Run check lint outside of the container

examples/python/custom_lp.py

@@ -1,10 +1,11 @@
 from pathlib import Path
 
+from omegaconf import OmegaConf
+
 import marius as m
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import LinkPredictionDataset
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

examples/python/custom_nc_graphsage.py

@@ -1,14 +1,15 @@
 from pathlib import Path
 
-import marius as m
 import numpy as np
 import pandas as pd
+from omegaconf import OmegaConf
+
+import marius as m
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import NodeClassificationDataset
 from marius.tools.preprocess.datasets.dataset_helpers import remap_nodes
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

examples/python/fb15k_237.py

@@ -1,8 +1,9 @@
 from pathlib import Path
 
+from omegaconf import OmegaConf
+
 import marius as m
 from marius.tools.preprocess.datasets.fb15k_237 import FB15K237
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

examples/python/fb15k_237_gpu.py

@@ -1,8 +1,9 @@
 from pathlib import Path
 
+from omegaconf import OmegaConf
+
 import marius as m
 from marius.tools.preprocess.datasets.fb15k_237 import FB15K237
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

examples/python/ogbn_arxiv_nc.py

@@ -1,8 +1,9 @@
 from pathlib import Path
 
+from omegaconf import OmegaConf
+
 import marius as m
 from marius.tools.preprocess.datasets.ogbn_arxiv import OGBNArxiv
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

src/cpp/src/data/samplers/neighbor.cpp

@@ -153,7 +153,7 @@ std::tuple<torch::Tensor, torch::Tensor> sample_uniform_cpu(torch::Tensor edges,
 
     if (num_columns == 3) {
 #pragma omp parallel default(none) shared(tid_seeds, local_offsets_accessor, local_offsets, global_offsets_accessor, global_offsets, num_neighbors_accessor, \
-                                          num_neighbors, max_neighbors, sorted_list_ptr, edges, ret_neighbor_id_edges_mem, ret_neighbor_id_edges)
+                                              num_neighbors, max_neighbors, sorted_list_ptr, edges, ret_neighbor_id_edges_mem, ret_neighbor_id_edges)
         {
 #ifdef MARIUS_OMP
             unsigned int seed = tid_seeds[omp_get_thread_num()];
@@ -193,7 +193,7 @@ std::tuple<torch::Tensor, torch::Tensor> sample_uniform_cpu(torch::Tensor edges,
         }
     } else {
 #pragma omp parallel default(none) shared(tid_seeds, local_offsets_accessor, local_offsets, global_offsets_accessor, global_offsets, num_neighbors_accessor, \
-                                          num_neighbors, max_neighbors, sorted_list_ptr, edges, ret_neighbor_id_edges_mem, ret_neighbor_id_edges)
+                                              num_neighbors, max_neighbors, sorted_list_ptr, edges, ret_neighbor_id_edges_mem, ret_neighbor_id_edges)
         {
 #ifdef MARIUS_OMP
             unsigned int seed = tid_seeds[omp_get_thread_num()];

src/python/tools/configuration/marius_config.py

@@ -8,6 +8,8 @@
 from pathlib import Path
 from typing import List
 
+from omegaconf import MISSING, DictConfig, OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.configuration.datatypes import (
     AdagradOptions,
@@ -40,7 +42,6 @@
     validate_dataset_config,
     validate_storage_config,
 )
-from omegaconf import MISSING, DictConfig, OmegaConf
 
 
 def get_model_dir_path(dataset_dir):

src/python/tools/marius_predict.py

@@ -3,9 +3,10 @@
 import pathlib
 from argparse import RawDescriptionHelpFormatter
 
-import marius as m
 import numpy as np
 import pandas as pd
+
+import marius as m
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.prediction.link_prediction import infer_lp
 from marius.tools.prediction.node_classification import infer_nc

src/python/tools/postprocess/in_memory_exporter.py

@@ -3,9 +3,10 @@
 
 import numpy as np
 import pandas as pd
-from marius.tools.configuration.constants import PathConstants
 from omegaconf import OmegaConf
 
+from marius.tools.configuration.constants import PathConstants
+
 import torch  # isort:skip
 
