def linear_nn(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
explain=False,
static="features",
ignore_vars=None,
num_epochs=50,
early_stopping=5,
layer_sizes=[100],
predict_delta=False,
spatial_mask=None,
include_latlons=False,
):
predictor = LinearNetwork(
layer_sizes=layer_sizes,
data_folder=get_data_path(),
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels,
static=static,
ignore_vars=ignore_vars,
predict_delta=predict_delta,
spatial_mask=spatial_mask,
include_latlons=include_latlons,
)
predictor.train(num_epochs=num_epochs, early_stopping=early_stopping)
predictor.evaluate(save_preds=True)
predictor.save_model()
if explain:
_ = predictor.explain(save_shap_values=True)
def linear_nn(experiment='one_month_forecast',
include_pred_month=True,
surrounding_pixels=1):
# 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')
predictor = LinearNetwork(layer_sizes=[100],
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()
_ = predictor.explain(save_shap_values=True)
def linear_nn(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
ignore_vars=None,
pretrained=False,
):
predictor = LinearNetwork(
layer_sizes=[100],
data_folder=get_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()
_ = predictor.explain(save_shap_values=True)
x_vars = np.repeat(val.x_vars, 11)
df = pd.DataFrame(
dict(variable=x_vars, month=np.tile(np.arange(1, 12), 5), value=values)
)
fig, axs = plt.subplots(3, 2, sharex=True, sharey=True)
for i, var in enumerate(val.x_vars):
d = df.loc[df.variable == var]
ax_ix = np.unravel_index(i, (3, 2))
ax = axs[ax_ix]
d.plot(x="month", y="value", ax=ax, label=var, color=sns.color_palette()[i])
ax.axhline(0, "k--", alpha=0.7)
fig.savefig("scripts/ts_variable_importance_linear_regression.png", dpi=300)
# ------------------------------------------------------------------------------
# Explain the Linear Network
# ------------------------------------------------------------------------------
test_arrays_loader = DataLoader(
data_path=data_path,
batch_file_size=1,
shuffle_data=False,
mode="test",
to_tensor=True,
)
key, val = list(next(iter(test_arrays_loader)).items())[0]
explanations = ln.explain(val.x)
#