Use ruff instead of other linting tools (#408)

* Use ruff instead of other linting tools

* Make isort compatible with black again, needed for notebooks

* Add return type to default internal fn

* fix mypy errors for MetricCollection + minor ruff errors

* fix ruff errors for evaluate package

* Fix ruff errors for query, utils and models packages

* Remove pylint config from pyproject.toml

* Add --fix arg to ruff check in pre-commit

* Add additional ruff fixes

* Apply ruff fixes again

* Apply ruff fixes on jupyter notebooks

* Ignore names that start with X

* Add max-doc-length setting to ruff pycodestyle check

* Add more fixes

* Update deps

* Add final round of fixes

* Remove pylint disables

---------

Co-authored-by: Franklin <[email protected]>

Author: amrit110

.pre-commit-config.yaml

@@ -20,32 +20,12 @@ repos:
     hooks:
     - id: black
 
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: 'v0.0.286'
     hooks:
-    - id: isort
-
-  - repo: https://github.com/myint/docformatter
-    rev: v1.7.5
-    hooks:
-    - id: docformatter
-      args: [--in-place, --wrap-summaries=88, --wrap-descriptions=88, --blank]
-      files: ".*.py$"
-
-  - repo: local
-    hooks:
-    - id: flake8
-      name: flake8
-      language: python
-      entry: pflake8
-      files: ".*.py$"
-
-  - repo: https://github.com/PyCQA/pydocstyle
-    rev: 6.3.0
-    hooks:
-    - id: pydocstyle
-      args: [--convention=numpy]
-      additional_dependencies: [toml, tomli]
+    - id: ruff
+      args: [--fix, --exit-non-zero-on-fix]
+      types_or: [python, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.5.1
@@ -56,15 +36,6 @@ repos:
       types: [python]
       exclude: "apps|use_cases|tests|cyclops/(process|models|tasks|monitor|report/plot)"
 
-  - repo: local
-    hooks:
-    - id: pylint
-      name: pylint
-      language: python
-      entry: pylint
-      files: ".*.py$"
-      exclude: fsd
-
   - repo: local
     hooks:
     - id: pytest
@@ -74,18 +45,6 @@ repos:
       pass_filenames: false
       always_run: true
 
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.7.0
-    hooks:
-    - id: nbqa-black
-    - id: nbqa-isort
-    - id: nbqa-check-ast
-    - id: nbqa-flake8
-    # ignore E203/W503 to avoid conflict with black:
-    # https://github.com/psf/black/issues/354
-      args: ['--ignore=E203,W503']
-    # - id: nbqa-mypy
-
   - repo: local
     hooks:
     - id: nbstripout

apps/interface/app.py

@@ -44,6 +44,7 @@
     visualizer_page_components,
 )
 
+
 ANALYZE_DATA = None
 
 app = Dash(external_stylesheets=[dbc.themes.UNITED], suppress_callback_exceptions=True)
@@ -170,7 +171,7 @@ def toggle_advanced_options(n_clicks, is_open):
         State(f"{APP_DIAG}-substring", "value"),
     ],
 )
-def run_query(  # pylint: disable=too-many-arguments, too-many-locals, too-many-branches
+def run_query(
     n_clicks: int,
     display_limit: int,
     save_queries_checked: bool,
@@ -274,10 +275,13 @@ def run_query(  # pylint: disable=too-many-arguments, too-many-locals, too-many-
     ],
 )
 def upload_data(
-    local_contents, server_upload_click_timestamp, server_filepath, display_limit
+    local_contents,
+    server_upload_click_timestamp,
+    server_filepath,
+    display_limit,
 ):
     """Upload data and display the relevant information."""
-    global ANALYZE_DATA  # pylint: disable=global-statement
+    global ANALYZE_DATA
 
     if display_limit is None:
         return None, *tuple([None] * 2)
@@ -325,7 +329,7 @@ def upload_data(
 )
 def analyze_column(col_name):
     """Display relevant information given a column name of the data being analyzed."""
-    global ANALYZE_DATA  # pylint: disable=global-statement, W0602
+    global ANALYZE_DATA
 
     if ANALYZE_DATA is None:
         return (None,)
@@ -338,7 +342,8 @@ def analyze_column(col_name):
         ANALYZE_DATA[col_name].value_counts().iloc[:50].to_frame().reset_index()
     )
     value_counts_df = value_counts_df.rename(
-        {"index": "value", col_name: "count"}, axis=1
+        {"index": "value", col_name: "count"},
+        axis=1,
     )
     value_count_components = generate_table_contents(value_counts_df)
     return (value_count_components,)
@@ -354,7 +359,7 @@ def analyze_column(col_name):
 )
 def update_column_plot(col_name):
     """Update column analysis plot."""
-    global ANALYZE_DATA  # pylint: disable=global-statement, W0602
+    global ANALYZE_DATA
 
     return [plot_histogram(ANALYZE_DATA, names=col_name, return_fig=True)]
 

apps/interface/app_query.py

@@ -1,7 +1,5 @@
 """Querying functions used in the query page."""
 
