def regression(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
explain=False,
static="features",
ignore_vars=None,
predict_delta=False,
spatial_mask=None,
include_latlons=False,
):
predictor = LinearRegression(
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()
predictor.evaluate(save_preds=True)
# mostly to test it works
if explain:
predictor.explain(save_shap_values=True)
def regression(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 = LinearRegression(data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels)
predictor.train()
predictor.evaluate(save_preds=True)
# mostly to test it works
predictor.explain(save_shap_values=True)
def regression(
experiment="one_month_forecast",
include_pred_month=True,
surrounding_pixels=None,
ignore_vars=None,
):
data_path = get_data_path()
predictor = LinearRegression(
data_path,
experiment=experiment,
include_pred_month=include_pred_month,
surrounding_pixels=surrounding_pixels,
ignore_vars=ignore_vars,
static="embeddings",
spatial_mask=data_path /
"interim/boundaries_preprocessed/kenya_asal_mask.nc",
)
predictor.train()
predictor.evaluate(save_preds=True)
# mostly to test it works
predictor.explain(save_shap_values=True)
data_path = Path("data")
l = LinearRegression(data_path)
l.train()
ln = LinearNetwork(layer_sizes=[100], data_folder=data_path)
ln.train(num_epochs=10)
# ------------------------------------------------------------------------------
# try and explain the LinearRegression model
# ------------------------------------------------------------------------------
test_arrays_loader = DataLoader(
data_path=data_path, batch_file_size=1, shuffle_data=False, mode="test"
)
key, val = list(next(iter(test_arrays_loader)).items())[0]
explanations = l.explain(val.x)
# plot the SHAP explanations
# 1. mean spatial and temporal response
mean_expl = explanations.mean(axis=0).mean(axis=0)
x_vars = val.x_vars
df = pd.DataFrame(dict(variables=x_vars, values=mean_expl))
sns.barplot(x="variables", y="values", data=df)
fig = plt.gcf()
plt.title(f"{key} {val.y_var} mean SHAP Values for Linear Regression")
fig.savefig("scripts/mean_variable_importance_linear_regression.png", dpi=300)
# 2. mean spatial response
values = explanations.mean(axis=0).T.flatten()