Merge pull request #260 from basf/lss_fix

Lss fix

Author: mkumar73

.gitignore

@@ -0,0 +1,176 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+.DS_Store
+
+dist/
+
+# pkl files
+*.pkl
+
+# logs and checkpoints
+examples/lightning_logs
+*.ckpt
+
+docs/_build/doctrees/*
+docs/_build/html/*
+
+
+dev/*

README.md

@@ -120,8 +120,11 @@ pip install mamba-ssm
 
 <h2> Preprocessing </h2>
 
-Mambular simplifies data preprocessing with a range of tools designed for easy transformation of tabular data.
-Specify a default method, or a dictionary defining individual preprocessing methods for each feature.
+Mambular uses pretab preprocessing: https://github.com/OpenTabular/PreTab
+
+Hence, datatypes etc. are detected automatically and all preprocessing methods from pretab as well as from Sklearn.preprocessing are available.
+Additionally, you can specify that each feature is preprocessed differently, according to your requirements, by setting the `feature_preprocessing={}`argument during model initialization.
+For an overview over all available methods: [pretab](https://github.com/OpenTabular/PreTab)
 
 <h3> Data Type Detection and Transformation </h3>
 

docs/api/preprocessing/Preprocessor.rst

@@ -17,5 +17,5 @@
 
 # The following line *must* be the last in the module, exactly as formatted:
 
-__version__ = "1.4.0"
+__version__ = "1.5.0"
 

docs/api/preprocessing/index.rst

@@ -14,7 +14,7 @@
 
 from ...base_models.utils.lightning_wrapper import TaskModel
 from ...data_utils.datamodule import MambularDataModule
-from ...preprocessing import Preprocessor
+from pretab.preprocessor import Preprocessor
 
 from ...utils.distributional_metrics import (
     beta_brier_score,
@@ -245,8 +245,11 @@ def build_model(
             num_classes=self.family.param_count,
             family=self.family,
             config=self.config,
-            cat_feature_info=self.data_module.cat_feature_info,
-            num_feature_info=self.data_module.num_feature_info,
+            feature_information=(
+                self.data_module.num_feature_info,
+                self.data_module.cat_feature_info,
+                self.data_module.embedding_feature_info,
+            ),
             lr=lr if lr is not None else self.config.lr,
             lr_patience=(
                 lr_patience if lr_patience is not None else self.config.lr_patience
@@ -454,11 +457,13 @@ def fit(
         )
         self.trainer.fit(self.task_model, self.data_module)  # type: ignore
 
-        best_model_path = checkpoint_callback.best_model_path
-        if best_model_path:
-            checkpoint = torch.load(best_model_path)
+        self.best_model_path = checkpoint_callback.best_model_path
+        if self.best_model_path:
+            torch.serialization.add_safe_globals([type(self.config)])
+            checkpoint = torch.load(self.best_model_path, weights_only=False)
             self.task_model.load_state_dict(checkpoint["state_dict"])  # type: ignore
 
+        self.is_fitted_ = True
         return self
 
     def predict(self, X, raw=False, device=None):

mamba_tabular_summary.pdf

@@ -12,7 +12,7 @@
 
 from ...base_models.utils.lightning_wrapper import TaskModel
 from ...data_utils.datamodule import MambularDataModule
-from ...preprocessing import Preprocessor
+from pretab.preprocessor import Preprocessor
 from ...utils.config_mapper import (
     activation_mapper,
     get_search_space,