hello.ipynb

import matplotlib.pyplot
import numpy
from sklearn import datasets
from sklearn.model_selection import train_test_split

x, y = datasets.make_classification(
    n_features=2, n_redundant=0, n_informative=2, n_classes=2,
    random_state=1, n_clusters_per_class=1)
rng = numpy.random.RandomState(2)
x += 0 * rng.uniform(size=x.shape)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.5, random_state=42)
number_of_features = x_train.shape[1]
number_of_training_data = x_train.shape[0]
number_of_test_data = x_test.shape[0]
y = numpy.append(y_train, y_test)
number_of_classes = len(numpy.unique(y))

# draw data
# h = .02
# X = numpy.vstack([x_train, x_test])
# x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
# y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
#
# cm = matplotlib.pyplot.cm.jet
# # Plot the training points
# matplotlib.pyplot.scatter(x_train[:, 0], x_train[:, 1], c=y_train, cmap=cm, edgecolors='k', label='Training Data')
# # and testing points
# matplotlib.pyplot.scatter(x_test[:, 0], x_test[:, 1], c=y_test, cmap=cm, edgecolors='k', marker='x', linewidth=3,
#                           label='Test Data')
#
# matplotlib.pyplot.xlim(x_min, x_max)
# matplotlib.pyplot.ylim(y_min, y_max)
# matplotlib.pyplot.xticks(())
# matplotlib.pyplot.yticks(())
# matplotlib.pyplot.legend()
# matplotlib.pyplot.title(s="synthetic-easy")
# matplotlib.pyplot.show()
number_of_features = x_train.shape[1]
w_vector = numpy.random.rand(number_of_features + 1)
x_extended = numpy.hstack([x_train, numpy.ones([x_train.shape[0], 1])])
w_t_x = numpy.dot(x_extended, w_vector)
my_sigmoid = numpy.divide(1, numpy.add(1, numpy.exp(-w_t_x)))
y_n = my_sigmoid.reshape(-1)
loss2 = -(numpy.dot(y_train, numpy.log(y_n)) + numpy.dot(numpy.subtract(1, y_train), numpy.log(numpy.subtract(1, y_n))))
d_loss = loss2
eta = 1.01
while d_loss > 0.05 or d_loss < 0.0:
    gradient_e = numpy.dot(numpy.subtract(y_n, y_train), x_extended)
    w_vector = numpy.subtract(w_vector, numpy.multiply(eta, gradient_e))
    w_t_x = numpy.dot(x_extended, w_vector)
    my_sigmoid = numpy.divide(1, numpy.add(1, numpy.exp(-w_t_x)))
    y_n = my_sigmoid.reshape(-1)
    y_n[y_n < 0.05] = 0.05
    y_n[y_n >= 1] = 0.95
    loss1 = loss2
    loss2 = -(
        numpy.dot(y_train, numpy.log(y_n)) + numpy.dot(numpy.subtract(1, y_train), numpy.log(numpy.subtract(1, y_n))))
    if abs(loss1 > loss2) < d_loss:
        eta = 1.01
    else:
        eta = -0.5
    d_loss = abs(loss1 - loss2)
print(w_vector)
assert len(w_vector) == x_train.shape[1] + 1
reshaped_w_vector = numpy.reshape(w_vector, (-1, 1))
x_extended = numpy.hstack([x_train, numpy.ones([x_train.shape[0], 1])])
y_predicted = numpy.ravel(numpy.sign(numpy.dot(x_extended, reshaped_w_vector)))
y_predicted_final = numpy.maximum(numpy.zeros(y_predicted.shape), y_predicted)
assert len(y_predicted_final) == len(y_train)
training_score = numpy.sum(y_predicted_final == y_train) / float(len(y_predicted_final))
print(training_score)
x_extended_test = numpy.hstack([x_test, numpy.ones([x_test.shape[0], 1])])
y_predicted_test = numpy.ravel(numpy.sign(numpy.dot(x_extended_test, reshaped_w_vector)))
y_predicted_final_test = numpy.maximum(numpy.zeros(y_predicted_test.shape), y_predicted_test)
assert len(y_predicted_final_test) == len(y_test)
testing_score = numpy.sum(y_predicted_final_test == y_test) / float(len(y_predicted_final_test))
print(testing_score)