UCL · matt-graham · Sep 23, 2024 · Sep 23, 2024 · Sep 23, 2024 · Sep 23, 2024
diff --git a/pyproject.toml b/pyproject.toml
@@ -122,6 +122,10 @@ markers = ["group2", "slow"]
 target-version = "py311"
 line-length = 120
 
+[tool.ruff.lint]
+select = ["E", "F", "I", "W"]
+per-file-ignores = {"src/scripts/**" = ["E501", "W"]}
+
 [tool.setuptools.packages.find]
 where = ["src"]
 

diff --git a/src/scripts/hiv/projections_jan2023/analysis_full_model.py b/src/scripts/hiv/projections_jan2023/analysis_full_model.py
@@ -5,7 +5,6 @@
 
 import datetime
 import pickle
-# import random
 from pathlib import Path
 
 from tlo import Date, Simulation, logging

diff --git a/src/scripts/profiling/run_profiling.py b/src/scripts/profiling/run_profiling.py
@@ -298,7 +298,7 @@ def run_profiling(
         print(f"Writing {output_ipysession_file}", end="...", flush=True)
         scale_run_session.save(output_ipysession_file)
         print("done")
-        
+
     if write_flat_html:
         output_html_file = output_dir / f"{output_name}.flat.html"
         console_renderer = ConsoleRenderer(

diff --git a/src/scripts/profiling/scale_run.py b/src/scripts/profiling/scale_run.py
@@ -27,10 +27,10 @@ def save_arguments_to_json(arguments_dict: dict, output_path: Path):
     with open(output_path, "w") as f:
         json.dump(
             {
-                k: str(v) if isinstance(v, Path) else v 
+                k: str(v) if isinstance(v, Path) else v
                 for k, v in arguments_dict.items()
-            }, 
-            f, 
+            },
+            f,
             indent=4
         )
 

diff --git a/src/scripts/task_runner/generate_html.py b/src/scripts/task_runner/generate_html.py
@@ -101,8 +101,8 @@ def get_html_for_commit(commit_dir: Path) -> str:
 <body>
 <h1>$title</h1>
 <p style="font-size: small;">
-    This page was generated on $generated_time. The 
-    <a href="https://github.com/UCL/TLOmodel/actions/workflows/calibration.yaml">calibration workflow</a> runs every 
+    This page was generated on $generated_time. The
+    <a href="https://github.com/UCL/TLOmodel/actions/workflows/calibration.yaml">calibration workflow</a> runs every
     night on the latest new commit on the master branch. <a href="#" id="toggleIncomplete">toggle incomplete</a>
 </p>
 $body

diff --git a/src/tlo/analysis/utils.py b/src/tlo/analysis/utils.py
@@ -89,7 +89,7 @@ def parse_log_file(log_filepath, level: int = logging.INFO):
 
 def merge_log_files(log_path_1: Path, log_path_2: Path, output_path: Path) -> None:
     """Merge two log files, skipping any repeated header lines.
-    
+
     :param log_path_1: Path to first log file to merge. Records from this log file will
         appear first in merged log file.
     :param log_path_2: Path to second log file to merge. Records from this log file will

diff --git a/src/tlo/bitset_handler/bitset_extension.py b/src/tlo/bitset_handler/bitset_extension.py
@@ -46,16 +46,16 @@
 
 class BitsetDtype(ExtensionDtype):
     """
-    A Bitset is represented by a fixed-width string, whose characters are each a uint8.
-    Elements of the set map 1:1 to these characters.
+    A Bitset is represented by a fixed-width string, whose characters are each a uint8. Elements of the set map 1:1 to
+    these characters.
 
-    If the elements set is indexed starting from 0, then:
-    - The quotient of these indices (modulo 8) is the character within the string that contains the bit representing the element,
-    - The remainder (modulo 8) is the index within said character that represents the element itself.
+    If the elements set is indexed starting from 0, then: - The quotient of these indices (modulo 8) is the character
+    within the string that contains the bit representing the element, - The remainder (modulo 8) is the index within
+    said character that represents the element itself.
 
