mlwiz 1.0.0__tar.gz

mlwiz-1.0.0/LICENSE

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2024, Federico Errica
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

mlwiz-1.0.0/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.1
+Name: mlwiz
+Version: 1.0.0
+Summary: Machine Learning Research Wizard
+Author-email: Federico Errica <f.errica@protonmail.com>
+Project-URL: Homepage, https://mlwiz.readthedocs.io/en/latest/
+Keywords: machine-learning,deep-learning,experiments,research,evaluation-framework
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: PyYAML>=5.4
+Requires-Dist: tqdm>=4.66.1
+Requires-Dist: Requests>=2.31.0
+Requires-Dist: scikit_learn>=1.3.0
+Requires-Dist: tensorboard>=2.11.0
+Requires-Dist: tqdm>=4.47.0
+Requires-Dist: ray>=2.6.0
+Requires-Dist: torchvision>=0.18.1
+Requires-Dist: torch>=2.3.1
+Requires-Dist: torch-geometric<=2.4.0,>=2.3.0
+
+<p align="center">
+  <img src="https://github.com/diningphil/MLWiz/blob/main/docs/_static/mlwiz-logo.png"  width="300"/>
+</p>
+
+# MLWiz: the Machine Learning Research Wizard 
+[![License](https://img.shields.io/badge/License-BSD_3--Clause-gray.svg)](https://opensource.org/licenses/BSD-3-Clause)
+[![Documentation Status](https://readthedocs.org/projects/mlwiz/badge/?version=latest)](https://mlwiz.readthedocs.io/en/latest/?badge=latest)
+[![Python Package](https://github.com/diningphil/MLWiz/actions/workflows/python-publish.yml/badge.svg)](https://github.com/diningphil/MLWiz/actions/workflows/python-publish.yml)
+[![Downloads](https://static.pepy.tech/personalized-badge/mlwiz?period=total&units=international_system&left_color=grey&right_color=blue&left_text=Downloads)](https://pepy.tech/project/mlwiz)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Interrogate](https://github.com/diningphil/MLWiz/blob/main/.badges/interrogate_badge.svg)](https://interrogate.readthedocs.io/en/latest/)
+[![Coverage](https://github.com/diningphil/MLWiz/blob/main/.badges/coverage_badge.svg)]()
+
+## [Documentation](https://mlwiz.readthedocs.io/en/latest/index.html)
+
+MLWiz is a Python library that fosters machine learning research by reducing the boilerplate code 
+to run reproducible experiments. It provides automatic management of data splitting, loading and common 
+experimental settings. It especially handles both model selection and risk assessment procedures, by trying many different
+configurations in parallel (CPU or GPU). It is a generalized version of [PyDGN](https://github.com/diningphil/PyDGN)
+that can handle different kinds of data and models (vectors, images, time-series, graphs).
+
+## Installation:
+
+Requires at least Python 3.10. Simply run
+    
+    pip install mlwiz
+
+## Quickstart:
+
+#### Build dataset and data splits
+
+    mlwiz-data --config-file examples/DATA_CONFIGS/config_NCI1.yml [--debug]
+
+#### Launch experiments
+
+    mlwiz-exp  --config-file examples/MODEL_CONFIGS/config_SupToyDGN.yml [--debug]
+
+
+#### Stop experiments
+Use ``CTRL-C``, then type ``ray stop --force`` to stop **all** ray processes you have launched.
+
+### Using the Trained Models
+
+It's very easy to load the model from the experiments (see also the [Tutorial](https://mlwiz.readthedocs.io/en/latest/tutorial.html)):
+
+    from mlwiz.evaluation.util import *
+
+    config = retrieve_best_configuration('RESULTS/supervised_grid_search_toy_NCI1/MODEL_ASSESSMENT/OUTER_FOLD_1/MODEL_SELECTION/')
+    splits_filepath = 'examples/DATA_SPLITS/CHEMICAL/NCI1/NCI1_outer10_inner1.splits'
+    device = 'cpu'
+
+    # instantiate dataset
+    dataset = instantiate_dataset_from_config(config)
+
+    # instantiate model
+    model = instantiate_model_from_config(config, dataset, config_type="supervised_config")
+
+    # load model's checkpoint, assuming the best configuration has been loaded
+    checkpoint_location = 'RESULTS/supervised_grid_search_toy_NCI1/MODEL_ASSESSMENT/OUTER_FOLD_1/final_run1/best_checkpoint.pth'
+    load_checkpoint(checkpoint_location, model, device=device)
+
+    # you can now call the forward method of your model
+    y, embeddings = model(dataset[0])

