Python Classifier.train方法代碼示例

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
def load_classifier(neighbours, blur_scale, c=None, gamma=None, verbose=0):
    classifier_file = 'classifier_%s_%s.dat' \
            % (blur_scale, neighbours)
    classifier_path = DATA_FOLDER + classifier_file

    if exists(classifier_file):
        if verbose:
            print 'Loading classifier...'

        classifier = Classifier(filename=classifier_path, \
                neighbours=neighbours, verbose=verbose)
    elif c != None and gamma != None:
        if verbose:
            print 'Training new classifier...'

        classifier = Classifier(c=c, gamma=gamma, neighbours=neighbours, \
                verbose=verbose)
        learning_set = load_learning_set(neighbours, blur_scale, \
                verbose=verbose)
        classifier.train(learning_set)
        classifier.save(classifier_path)
    else:
        raise Exception('No soft margin and gamma specified.')

    return classifier

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
def main():
    try:
        trainingData, tuningData, testData, priorSpam = buildDataSets()
        nbc = Classifier(priorSpam, COUNT_THRESHOLD, SMOOTHING_FACTOR, DEFAULT_PROBABILITY)
        # nbc = Classifier2(priorSpam, 0, .01, None)
        nbc.train(trainingData)

        nbc.classify(testData)
        report(testData)

    except Exception as e:
        print e
        return 5

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
def run():
	clf= Classifier('breast-cancer-wisconsin.data.txt')
	clf.clf_fit_transform()
	
	clf.default_accuracy_lr()
	
	clf.weight_coefficent_lr()
	clf.SBS_lf()
	# it takes long time to run the Random forest Code ...uncomment to check the result
	# clf.feature_selection_rf()
	clf.PCA()
	clf.pipe_kf_validation()
	clf.clf_learning_curve()
	clf.clf_validation_curve()
	clf.clf_roc_curve()
	
	clf.train()
	clf.l1l2()
	
	
	dest = os.path.join('classifier', 'pkl_objects')
	if not os.path.exists(dest):
		os.makedirs(dest)
	pickle.dump(clf,	open(os.path.join(dest, 'classifier.pkl'), 'wb'),	protocol=2)

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
              ('I had a ton of homework', 'hyperbole'),
              ('If I can’t buy that new game I will die', 'hyperbole')]

nor_tweets = [('I do not like this car', 'normal'),
              ('I like this car', 'normal'),
              ('This view is horrible', 'normal'),
              ('I feel tired this morning', 'normal'),
              ('I am not looking forward to the concert', 'normal'),
              ('The door is black', 'normal'),
              ('I love you', 'normal'),
              ('He is my enemy', 'normal')]

tweets = hyp_tweets + nor_tweets

classifier = Classifier()

classifier.train(tweets)
# for tweet in Fetcher.fetch("hyperbole", 10):
#   print(classifier.classify(tweet))

@app.route('/')
@app.route("/<count>")
def index(count=10):
    tweets = []
    for tweet in Fetcher.fetch("hyperbole", int(count)):
        tweets.append((tweet, classifier.classify(tweet)))
    return render_template('index.html', tweets=set(tweets), count=count)

if __name__ == "__main__":
    app.debug = True
    app.run()

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
	def test_predict(self):
		x = Classifier()
		x.train()
		predicted = x.predict("train", "directory")
		actual = [(u'intermediate test', 2), (u'elementary test', 1), (u'advanced test', 0)]
		self.assertEqual(predicted, actual)

# 需要導入模塊: from Classifier import Classifier [as 別名]
# 或者: from Classifier.Classifier import train [as 別名]
# Load learning set and test set
learning_set = load_learning_set(neighbours, blur_scale, verbose=1)
test_set = load_test_set(neighbours, blur_scale, verbose=1)

# Perform a grid-search to find the optimal values for C and gamma
C = [float(2 ** p) for p in xrange(-5, 16, 2)]
Y = [float(2 ** p) for p in xrange(-15, 4, 2)]

results = []
best = (0,)
i = 0

for c in C:
    for y in Y:
        classifier = Classifier(c=c, gamma=y, neighbours=neighbours, verbose=1)
        classifier.train(learning_set)
        result = classifier.test(test_set)

        if result > best[0]:
            best = (result, c, y, classifier)

        results.append(result)
        i += 1
        print '%d of %d, c = %f, gamma = %f, result = %d%%' \
              % (i, len(C) * len(Y), c, y, int(round(result * 100)))

i = 0
s = '     c\y'

for y in Y:
    s += ' | %f' % y