-# pylint: disable=no-member
-
 from typing import Dict
 
 import pandas as pd
@@ -13,6 +11,7 @@
 
 from .consts import APP_DIAG, APP_ENC  # , APP_EVENT
 
+
 db = MIMICIVQuerier()
 
 
@@ -42,7 +41,7 @@ def patient_diagnoses(kwargs):
     return db.patient_diagnoses(**kwargs)
 
 
-def query(  # pylint: disable=too-many-arguments
+def query(
     encounter_checked,
     encounter_kwargs,
     age_min,
@@ -67,7 +66,9 @@ def query(  # pylint: disable=too-many-arguments
         else:
             diagnoses = patient_diagnoses(diagnosis_kwargs).run()
             datas[APP_ENC] = pd.merge(
-                encounters, diagnoses.drop(SUBJECT_ID, axis=1), on=ENCOUNTER_ID
+                encounters,
+                diagnoses.drop(SUBJECT_ID, axis=1),
+                on=ENCOUNTER_ID,
             )
 
     # datas[APP_EVENT] = ...

apps/interface/component_utils.py

@@ -16,7 +16,8 @@ def flatten_2d_tuple(tuple_of_tuples):
 
 
 def generate_table_contents(
-    data: pd.DataFrame, display_limit: Optional[int] = None
+    data: pd.DataFrame,
+    display_limit: Optional[int] = None,
 ) -> List:
     """Generate the table content objects."""
     if display_limit is not None:
@@ -25,8 +26,7 @@ def generate_table_contents(
     columns, values = data.columns, data.astype(str).values
     header = [html.Tr([html.Th(col) for col in columns])]
     rows = [html.Tr([html.Td(cell) for cell in row]) for row in values]
-    table = [html.Thead(header), html.Tbody(rows)]
-    return table
+    return [html.Thead(header), html.Tbody(rows)]
 
 
 def table_result(title, id_):
@@ -70,7 +70,7 @@ def get_dataframe_info(data):
             "Column": data.columns,
             "Non-Null Count": len(data) - data.isnull().sum().values,
             "Dtype": data.dtypes.values,
-        }
+        },
     )
 
 

apps/interface/tabs/analyze_tab.py

@@ -7,6 +7,7 @@
 from ..component_utils import table_result
 from ..consts import APP_PAGE_ANALYZE
 
+
 upload_components = (
     html.Label("Specify filename from results"),
     dmc.Space(h=10),

apps/interface/tabs/query_tab.py

@@ -8,6 +8,7 @@
 from ..component_utils import flatten_2d_tuple, table_result
 from ..consts import APP_DIAG, APP_ENC, APP_EVENT, APP_PAGE_QUERY, TABLE_IDS, TABLES
 
+
 encounter_components = (
     dmc.Checkbox(
         id=f"{APP_ENC}-checkbox",
@@ -30,8 +31,8 @@
                         dcool.TagInput(
                             id=f"{APP_ENC}-sex",
                             placeholder="Specify sexes (Blank = All)",
-                        )
-                    ]
+                        ),
+                    ],
                 ),
                 dmc.Space(h=50),
                 html.Label("Age"),
@@ -49,10 +50,10 @@
                             placeholder="Max (Blank = No max)",
                             min=0,
                         ),
-                    ]
+                    ],
                 ),
                 dmc.Space(h=50),
-            ]
+            ],
         ),
         id=f"{APP_ENC}-collapse",
     ),
@@ -76,8 +77,8 @@
                         dcool.TagInput(
                             id=f"{APP_DIAG}-code",
                             placeholder="Specify codes (Blank = All)",
-                        )
-                    ]
+                        ),
+                    ],
                 ),
                 dmc.Space(h=50),
                 html.Label("Diagnosis substring"),
@@ -87,12 +88,12 @@
                         dcool.TagInput(
                             id=f"{APP_DIAG}-substring",
                             placeholder="Specify substrings (Blank = All)",
-                        )
-                    ]
+                        ),
+                    ],
                 ),
                 dmc.Space(h=50),
                 dmc.Space(h=20),
-            ]
+            ],
         ),
         id=f"{APP_DIAG}-collapse",
     ),

apps/interface/tabs/visualizer_tab.py

@@ -11,6 +11,7 @@
 
 from ..css import CONTENT_STYLE, SIDEBAR_LIST_STYLE, SIDEBAR_STYLE, TEXT_ALIGN_CENTER
 
+
 STATIC = "static"
 TEMPORAL = "temporal"
 
