def main():
train_set, test_set = split_data()
X = np.matrix((
np.ones(train_set.shape[0]),
train_set['number_of_rooms'],
train_set['living_space'])
).T
Y = np.matrix((train_set['price'])).T
ne_theta = normal_equation.learn(X, Y)
gd_theta = gradient_descent.learn(X, Y, 0.00015, 100)
test_set = test_set[['number_of_rooms', 'living_space', 'price']].values
for rooms, area, price in test_set:
ne_price = int(round(predict(rooms, area, ne_theta)))
gd_price = int(round(predict(rooms, area, gd_theta)))
print 'Number of rooms %s, area %s sqm:' % (rooms, area)
print 'actual price: %s EUR' % price
print 'ne predict: %s EUR (%s%%)' %(
ne_price, int(100. * ne_price / price))
print 'gd predict: %s EUR (%s%%)' % (
gd_price, int(100. * gd_price / price))
def main():
train_set, test_set = split_data(district='Steglitz')
#train_set, test_set = split_data()
X_train = np.matrix([
np.ones(train_set.shape[0]),
train_set['number_of_rooms'],
train_set['living_space']
]).T
Y_train = np.matrix((train_set['price'])).T
alpha = 0.00015
n_iterations = 50
thetas = gradient_descent.learn(X_train, Y_train, alpha, n_iterations, True)
theta = thetas[-1]
X_test = np.matrix([
np.ones(test_set.shape[0]),
test_set['number_of_rooms'],
test_set['living_space']
]).T
Y_test = np.matrix((test_set['price'])).T
test_predictions = np.dot(X_test, theta)
costs = calc_cost_functions(X_train, Y_train, thetas)
print 'Train error', calc_error(X_train, Y_train, theta)
print 'Test error', calc_error(X_test, Y_test, theta)
print 'Train R squared', r_squared(X_train, Y_train, theta)
print 'Test R squared', r_squared(X_test, Y_test, theta)
figure = pl.figure(1)
ax = figure.add_subplot(211)
ax.scatter(test_set['price'], test_set['living_space'],
label='test set')
ax.scatter(train_set['price'], train_set['living_space'], color='g',
label='train set')
ax.plot(test_predictions, test_set['living_space'], color='red',
label='regression')
ax.set_xlabel('Living space, sqm')
ax.set_ylabel('Price, EUR')
ax.legend()
ax = figure.add_subplot(212)
ax.scatter(np.arange(len(costs)), costs)
ax.set_xlabel('Iteration')
ax.set_ylabel('Cost function')
pl.show()
