def main():
data = load_data.load('data2.txt')
X = data[:, 0:2]
print('X is \n{0}\n'.format(X))
print('mean(X) is {0}'.format(np.mean(X, axis=0)))
print('std(X) is {0}'.format(np.std(X, axis=0)))
print('normalization of X is\n {0}'.format(normalize.normalize(X)))
def main():
data = load_data.load('data1.txt')
X = data[:, 0]
Y = data[:, 1]
plot_data.plot(X, Y, 'house size', 'house price', {
'show': True,
'title': 'Original Data',
'fmt': 'rx'
})
def main():
X, y, origin_X = load_data.load_and_process('data1.txt')
initial_theta = np.zeros(X.shape[1])
res = minimize(cost_function, initial_theta, args=(X, y), method=None, jac=gradient, options={'maxiter': 400})
print(res)
theta = res.x
data = load_data.load('data1.txt')
pos_values = data[(data[:, 2] == 1)]
neg_values = data[(data[:, 2] == 0)]
plot_data.plot(pos_values[:, 0], pos_values[:, 1], 'score1', 'score2',
{
'fmt': 'bx',
'markersize': 5
})
plot_data.plot(neg_values[:, 0], neg_values[:, 1], 'score1', 'score2',
{
'fmt': 'yo',
'markersize': 5,
'show': False
})
score1 = np.linspace(25, 100)
score2 = []
for item in score1:
score2.append(((0.5 - theta[0]) - theta[1] * item) / theta[2])
score2 = np.array(score2)
plot_data.plot(score1, score2, 'score1', 'score2',
{
'fmt': 'r-',
'label': 'minimize',
'show': False
})
theta_from_cal = np.array([-4.81180027, 0.04528064, 0.03819149]) # 0.001 10 0000
theta_from_cal_2 = np.array([-15.39517866, 0.12825989, 0.12247929]) # 0.001 100 0000
theta_from_cal_3 = np.array([-22.21628108, 0.18268725, 0.17763448]) # 0.003 100 0000
score3 = []
for item in score1:
score3.append(((0.5 - theta_from_cal_3[0]) - theta_from_cal_3[1] * item) / theta_from_cal_3[2])
score3 = np.array(score3)
plot_data.plot(score1, score3, 'score1', 'score2',
{
'fmt': 'g-',
'label': 'gredient-descent',
'legend_loc': 'upper right',
'show': True
})
print(predict(45, 85, theta_from_cal_3))
def main():
data = load_data.load('data1.txt')
pos_values = data[(data[:, 2] == 1)]
neg_values = data[(data[:, 2] == 0)]
plot_data.plot(pos_values[:, 0], pos_values[:, 1], 'score1', 'score2', {
'fmt': 'bx',
'markersize': 5
})
plot_data.plot(neg_values[:, 0], neg_values[:, 1], 'score1', 'score2', {
'fmt': 'yo',
'markersize': 5,
'show': True
})
def main():
x, y, origin_x = load_data.load_and_process('data1.txt')
alpha = 0.003
iterations = 1000000
theta, j_list = gradient_descent(x, y, alpha, iterations)
print(theta)
iteration_array = range(iterations)
plot_data.plot(iteration_array, j_list, 'iteration', "lost", {
'fmt': 'b-',
'title': 'Lost',
'show': True
})
data = load_data.load('data1.txt')
pos_values = data[(data[:, 2] == 1)]
neg_values = data[(data[:, 2] == 0)]
plot_data.plot(pos_values[:, 0], pos_values[:, 1], 'score1', 'score2', {
'fmt': 'bx',
'markersize': 5
})
plot_data.plot(neg_values[:, 0], neg_values[:, 1], 'score1', 'score2', {
'fmt': 'yo',
'markersize': 5,
'show': False
})
score1 = np.linspace(25, 100)
score2 = []
for item in score1:
score2.append(((0.5 - theta[0, 0]) - theta[1, 0] * item) / theta[2, 0])
score2 = np.array(score2)
plot_data.plot(score1, score2, 'score1', 'score2', {
'fmt': 'r-',
'show': True
})
def main():
fig, axes = plt.subplots(1, 3, sharey=True, figsize=(17, 5))
data = load_data.load('data2.txt', dtype=np.float128)
X = data[:, 0:2]
X_map = feature_map.map(X)
y = data[:, 2].reshape(-1, 1)
initial_theta = np.zeros(X_map.shape[1])
#C = 0
#res = minimize(cost_function_reg, initial_theta, args=(C, X_map, y), method=None, jac=gradient_reg, options={'maxiter': 3000})
#print(res)
for i, C in enumerate([0, 1, 100]):
# Optimize costFunctionReg
res2 = minimize(cost_function_reg,
initial_theta,
args=(C, X_map, y),
method=None,
jac=gradient_reg,
options={'maxiter': 3000})
accuracy = 100 * sum(predict(res2.x, X_map) == y.ravel()) / y.size
plotData(data, 'Microchip Test 1', 'Microchip Test 2', 'y = 1',
'y = 0',
axes.flatten()[i])
# Plot decisionboundary
x1_min, x1_max = X[:, 0].min(), X[:, 0].max(),
x2_min, x2_max = X[:, 1].min(), X[:, 1].max(),
xx1, xx2 = np.meshgrid(np.linspace(x1_min, x1_max),
np.linspace(x2_min, x2_max))
h = sigmoid.sigmoid(
feature_map.map(np.c_[xx1.ravel(),
xx2.ravel()]).dot(res2.x.reshape(-1, 1)))
h = h.reshape(xx1.shape)
axes.flatten()[i].contour(xx1, xx2, h, [0.5], linewidths=1, colors='g')
axes.flatten()[i].set_title(
'Train accuracy {}% with Lambda = {}'.format(
np.round(accuracy, decimals=2), C))
plt.show()
# python analysis.py basic.utt courses.utt lecturers.utt rooms.utt curricula.utt relation.utt unavailability.utt 0
params = sys.argv[1:]
datasets = [1, 5, 12, 13]
population_sizes = [100, 50, 35, 15, 10]
mutation_probabilities = [0.02, 0.05, 0.08, 0.15, 0.2]
compactness_initializations = [False]
no_runs = 4
runs = range(no_runs)
results = {}
for dataset in datasets:
path = directory + 'dataset_' + str(dataset)
data = load_data.load(params, index=dataset)
num_lectures = []
for k, v in data['courses'].iteritems():
num_lectures.append(v['number_of_lectures'])
max_lectures = max(num_lectures)
horizontal_sizes = [3, 4]
crossover_window_sizes = [(hs, max_lectures + vs) for hs, vs in zip(
4 * [horizontal_sizes[0]] + 4 * [horizontal_sizes[1]], 2 *
[-2, -1, 0, 1])]
values_min = []
for ps in population_sizes:
for ci in compactness_initializations: