def grade1():
marks = 0
try:
X = np.random.rand(110, 5)
Y = np.random.rand(110, 1)
X_train, Y_train, X_test, Y_test = utils.split_data(X, Y, 0.75)
assert np.allclose(np.vstack([X_train, X_test]), X)
assert np.allclose(np.vstack([Y_train, Y_test]), Y)
assert len(X_train) == 82 and len(Y_train) == 82
marks += 0.5
except:
print('Q1 split_data() incorrect', file=stderr)
return marks
try:
x = np.array([
9.71711545, 5.27658861, 0.74957658, 7.25267862, 1.57512235,
4.95493874, 4.6645458, 8.81014817, 5.6875507, 8.9270358
]).reshape(10, 1)
y = np.array([
7.4395211, 1.29711056, 4.99824035, 1.87706798, 0.93306619,
6.65645683, 8.6573449, 2.54946024, 1.3023241, 6.52289899
]).reshape(10, 1)
w = 0.513244
b = 1.839345
assert np.isclose(single_var_reg.mse(x, y, w, b), 4.319008411331635)
marks += 0.5
except:
print('Q1 mse() incorrect', file=stderr)
return marks
try:
X, Y = utils.load_data1('data1.csv')
X_train, Y_train, X_test, Y_test = utils.split_data(X, Y)
w, b, train_mses, test_mses = single_var_reg.ordinary_least_squares(
X_train, Y_train, X_test, Y_test)
assert train_mses[-1] < 52
assert test_mses[-1] < 68
for i in range(len(train_mses) - 1):
assert train_mses[i] >= train_mses[i + 1]
marks += 3
except:
print('Q1 ordinary_least_squares() incorrect', file=stderr)
return marks
return marks
## END TODO
train_mses.append(train_mse)
test_mses.append(test_mse)
## TODO: Update w and b using a single step of gradient descent
## END TODO
return w, b, train_mses, test_mses
if __name__ == '__main__':
# Load and split data
X, Y = load_data1('data1.csv')
X_train, Y_train, X_test, Y_test = split_data(X, Y)
w, b, train_mses, test_mses = ordinary_least_squares(
X_train, Y_train, X_test, Y_test)
# Plots
plt.figure(figsize=(8, 4))
plt.subplot(121)
plt.plot(train_mses)
plt.plot(test_mses)
plt.legend(['Train MSE', 'Test MSE'])
plt.xlabel('Iteration')
plt.ylabel('MSE')
plt.subplot(122)
plt.plot([-20, 50], [-20 * w + b, 50 * w + b], color='r')