def test_TimeSeriesRegressor_predict():
np.random.seed(0)
X = pd.DataFrame(np.random.randn(100, 2))
y = pd.Series(np.random.randn(100))
na = 3
nb = [3, 3]
nk = [1, 1]
step = 2
mdl = NARX(LinearRegression(), auto_order=na, exog_order=nb, exog_delay=nk)
mdl.fit(X, y)
ypred_act = mdl.predict(X, y, step=step)
mdl.score(X, y, step=step, method="r2")
mdl.score(X, y, step=step, method="mse")
# -------- manual computation ---------------
kernel_mdl = LinearRegression()
Xfeatures_exp, ytarget_exp = helper_preprocess(X,
y,
na,
nb,
nk,
removeNA=False)
mask = np.isnan(ytarget_exp) | np.isnan(Xfeatures_exp).any(axis=1)
kernel_mdl.fit(Xfeatures_exp[~mask, :], ytarget_exp[~mask])
ypred_exp1 = np.empty(X.shape[0]) * np.nan
ypred_exp1[~mask] = kernel_mdl.predict(Xfeatures_exp[~mask, :])
X1 = copy.deepcopy(Xfeatures_exp)
X2 = copy.deepcopy(Xfeatures_exp)
# Xfeatures_updated = mdl._update_lag_features(X1, ypred_exp1)
X2[:, 1:3] = X2[:, 0:2]
X2[:, 0] = ypred_exp1
X2[:, 4:6] = X2[:, 3:5]
X2[:, 3] = shift(X2[:, 3], -1)
X2[:, 7:9] = X2[:, 6:8]
X2[:, 6] = shift(X2[:, 6], -1)
mask = ~np.isnan(X2).any(axis=1)
ypred_exp2 = np.empty(X2.shape[0]) * np.nan
ypred_exp2[mask] = kernel_mdl.predict(X2[mask, :])
ypred_exp2 = np.concatenate([np.empty(2) * np.nan, ypred_exp2])[0:len(y)]
# print(X2)
# print(ypred_act)
np.testing.assert_array_almost_equal(ypred_act, ypred_exp2)
def _preprocess_data(self, X, y):
p = self._get_lag_feature_processor(X, y)
features = p.generate_lag_features()
target = shift(y, -self.pred_step)
# Remove NaN
all_data = np.concatenate([target.reshape(-1, 1), features], axis=1)
mask = np.isnan(all_data).any(axis=1)
features, target = features[~mask], target[~mask]
return features, target
def _preprocess_data(self, X, y):
"""
Helper function to prepare the data for base_estimator.
"""
p = self._get_lag_feature_processor(X, y)
features = p.generate_lag_features()
target = shift(y, -self.pred_step)
# Remove NaN introduced by shift
all_data = np.concatenate([target.reshape(-1, 1), features], axis=1)
mask = np.isnan(all_data).any(axis=1)
features, target = features[~mask], target[~mask]
return features, target
def test_shift():
x = np.array([1., 2., 3., 4.])
x1 = shift(x, 2)
np.testing.assert_array_equal(x1, np.array([np.nan, np.nan, 1, 2]))
x2 = shift(x, -2)
np.testing.assert_array_equal(x2, np.array([3, 4, np.nan, np.nan]))
x3 = shift(x, 6)
np.testing.assert_array_equal(x3,
np.array([np.nan, np.nan, np.nan, np.nan]))
x4 = shift(x, -6)
np.testing.assert_array_equal(x4,
np.array([np.nan, np.nan, np.nan, np.nan]))
x5 = shift(x, 0)
np.testing.assert_array_equal(x5, x)
x6 = shift(x, 4)
np.testing.assert_array_equal(x6,
np.array([np.nan, np.nan, np.nan, np.nan]))
x7 = shift(x, 4)
np.testing.assert_array_equal(x7,
np.array([np.nan, np.nan, np.nan, np.nan]))
y = np.array([[1., 2., 3.], [4., 5., 6.]])
y1 = shift(y, -1)
np.testing.assert_array_equal(
y1, np.array([[4., 5., 6.], [np.nan, np.nan, np.nan]]))
y = np.array([[1., 2., 3.], [4., 5., 6.]])
y1 = shift(y, 1)
np.testing.assert_array_equal(
y1, np.array([[np.nan, np.nan, np.nan], [1., 2., 3.]]))
def add_lags(X, y, auto_order, exog_order, exog_delay):
"""
Adds lags based the orders and delays of the endogenous and exogenous
variables.
Takes the following:
* X (dataframe): design matrix
* y (dataframe): target variable
* auto_order (int): the autoregressive order of the model
* exog_order (list): the order of the exogenous variables
* exog_delay (list): delay of the exogenous variables
Returns:
* features (array): transformed design matrix
* target (array): transformed target variable
"""
m = utils.MetaLagFeatureProcessor(X.values, y.values, auto_order,
exog_order, exog_delay)
features = m.generate_lag_features()
target = utils.shift(y, -1)
all_data = np.concatenate([target.reshape(-1, 1), features], axis=1)
mask = np.isnan(all_data).any(axis=1)
features, target = features[~mask], target[~mask]
return features, target