diff --git a/test_split/general_merger.py b/test_split/general_merger.py
new file mode 100644
index 0000000000000000000000000000000000000000..32ba63ebc78481e9f78b2ecd0ea0833fe0226ccf
--- /dev/null
+++ b/test_split/general_merger.py
@@ -0,0 +1,37 @@
+import os
+import laspy
+import pandas as pd
+
+class GeneralMerger(object):
+ def __init__(self, folder_path, file_name):
+ self.folder_path = folder_path
+ self.file_name = file_name
+
+ def merge(self):
+ # read files in the folder_path
+ files = [os.path.join(self.folder_path, f) for f in os.listdir(self.folder_path) if f.endswith('.txt')]
+
+ # create an empty list to hold dataframes
+ dfs = []
+
+ # get the header from the first file
+ header = pd.read_csv(files[0], sep=',', header=None).iloc[0]
+
+ # read each file and append to the list
+ for file in files:
+ dfs.append(pd.read_csv(file, sep=',', header=None))
+
+ # concatenate all dataframes into a single one
+ merged_df = pd.concat(dfs, ignore_index=True)
+
+ # add the header
+ merged_df.columns = header
+
+ # write the merged dataframe to a csv file
+ merged_df.to_csv(self.file_name, index=False)
+
+# test the code
+folder_path = '/home/nibio/mutable-outside-world/code/nibio_graph_sem_seg/test_split/output_text'
+file_name = '/home/nibio/mutable-outside-world/code/nibio_graph_sem_seg/test_split/merged_output.txt'
+merger = GeneralMerger(folder_path, file_name)
+merger.merge()
diff --git a/test_split/general_splitter.py b/test_split/general_splitter.py
new file mode 100644
index 0000000000000000000000000000000000000000..2ae83aafa6e6d719992cdc5348b2b109377b0937
--- /dev/null
+++ b/test_split/general_splitter.py
@@ -0,0 +1,110 @@
+import json
+import os
+import argparse
+import laspy
+import numpy as np
+from sklearn.neighbors import KDTree
+
+SPLIT_TEMPLATE = json.dumps({
+ "pipeline": [
+ "input.las",
+ {
+ "type": "filters.chipper",
+ "capacity": "5000"
+ },
+ {
+ "type": "writers.las",
+ "filename": "output_#.las"
+ }
+ ]
+})
+
+LIST_OF_LAS_FIELDS = ['label', 'treeID']
+
+class GeneralSplitter(object):
+ def __init__(self, input_file, output_folder, capacity=5000):
+ self.input_file = input_file
+ self.output_folder = output_folder
+ self.capacity = capacity
+
+ def split(self):
+ # create the output folder if it does not exist
+ if not os.path.exists(self.output_folder):
+ os.makedirs(self.output_folder)
+
+ with open('split_pipeline.json', 'w') as f:
+ f.write(
+ SPLIT_TEMPLATE.replace('input.las',
+ self.input_file).replace('5000', str(self.capacity)).replace('output_#.las',
+ self.output_folder + '/output_#.las'))
+ # run the pipeline
+ os.system('pdal pipeline split_pipeline.json')
+ # remove the pipeline file
+ os.remove('split_pipeline.json')
+
+ def transfer_extra_fields(self):
+ # get list of extra fields in the input file using laspy
+ input_file = os.path.join(self.input_file)
+ las = laspy.read(input_file)
+
+ # get pointcloud and put it into KDTree
+ point_cloud = np.vstack((las.x, las.y, las.z)).transpose()
+
+ tree = KDTree(point_cloud)
+
+ # get the list of output files
+ output_files = [os.path.join(self.output_folder, f) for f in os.listdir(self.output_folder) if f.endswith('.las')]
+ for output_file in output_files:
+ # read the output file
+ target = laspy.read(output_file)
+ target_xyz = target.xyz
+ # find the nearest neighbor for each point in target las file
+ ind = tree.query(target_xyz, k=1, return_distance=False)
+
+ selected_points_x = las.x[ind.ravel()]
+ selected_points_y = las.y[ind.ravel()]
+ selected_points_z = las.z[ind.ravel()]
+ selected_points = np.vstack([selected_points_x, selected_points_y, selected_points_z]).T
+
+
+ new_header = laspy.LasHeader(point_format=las.point_format.id, version=las.header.version)
+
+ # add extra dimensions to new las file
+ for item in LIST_OF_LAS_FIELDS:
+ new_header.add_extra_dim(laspy.ExtraBytesParams(name=item, type=np.int32))
+
+ new_las = laspy.LasData(new_header)
+
+ # copy x, y, z, gt_label and target_label from target las file to the new las file
