[-2,3],
[2,4],
[4,2],
[-3,-2],
[0,-2],
[3,-3]])
loose_labels = np.array([1,1,1,1,-1,-1,-1])
average_theta, average_theta_0 = p1.averager(loose_points, loose_labels)
p1.plot_2d_examples(loose_points, loose_labels, average_theta_0, average_theta, 'Averager - loose points')
perceptron_theta, perceptron_theta_0 = p1.train_perceptron(loose_points, loose_labels)
p1.plot_2d_examples(loose_points, loose_labels, perceptron_theta_0, perceptron_theta, 'Perceptron - loose points')
pa_theta, pa_theta_0 = p1.train_passive_agressive(loose_points, loose_labels, 1000)
p1.plot_2d_examples(loose_points, loose_labels, pa_theta_0, pa_theta, 'Passive Agressive - loose points')
close_points = np.array([
[-1,-1.25],
[-1.5, -1],
[1,4],
[1.5,1.5],
[4,10],
[-1,-1]])
close_labels = np.array([-1, 1, 1, -1, 1, -1])
average_theta, average_theta_0 = p1.averager(close_points, close_labels)
p1.plot_2d_examples(close_points, close_labels, average_theta_0, average_theta, 'Averager - close points')
loose_points = np.array([[-3, 4], [-2, 3], [2, 4], [4, 2], [-3, -2], [0, -2],
[3, -3]])
loose_labels = np.array([1, 1, 1, 1, -1, -1, -1])
average_theta, average_theta_0 = p1.averager(loose_points, loose_labels)
p1.plot_2d_examples(loose_points, loose_labels, average_theta_0, average_theta,
'Averager - loose points')
perceptron_theta, perceptron_theta_0 = p1.train_perceptron(
loose_points, loose_labels)
p1.plot_2d_examples(loose_points, loose_labels, perceptron_theta_0,
perceptron_theta, 'Perceptron - loose points')
pa_theta, pa_theta_0 = p1.train_passive_agressive(loose_points, loose_labels,
1000)
p1.plot_2d_examples(loose_points, loose_labels, pa_theta_0, pa_theta,
'Passive Agressive - loose points')
close_points = np.array([[-1, -1.25], [-1.5, -1], [1, 4], [1.5, 1.5], [4, 10],
[-1, -1]])
close_labels = np.array([-1, 1, 1, -1, 1, -1])
average_theta, average_theta_0 = p1.averager(close_points, close_labels)
p1.plot_2d_examples(close_points, close_labels, average_theta_0, average_theta,
'Averager - close points')
perceptron_theta, perceptron_theta_0 = p1.train_perceptron(
close_points, close_labels)
p1.plot_2d_examples(close_points, close_labels, perceptron_theta_0,
print 'Size', len(dictionary)
print 'T_0', perceptron_theta_0
correct = 0
for i in xrange(0, len(label_output)):
if(label_output[i] == labels[i]):
correct = correct + 1
percentage_correct = 100.0 * correct / len(label_output)
print("Perceptron gets " + str(percentage_correct) + "% correct (" + str(correct) + " out of " + str(len(label_output)) + ").")
######################
# PASSIVE-AGRESSIVE
######################
pa_theta, pa_theta_0 = p1.train_passive_agressive(feature_matrix, labels, 50)
label_output = p1.perceptron_classify(feature_matrix, pa_theta_0, pa_theta)
correct = 0
for i in xrange(0, len(label_output)):
if(label_output[i] == labels[i]):
correct = correct + 1
percentage_correct = 100.0 * correct / len(label_output)
print("Passive-agressive gets " + str(percentage_correct) + "% correct (" + str(correct) + " out of " + str(len(label_output)) + ").")
# ######################
# # CROSS VALIDATION
# ######################
K = 40
print 'K =', K
import numpy as np
import project1_code as p1
######################
# INITIALIZE
######################
adjectives = p1.extract_set('adjectives.txt')
dictionary = p1.extract_dictionary('train-tweet.txt')
train_labels = p1.read_vector_file('train-answer.txt')
train_feature_matrix = p1.extract_feature_vectors_with_keywords(
'train-tweet.txt', dictionary, adjectives)
test_feature_matrix = p1.extract_feature_vectors_with_keywords(
'test-tweet.txt', dictionary, adjectives)
######################
# TRAIN
######################
pa_theta, pa_theta_0 = p1.train_passive_agressive(train_feature_matrix,
train_labels, 1000)
######################
# CLASSIFY
######################
label_output = p1.perceptron_classify(test_feature_matrix, pa_theta_0,
pa_theta)
print train_feature_matrix.shape
print test_feature_matrix.shape
p1.write_label_answer(label_output, 'tweet_labels.txt')
import numpy as np
import project1_code as p1
######################
# INITIALIZE
######################
adjectives = p1.extract_set('adjectives.txt')
dictionary = p1.extract_dictionary('train-tweet.txt')
train_labels = p1.read_vector_file('train-answer.txt')
train_feature_matrix = p1.extract_feature_vectors_with_keywords('train-tweet.txt', dictionary, adjectives)
test_feature_matrix = p1.extract_feature_vectors_with_keywords('test-tweet.txt', dictionary, adjectives)
######################
# TRAIN
######################
pa_theta, pa_theta_0 = p1.train_passive_agressive(train_feature_matrix, train_labels, 1000)
######################
# CLASSIFY
######################
label_output = p1.perceptron_classify(test_feature_matrix, pa_theta_0, pa_theta)
print train_feature_matrix.shape
print test_feature_matrix.shape
p1.write_label_answer(label_output, 'tweet_labels.txt')