def gradient_Descent(X, y, theta, alpha, epoch, l):
cost_1 = []
for i in range(epoch):
theta = theta - alpha * (1 / len(X) *
(sigmoid(X @ theta.T) - y).T @ X +
l / len(X) * theta)
# print(cost_reg(X,y,theta,l))
cost_1.append(cost_reg(X, y, theta, l))
return theta, cost_1
def predict_tweet(tweet, freqs, theta):
"""
:param tweet: a string
:param freqs: a dictionary corresponding to frequency of each tupple (word,label)
:param theta: (3,1) weight vector
:return: y_pred: the probability of tweet being positive or negative
"""
x = extract_features(tweet, freqs)
y_pred = sigmoid(np.dot(x, theta))
return y_pred
# print("Entrenando")
# for i in range(k):
# progress(i + 1, k)
# tmp_y = np.array(y == i, dtype = int)
# optTheta = logisticRegression(X, tmp_y, np.zeros((n,1))).x
# all_theta[i] = optTheta
#
# #Salvo los vectores theta como un archivo csv
#
# predictores = pd.DataFrame(all_theta)
# predictores.to_csv('all_theta.csv',index = False)
#Predicciones para cada numero
p = np.zeros((m, 1))
for i in range(m):
p[i] = np.argmax(sigmoid(X[i, :].dot(all_theta.T)))
s = sum([1 if p[i] == y[i] else 0 for i in range(m)])
print("\n\n")
print("Train Accuracy ", (s / m) * 100, " %")
plt.ion() #modo interactivo
plt.gray()
fig = plt.figure()
out = "y"
all_theta = pd.read_csv('all_theta.csv').as_matrix()
print(all_theta.shape)
data = pd.read_csv("ex2data1.csv", names = ['test1', 'test2', 'condicion'])
#Preparando los datos
X = np.ones((100,3))
y = np.ones((100,1))
X[:,1] = data['test1'].values
X[:,2] = data['test2'].values
y[:,0] = data['condicion'].values
m = len(y)
initial_theta = np.zeros((3, 1))
optimized_theta = logisticRegression(X, y, initial_theta).x
#Predicciones para los datos de entrada
p = sigmoid(X.dot(optimized_theta)) >= 0.5
#Numero de predicciones exitosas
s = sum([1 if p[i] == y[i] else 0 for i in range(m)])
print("Train Accuracy ", (s / m) * 100 , " %")
prob_test = sigmoid(np.array([1, 45, 85]).dot(optimized_theta))
print('For a student with scores 45 and 85, we predict an admission probability of ', prob_test)
#Graficando los datos
admitidos = [x for x in data.values if x[2] == 1.]
rechazados = [x for x in data.values if x[2] == 0.]
plt.scatter([x[0] for x in admitidos], [y[1] for y in admitidos], s = 60, c = 'blue', marker='+',label = 'admitido')
plt.scatter([x[0] for x in rechazados], [y[1] for y in rechazados], s = 60, c = 'red', marker='o',label = 'rechazado')
plt.xlim(30,100)
plt.ylim(30,100)
plt.xlabel('Exam 1 Score')
all_theta = np.zeros((k, n + 1))
#Entrenamiento
#OneVsAll
print("Entrenando")
i = 0
for flor in Species:
progress(i + 1, k)
tmp_y = np.array(y_train == flor, dtype=int)
optTheta = logisticRegression(X_train, tmp_y, np.zeros((n + 1, 1))).x
all_theta[i] = optTheta
i += 1
#Predicciones
P = sigmoid(X_test.dot(all_theta.T))
p = [Species[np.argmax(P[i, :])] for i in range(X_test.shape[0])]
s = sum(np.array(p == y_test, dtype=int))
print("\n\n")
print("Test Accuracy ", (s / X_test.shape[0]) * 100, "%")
#Matrix de confusion
cfm = confusion_matrix(y_test, p, labels=Species)
#plt.yticks(cfm[:,0], Species, rotation = 'horizontal')
sb.heatmap(cfm, annot=True, xticklabels=Species, yticklabels=Species)
plt.show()