X[i][j] = (X[i][j] - MIN[j]) / (MAX[j] - MIN[j])
X = np.hstack((np.ones((len(X), 1)), X))
testing_X = np.array(X)
return training_X, training_Y, testing_X
def sigmoid(z):
return 1 / (1 + np.exp(-z))
if __name__ == "__main__":
training_X, training_y, testing_X = extract_features(normalization=True)
model = LogisticRegression(training_X, training_y)
weight = model.GradientDescent(optimizer="Adagrad")
testing_y = sigmoid(np.dot(testing_X, weight))
with open("output.csv", "w") as f:
print("id,label", file=f)
for i in range(testing_y.shape[0]):
if testing_y[i] >= 0.5:
print("{},1".format(i + 1), file=f)
else:
print("{},0".format(i + 1), file=f)
X = np.hstack((np.ones((len(X), 1)), X))
for r in [1, 2, 4, 5, 6]:
X = np.hstack((X, np.array([X[:, r]**2]).T))
testing_X = np.array(X)
return training_X, training_Y, testing_X
def sigmoid(z):
return 1 / (1 + np.exp(-z))
if __name__ == "__main__":
training_X, training_y, testing_X = extract_features(normalization=True)
model = LogisticRegression(training_X, training_y)
weight = model.GradientDescent()
testing_y = sigmoid(np.dot(testing_X, weight))
with open("output.csv", "w") as f:
print("id,label", file=f)
for i in range(testing_y.shape[0]):
if testing_y[i] >= 0.5:
print("{},1".format(i + 1), file=f)
else:
print("{},0".format(i + 1), file=f)
