Add files via upload

info.json

@@ -0,0 +1,55 @@
+{
+"author": "Xinping Song"
+"algorithm": "RF-SCM/Magpie v1.0"
+"algorithm_long": 
+"bibtex_refs": ['@article{Dunn2020,\n'
+ '  doi = {10.1038/s41524-020-00406-3},\n'
+ '  url = {https://doi.org/10.1038/s41524-020-00406-3},\n'
+ '  year = {2020},\n'
+ '  month = sep,\n'
+ '  publisher = {Springer Science and Business Media {LLC}},\n'
+ '  volume = {6},\n'
+ '  number = {1},\n'
+ '  author = {Alexander Dunn and Qi Wang and Alex Ganose and Daniel Dopp and '
+ 'Anubhav Jain},\n'
+ '  title = {Benchmarking materials property prediction methods: the Matbench '
+ 'test set and Automatminer reference algorithm},\n'
+ '  journal = {npj Computational Materials}\n'
+ '}',
+ '@article{Breiman2001,\n'
+ '  doi = {10.1023/a:1010933404324},\n'
+ '  url = {https://doi.org/10.1023/a:1010933404324},\n'
+ '  year = {2001},\n'
+ '  publisher = {Springer Science and Business Media {LLC}},\n'
+ '  volume = {45},\n'
+ '  number = {1},\n'
+ '  pages = {5--32},\n'
+ '  author = {Leo Breiman},\n'
+ '  journal = {Machine Learning}\n'
+ '}',
+ '@article{Ward2016,\n'
+ '  doi = {10.1038/npjcompumats.2016.28},\n'
+ '  url = {https://doi.org/10.1038/npjcompumats.2016.28},\n'
+ '  year = {2016},\n'
+ '  month = aug,\n'
+ '  publisher = {Springer Science and Business Media {LLC}},\n'
+ '  volume = {2},\n'
+ '  number = {1},\n'
+ '  author = {Logan Ward and Ankit Agrawal and Alok Choudhary and Christopher '
+ 'Wolverton},\n'
+ '  title = {A general-purpose machine learning framework for predicting '
+ 'properties of inorganic materials},\n'
+ '  journal = {npj Computational Materials}\n'
+ '}',
+ '@article {QUA:QUA24917,author = {Faber, Felix and Lindmaa, Alexander and von '
+ 'Lilienfeld, O. Anatole and Armiento, Rickard},title = {Crystal structure '
+ 'representations for machine learning models of formation energies},journal = '
+ '{International Journal of Quantum Chemistry},volume = {115},number = '
+ '{16},issn = {1097-461X},url = {http://dx.doi.org/10.1002/qua.24917},doi = '
+ '{10.1002/qua.24917},pages = {1094--1101},keywords = {machine learning, '
+ 'formation energies, representations, crystal structure, periodic '
+ 'systems},year = {2015},}']
+"notes":
+"requirements":{"python": ["scikit-learn==0.23.2", "numpy==1.22.4", "matbench==0.6.0"]}
+
+}

my_python_file.py.py

@@ -0,0 +1,66 @@
+"""
+Code for training and recording the matbench_v0.1 random forest benchmark.
+
+The ML pipeline is placed within the Automatminer pipeline code infrastructure for convenience.
+
+All training and inference was done on a single 128-core HPC node.
+
+Reduce the number of jobs n_jobs for less memory usage on consumer machines.
+"""
+
+if __name__ == '__main__':
+    from automatminer import MatPipe
+    from automatminer.automl.adaptors import SinglePipelineAdaptor, TPOTAdaptor
+    from automatminer.featurization import AutoFeaturizer
+    from automatminer.preprocessing import DataCleaner, FeatureReducer
+    from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
+
+    from matbench.bench import MatbenchBenchmark
+    from multiprocessing import set_start_method
+
+    set_start_method("spawn", force=True)
+
+    # The learner is a single 500-estimator Random Forest model
+    learner = SinglePipelineAdaptor(
+                    regressor=RandomForestRegressor(n_estimators=500),
+                    classifier=RandomForestClassifier(n_estimators=500),
+                )
+    pipe_config = {
+                "learner": learner,
+                "reducer": FeatureReducer(reducers=[]),
+                "cleaner": DataCleaner(feature_na_method="mean", max_na_frac=0.01, na_method_fit="drop", na_method_transform="mean"),
+                "autofeaturizer": AutoFeaturizer(n_jobs=8, preset="debug"),
+            }
+
+    pipe = MatPipe(**pipe_config)
+
+    mb = MatbenchBenchmark(autoload=False)
+
+    i = 0
+
+    #for task in mb.tasks:
+    task = mb.matbench_jdft2d
+    print(task)
+    task.load()
+    for fold in task.folds:
+
+        df_train = task.get_train_and_val_data(fold, as_type="df")
+
+        # Fit the RF with matpipe
+        pipe.fit(df_train, task.metadata.target)
+
+        df_test = task.get_test_data(fold, include_target=False, as_type="df")
+        predictions = pipe.predict(df_test)[f"{task.metadata.target} predicted"]
+
+        # A single configuration is used
+        params = {'note': 'single config; see benchmark user metadata'}
+
+        task.record(fold, predictions, params=params)
+
+    mb.to_file("results_" + str(i) + ".json.gz")
+    i += 1
+
+    # Save your results
+    mb.to_file("results.json.gz")
+
+