 SUPPORTED_FORMATS = ["CSV", "PARQUET", "BINARY", "BIN"]

src/python/tools/preprocess/converters/partitioners/spark_partitioner.py

@@ -1,10 +1,11 @@
 import math
 
+from pyspark.sql.dataframe import DataFrame
+from pyspark.sql.functions import floor
+
 from marius.tools.preprocess.converters.partitioners.partitioner import Partitioner
 from marius.tools.preprocess.converters.spark_constants import DST_EDGE_BUCKET_COL, INDEX_COL, SRC_EDGE_BUCKET_COL
 from marius.tools.preprocess.utils import get_df_count
-from pyspark.sql.dataframe import DataFrame
-from pyspark.sql.functions import floor
 
 
 def get_partition_size(nodes, num_partitions):

src/python/tools/preprocess/converters/partitioners/torch_partitioner.py

@@ -1,4 +1,5 @@
 import numpy as np
+
 from marius.tools.preprocess.converters.partitioners.partitioner import Partitioner
 
 import torch  # isort:skip

src/python/tools/preprocess/converters/readers/pandas_readers.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 
 import pandas as pd
+
 from marius.tools.preprocess.converters.readers.reader import Reader
 
 

src/python/tools/preprocess/converters/readers/spark_readers.py

@@ -1,9 +1,10 @@
 from pathlib import Path
 
-from marius.tools.preprocess.converters.readers.reader import Reader
 from pyspark.sql import SparkSession
 from pyspark.sql.dataframe import DataFrame
 
+from marius.tools.preprocess.converters.readers.reader import Reader
+
 
 class SparkDelimitedFileReader(Reader):
     def __init__(

src/python/tools/preprocess/converters/spark_converter.py

@@ -2,6 +2,10 @@
 import os
 from pathlib import Path
 
+from pyspark.sql import SparkSession
+from pyspark.sql.functions import col, monotonically_increasing_id, rand, row_number
+from pyspark.sql.window import Window
+
 from marius.tools.preprocess.converters.partitioners.spark_partitioner import SparkPartitioner
 from marius.tools.preprocess.converters.readers.spark_readers import SparkDelimitedFileReader
 from marius.tools.preprocess.converters.spark_constants import (
@@ -17,9 +21,6 @@
     TMP_DATA_DIRECTORY,
 )
 from marius.tools.preprocess.converters.writers.spark_writer import SparkWriter
-from pyspark.sql import SparkSession
-from pyspark.sql.functions import col, monotonically_increasing_id, rand, row_number
-from pyspark.sql.window import Window
 
 SUPPORTED_DELIM_FORMATS = ["CSV", "TSV", "TXT", "DELIM", "DELIMITED"]
 SUPPORTED_NON_DELIM_FILE_FORMATS = ["PARQUET"]

src/python/tools/preprocess/converters/torch_converter.py

@@ -3,6 +3,7 @@
 
 import numpy as np
 import pandas as pd
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.partitioners.torch_partitioner import TorchPartitioner
 from marius.tools.preprocess.converters.readers.pandas_readers import PandasDelimitedFileReader

src/python/tools/preprocess/converters/writers/spark_writer.py

@@ -7,6 +7,8 @@
 
 import numpy as np
 import pandas as pd
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.configuration.marius_config import DatasetConfig
 from marius.tools.preprocess.converters.spark_constants import (
@@ -18,7 +20,6 @@
     TMP_DATA_DIRECTORY,
 )
 from marius.tools.preprocess.utils import get_df_count
-from omegaconf import OmegaConf
 
 
 # TODO can this be made faster? Pandas is pretty slow and not parallel

src/python/tools/preprocess/converters/writers/torch_writer.py

@@ -1,8 +1,9 @@
 from pathlib import Path
 
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.configuration.marius_config import DatasetConfig
-from omegaconf import OmegaConf
 
 
 class TorchWriter(object):

src/python/tools/preprocess/custom.py

@@ -1,9 +1,10 @@
 import importlib
 from pathlib import Path
 
-from marius.tools.preprocess.dataset import LinkPredictionDataset
 from preprocess.converters.torch_converter import TorchEdgeListConverter
 