     The element map takes an element of the bitset as a key, and returns a tuple whose first element is the
-    corresponding string-character index, and the latter the uint8 representation of the element within that
-    string character.
+    corresponding string-character index, and the latter the uint8 representation of the element within that string
+    character.
     """
     _element_map: Dict[ElementType, Tuple[int, np.uint8]]
     _elements: Tuple[ElementType]
@@ -71,7 +71,7 @@ def construct_from_string(cls, string: str) -> BitsetDtype:
         """
         Construct an instance of this class by passing in a string of the form
         that str(<instance of this class>) produces.
-        
+
         That is, given a string of the form
         bitset(#elements): e1, e2, e3, ...
 
@@ -101,7 +101,8 @@ def construct_from_string(cls, string: str) -> BitsetDtype:
             iterable_values = tuple(s.strip() for s in string.split(","))
         if n_elements is not None and len(iterable_values) != n_elements:
             raise ValueError(
-                f"Requested bitset with {n_elements} elements, but provided {len(iterable_values)} elements: {iterable_values}"
+                f"Requested bitset with {n_elements} elements, "
+                f"but provided {len(iterable_values)} elements: {iterable_values}"
             )
         return BitsetDtype(s.strip() for s in string.split(","))
 
@@ -351,7 +352,7 @@ def _uint8_view(self) -> NDArray[np.bytes_]:
         Each row ``i`` of this view corresponds to a bitset stored in this array.
         The value at index ``i, j`` in this view is the ``uint8`` that represents
         character ``j`` in ``self._data[i]``, which can have bitwise operations
-        performed on it.  
+        performed on it.
         """
         return self._data.view(self._uint8_view_format)
 
@@ -463,17 +464,17 @@ def __cast_to_uint8(self, other: CastableForPandasOps) -> NDArray[np.uint8]:
 
         Scalar elements:
             Cast to single-element sets, then treated as set.
-        
+
         Sets:
             Are converted to the (array of) uint8s that represents the set.
-        
+
         ``np.ndarray``s of ``np.uint8``
             Are returned if they have the same number of columns as ``self._uint8_view``.
-        
+
         ``np.ndarray``s of ``np.dtype("Sx")``
             If ``x`` corresponds to the same fixed-width as ``self.dtype.np_array_dtype``, are cast
             to the corresponding ``np.uint8`` view, like ``self._uint8_view`` is from ``self._data``.
-        
+
         BitsetArrays
             Return their ``_uint8_view`` attribute.
         """
@@ -508,13 +509,17 @@ def __cast_to_uint8(self, other: CastableForPandasOps) -> NDArray[np.uint8]:
             cast = self.dtype.as_uint8_array(other)
         return cast
 
-    def __comparison_op(self, other: CastableForPandasOps, op: Callable[[Set[ElementType], Set[ElementType]], bool]) -> BooleanArray:
+    def __comparison_op(
+        self,
+        other: CastableForPandasOps,
+        op: Callable[[Set[ElementType], Set[ElementType]], bool],
+    ) -> BooleanArray:
         """
         Abstract method for strict and non-strict comparison operations.
 
         Notably, __eq__ does not redirect here since it is more efficient for us to convert
         the single value to a bytestring and use numpy array comparison.
-        
+
         For the other set comparison methods however, it's easier as a first implementation
         for us to convert to sets and run the set operations.  If there was a Pythonic way
         of doing "bitwise less than" and "bitwise greater than", we could instead take the
@@ -678,7 +683,8 @@ def copy(self) -> BitsetArray:
 
     def isna(self) -> NDArray:
         """
-        TODO: This isn't a great way to express missing data, but equally a bitset doesn't really ever contain missing data...
+        TODO: This isn't a great way to express missing data, but equally a bitset doesn't really ever contain
+        missing data...
         """
         return np.isnan(self._data)
 

diff --git a/src/tlo/core.py b/src/tlo/core.py
@@ -170,7 +170,7 @@ def _default_value(self) -> Any:
         """
         Default value for this property, which will be used to fill the respective columns
         of the population dataframe, for example.
-        
+
         If not explicitly set, it will fall back on the ``PANDAS_TYPE_DEFAULT_TYPE_MAP``.
         If a value is provided, it must:
 
@@ -386,8 +386,8 @@ def initialise_population(self, population: Population) -> None:
 
