From 5230fd58d1ace765886ed8c59a396e314373e551 Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Wed, 13 May 2020 12:12:05 -0700
Subject: [PATCH 1/7] rm individual pmg requirement and put all pmg requirement
 onto matminer

---
 requirements.txt | 1 -
 1 file changed, 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 8bf88cb5..b6ef2635 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,5 @@
 # Direct requirements of this project alone
 matminer==0.6.2
-pymatgen==2020.01.28
 xgboost==0.80
 tpot==0.11.0
 skrebate==0.6

From c2a6ae4ed2d6e6ba26fcc11c61ba274fa105ce7b Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Tue, 7 Jul 2020 17:01:40 -0700
Subject: [PATCH 2/7] fix automatminer_dev matbench files

---
 automatminer_dev/matbench/expt_gap.py      | 4 ++++
 automatminer_dev/matbench/expt_is_metal.py | 4 ++++
 automatminer_dev/matbench/steels.py        | 2 ++
 3 files changed, 10 insertions(+)

diff --git a/automatminer_dev/matbench/expt_gap.py b/automatminer_dev/matbench/expt_gap.py
index 9c79b767..c2907651 100644
--- a/automatminer_dev/matbench/expt_gap.py
+++ b/automatminer_dev/matbench/expt_gap.py
@@ -73,6 +73,10 @@
 df_new = df_new.reset_index(drop=True)
 
 
+# you need to manually change GaAs0.1P0.9G1128 to its correct composition, which
+# is GaAs0.1P0.9 from Solid Solutions in Semiconducting Systems.Handbook,
+# M., Nauka 1978, 200 p. and was gathered from http://bg.imet-db.ru
+
 store_dataframe_as_json(df_new, "expt_gap.json.gz", compression="gz")
 
 print(df_new)
diff --git a/automatminer_dev/matbench/expt_is_metal.py b/automatminer_dev/matbench/expt_is_metal.py
index 5cafe935..a33c802c 100644
--- a/automatminer_dev/matbench/expt_is_metal.py
+++ b/automatminer_dev/matbench/expt_is_metal.py
@@ -74,6 +74,10 @@
 
 df_new["is_metal"] = df_new["is_metal"] == 1
 
+# you need to manually change GaAs0.1P0.9G1128 to its correct composition, which
+# is GaAs0.1P0.9 from Solid Solutions in Semiconducting Systems.Handbook,
+# M., Nauka 1978, 200 p. and was gathered from http://bg.imet-db.ru
+
 store_dataframe_as_json(df_new, "expt_is_metal.json.gz", compression="gz")
 
 print(df_new)
diff --git a/automatminer_dev/matbench/steels.py b/automatminer_dev/matbench/steels.py
index bc0233cb..71a10114 100644
--- a/automatminer_dev/matbench/steels.py
+++ b/automatminer_dev/matbench/steels.py
@@ -8,6 +8,8 @@
 from matminer.datasets.dataset_retrieval import load_dataset
 
 
+
+# Note the units are in MPa, NOT GPa
 if __name__ == "__main__":
     df = load_dataset("steel_strength")
     df = df[["formula", "yield strength"]]

From 20723109cabc1ad7a03b2ff613ca876596b4e966 Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Tue, 7 Jul 2020 18:36:26 -0700
Subject: [PATCH 3/7] update docs

