fix flake8 linting errors and add lint check in CI

.github/workflows/lint.yml

@@ -0,0 +1,44 @@
+name: Lint Python scripts
+
+on:
+  push:
+    paths:
+      - '**.py'
+  pull_request:
+    paths:
+      - '**.py'
+
+jobs:
+  lint:
+    name: Lint Python scripts
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.11', '3.12']
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        persist-credentials: false
+
+    - uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Cache pip
+      uses: actions/cache@v4
+      id: cache-pip
+      with:
+        path: ~/.cache/pip
+        key: pip_cache_py_${{ matrix.python-version }}_${{ hashFiles('**/pyproject.toml') }}
+
+    - name: Install linters
+      run: |
+        python -m pip install --upgrade pip
+        pip install isort flake8
+
+    - name: Run isort
+      run: isort --check-only --diff .
+
+    - name: Run flake8
+      run: flake8 . --max-line-length=120

examples/tutorials/cbioportal.ipynb

@@ -13,7 +13,7 @@
         "import numpy as np\n",
         "import pandas as pd\n",
         "\n",
-        "STUDY_ID = 'pancan_pcawg_2020'"
+        "STUDY_ID = 'coad_cptac_2019'"
       ]
     },
     {
@@ -37,6 +37,24 @@
         "cbio.get_cbioportal_data(cbio.study_id)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "b08670ec",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Check the specific files the notebook needs are present\n",
+        "required_files = [\"data_cna.txt\", \"data_mutations.txt\", \"data_clinical_sample.txt\"]\n",
+        "missing = [f for f in required_files if not os.path.exists(os.path.join(STUDY_ID, f))]\n",
+        "assert not missing, f\"Missing required files in {STUDY_ID}: {missing}\"\n",
+        "\n",
+        "print(f\"All required files present in ./{STUDY_ID}/:\")\n",
+        "for f in required_files:\n",
+        "    size = os.path.getsize(os.path.join(STUDY_ID, f))\n",
+        "    print(f\"   {f}  ({size:,} bytes)\")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -144,7 +162,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "counts = np.unique(list(data['clin'].CANCER_TYPE), return_counts=True) "
+        "counts = np.unique(list(data['clin'].CANCER_TYPE), return_counts=True)"
       ]
     },
     {
@@ -274,8 +292,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "data_importer = flexynesis.data.DataImporter(path=f'{STUDY_ID}/', \n",
-        "                                       data_types = ['mut', 'cna'], \n",
+        "data_importer = flexynesis.data.DataImporter(path=f'{STUDY_ID}/',\n",
+        "                                       data_types = ['mut', 'cna'],\n",
         "                                        concatenate=False, top_percentile=10, variance_threshold=0.8,\n",
         "                                        min_features=500)\n",
         "train_dataset, test_dataset = data_importer.import_data()"
@@ -324,7 +342,7 @@
   ],
   "metadata": {
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": "flexy",
       "language": "python",
       "name": "python3"
     },
@@ -338,7 +356,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.11.0"
+      "version": "3.14.4"
     }
   },
   "nbformat": 4,

flexynesis/__init__.py

@@ -1,9 +1,10 @@
 # Lazy imports to avoid slow startup
 # Only import essential components that are needed for basic functionality
 
+from importlib.metadata import PackageNotFoundError, version
+
 # Import core modules without heavy dependencies
 from .config import search_spaces
-from importlib.metadata import PackageNotFoundError, version
 
 # Use the distribution name as published on PyPI (may differ from import name in some projects)
 _DISTRIBUTION_NAME = "flexynesis"
@@ -13,72 +14,81 @@
 except PackageNotFoundError:
     # Happens in some dev scenarios before the package is installed
     __version__ = "0+unknown"
-
+
+
 class LazyModule:
     """Lazy module that only imports when accessed."""
-    
+
     def __init__(self, module_name):
         self._module_name = module_name
         self._module = None
         self._import_error = None
-    
+
     def _import_module(self):
         if self._module is None and self._import_error is None:
             try:
                 import importlib
-                self._module = importlib.import_module(f'.{self._module_name}', package=__name__)
+
+                self._module = importlib.import_module(
+                    f".{self._module_name}", package=__name__
+                )
             except ImportError as e:
                 self._import_error = e
-                raise ImportError(f"Failed to import {self._module_name} module: {e}. "
-                               f"This usually means some dependencies are missing. "
-                               f"Try installing required packages or check your environment.")
+                raise ImportError(
+                    f"Failed to import {self._module_name} module: {e}. "
+                    f"This usually means some dependencies are missing. "
+                    f"Try installing required packages or check your environment."
+                )
         elif self._import_error is not None:
             raise self._import_error
         return self._module
-    
+
     def __getattr__(self, name):
         module = self._import_module()
         return getattr(module, name)
-    
+
     def __dir__(self):
         if self._module is None:
             return []
         module = self._import_module()
         return dir(module)
-    
+
     def __repr__(self):
         if self._module is None:
             return f"<LazyModule '{self._module_name}' (not yet imported)>"
         else:
             return f"<LazyModule '{self._module_name}' (imported)>"
 
+
 # Create lazy module proxies - these are NOT imported yet
-modules = LazyModule('modules')
-data = LazyModule('data')
-main = LazyModule('main')
-models = LazyModule('models')
-feature_selection = LazyModule('feature_selection')
-utils = LazyModule('utils')
+modules = LazyModule("modules")
+data = LazyModule("data")
+main = LazyModule("main")
+models = LazyModule("models")
+feature_selection = LazyModule("feature_selection")
+utils = LazyModule("utils")
+
 
 # Import commonly used classes directly for easy access
 # These will be imported lazily when first accessed
 def _get_data_importer():
     """Lazy getter for DataImporter class."""
     return data.DataImporter
 
+
 def _get_models():
     """Lazy getter for model classes."""
     return models
 
+
 # Export all modules and commonly used classes
 __all__ = [
     "search_spaces",
     "modules",
-    "data", 
+    "data",
     "main",
     "models",
     "feature_selection",
     "utils",
-    "DataImporter"
+    "DataImporter",
 ]
-