def earnn(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
pretrained=True,
ignore_vars=None,
):
data_path = get_data_path()
if not pretrained:
predictor = EARecurrentNetwork(
hidden_size=128,
data_folder=data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels,
ignore_vars=ignore_vars,
)
predictor.train(num_epochs=50, early_stopping=5)
predictor.evaluate(save_preds=True)
predictor.save_model()
else:
predictor = load_model(data_path /
f"models/{experiment}/ealstm/model.pt")
test_file = data_path / f"features/{experiment}/test/2018_3"
assert test_file.exists()
all_explanations_for_file(test_file, predictor, batch_size=100)
def earnn(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
pretrained=True,
ignore_vars=None,
include_static=True,
):
# if the working directory is alread ml_drought don't need ../data
if Path(".").absolute().as_posix().split("/")[-1] == "ml_drought":
data_path = Path("data")
else:
data_path = Path("../data")
if not pretrained:
predictor = EARecurrentNetwork(
hidden_size=128,
data_folder=data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels,
ignore_vars=ignore_vars,
include_static=include_static,
)
predictor.train(num_epochs=50, early_stopping=10)
predictor.evaluate(save_preds=True)
predictor.save_model()
else:
predictor = load_model(data_path /
f"models/{experiment}/ealstm/model.pt")
def earnn(experiment='one_month_forecast',
include_pred_month=True,
surrounding_pixels=None,
pretrained=True):
# if the working directory is alread ml_drought don't need ../data
if Path('.').absolute().as_posix().split('/')[-1] == 'ml_drought':
data_path = Path('data')
else:
data_path = Path('../data')
if not pretrained:
predictor = EARecurrentNetwork(hidden_size=128,
data_folder=data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels)
predictor.train(num_epochs=50, early_stopping=5)
predictor.evaluate(save_preds=True)
predictor.save_model()
else:
predictor = load_model(data_path /
f'models/{experiment}/ealstm/model.pt')
test_file = data_path / f'features/{experiment}/test/2018_3'
assert test_file.exists()
all_shap_for_file(test_file, predictor, batch_size=100)
def earnn(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
pretrained=False,
explain=False,
static="features",
ignore_vars=None,
num_epochs=50,
early_stopping=5,
static_embedding_size=10,
hidden_size=128,
predict_delta=False,
spatial_mask=None,
include_latlons=False,
normalize_y=True,
include_prev_y=True,
include_yearly_aggs=True, # new
clear_nans=True,
weight_observations=False,
pred_month_static=False,
):
data_path = get_data_path()
if not pretrained:
predictor = EARecurrentNetwork(
hidden_size=hidden_size,
data_folder=data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels,
static=static,
static_embedding_size=static_embedding_size,
ignore_vars=ignore_vars,
predict_delta=predict_delta,
spatial_mask=spatial_mask,
include_latlons=include_latlons,
normalize_y=normalize_y,
include_prev_y=include_prev_y,
include_yearly_aggs=include_yearly_aggs,
clear_nans=clear_nans,
weight_observations=weight_observations,
pred_month_static=pred_month_static,
)
predictor.train(num_epochs=num_epochs, early_stopping=early_stopping)
predictor.evaluate(save_preds=True)
predictor.save_model()
else:
predictor = load_model(data_path /
f"models/{experiment}/ealstm/model.pt")
if explain:
test_file = data_path / f"features/{experiment}/test/2018_3"
assert test_file.exists()
all_explanations_for_file(test_file, predictor, batch_size=100)
static_ignore_vars=static_ignore_vars,
target_var='discharge_spec',
test_years=np.arange(2011, 2017),
)
print("** Initialised Models! **")
# test the training functionality
ealstm.train(
num_epochs=1, # 100
# early_stopping=10
)
# test the prediction functionality
# test_arrays_dict, preds_dict = ealstm.predict()
ealstm.evaluate(
spatial_unit_name='station_id',
save_preds=True
)
results_dict = json.load(open('data/models/one_timestep_forecast/ealstm/results.json', 'rb'))
print("Overall RMSE: ", results_dict['total'])
# 1 epoch = 1.04 / 2.81
# 100 epochs = 0.72 / 2.04
# save the model
ealstm.save_model()
# load the model
from src.models import load_model
ealstm2 = load_model(Path('data/models/one_timestep_forecast/ealstm/model.pt'))
# ------------------------------------------------------------------------