formatting and import optimizations

scarf/__init__.py

@@ -33,6 +33,7 @@
 """
 
 import warnings
+
 from dask.array import PerformanceWarning
 from importlib_metadata import version
 

scarf/ann.py

@@ -1,12 +1,12 @@
 from typing import Optional
+
+import dask.array as da
 import numpy as np
 import pandas as pd
-import dask.array as da
-
 from threadpoolctl import threadpool_limits
-from .utils import controlled_compute, logger, tqdmbar
-from .harmony import run_harmony
 
+from .harmony import run_harmony
+from .utils import controlled_compute, logger, tqdmbar
 
 __all__ = ["AnnStream", "instantiate_knn_index", "fix_knn_query"]
 

scarf/assay.py

@@ -9,14 +9,15 @@
                 method for feature selection.
 """
 
-
 from typing import Tuple, List, Generator, Optional, Union
+
 import numpy as np
+import pandas as pd
 from dask.array.core import Array as daskArrayType
 from dask.array.core import from_zarr
-from zarr import hierarchy as z_hierarchy
 from scipy.sparse import csr_matrix, vstack
-import pandas as pd
+from zarr import hierarchy as z_hierarchy
+
 from .metadata import MetaData
 from .utils import show_dask_progress, controlled_compute, logger
 

scarf/bio_data.py

@@ -2,6 +2,7 @@
 
 g. cell cycle genes).
 """
+
 from typing import List
 
 __all__ = ["s_phase_genes", "g2m_phase_genes"]

scarf/datastore/base_datastore.py

@@ -1,10 +1,12 @@
 from typing import List, Union, Optional
+
 import numpy as np
 import zarr
 from loguru import logger
-from ..utils import show_dask_progress, controlled_compute, load_zarr, ZARRLOC
+
 from ..assay import RNAassay, ATACassay, ADTassay, Assay
 from ..metadata import MetaData
+from ..utils import show_dask_progress, controlled_compute, load_zarr, ZARRLOC
 
 
 def sanitize_hierarchy(

scarf/datastore/datastore.py

@@ -1,13 +1,15 @@
 from typing import Iterable, Optional, Union, List, Literal, Tuple
+
 import numpy as np
 import pandas as pd
 from dask import array as daskarr
 from loguru import logger
+
 from .mapping_datastore import MappingDatastore
-from ..writers import create_zarr_obj_array, create_zarr_dataset
-from ..utils import tqdmbar, controlled_compute, ZARRLOC
 from ..assay import RNAassay, ATACassay
 from ..feat_utils import hto_demux
+from ..utils import tqdmbar, controlled_compute, ZARRLOC
+from ..writers import create_zarr_obj_array, create_zarr_dataset
 
 __all__ = ["DataStore"]
 

scarf/datastore/graph_datastore.py

@@ -1,13 +1,15 @@
-from typing import Tuple, Optional, Union, List, Callable
 import os
+from typing import Tuple, Optional, Union, List, Callable
+
 import numpy as np
 import pandas as pd
+from dask.array import from_zarr  # type: ignore
 from loguru import logger
 from scipy.sparse import csr_matrix, coo_matrix
-from dask.array import from_zarr  # type: ignore
+
 from .base_datastore import BaseDataStore
-from ..utils import clean_array, show_dask_progress, system_call, tqdmbar
 from ..assay import Assay
+from ..utils import clean_array, show_dask_progress, system_call, tqdmbar
 from ..writers import create_zarr_dataset
 