+from marius.tools.preprocess.dataset import LinkPredictionDataset
+
 pyspark_loader = importlib.find_loader("pyspark")
 pyspark_found = pyspark_loader is not None
 

src/python/tools/preprocess/datasets/ogb_mag240m.py

@@ -2,12 +2,13 @@
 from pathlib import Path
 
 import numpy as np
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import NodeClassificationDataset
 from marius.tools.preprocess.datasets.dataset_helpers import remap_nodes
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

src/python/tools/preprocess/datasets/ogb_wikikg90mv2.py

@@ -1,11 +1,12 @@
 from pathlib import Path
 
 import numpy as np
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import LinkPredictionDataset
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 
 class OGBWikiKG90Mv2(LinkPredictionDataset):

src/python/tools/preprocess/datasets/ogbl_citation2.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 
 import numpy as np
+
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import LinkPredictionDataset
 from marius.tools.preprocess.utils import download_url, extract_file

src/python/tools/preprocess/datasets/ogbl_collab.py

@@ -2,6 +2,7 @@
 
 import numpy as np
 import pandas as pd
+
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import LinkPredictionDataset
 from marius.tools.preprocess.utils import download_url, extract_file

src/python/tools/preprocess/datasets/ogbl_wikikg2.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 
 import numpy as np
+
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import LinkPredictionDataset
 from marius.tools.preprocess.utils import download_url, extract_file

src/python/tools/preprocess/datasets/ogbn_arxiv.py

@@ -1,12 +1,13 @@
 from pathlib import Path
 
 import numpy as np
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import NodeClassificationDataset
 from marius.tools.preprocess.datasets.dataset_helpers import remap_nodes
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 
 class OGBNArxiv(NodeClassificationDataset):

src/python/tools/preprocess/datasets/ogbn_papers100m.py

@@ -1,12 +1,13 @@
 from pathlib import Path
 
 import numpy as np
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import NodeClassificationDataset
 from marius.tools.preprocess.datasets.dataset_helpers import remap_nodes
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 import torch  # isort:skip
 

src/python/tools/preprocess/datasets/ogbn_products.py

@@ -1,12 +1,13 @@
 from pathlib import Path
 
 import numpy as np
+from omegaconf import OmegaConf
+
 from marius.tools.configuration.constants import PathConstants
 from marius.tools.preprocess.converters.torch_converter import TorchEdgeListConverter
 from marius.tools.preprocess.dataset import NodeClassificationDataset
 from marius.tools.preprocess.datasets.dataset_helpers import remap_nodes
 from marius.tools.preprocess.utils import download_url, extract_file
-from omegaconf import OmegaConf
 
 
 class OGBNProducts(NodeClassificationDataset):

test/python/bindings/end_to_end/test_lp_basic.py

@@ -6,9 +6,10 @@
 from test.test_configs.generate_test_configs import generate_configs_for_dataset
 from test.test_data.generate import generate_random_dataset
 
-import marius as m
 import pytest
 
+import marius as m
+
 
 def run_configs(directory, partitioned_eval=False):
     for filename in os.listdir(directory):

test/python/bindings/end_to_end/test_lp_buffer.py

@@ -6,9 +6,10 @@
 from test.test_configs.generate_test_configs import generate_configs_for_dataset
 from test.test_data.generate import generate_random_dataset
 
-import marius as m
 import pytest
 
+import marius as m
+
 
 def run_configs(directory, partitioned_eval=False):
     for filename in os.listdir(directory):

test/python/bindings/end_to_end/test_lp_storage.py

@@ -6,9 +6,10 @@
 from test.test_configs.generate_test_configs import generate_configs_for_dataset
 from test.test_data.generate import generate_random_dataset
 
-import marius as m
 import pytest
 
+import marius as m
+
 
 def run_configs(directory, partitioned_eval=False):
     for filename in os.listdir(directory):

test/python/bindings/end_to_end/test_model_dir.py

@@ -6,9 +6,10 @@
 from test.test_configs.generate_test_configs import generate_configs_for_dataset
 from test.test_data.generate import generate_random_dataset
 
-import marius as m
 import pytest
 
+import marius as m
+
 
 def run_configs(directory, model_dir=None, partitioned_eval=False, sequential_train_nodes=False):
     for filename in os.listdir(directory):

test/python/bindings/end_to_end/test_nc_basic.py

@@ -6,9 +6,10 @@
 from test.test_configs.generate_test_configs import generate_configs_for_dataset
 from test.test_data.generate import generate_random_dataset
 
-import marius as m
 import pytest
 
+import marius as m
+
 
 def run_configs(directory, partitioned_eval=False):
     for filename in os.listdir(directory):