         Modules that wish to implement this behaviour do not need to implement this method,
         it will be inherited automatically. Modules that wish to perform additional steps
-        during the initialise_population stage should reimplement this method and call 
-        
+        during the initialise_population stage should reimplement this method and call
+
         ```python
         super().initialise_population(population=population)
         ```

diff --git a/src/tlo/logging/helpers.py b/src/tlo/logging/helpers.py
@@ -59,11 +59,11 @@ def get_dataframe_row_as_dict_for_logging(
     columns: Optional[Iterable[str]] = None,
 ) -> dict:
     """Get row of a pandas dataframe in a format suitable for logging.
-    
+
     Retrieves entries for all or a subset of columns for a particular row in a dataframe
     and returns a dict keyed by column name, with values NumPy or pandas extension types
     which should be the same for all rows in dataframe.
-    
+
     :param dataframe: Population properties dataframe to get properties from.
     :param row_label: Unique index label identifying row in dataframe.
     :param columns: Set of column names to extract - if ``None``, the default, all

diff --git a/src/tlo/methods/alri.py b/src/tlo/methods/alri.py
@@ -3040,7 +3040,8 @@ def apply(self, person_id):
 
         assert 'fast_breathing_pneumonia' == \
                self.module.get_imci_classification_based_on_symptoms(
-                   child_is_younger_than_2_months=False, symptoms=self.sim.modules['SymptomManager'].has_what(person_id=person_id)
+                   child_is_younger_than_2_months=False,
+                   symptoms=self.sim.modules['SymptomManager'].has_what(person_id=person_id)
                )
 
 

diff --git a/src/tlo/methods/contraception.py b/src/tlo/methods/contraception.py
@@ -164,7 +164,9 @@ def read_parameters(self, data_folder):
         """Import the relevant sheets from the ResourceFile (excel workbook) and declare values for other parameters
         (CSV ResourceFile).
         """
-        workbook = pd.read_excel(Path(self.resourcefilepath) / 'contraception' / 'ResourceFile_Contraception.xlsx', sheet_name=None)
+        workbook = pd.read_excel(
+            Path(self.resourcefilepath) / 'contraception' / 'ResourceFile_Contraception.xlsx', sheet_name=None
+        )
 
         # Import selected sheets from the workbook as the parameters
         sheet_names = [

diff --git a/src/tlo/methods/demography.py b/src/tlo/methods/demography.py
@@ -134,7 +134,7 @@ def __init__(self, name=None, resourcefilepath=None, equal_allocation_by_distric
         ),
 
         'district_num_of_residence': Property(
-            Types.CATEGORICAL, 
+            Types.CATEGORICAL,
             'The district number in which the person is resident',
             categories=['SET_AT_RUNTIME']
         ),

diff --git a/src/tlo/methods/epilepsy.py b/src/tlo/methods/epilepsy.py
@@ -628,7 +628,9 @@ def __init__(self, module, person_id):
         self.EXPECTED_APPT_FOOTPRINT = self.make_appt_footprint({'Over5OPD': 1})
         self.ACCEPTED_FACILITY_LEVEL = '1b'
 
-        self._MAX_NUMBER_OF_FAILED_ATTEMPTS_BEFORE_DEFAULTING = module.parameters['max_num_of_failed_attempts_before_defaulting']
+        self._MAX_NUMBER_OF_FAILED_ATTEMPTS_BEFORE_DEFAULTING = module.parameters[
+            "max_num_of_failed_attempts_before_defaulting"
+        ]
         self._counter_of_failed_attempts_due_to_unavailable_medicines = 0
 
     def apply(self, person_id, squeeze_factor):
@@ -679,8 +681,10 @@ class HSI_Epilepsy_Follow_Up(HSI_Event, IndividualScopeEventMixin):
     def __init__(self, module, person_id):
         super().__init__(module, person_id=person_id)
 
-        self._MAX_NUMBER_OF_FAILED_ATTEMPTS_BEFORE_DEFAULTING = module.parameters['max_num_of_failed_attempts_before_defaulting']
-        self._DEFAULT_APPT_FOOTPRINT = self.make_appt_footprint({'Over5OPD': 1})
+        self._MAX_NUMBER_OF_FAILED_ATTEMPTS_BEFORE_DEFAULTING = module.parameters[
+            "max_num_of_failed_attempts_before_defaulting"
+        ]
+        self._DEFAULT_APPT_FOOTPRINT = self.make_appt_footprint({"Over5OPD": 1})
         self._REPEATED_APPT_FOOTPRINT = self.make_appt_footprint({'PharmDispensing': 1})
 
         self.TREATMENT_ID = "Epilepsy_Treatment_Followup"