def test_predict_and_explain(self, tmp_path, use_pred_months,
predict_delta):
x, _, _ = _make_dataset(size=(5, 5), const=True)
y = x.isel(time=[-1])
train_features = tmp_path / "features/one_month_forecast/train/1980_1"
train_features.mkdir(parents=True)
test_features = tmp_path / "features/one_month_forecast/test/1980_1"
test_features.mkdir(parents=True)
norm_dict = {"VHI": {"mean": 0.0, "std": 1.0}}
with (tmp_path / "features/one_month_forecast/normalizing_dict.pkl"
).open("wb") as f:
pickle.dump(norm_dict, f)
x.to_netcdf(test_features / "x.nc")
y.to_netcdf(test_features / "y.nc")
x.to_netcdf(train_features / "x.nc")
y.to_netcdf(train_features / "y.nc")
# static
x_static, _, _ = _make_dataset(size=(5, 5), add_times=False)
static_features = tmp_path / f"features/static"
static_features.mkdir(parents=True)
x_static.to_netcdf(static_features / "data.nc")
static_norm_dict = {"VHI": {"mean": 0.0, "std": 1.0}}
with (tmp_path /
f"features/static/normalizing_dict.pkl").open("wb") as f:
pickle.dump(static_norm_dict, f)
dense_features = [10]
hidden_size = 128
rnn_dropout = 0.25
model = EARecurrentNetwork(
hidden_size=hidden_size,
dense_features=dense_features,
rnn_dropout=rnn_dropout,
data_folder=tmp_path,
predict_delta=predict_delta,
normalize_y=True,
)
model.train()
test_arrays_dict, pred_dict = model.predict()
# the foldername "1980_1" is the only one which should be in the dictionaries
assert ("1980_1" in test_arrays_dict.keys()) and (len(test_arrays_dict)
== 1)
assert ("1980_1" in pred_dict.keys()) and (len(pred_dict) == 1)
if not predict_delta:
# _make_dataset with const=True returns all ones
assert (test_arrays_dict["1980_1"]["y"] == 1).all()
else:
# _make_dataset with const=True & predict_delta
# returns a change of 0
assert (test_arrays_dict["1980_1"]["y"] == 0).all()
# test the Morris explanation works
test_dl = next(
iter(
model.get_dataloader(mode="test",
to_tensor=True,
shuffle_data=False)))
for key, val in test_dl.items():
output_m = model.explain(val.x,
save_explanations=True,
method="morris")
assert type(output_m) is TrainData
assert (model.model_dir /
"analysis/morris_value_historical.npy").exists()
)
# test the training functionality
ealstm.train()
# test the prediction functionality
ealstm.predict()
#
captured = capsys.readouterr()
expected_stdout = "`include_yearly_aggs` does not yet work for dynamic dataloder. Setting to False"
assert (
captured.out == expected_stdout
), f"Expected stdout to be {expected_stdout}, got {captured.out}"
# test getting the dataloader
dl = ealstm.get_dataloader(mode='train')
X, y = dl.__iter__().__next__()
# the dataloader loaded is the dynamic ?
test_years = np.arange(2011, 2017)
assert isinstance(dl, DynamicDataLoader)
assert all([pd.to_datetime(t).year in [y for y in test_years] for t in dl.valid_test_times]), "Test times are validly chosen"
assert all([pd.to_datetime(t).year not in [y for y in test_years]
for t in dl.valid_train_times]), "Train times are validly chosen"
# the dataloder data is legit?
assert isinstance(X, tuple)
assert isinstance(X[0], np.ndarray)
assert isinstance(y, np.ndarray)
assert y.shape[-1] == 1