the classifier =", round(accuracy, 2), "%"
    
42. 
    
43. plot_classifier(classifier_gaussiannb_new, X_test, y_test)
    
44. 
    
45. ###############################################
    
46. # Cross validation and scoring functions
    
47. 
    
48. num_validations = 5
    
49. accuracy = cross_validation.cross_val_score(classifier_gaussiannb,
    
50.         X, y, scoring='accuracy', cv=num_validations)
    
51. print "Accuracy: " + str(round(100*accuracy.mean(), 2)) + "%"
    
52. 
    
53. f1 = cross_validation.cross_val_score(classifier_gaussiannb,
    
54.         X, y, scoring='f1_weighted', cv=num_validations)
    
55. print "F1: " + str(round(100*f1.mean(), 2)) + "%"
    
56. 
    
57. precision = cross_validation.cross_val_score(classifier_gaussiannb,
    
58.         X, y, scoring='precision_weighted', cv=num_validations)
    
59. print "Precision: " + str(round(100*precision.mean(), 2)) + "%"
    
60. 
    
61. recall = cross_validation.cross_val_score(classifier_gaussiannb,
    
62.         X, y, scoring='recall_weighted', cv=num_validations)
    
63. print "Recall: " + str(round(100*recall.mean(), 2)) + "%"

复制代码

看看     

谢谢分享