def standardize_pre_and_post_data(
pre_data: pd.DataFrame,
post_data: pd.DataFrame
) -> Tuple[pd.DataFrame, pd.DataFrame, Tuple[float, float]]:
"""
Applies standardization in pre and post data, based on mean and standard deviation
of `pre_data` (as it's used for training the causal impact model).
Args
----
pre_data: pd.DataFrame
data selected to be the pre-intervention dataset of causal impact.
post_data: pd.DataFrame
Returns
-------
Tuple[pd.DataFrame, pd.DataFrame, Tuple[float, float]]
`pre_data` and `post_data` normalized along with the mean and variance used for
response variable `y` only.
"""
normed_pre_data, (mu, sig) = standardize(pre_data)
normed_post_data = (post_data - mu) / sig
mu_sig = (mu[0], sig[0])
return (normed_pre_data, normed_post_data, mu_sig)
def test_standardize_raises_single_input():
with pytest.raises(ValueError):
standardize(pd.DataFrame([1]))
def test_standardize_w_various_distinct_inputs():
test_data = [[1, 2, 1], [1, np.nan, 3], [10, 20, 30]]
test_data = [pd.DataFrame(data, dtype="float") for data in test_data]
for data in test_data:
result, (mu, sig) = standardize(data)
pd.util.testing.assert_frame_equal(unstandardize(result, (mu, sig)), data)