blackify

.github/workflows/black_lint_test.yml

@@ -23,7 +23,7 @@ jobs:
       - name: Install spoc, black and pylint
         run: pip install . && pip install black==23.9.1 && pip install pylint==2.15.5
       - name: Run black
-        run: black --check --extend-exclude .
+        run: black --check .
       - name: Run pylint
         run: pylint --fail-under=8 spoc/* tests/test_*.py
       - name: Run tests

spoc/cli.py

@@ -29,7 +29,7 @@ def expand(fragments_path, expanded_contacts_path, n_fragments):
         fragments_path (str): Path to the labelled fragments file.
         expanded_contacts_path (str): Path to the output contacts file.
         n_fragments (int, optional): Number of fragments per read to expand. Defaults to 3.
-    
+
     """
     expander = FragmentExpander(number_fragments=n_fragments)
     file_manager = FileManager()
@@ -49,7 +49,7 @@ def annotate(fragments_path, label_library_path, labelled_fragments_path):
         fragments_path (str): Path to the input fragments file.
         label_library_path (str): Path to the label library file.
         labelled_fragments_path (str): Path to the output labelled fragments file.
-    
+
     """
     file_manager = FileManager()
     label_library = file_manager.load_label_library(label_library_path)
@@ -71,13 +71,13 @@ def bin_contacts(
     same_chromosome,
 ):
     """Script for binning contacts
-    
+
     Args:
         contact_path (str): Path to the input contact file.
         pixel_path (str): Path to the output pixel file.
         bin_size (int, optional): Size of the bins. Defaults to 10000.
         same_chromosome (bool, optional): Only bin contacts on the same chromosome. Defaults to False.
-    
+
     """
     # load data from disk
     file_manager = FileManager(use_dask=True)
@@ -99,7 +99,7 @@ def merge():
 @click.option("-o", "--output", help="output path")
 def merge_contacts(contact_paths, output):
     """Functionality to merge annotated fragments
-    
+
     Args:
         contact_paths (tuple): Paths to the input contact files.
         output (str, optional): Path to the output merged contact file.

spoc/contacts.py

@@ -12,15 +12,15 @@
 
 class Contacts:
     """N-way genomic contacts
-    
+
     Args:
         contact_frame (DataFrame): DataFrame containing the contact data.
         number_fragments (int, optional): Number of fragments. Defaults to None.
         metadata_combi (List[str], optional): List of metadata combinations. Defaults to None.
         label_sorted (bool, optional): Whether the labels are sorted. Defaults to False.
         binary_labels_equal (bool, optional): Whether the binary labels are equal. Defaults to False.
         symmetry_flipped (bool, optional): Whether the symmetry is flipped. Defaults to False.
-    
+
     Attributes:
         contains_metadata (bool): Whether the contact data contains metadata.
         number_fragments (int): Number of fragments.
@@ -107,7 +107,7 @@ def data(self):
     @data.setter
     def data(self, contact_frame):
         """Sets the contact data
-        
+
         Args:
             contact_frame (DataFrame): DataFrame containing the contact data.
         """
@@ -123,7 +123,7 @@ class ContactManipulator:
 
     def merge_contacts(self, merge_list: List[Contacts]) -> Contacts:
         """Merge contacts
-        
+
         Args:
             merge_list (List[Contacts]): List of Contacts objects to merge.
 
@@ -274,7 +274,7 @@ def _flip_labelled_contacts(
 
     def sort_labels(self, contacts: Contacts) -> Contacts:
         """Sorts labels in ascending, alphabetical order
-        
+
         Args:
             contacts (Contacts): Contacts object to sort.
 
@@ -367,7 +367,7 @@ def _generate_binary_label_mapping(
     def equate_binary_labels(self, contacts: Contacts) -> Contacts:
         """
         Equate binary labels.
-        
+
         Binary labels often only carry information about whether
         they happen between the same or different fragments. This
         method equates these labels be replacing all equivalent binary labels with
@@ -423,14 +423,14 @@ def subset_on_metadata(
         self, contacts: Contacts, metadata_combi: List[str]
     ) -> Contacts:
         """Subset contacts based on metadata
-        
+
         Args:
             contacts (Contacts): Contacts object to subset.
             metadata_combi (List[str]): List of metadata combinations to subset on.
 
         Returns:
             Contacts: Subsetted Contacts object.
-        
+
         """
         # check if metadata is present
         assert contacts.contains_metadata, "Contacts do not contain metadata!"
@@ -462,14 +462,14 @@ def flip_symmetric_contacts(
         self, contacts: Contacts, sort_chromosomes: bool = False
     ) -> Contacts:
         """Flips contacts based on inherent symmetry
-        
+
         Args:
             contacts (Contacts): Contacts object to flip symmetric contacts.
             sort_chromosomes (bool, optional): Whether to sort chromosomes. Defaults to False.
 
