Lint

Author: keller-mark

tests/create_xenium_filtered_points.py

@@ -17,10 +17,10 @@
     if not isfile(zip_filepath):
         os.makedirs(data_dir, exist_ok=True)
         urlretrieve('https://s3.embl.de/spatialdata/spatialdata-sandbox/xenium_rep1_io.zip', zip_filepath)
-    with zipfile.ZipFile(zip_filepath,"r") as zip_ref:
+    with zipfile.ZipFile(zip_filepath, "r") as zip_ref:
         zip_ref.extractall(data_dir)
         os.rename(join(data_dir, "data.zarr"), spatialdata_filepath)
-        
+
         # This Xenium dataset has an AnnData "raw" element.
         # Reference: https://github.com/giovp/spatialdata-sandbox/issues/55
         raw_dir = join(spatialdata_filepath, "tables", "table", "raw")
@@ -32,17 +32,20 @@
 ddf = sdata.points["transcripts"]
 
 # 2. Define a function to take every 100th row from a partition
+
+
 def select_every_200th(partition):
     # Each 'partition' is a Pandas DataFrame
     # .iloc[::100] is the efficient pandas way to get every 100th row
     return partition.iloc[::200]
 
+
 # 3. Apply this function to every partition in the Dask DataFrame
 result = ddf.map_partitions(select_every_200th)
 
 # 4. Compute the result to see it
 filtered_ddf = result[["x", "y", "z", "feature_name", "cell_id"]]
 
-small_sdata = SpatialData(points={ "transcripts": filtered_ddf })
+small_sdata = SpatialData(points={"transcripts": filtered_ddf})
 
-small_sdata.write("xenium_rep1_io.points_only.spatialdata.zarr", overwrite=True)
+small_sdata.write("xenium_rep1_io.points_only.spatialdata.zarr", overwrite=True)

tests/test_sdata_points_zorder.py

@@ -15,11 +15,14 @@
     MORTON_CODE_VALUE_MAX,
 )
 
+
 def is_sorted(l):
     return all(l[i] <= l[i + 1] for i in range(len(l) - 1))
 
+
 data_path = Path('tests/data')
 
+
 @pytest.fixture
 def sdata_with_points():
     sdata = read_zarr(data_path / "xenium_rep1_io.points_only.spatialdata.zarr")
@@ -59,7 +62,7 @@ def test_zorder_query(sdata_with_points):
     sdata_morton_sort_points(sdata, "transcripts")
 
     # Query a rectangle that should return some points
-    orig_rect = [[50.0, 50.0], [100.0, 150.0]] # x0, y0, x1, y1
+    orig_rect = [[50.0, 50.0], [100.0, 150.0]]  # x0, y0, x1, y1
     matching_row_ranges, rows_checked = sdata_morton_query_rect_debug(sdata, "transcripts", orig_rect)
     rect_row_indices = row_ranges_to_row_indices(matching_row_ranges)
 
@@ -98,7 +101,7 @@ def test_zorder_query(sdata_with_points):
 
     # Check that the number of rows checked is less than the total number of points
     assert len(rows_checked) <= 19858
-    assert len(matching_row_ranges) == 2 # Kind of an implementation detail.
+    assert len(matching_row_ranges) == 2  # Kind of an implementation detail.
 
     # Do a second check, this time against x_uint/y_uint (the normalized coordinates)
     # TODO: does this ensure that estimated == exact?
@@ -130,9 +133,9 @@ def test_zorder_query(sdata_with_points):
 
     assert len(exact_row_indices_norm) == 4
     assert len(estimated_row_indices) <= 4
-    
+
     # ========= Another query ==========
-    orig_rect = [[500.0, 500.0], [600.0, 600.0]] # x0, y0, x1, y1
+    orig_rect = [[500.0, 500.0], [600.0, 600.0]]  # x0, y0, x1, y1
 
     # Query using z-order
     matching_row_ranges, rows_checked = sdata_morton_query_rect_debug(sdata, "transcripts", orig_rect)
@@ -159,7 +162,7 @@ def test_zorder_query(sdata_with_points):
 
     # Check that the number of rows checked is less than the total number of points
     assert len(rows_checked) <= 71675
-    assert len(matching_row_ranges) == 13 # Kind of an implementation detail.
+    assert len(matching_row_ranges) == 13  # Kind of an implementation detail.
 
     # Do the same query the "dumb" way, by checking all points
     in_rect = (
@@ -197,5 +200,3 @@ def test_zorder_query(sdata_with_points):
     # Check that the estimated rows contain all of the exact rows.
     assert len(exact_row_indices_norm) == 91
     assert len(estimated_row_indices) <= 95
-    
-