fixed pre-commit issues, should run properly now without mypy errors

.pre-commit-config.yaml

@@ -24,27 +24,27 @@ repos:
       - id: requirements-txt-fixer
       - id: trailing-whitespace
 
-#  - repo: https://github.com/pre-commit/mirrors-prettier
-#    rev: "v3.0.3"
-#    hooks:
-#      - id: prettier
-#        types_or: [yaml, markdown, html, css, scss, javascript, json]
-#        args: [--prose-wrap=always]
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v3.0.3"
+    hooks:
+      - id: prettier
+        types_or: [yaml, markdown, html, css, scss, javascript, json]
+        args: [--prose-wrap=always]
 
-  #  - repo: https://github.com/astral-sh/ruff-pre-commit
-  #    rev: "v0.0.287"
-  #    hooks:
-  #      - id: ruff
-  #        args: ["--fix", "--show-fixes"]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.0.287"
+    hooks:
+      - id: ruff
+        args: ["--fix", "--show-fixes"]
 
-  #  - repo: https://github.com/pre-commit/mirrors-mypy
-  #    rev: "v1.5.1"
-  #    hooks:
-  #      - id: mypy
-  #        files: src|tests
-  #        args: []
-  #        additional_dependencies:
-  #          - pytest
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: "v1.7.1"
+    hooks:
+      - id: mypy
+        files: src|tests
+        args: [--ignore-missing-imports]
+        additional_dependencies:
+          - pytest
 
   - repo: https://github.com/shellcheck-py/shellcheck-py
     rev: "v0.9.0.5"

src/caked/base.py

@@ -10,9 +10,9 @@ def __init__(
         self,
         pipeline: str,
         classes: list[str],
-        dataset_size: int,
         save_to_disk: bool,
         training: bool,
+        dataset_size: int | None = None,
     ):
         self.pipeline = pipeline
         self.classes = classes

src/caked/dataloader.py

@@ -4,6 +4,7 @@
 import os
 import random
 import typing
+from pathlib import Path
 
 import mrcfile
 import numpy as np
@@ -23,9 +24,12 @@ def __init__(
         classes: list[str] | None = None,
         pipeline: str = "disk",
     ) -> None:
+        self.dataset_size = dataset_size
+        self.save_to_disk = save_to_disk
+        self.training = training
+        self.pipeline = pipeline
         if classes is None:
             classes = []
-        super().__init__(pipeline, classes, dataset_size, save_to_disk, training)
 
     def load(self, datapath, datatype):
         paths = [f for f in os.listdir(datapath) if "." + datatype in f]
@@ -46,11 +50,11 @@ def load(self, datapath, datatype):
                 raise RuntimeError(msg)
             class_check = np.in1d(ids, self.classes)
             if not np.all(class_check):
+                logging.basicConfig(format="%(message)s", level=logging.INFO)
                 logging.info(
                     "Not all classes in the directory are present in the "
-                    "classes list. Missing classes: {}. They will be ignored.".format(
-                        np.asarray(ids)[~class_check]
-                    )
+                    "classes list. Missing classes: %s. They will be ignored.",
+                    (np.asarray(ids)[~class_check]),
                 )
 
             # subset affinity matrix with only the relevant classes
@@ -103,15 +107,15 @@ def __getitem__(self, item):
         x = self.transformation(data)
 
         # ground truth
-        y = os.path.basename(filename).split("_")[0]
+        y = Path(filename).name.split("_")[0]
 
         return x, y
 
     def read(self, filename):
         if self.datatype == "npy":
             return np.load(filename)
 
-        elif self.datatype == "mrc":
+        if self.datatype == "mrc":
             with mrcfile.open(filename) as f:
                 return np.array(f.data)