def create_feature_from_diff_bins_with_dim(diff: pd.DataFrame,
removed_nodes: [int],
original_graph: gc.Graph,
num_of_bins,
save_info: sl.MemoryAccess,
save: bool = True,
output_feature: bool = False,
check_for_existing: bool = True):
if check_for_existing and save_info.has_training_data(
removed_nodes=removed_nodes,
feature_type=ft.FeatureType.DIFF_BIN_WITH_DIM,
num_of_bins=num_of_bins):
# print("training feature for removed nodes '{}' and feature type '{}' already exists"
# .format(removed_nodes, ft.FeatureType.DIFF_BIN_WITH_DIM.to_str(num_of_bins)))
if output_feature:
data = save_info.load_training_data(
removed_nodes=removed_nodes,
feature_type=ft.FeatureType.DIFF_BIN_WITH_DIM,
num_of_bins=num_of_bins)
features = data.drop(["y"], axis=1)
labels = data["y"]
return features, labels
else:
return
features, target = create_feature_from_diff_bins(
diff=diff,
removed_nodes=removed_nodes,
original_graph=original_graph,
num_of_bins=num_of_bins,
save_info=save_info,
save=False)
labels = utils.get_row_labels(diff)
degrees = compute_degrees(graph=original_graph, labels=labels)
features = utils.pd_append_column(features, degrees)
if save:
save_info.save_training_data(
removed_nodes,
feature_type=ft.FeatureType.DIFF_BIN_WITH_DIM,
num_of_bins=num_of_bins,
training_data=utils.pd_append_column(features, target))
if output_feature:
# output format is different for data loaded from file!
return features, target
def create_features(diff: pd.DataFrame,
removed_nodes: [int],
original_graph: gc.Graph,
num_of_bins,
feature_type: ft.FeatureType,
save_info: sl.MemoryAccess,
save: bool = True,
output_feature: bool = False,
check_for_existing: bool = True):
if feature_type == ft.FeatureType.DIFF_BIN_WITH_DIM:
return create_feature_from_diff_bins_with_dim(
diff=diff,
removed_nodes=removed_nodes,
original_graph=original_graph,
num_of_bins=num_of_bins,
save_info=save_info,
save=save,
output_feature=output_feature,
check_for_existing=check_for_existing)
elif feature_type == ft.FeatureType.DIFF_BIN_WITH_DIM_2_HOP:
features, target = create_feature_from_diff_bins_with_dim(
diff=diff,
removed_nodes=removed_nodes,
original_graph=original_graph,
num_of_bins=num_of_bins,
save_info=save_info,
save=False,
output_feature=True)
target = two_hop_neighbours(nodes=utils.get_row_labels(features),
graph=original_graph,
node_to_predict=removed_nodes[-1])
if save:
save_info.save_training_data(
removed_nodes=removed_nodes,
feature_type=ft.FeatureType.DIFF_BIN_WITH_DIM_2_HOP,
num_of_bins=num_of_bins,
training_data=utils.pd_append_column(features, target))
return features, target
elif feature_type == ft.FeatureType.EVEN_DIST:
raise NotImplementedError()
else:
raise ValueError(f"Feature type {feature_type} is not known!")
def create_feature_from_diff_bins(diff: pd.DataFrame,
removed_nodes: [int],
original_graph: gc.Graph,
num_of_bins: int,
save_info: sl.MemoryAccess,
save: bool = True):
target = create_target_vector(utils.get_row_labels(diff), original_graph,
removed_nodes[-1])
# calculate bin distribution for all labels
features = get_features_from_bins(diff=diff, num_of_bins=num_of_bins)
if save:
save_info.save_training_data(
removed_nodes,
feature_type=ft.FeatureType.DIFF_BIN_WITH_DIM,
num_of_bins=num_of_bins,
training_data=utils.pd_append_column(features, target))
return features, target