 

scarf/datastore/mapping_datastore.py

@@ -1,20 +1,22 @@
-from typing import Generator, Tuple, List, Dict, Union, Callable, Optional
 import os
+from typing import Generator, Tuple, List, Dict, Union, Callable, Optional
+
 import numpy as np
 import pandas as pd
 from dask import array as daskarr
 from loguru import logger
 from scipy.sparse import csr_matrix
+
 from .graph_datastore import GraphDataStore
 from ..assay import Assay, RNAassay
-from ..writers import create_zarr_dataset
 from ..utils import (
     show_dask_progress,
     clean_array,
     tqdmbar,
     controlled_compute,
     system_call,
 )
+from ..writers import create_zarr_dataset
 
 
 class MappingDatastore(GraphDataStore):

scarf/dendrogram.py

@@ -1,6 +1,8 @@
-import numpy as np
 from typing import List, Dict
+
 import networkx as nx
+import numpy as np
+
 from .utils import logger, tqdmbar
 
 __all__ = ["BalancedCut", "CoalesceTree", "make_digraph"]

scarf/downloader.py

@@ -10,12 +10,14 @@
     - fetch_dataset: Downloads datasets from online repositories and saves them in as-is format
 """
 
+import io
 import os
 import tarfile
-import pandas as pd
-import io
 import time
 from json import JSONDecodeError
+
+import pandas as pd
+
 from .utils import logger, tqdmbar
 
 __all__ = ["show_available_datasets", "fetch_dataset"]

scarf/feat_utils.py

@@ -1,8 +1,10 @@
 """Utility functions for features."""
-import pandas as pd
-import numpy as np
+
 from typing import List, Tuple
 
+import numpy as np
+import pandas as pd
+
 __all__ = ["fit_lowess", "binned_sampling", "hto_demux"]
 
 

scarf/harmony.py

@@ -1,7 +1,9 @@
 from functools import partial
-import pandas as pd
+
 import numpy as np
+import pandas as pd
 from sklearn.cluster import KMeans
+
 from .utils import tqdmbar, logger
 
 

scarf/knn_utils.py

@@ -1,13 +1,15 @@
 """Utility functions for running the KNN algorithm."""
+
 from typing import List, Tuple
+
 import numpy as np
 import pandas as pd
-from scipy.sparse import csr_matrix, coo_matrix
 from numba import jit
-from .writers import create_zarr_dataset
+from scipy.sparse import csr_matrix, coo_matrix
+
 from .ann import AnnStream
 from .utils import tqdmbar, controlled_compute
-
+from .writers import create_zarr_dataset
 
 __all__ = [
     "self_query_knn",

scarf/mapping_utils.py

@@ -1,10 +1,13 @@
 """Utility functions for the mapping."""
+
+from typing import Tuple
+
 import dask.array as daskarr
 import numpy as np
-from typing import Tuple
+import pandas as pd
+
 from .assay import Assay
 from .utils import controlled_compute, show_dask_progress, logger, tqdmbar
-import pandas as pd
 
 __all__ = ["align_features", "coral"]
 

scarf/markers.py

@@ -1,13 +1,16 @@
 """Module to find biomarkers."""
-from scarf.assay import Assay
-from scarf.utils import logger, tqdmbar
-from numba import jit
+
+from typing import Optional
+
 import numpy as np
 import pandas as pd
+from numba import jit
 from scipy.stats import linregress
-from typing import Optional
 from scipy.stats import rankdata
 
+from scarf.assay import Assay
+from scarf.utils import logger, tqdmbar
+
 
 def read_prenormed_batches(store, cell_idx: np.ndarray, batch_size: int, desc: str):
     batch = {}

scarf/meld_assay.py

@@ -10,17 +10,18 @@
     - coordinate_melding:
 """
 
+import gzip
 import logging
 from typing import Tuple, List, Union
-import pandas as pd
+
 import numpy as np
-import gzip
+import pandas as pd
 from numba import jit
-from zarr import hierarchy
 from scipy.sparse import coo_matrix
-from .writers import create_zarr_count_assay
-from .utils import controlled_compute, logger, tqdmbar
+from zarr import hierarchy
 
+from .utils import controlled_compute, logger, tqdmbar
+from .writers import create_zarr_count_assay
 
