Knn classification folder

operators.ml3d.knn_classification_folder(client, in_folder_to_points='/in_folder_to_points', in_folder_from_points='/in_folder_from_points', out_folder_labels='/out_folder_labels', out_folder_probs='/out_folder_probs', k=3, max_distance=1.0, to_points_names='X,Y,Z', from_point_names='X,Y,Z', from_class_name='classification', worker_instance_type='x2large', manager_instance_type='small', extension_in_path_to_points='.laz', extension_in_path_from_points='.laz', extension_out_path_labels='.labels', extension_out_path_probs='.npy', skip_existing_files=False)

knn_classification_folder(client,
in_folder_to_points=’/in_folder_to_points’,
in_folder_from_points=’/in_folder_from_points’,
out_folder_labels=’/out_folder_labels’,
out_folder_probs=’/out_folder_probs’,
k=3,
max_distance=1.0,
to_points_names=’X,Y,Z’,
from_point_names=’X,Y,Z’,
from_class_name=’classification’,
worker_instance_type=’x2large’,
manager_instance_type=”small”,
extension_in_folder_to_points=”.laz”,
extension_in_folder_from_points=”.laz”,
extension_out_folder_labels=”.labels”,
extension_out_folder_probs=”.npy”,
skip_existing_files = False )
Parameters:

  • k – number of neighbors

  • max_distance – maximum distance

  • to_points_names – names of points to be labeled

  • from_point_names – names of reference points

  • from_class_name – name of reference classification

  • in_folder_to_points – input point cloud to be labeled

  • in_folder_from_points – input reference point cloud

  • out_folder_labels – out class labels

  • out_folder_probs – out class probabilities

  • worker_instance_type – cloud instance type of worker nodes

  • manager_instance_type – cloud instance type of manager node

  • extension_in_folder_to_points – File extension of files in folder for in_folder_to_points

  • extension_in_folder_from_points – File extension of files in folder for in_folder_from_points

  • extension_out_folder_labels – File extension of files in folder for out_folder_labels

  • extension_out_folder_probs – File extension of files in folder for out_folder_probs

  • skip_existing_files – skip files that already exist in the output folder