@@ -27,7 +28,7 @@
         "cyclops/use_cases/mimiciv/mortality_decompensation",
         "data/1-cleaned",
         "batch_0017.parquet",
-    )
+    ),
 )
 encounters_events = list(events[ENCOUNTER_ID].unique())[0:80]
 
@@ -169,7 +170,7 @@
             title="Options",
             is_open=False,
         ),
-    ]
+    ],
 )
 
 

cyclops/data/features/medical_image.py

@@ -23,12 +23,11 @@
 
 from cyclops.utils.log import setup_logging
 
+
 # Logging.
 LOGGER = logging.getLogger(__name__)
 setup_logging(print_level="INFO", logger=LOGGER)
 
-# pylint: disable=fixme
-
 
 @dataclass
 class MedicalImage(Image):  # type: ignore
@@ -52,15 +51,16 @@ class MedicalImage(Image):  # type: ignore
         [
             LoadImage(reader=reader, simple_keys=True, dtype=None, image_only=True),
             ToNumpy(),
-        ]
+        ],
     )
     # Automatically constructed
     dtype: ClassVar[str] = "dict"
     pa_type: ClassVar[Any] = pa.struct({"bytes": pa.binary(), "path": pa.string()})
     _type: str = field(default="MedicalImage", init=False, repr=False)
 
     def encode_example(
-        self, value: Union[str, Dict[str, Any], npt.NDArray[Any]]
+        self,
+        value: Union[str, Dict[str, Any], npt.NDArray[Any]],
     ) -> Dict[str, Any]:
         """Encode example into a format for Arrow.
 
@@ -89,7 +89,9 @@ def encode_example(
             if filename is not None and filename != "":
                 output_ext_ = os.path.splitext(filename)[1]
             return _encode_ndarray(
-                value["array"], metadata=metadata_, image_format=output_ext_
+                value["array"],
+                metadata=metadata_,
+                image_format=output_ext_,
             )
         if value.get("path") is not None and os.path.isfile(value["path"]):
             # we set "bytes": None to not duplicate the data
@@ -102,7 +104,7 @@ def encode_example(
 
         raise ValueError(
             "An image sample should have one of 'path' or 'bytes' "
-            f"but they are missing or None in {value}."
+            f"but they are missing or None in {value}.",
         )
 
     def decode_example(
@@ -130,7 +132,7 @@ def decode_example(
         if not self.decode:
             raise RuntimeError(
                 "Decoding is disabled for this feature. "
-                "Please use MedicalImage(decode=True) instead."
+                "Please use MedicalImage(decode=True) instead.",
             )
 
         if token_per_repo_id is None:
@@ -141,7 +143,7 @@ def decode_example(
             if path is None:
                 raise ValueError(
                     "An image should have one of 'path' or 'bytes' but both are "
-                    f"None in {value}."
+                    f"None in {value}.",
                 )
 
             if is_local_path(path):
@@ -170,7 +172,8 @@ def decode_example(
         return {"array": image, "metadata": metadata}
 
     def _read_file_from_bytes(
-        self, buffer: BytesIO
+        self,
+        buffer: BytesIO,
     ) -> Tuple[npt.NDArray[Any], Dict[str, Any]]:
         """Read an image from bytes.
 
@@ -203,8 +206,8 @@ def _encode_ndarray(
 
     Parameters
     ----------
-    array_or_tensor : NdarrayOrTensor
-        Numpy array or torch tensor.
+    array : numpy.ndarray
+        Numpy array to encode.
     metadata : dict, optional, default=None
         Metadata dictionary.
     image_format : str, optional, default=".png"

cyclops/data/loader.py

@@ -18,5 +18,4 @@ def load_nihcxr(path: str) -> Dataset:
         "timestamp",
         pd.date_range(start="1/1/2019", end="12/25/2019", periods=nih_ds.num_rows),
     )
-    nih_ds = nih_ds.cast_column("features", Image(decode=True))
-    return nih_ds
+    return nih_ds.cast_column("features", Image(decode=True))