 __all__ = ["GffReader", "coordinate_melding"]
 

scarf/metadata.py

@@ -3,12 +3,14 @@
 
 import re
 from typing import List, Iterable, Any, Dict, Tuple, Optional, Union
+
 import numpy as np
-from zarr import hierarchy as z_hierarchy
 import pandas as pd
+from zarr import hierarchy as z_hierarchy
+
 from .feat_utils import fit_lowess
-from .writers import create_zarr_obj_array
 from .utils import logger
+from .writers import create_zarr_obj_array
 
 zarrGroup = z_hierarchy.Group
 

scarf/plots.py

@@ -1,11 +1,14 @@
 """Contains the code for plotting in Scarf."""
-import matplotlib.pyplot as plt
+
+from typing import Tuple, Optional, Union, List
+
 import matplotlib as mpl
-import seaborn as sns
+import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-from typing import Tuple, Optional, Union, List
+import seaborn as sns
 from cmocean import cm
+
 from .utils import logger
 
 plt.rcParams["svg.fonttype"] = "none"
@@ -1258,7 +1261,6 @@ def plot_annotated_heatmap(
     save_dpi: int = 300,
     show_fig: bool = True,
 ):
-    import matplotlib.gridspec as gridspec
     import matplotlib.ticker as mticker
 
     if display_row_labels is None:

scarf/readers.py

@@ -9,14 +9,16 @@
     - LoomReader: A class to read in data in the form of a Loom file.
 """
 
+import os
 from abc import ABC, abstractmethod
 from typing import Generator, Dict, List, Optional, Tuple
+from typing import IO
+
+import h5py
 import numpy as np
 import pandas as pd
-import os
 from scipy.sparse import coo_matrix
-from typing import IO
-import h5py
+
 from .utils import logger, tqdmbar
 
 __all__ = [

scarf/tests/__init__.py

@@ -1,6 +1,7 @@
 import os
 import shutil
 import sys
+
 from ..utils import logger
 
 logger.remove()

scarf/tests/conftest.py

@@ -1,3 +1 @@
-from .fixtures_downloader import *
-from .fixtures_readers import *
-from .fixtures_datastore import *
+

scarf/tests/fixtures_datastore.py

@@ -1,7 +1,8 @@
-import pytest
-from . import full_path, remove
 import numpy as np
 import pandas as pd
+import pytest
+
+from . import full_path, remove
 
 
 @pytest.fixture(scope="session")

scarf/tests/fixtures_downloader.py

@@ -1,4 +1,5 @@
 import pytest
+
 from . import full_path, remove
 
 

scarf/tests/fixtures_readers.py

@@ -1,4 +1,5 @@
 import pytest
+
 from . import full_path, remove
 
 

scarf/tests/test_datastore.py

@@ -1,5 +1,6 @@
-import pandas as pd
 import numpy as np
+import pandas as pd
+
 from . import full_path, remove
 
 
@@ -174,9 +175,7 @@ def test_run_pseudotime_marker_search(self, pseudotime_markers):
             full_path("pseudotime_markers_r_values.csv"), index_col=0
         )
         assert np.all(precalc_markers.index == pseudotime_markers.index)
-        assert np.all(
-            precalc_markers.names.values == pseudotime_markers.names.values
-        )
+        assert np.all(precalc_markers.names.values == pseudotime_markers.names.values)
         assert np.allclose(
             precalc_markers.I__RNA_pseudotime__r.values,
             pseudotime_markers.I__RNA_pseudotime__r.values,

scarf/tests/test_metadata.py

@@ -1,5 +1,6 @@
-import pytest
 import numpy as np
+import pytest
+
 from . import full_path, remove
 
 

scarf/tests/test_writers.py

@@ -1,6 +1,7 @@
-from . import full_path, remove
 import numpy as np
 
+from . import full_path, remove
+
 
 def test_crtozarr(crh5_reader):
     from ..writers import CrToZarr