def test_f_regression_input_dtype():
"""
Test whether f_regression returns the same value
for any numeric data_type
"""
X = np.random.rand(10, 20)
y = np.arange(10).astype(int)
F1, pv1 = f_regression(X, y)
F2, pv2 = f_regression(X, y.astype(float))
assert_array_equal(F1, F2)
assert_array_equal(pv1, pv2)
def test_f_regression_input_dtype():
"""
Test whether f_regression returns the same value
for any numeric data_type
"""
X = np.random.rand(10, 20)
y = np.arange(10).astype(np.int)
F1, pv1 = f_regression(X, y)
F2, pv2 = f_regression(X, y.astype(np.float))
assert_array_almost_equal(F1, F2, 5)
assert_array_almost_equal(pv1, pv2, 5)
def test_f_regression():
"""
Test whether the F test yields meaningful results
on a simple simulated regression problem
"""
X, Y = make_regression(n_samples=200, n_features=20, n_informative=5, shuffle=False, random_state=0)
F, pv = f_regression(X, Y)
assert (F > 0).all()
assert (pv > 0).all()
assert (pv < 1).all()
assert (pv[:5] < 0.05).all()
assert (pv[5:] > 1.0e-4).all()
def test_f_regression():
"""
Test whether the F test yields meaningful results
on a simple simulated regression problem
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
F, pv = f_regression(X, Y)
assert(F > 0).all()
assert(pv > 0).all()
assert(pv < 1).all()
assert(pv[:5] < 0.05).all()
assert(pv[5:] > 1.e-4).all()
# Store data in a consistent place
DATA_DIR = '/users/ansonau/DS_HK_2/data/'
cars = read_csv(DATA_DIR + 'cars93.csv')
#Clean Data
#Get only Numeric Data from cars
car_x = cars._get_numeric_data()
car_x = car_x.fillna(car_x.mean())
#Drop y Values
car_x = cars.drop(['MPG.highway', 'MPG.city'], 1)
#car_x = cars[['EngineSize','Horsepower','RPM','Rev.per.mile','Fuel.tank.capacity','Passengers','Length','Wheelbase','Width','Turn.circle','Weight']]
car_y = cars['MPG.highway']
f, p = f_regression(car_x, car_y.values)
print[[x, y] for x, y in zip(f, p)]
# Regression on Weight
#Polynomial Regression
cars['Weight_squared'] = cars['Weight']**2
cars['Weight_cubed'] = cars['Weight']**3
cars['Weigh_fourth'] = cars['Weight']**4
MPG = cars['MPG.city']
Weight_poly = [[
w, x, y, z
] for w, x, y, z in zip(cars['Weight'].values, cars['Weight_squared'].values,
cars['Weight_cubed'], cars['Weigh_fourth'])]
ridge = linear_model.Ridge()
