def _get_data(subchunk, config):
features_names = geoio.feature_names(config)
# NOTE: This returns an *untransformed* x,
# which is ok as we just need dummies here
if config.mask:
mask_x = _mask(subchunk, config)
all_mask_x = np.ma.vstack(mpiops.comm.allgather(mask_x))
if all_mask_x.shape[0] == np.sum(all_mask_x.mask):
x = np.ma.zeros((mask_x.shape[0], len(features_names)),
dtype=np.bool)
x.mask = True
log.info('Partition {} covariates are not loaded as '
'the partition is entirely masked.'.format(subchunk + 1))
return x, features_names
transform_sets = [k.transform_set for k in config.feature_sets]
extracted_chunk_sets = geoio.image_subchunks(subchunk, config)
log.info("Applying feature transforms")
x = features.transform_features(extracted_chunk_sets, transform_sets,
config.final_transform, config)[0]
# only check/correct float32 conversion for Ensemble models
if not config.clustering:
if (isinstance(modelmaps[config.algorithm](), BaseEnsemble)
or config.multirandomforest):
x = _fix_for_corrupt_data(x, features_names)
return _mask_rows(x, subchunk, config), features_names
def permutation_importance(model, x_all, targets_all, config):
_logger.info("Computing permutation importance!!")
if config.algorithm not in transformed_modelmaps.keys():
raise AttributeError("Only the following can be used for permutation "
"importance {}".format(
list(transformed_modelmaps.keys())))
y = targets_all.observations
classification = hasattr(model, 'predict_proba')
if not classification:
for score in ['explained_variance',
'r2',
'neg_mean_absolute_error',
'neg_mean_squared_error']:
pi_cv = apply_multiple_masked(
PermutationImportance(model, scoring=score,
cv='prefit', n_iter=10,
refit=False).fit, data=(x_all, y)
)
feature_names = geoio.feature_names(config)
df_picv = eli5.explain_weights_df(
pi_cv, feature_names=feature_names, top=100)
csv = Path(config.output_dir).joinpath(
config.name + "_permutation_importance_{}.csv".format(
score)).as_posix()
df_picv.to_csv(csv, index=False)
def _get_data(subchunk, config):
features_names = geoio.feature_names(config)
if config.mask:
mask_x = _mask(subchunk, config)
all_mask_x = np.ma.vstack(mpiops.comm.allgather(mask_x))
if all_mask_x.shape[0] == np.sum(all_mask_x.mask):
x = np.ma.zeros((mask_x.shape[0], len(features_names)),
dtype=np.bool)
x.mask = True
log.info('Partition {} covariates are not loaded as '
'the partition is entirely masked.'.format(subchunk + 1))
return x, features_names
extracted_chunk_sets = geoio.image_subchunks(subchunk, config)
transform_sets = [k.transform_set for k in config.feature_sets]
log.info("Applying feature transforms")
x = features.transform_features(extracted_chunk_sets, transform_sets,
config.final_transform, config)[0]
return _mask_rows(x, subchunk, config), features_names