def output_round(features, ada_classifiers, round):
best_feature_idx = ada_classifiers[round - 1]['index']
best_feature = features[best_feature_idx]
print("\nAdaboost rounds: %d" % round)
# print image with top feature rectangle
if best_feature.type == FeatureType.TWO_HORIZONTAL:
printed_img = draw_feature_2h(open_face(test_face_images[0]),
best_feature)
print("\nType: TWO_HORIZONTAL")
elif best_feature.type == FeatureType.TWO_VERTICAL:
printed_img = draw_feature_2v(open_face(test_face_images[0]),
best_feature)
print("Type: TWO_VERTICAL")
elif best_feature.type == FeatureType.THREE_HORIZONTAL:
printed_img = draw_feature_3h(open_face(test_face_images[0]),
best_feature)
print("Type: THREE_HORIZONTAL")
elif best_feature.type == FeatureType.THREE_VERTICAL:
printed_img = draw_feature_2v(open_face(test_face_images[0]),
best_feature)
print("Type: THREE_VERTICAL")
elif best_feature.type == FeatureType.FOUR:
printed_img = draw_feature_4(open_face(test_face_images[0]),
best_feature)
print("Type: FOUR")
print("Position: (%d, %d)" % (best_feature.x, best_feature.y))
print("Width: %d" % best_feature.width)
print("Height: %d" % best_feature.height)
print("Threshold: %f" % ada_classifiers[round - 1]['thresh'])
print("Training accuracy: %f" % ada_classifiers[round - 1]['accuracy'])
printed_img.show()
# classify
face_prediction = adaboost.classify(test_face_features, ada_classifiers)
non_face_prediction = adaboost.classify(test_non_face_features,
ada_classifiers)
false_positive_cnt = count_labels(face_prediction[0], -1.)
false_negative_cnt = count_labels(non_face_prediction[0], 1.)
sample_num = len(test_face_features) + len(test_non_face_features)
test_accuracy = (0. + sample_num - false_positive_cnt -
false_negative_cnt) / sample_num
print("Total accuracy: %f" % test_accuracy)
print("False Positive: %d" % false_positive_cnt)
print("False Negative: %d" % false_negative_cnt)
def adaboost_ml(train_data, test_data, stump_count):
"""
Adaboost algorithm
"""
model = adaboost.fit(read_data(train_data), stump_count)
accuracy, confusion, output = adaboost.classify(model, test_data)
confusion_printer(confusion)
print("Classification Accuracy of Adaboost: " + str(accuracy) + "%")
write_output(output, "adaboost_output.txt")
print("Done! Thank you!")
def test_classify(self):
print("Test Classify:")
print("Classify Simple Data:")
data_mat, labels_arr = adb.load_simple_data()
classifies_arr, est_agg = adb.train(data_mat, labels_arr, 30)
pred = adb.classify([[5, 5], [0, 0]], classifies_arr)
res = np.matrix([[1.], [-1.]])
self.assertEqual(True, (pred == res).all())
print("Classify Loaded Data:")
datArr, labelArr = adb.load_data_set('horseColicTraining2.txt')
classiferArray, aggClassEst = adb.train(datArr, labelArr, 10)
testArr, testLabelArr = adb.load_data_set('horseColicTest2.txt')
prediction10 = adb.classify(testArr, classiferArray)
errArr = np.mat(np.ones((67, 1)))
err_rate = errArr[prediction10 != np.mat(testLabelArr).T].sum() / 67
self.assertEqual(16.0 / 67, err_rate)
print("Test Error: %f%%" % (err_rate * 100))
# 绘制ROC和计算AUC
val_auc = adb.plot_roc(aggClassEst, labelArr)
self.assertLessEqual(0.8582969635, round(val_auc, 10))
import numpy as np
import adaboost
def createDataSet(filename):
file = open(filename, 'r')
lines = file.readlines()
file.close()
dataSet, labels = [], []
for line in lines:
data = line.split()
dataSet.append(list(map(float, data[:-1])))
labels.append(int(float(data[-1])))
return np.array(dataSet), np.array(labels)
trainingSet, trainingLabels = createDataSet('data/horse/training.txt')
stumps = adaboost.train(trainingSet, trainingLabels)
testSet, testLabels = createDataSet('data/horse/test.txt')
res = adaboost.classify(testSet, stumps)
a, b = np.sum(res == testLabels), len(testLabels)
print('Correctness: %d/%d = %.2f%%' % (a, b, a/b * 100))
train_size = int(training_block.shape[0]) att_size = int(len(attributes)) forest_size = 100 [ensemble_error, ensemble_pred] = rf.ensemble(test_block, test_label_block, rf.raise_forest(training_block,training_label_block, forest_size, train_size, att_size)) error[0]+= (1.0/k) * ensemble_error #cross validation for decision tree print "Cross Validating Decision Tree..." dec_tree = id3.id3(train_examples, attributes) dec_tree_errors = 0 for i in xrange(len(test_block)): if id3.classify(dec_tree, test_block[i]) != test_label_block[i]: dec_tree_errors += 1 error[1] += (1.0/k) * (float(dec_tree_errors) / set_size) print "Cross Validating AdaBoost..." adaboost_classifier = adaboost.adaboost(train_examples, adaboost_rounds) adaboost_errors = 0 for i in xrange(len(test_block)): if adaboost.classify(adaboost_classifier, test_block[i]) != test_label_block[i]: adaboost_errors += 1 error[2] += (1.0/k) * (float(adaboost_errors) / set_size) print (1-error[0]), (1-error[1]) print 'Estimated accuracy of Random Forest:', (1-error[0]) print 'Estimated accuracy of Decision Tree:', (1-error[1]) print 'Estimated accuracy of AdaBoost:', (1-error[2])