         Returns:
             Contacts: Contacts object with flipped symmetric contacts.
-        
+
         """
         if contacts.contains_metadata:
             if not contacts.label_sorted:

spoc/dataframe_models.py

@@ -35,7 +35,7 @@
 
 class ContactSchema:
     """Dynamic schema for N-way contacts
-    
+
     Args:
         number_fragments (int, optional): Number of fragments. Defaults to 3.
         contains_metadata (bool, optional): Whether the contact data contains metadata. Defaults to True.
@@ -103,7 +103,7 @@ def _expand_contact_fields(
     def validate_header(self, data_frame: DataFrame) -> None:
         """Validates only header, needed to validate that dask taskgraph can be built before
         evaluation.
-        
+
         Args:
             data_frame (DataFrame): The DataFrame to validate.
         """
@@ -115,7 +115,7 @@ def validate_header(self, data_frame: DataFrame) -> None:
 
     def validate(self, data_frame: DataFrame) -> DataFrame:
         """Validate multiway contact dataframe
-        
+
         Args:
             data_frame (DataFrame): The DataFrame to validate.
         """
@@ -125,7 +125,7 @@ def validate(self, data_frame: DataFrame) -> DataFrame:
 
 class PixelSchema:
     """Dynamic schema for N-way pixels
-    
+
     Args:
         number_fragments (int, optional): Number of fragments. Defaults to 3.
         same_chromosome (bool, optional): Whether the fragments are on the same chromosome. Defaults to True.
@@ -172,7 +172,7 @@ def _expand_contact_fields(self, expansions: Iterable = (1, 2, 3)) -> dict:
     def validate_header(self, data_frame: DataFrame) -> None:
         """Validates only header, needed to validate that dask taskgraph can be built before
         evaluation
-        
+
         Args:
             data_frame (DataFrame): The DataFrame to validate.
         """
@@ -184,9 +184,9 @@ def validate_header(self, data_frame: DataFrame) -> None:
 
     def validate(self, data_frame: DataFrame) -> DataFrame:
         """Validate multiway contact dataframe
-        
+
         Args:
             data_frame (DataFrame): The DataFrame to validate.
-        
+
         """
         return self._schema.validate(data_frame)

spoc/fragments.py

@@ -13,7 +13,7 @@
 
 class Fragments:
     """Genomic fragments that can be labelled or not.
-    
+
     Args:
         fragment_frame (DataFrame): DataFrame containing the fragment data.
     """
@@ -25,7 +25,7 @@ def __init__(self, fragment_frame: DataFrame) -> None:
     @property
     def data(self) -> DataFrame:
         """Returns the underlying dataframe.
-        
+
         Returns:
             DataFrame: Fragment data.
         """
@@ -34,7 +34,7 @@ def data(self) -> DataFrame:
     @property
     def contains_metadata(self) -> bool:
         """Returns whether the dataframe contains metadata.
-        
+
         Returns:
             bool: Whether the fragment data contains metadata.
         """
@@ -43,7 +43,7 @@ def contains_metadata(self) -> bool:
     @property
     def is_dask(self) -> bool:
         """Returns whether the underlying dataframe is dask.
-        
+
         Returns:
             bool: Whether the underlying dataframe is a dask dataframe.
         """
@@ -53,7 +53,7 @@ def is_dask(self) -> bool:
 # TODO: make generic such that label library can hold arbitrary information
 class FragmentAnnotator:
     """Responsible for annotating labels and sister identity of mapped read fragments.
-    
+
     Args:
         label_library (Dict[str, bool]): Dictionary containing the label library.
     """
@@ -93,13 +93,13 @@ def annotate_fragments(self, fragments: Fragments) -> Fragments:
         """Takes fragment dataframe and returns a copy of it with its labelling state in a separate
         column with name `is_labelled`. If drop_uninformative is true, drops fragments that
         are not in label library.
-        
+
         Args:
             fragments (Fragments): Fragments object containing the fragment data.
 
         Returns:
             Fragments: Fragments object with annotated fragment data.
-        
+
         """
         return Fragments(
             fragments.data.assign(is_labelled=self._assign_label_state)
@@ -112,11 +112,11 @@ def annotate_fragments(self, fragments: Fragments) -> Fragments:
 class FragmentExpander:
     """Expands n-way fragments over sequencing reads
     to yield contacts.
-    
+
     Args:
         number_fragments (int): Number of fragments.
         contains_metadata (bool, optional): Whether the fragment data contains metadata. Defaults to True.
-    
+
     """
 
     def __init__(self, number_fragments: int, contains_metadata: bool = True) -> None:
@@ -162,7 +162,7 @@ def _expand_single_read(
 
     def expand(self, fragments: Fragments) -> Contacts:
         """expand contacts n-ways
-        
+
         Args:
             fragments (Fragments): Fragments object containing the fragment data.