mlwiz-1.0.0/README.md

@@ -0,0 +1,63 @@
+<p align="center">
+  <img src="https://github.com/diningphil/MLWiz/blob/main/docs/_static/mlwiz-logo.png"  width="300"/>
+</p>
+
+# MLWiz: the Machine Learning Research Wizard 
+[![License](https://img.shields.io/badge/License-BSD_3--Clause-gray.svg)](https://opensource.org/licenses/BSD-3-Clause)
+[![Documentation Status](https://readthedocs.org/projects/mlwiz/badge/?version=latest)](https://mlwiz.readthedocs.io/en/latest/?badge=latest)
+[![Python Package](https://github.com/diningphil/MLWiz/actions/workflows/python-publish.yml/badge.svg)](https://github.com/diningphil/MLWiz/actions/workflows/python-publish.yml)
+[![Downloads](https://static.pepy.tech/personalized-badge/mlwiz?period=total&units=international_system&left_color=grey&right_color=blue&left_text=Downloads)](https://pepy.tech/project/mlwiz)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Interrogate](https://github.com/diningphil/MLWiz/blob/main/.badges/interrogate_badge.svg)](https://interrogate.readthedocs.io/en/latest/)
+[![Coverage](https://github.com/diningphil/MLWiz/blob/main/.badges/coverage_badge.svg)]()
+
+## [Documentation](https://mlwiz.readthedocs.io/en/latest/index.html)
+
+MLWiz is a Python library that fosters machine learning research by reducing the boilerplate code 
+to run reproducible experiments. It provides automatic management of data splitting, loading and common 
+experimental settings. It especially handles both model selection and risk assessment procedures, by trying many different
+configurations in parallel (CPU or GPU). It is a generalized version of [PyDGN](https://github.com/diningphil/PyDGN)
+that can handle different kinds of data and models (vectors, images, time-series, graphs).
+
+## Installation:
+
+Requires at least Python 3.10. Simply run
+    
+    pip install mlwiz
+
+## Quickstart:
+
+#### Build dataset and data splits
+
+    mlwiz-data --config-file examples/DATA_CONFIGS/config_NCI1.yml [--debug]
+
+#### Launch experiments
+
+    mlwiz-exp  --config-file examples/MODEL_CONFIGS/config_SupToyDGN.yml [--debug]
+
+
+#### Stop experiments
+Use ``CTRL-C``, then type ``ray stop --force`` to stop **all** ray processes you have launched.
+
+### Using the Trained Models
+
+It's very easy to load the model from the experiments (see also the [Tutorial](https://mlwiz.readthedocs.io/en/latest/tutorial.html)):
+
+    from mlwiz.evaluation.util import *
+
+    config = retrieve_best_configuration('RESULTS/supervised_grid_search_toy_NCI1/MODEL_ASSESSMENT/OUTER_FOLD_1/MODEL_SELECTION/')
+    splits_filepath = 'examples/DATA_SPLITS/CHEMICAL/NCI1/NCI1_outer10_inner1.splits'
+    device = 'cpu'
+
+    # instantiate dataset
+    dataset = instantiate_dataset_from_config(config)
+
+    # instantiate model
+    model = instantiate_model_from_config(config, dataset, config_type="supervised_config")
+
+    # load model's checkpoint, assuming the best configuration has been loaded
+    checkpoint_location = 'RESULTS/supervised_grid_search_toy_NCI1/MODEL_ASSESSMENT/OUTER_FOLD_1/final_run1/best_checkpoint.pth'
+    load_checkpoint(checkpoint_location, model, device=device)
+
+    # you can now call the forward method of your model
+    y, embeddings = model(dataset[0])

mlwiz-1.0.0/mlwiz/build_dataset.py

@@ -0,0 +1,38 @@
+import argparse
+import os
+import sys
+
+import yaml
+
+from mlwiz.data.util import preprocess_data
+from mlwiz.static import CONFIG_FILE_CLI_ARGUMENT, CONFIG_FILE
+
+
+def get_args_dict() -> dict:
+    """
+    Processes CLI arguments (i.e., the config file location) and returns
+    a dictionary.
+
+    Returns:
+        a dictionary with the name of the configuration file in the
+        :obj:`mlwiz.static.CONFIG_FILE` field.
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        CONFIG_FILE_CLI_ARGUMENT,
+        dest=CONFIG_FILE,
+        help="config file to parse the data",
+    )
+    return vars(parser.parse_args())
+
+
+def main():
+    """
+    Launches the data preparation pipeline.
+    """
+    # Necessary to locate dotted paths in projects that use MLWiz
+    sys.path.append(os.getcwd())
+
+    args = get_args_dict()
+    options = yaml.load(open(args[CONFIG_FILE], "r"), Loader=yaml.FullLoader)
+    preprocess_data(options)