def paint_graphic(X, y, true_score, theta1, theta2, mu, sigma):
figure, ax = plt.subplots()
pos = (y == 1).ravel()
neg = (y == 0).ravel()
plt.scatter(X[pos, 0], X[pos, 1], color='blue', marker='o', label = "Legendary")
plt.scatter(X[neg, 0], X[neg, 1], color='black', marker='x', label = "Non legendary")
x0_min, x0_max = X[:,0].min(), X[:,0].max()
x1_min, x1_max = X[:,1].min(), X[:,1].max()
xx1, xx2 = np.meshgrid(np.linspace(x0_min, x0_max), np.linspace(x1_min, x1_max))
aux = np.c_[ xx1.ravel(), xx2.ravel()]
p, aux = polinomial_features(aux, 5)
aux = Normalization.normalize(aux[:, 1:], mu, sigma)
sigm = forward_propagate(aux, theta1, theta2)[4]
sigm = np.reshape(sigm, np.shape(xx1))
plt.contour(xx1, xx2, sigm, [0.5], linewidths = 1, colors=['red', 'purple'])
#formatting the graphic with some labels
plt.xlabel("weight_kg")
plt.ylabel("speed")
plt.suptitle(("Score: " + str(float("{0:.3f}".format(true_score)))))
figure.legend()
#set the labels to non-normalized values
figure.canvas.draw()
labels = [item for item in plt.xticks()[0]]
for i in range(len(labels)):
labels[i] = int(round((labels[i] * sigma[0, 0]) + mu[0, 0], -1))
ax.xaxis.set_ticklabels(labels)
labels = [item for item in plt.yticks()[0]]
for i in range(len(labels)):
labels[i] = int(round((labels[i] * sigma[0, 1]) + mu[0, 1], -1))
ax.yaxis.set_ticklabels(labels)
plt.show()
currentTrainY = (trainY == j) * 1
currentValidationY = (validationY == j) * 1
currentTestingY = (testingY == j) * 1
current_svm, C, s = eleccion_parametros_C_y_Sigma(trainX, currentTrainY,
validationX,
currentValidationY, mu,
sigma)
current_score = true_score(testingX, currentTestingY, current_svm)
if np.shape(trainX)[1] == 2:
draw_decisition_boundary(testingX, currentTestingY, current_svm,
current_score, mu, sigma, C, s,
Data_Management.getTypeByIndex(j))
svms.append(current_svm)
print("Score con los ejemplos de testing: " + str(current_score) +
" Type: " + Data_Management.getTypeByIndex(j))
while True:
user_values = np.array(list(map(float,
input("Gimme stats: ").split())),
dtype=float) # (features, )
if user_values.size == 0:
break
user_values = np.reshape(user_values, (np.shape(user_values)[0], 1))
user_values = np.transpose(user_values)
user_values = polynomial_features(user_values, grado)
user_values = Normalization.normalize(user_values[:, 1:], mu,
sigma) #normalization of user values
sec, pokemon_type = predict_type(user_values, svms)
print("Predicted type: " + Data_Management.getTypeByIndex(pokemon_type) +
". Probability of that type: " + str(sec) + "\n")