+ new_las.x = selected_points_x
+ new_las.y = selected_points_y
+ new_las.z = selected_points_z
+
+ # copy contents of extra dimensions from target las file to the new las file
+ for item in new_header.point_format.dimension_names:
+ if item in LIST_OF_LAS_FIELDS:
+ new_las[item] = las[item][ind.ravel()]
+
+
+ # write the new las file
+ new_las.write(output_file)
+
+
+filepath = '/home/nibio/mutable-outside-world/code/nibio_graph_sem_seg/test_split/input.las'
+output_folder = '/home/nibio/mutable-outside-world/code/nibio_graph_sem_seg/test_split/output'
+splitter = GeneralSplitter(filepath, output_folder)
+splitter.split()
+splitter.transfer_extra_fields()
+
+
+# if __name__ == '__main__':
+# parser = argparse.ArgumentParser(description='Split a LAS file into multiple LAS files')
+# parser.add_argument('--input_file', type=str, help='Input LAS file')
+# parser.add_argument('--output_folder', type=str, help='Output folder')
+# parser.add_argument('--capacity', type=int, default=5000, help='Capacity of each output LAS file')
+# args = parser.parse_args()
+
+# splitter = GeneralSplitter(args.input_file, args.output_folder, args.capacity)
+# # splitter.split()
+# splitter.transfer_extra_fields()
+
diff --git a/utils/las2text_mapper.py b/utils/las2text_mapper.py
new file mode 100755
index 0000000000000000000000000000000000000000..654ae163ffc545f2e6096e044f68ed7b0bb33370
--- /dev/null
+++ b/utils/las2text_mapper.py
@@ -0,0 +1,94 @@
+import glob
+import os
+import pandas as pd
+import numpy as np
+from tqdm import tqdm
+import laspy
+import argparse
+
+class Las2TextMapper:
+
+ """ Mapper class for las2text.py """
+
+ def __init__(self, data_dir, save_dir, verbose=False):
+ self.data_dir = data_dir
+ self.save_dir = save_dir
+ self.verbose = verbose
+
+ #
+ def read_single_las(self, filepath):
+ """read_single_las.
+
+ Args:
+ filepath: path to the main las file
+
+ Returns:
+ points: numpy array of points
+ """
+ las = laspy.read(filepath)
+ # get x, y, z
+ points = np.vstack((las.x, las.y, las.z)).transpose()
+ # get intensity
+ # points = np.hstack((points, las.intensity[..., None]))
+ # get rgb
+ points = np.hstack((points, las.red[..., None]))
+ points = np.hstack((points, las.green[..., None]))
+ points = np.hstack((points, las.blue[..., None]))
+
+ # get label
+ points = np.hstack((points, las.label[..., None]))
+ # get treeID
+ points = np.hstack((points, las.treeID[..., None]))
+
+ # put all together to pandas dataframe
+ points = pd.DataFrame(
+ points,
+ columns=['x', 'y', 'z', 'red', 'green', 'blue', 'label', 'treeID']
+ )
+
+ return points
+
+ def process_folder(self):
+
+ """process_folder.
+
+ Args:
+ mode: train, test or validation
+ """
+ # read all las files in the folder data_dir using glob
+ list_of_files = glob.glob(self.data_dir + "/*.las", recursive=False)
+
+ # if self.save_dir does not exist, create it
+ if not os.path.exists(self.save_dir):
+ os.makedirs(self.save_dir)
+
+ # iterate over all files
+ for filepath in tqdm(list_of_files):
+ if self.verbose:
+ print("Processing file: ", filepath)
+ # read the las file
+ points = self.read_single_las(filepath)
+
+ # save the points as text file in self.save_dir
+ filepath = filepath.split("/")[-1].split(".")[0]
+ filepath = self.save_dir + "/" + filepath
+
+ # save the points
+ points.to_csv(filepath + ".txt", sep=',', index=False, header=True)
+
+if __name__ == "__main__":
+ # use argparse to get the data_dir and save_dir
+
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--data_dir', type=str, default='data/stpls3d/val', help='path to the data directory')
+ parser.add_argument('--save_dir', type=str, default='data/stpls3d/val', help='path to the save directory')
+ # get verbose
+ parser.add_argument('--verbose', action='store_true', help='verbose')
+ args = parser.parse_args()
+
+ # create the mapper
+ mapper = Las2TextMapper(args.data_dir, args.save_dir, args.verbose)
+
+ # process the folder
+ mapper.process_folder()
+