---
 docs/_sources/datasets.rst.txt       | 2 +-
 docs/automatminer.preprocessing.html | 2 +-
 docs/datasets.html                   | 2 +-
 docs/searchindex.js                  | 2 +-
 docs/source/datasets.rst             | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/_sources/datasets.rst.txt b/docs/_sources/datasets.rst.txt
index 6f52dcd9..c74ec98a 100644
--- a/docs/_sources/datasets.rst.txt
+++ b/docs/_sources/datasets.rst.txt
@@ -131,7 +131,7 @@ procedures, etc.) on a dataset with :code:`matminer.datasets.get_all_dataset_inf
     Description: Matbench v0.1 dataset for predicting steel yield strengths from chemical composition alone. Retrieved from Citrine informatics. Deduplicated.
     Columns:
         composition: Chemical formula.
-        yield strength: Target variable. Experimentally measured steel yield strengths, in GPa.
+        yield strength: Target variable. Experimentally measured steel yield strengths, in MPa.
     Num Entries: 312
     Reference: https://citrination.com/datasets/153092/
     Bibtex citations: ['@misc{Citrine Informatics,\ntitle = {Mechanical properties of some steels},\nhowpublished = {\\url{https://citrination.com/datasets/153092/},\n}']
diff --git a/docs/automatminer.preprocessing.html b/docs/automatminer.preprocessing.html
index 55e7ea82..c77af6b1 100644
--- a/docs/automatminer.preprocessing.html
+++ b/docs/automatminer.preprocessing.html
@@ -554,7 +554,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>tree_model</strong> (<em>instantiated sklearn tree-based model</em>) – </p></li>
 <li><p><strong>X</strong> (<em>pandas.dataframe</em>) – </p></li>
-<li><p><strong>y</strong> (<em>pandas.Series</em><em> or </em><a class="reference external" href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v1.17)"><em>numpy.ndarray</em></a>) – the target column</p></li>
+<li><p><strong>y</strong> (<em>pandas.Series</em><em> or </em><a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v1.19)"><em>numpy.ndarray</em></a>) – the target column</p></li>
 <li><p><strong>recursive</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.8)"><em>bool</em></a>) – </p></li>
 </ul>
 </dd>
diff --git a/docs/datasets.html b/docs/datasets.html
index e8beba2a..a41c8bf5 100644
--- a/docs/datasets.html
+++ b/docs/datasets.html
@@ -205,7 +205,7 @@ <h2>Getting dataset info<a class="headerlink" href="#getting-dataset-info" title
 Description: Matbench v0.1 dataset for predicting steel yield strengths from chemical composition alone. Retrieved from Citrine informatics. Deduplicated.
 Columns:
     composition: Chemical formula.
-    yield strength: Target variable. Experimentally measured steel yield strengths, in GPa.
+    yield strength: Target variable. Experimentally measured steel yield strengths, in MPa.
 Num Entries: 312
 Reference: https://citrination.com/datasets/153092/
 Bibtex citations: [&#39;@misc{Citrine Informatics,\ntitle = {Mechanical properties of some steels},\nhowpublished = {\\url{https://citrination.com/datasets/153092/},\n}&#39;]
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 9a45af2c..cff7b14b 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["advanced","automatminer","automatminer.automl","automatminer.automl.config","automatminer.automl.tests","automatminer.featurization","automatminer.featurization.tests","automatminer.preprocessing","automatminer.preprocessing.tests","automatminer.tests","automatminer.utils","automatminer.utils.tests","basic","datasets","index","installation","license","modules","tutorials"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.intersphinx":1,sphinx:56},filenames:["advanced.rst","automatminer.rst","automatminer.automl.rst","automatminer.automl.config.rst","automatminer.automl.tests.rst","automatminer.featurization.rst","automatminer.featurization.tests.rst","automatminer.preprocessing.rst","automatminer.preprocessing.tests.rst","automatminer.tests.rst","automatminer.utils.rst","automatminer.utils.tests.rst","basic.rst","datasets.rst","index.rst","installation.rst","license.rst","modules.rst","tutorials.rst"],objects:{"":{automatminer:[1,0,0,"-"]},"automatminer.automl":{adaptors:[2,0,0,"-"],base:[2,0,0,"-"],config:[3,0,0,"-"],tests:[4,0,0,"-"]},"automatminer.automl.adaptors":{SinglePipelineAdaptor:[2,1,1,""],TPOTAdaptor:[2,1,1,""]},"automatminer.automl.adaptors.SinglePipelineAdaptor":{backend:[2,2,1,""],best_pipeline:[2,2,1,""],features:[2,2,1,""],fit:[2,2,1,""],fitted_target:[2,2,1,""],mode:[2,3,1,""]},"automatminer.automl.adaptors.TPOTAdaptor":{backend:[2,3,1,""],best_models:[2,3,1,""],best_pipeline:[2,2,1,""],deserialize:[2,2,1,""],features:[2,2,1,""],fit:[2,2,1,""],fitted_target:[2,2,1,""],from_serialized:[2,3,1,""],mode:[2,3,1,""],models:[2,3,1,""],serialize:[2,2,1,""]},"automatminer.automl.base":{DFMLAdaptor:[2,1,1,""]},"automatminer.automl.base.DFMLAdaptor":{backend:[2,2,1,""],best_pipeline:[2,2,1,""],deserialize:[2,2,1,""],features:[2,2,1,""],fitted_target:[2,2,1,""],predict:[2,2,1,""],serialize:[2,2,1,""],transform:[2,2,1,""]},"automatminer.automl.config":{tpot_configs:[3,0,0,"-"]},"automatminer.automl.tests":{test_adaptors:[4,0,0,"-"],test_base:[4,0,0,"-"]},"automatminer.automl.tests.test_adaptors":{TestSinglePipelineAdaptor:[4,1,1,""],TestTPOTAdaptor:[4,1,1,""]},"automatminer.automl.tests.test_adaptors.TestSinglePipelineAdaptor":{setUp:[4,2,1,""],test_BaseEstimator:[4,2,1,""],test_BaseEstimator_classification:[4,2,1,""],test_Pipeline:[4,2,1,""],test_feature_mismatching:[4,2,1,""]},"automatminer.automl.tests.test_adaptors.TestTPOTAdaptor":{setUp:[4,2,1,""],test_classification:[4,2,1,""],test_feature_mismatching:[4,2,1,""],test_regression:[4,2,1,""],test_training_only:[4,2,1,""]},"automatminer.automl.tests.test_base":{TestAdaptorBad:[4,1,1,""],TestAdaptorGood:[4,1,1,""],TestBaseAutoMLTransformers:[4,1,1,""]},"automatminer.automl.tests.test_base.TestAdaptorGood":{backend:[4,2,1,""],best_pipeline:[4,2,1,""],features:[4,2,1,""],fit:[4,2,1,""],fitted_target:[4,2,1,""],predict:[4,2,1,""]},"automatminer.automl.tests.test_base.TestBaseAutoMLTransformers":{setUp:[4,2,1,""],test_DFMLAdaptor:[4,2,1,""]},"automatminer.base":{DFTransformer:[1,1,1,""]},"automatminer.base.DFTransformer":{fit:[1,2,1,""],fit_transform:[1,2,1,""],transform:[1,2,1,""]},"automatminer.featurization":{base:[5,0,0,"-"],core:[5,0,0,"-"],sets:[5,0,0,"-"],tests:[6,0,0,"-"]},"automatminer.featurization.base":{FeaturizerSet:[5,1,1,""]},"automatminer.featurization.base.FeaturizerSet":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.core":{AutoFeaturizer:[5,1,1,""]},"automatminer.featurization.core.AutoFeaturizer":{auto_featurizer:[5,3,1,""],converted_input_df:[5,3,1,""],features:[5,3,1,""],featurizers:[5,3,1,""],fit:[5,2,1,""],fitted_input_df:[5,3,1,""],min_precheck_frac:[5,3,1,""],removed_featurizers:[5,3,1,""],transform:[5,2,1,""]},"automatminer.featurization.sets":{AllFeaturizers:[5,1,1,""],BSFeaturizers:[5,1,1,""],CompositionFeaturizers:[5,1,1,""],DOSFeaturizers:[5,1,1,""],StructureFeaturizers:[5,1,1,""]},"automatminer.featurization.sets.AllFeaturizers":{all:[5,2,1,""],bandstructure:[5,2,1,""],composition:[5,2,1,""],debug:[5,2,1,""],dos:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""],structure:[5,2,1,""]},"automatminer.featurization.sets.BSFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.CompositionFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.DOSFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.StructureFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""],need_fit:[5,2,1,""]},"automatminer.featurization.tests":{test_base:[6,0,0,"-"],test_core:[6,0,0,"-"],test_sets:[6,0,0,"-"]},"automatminer.featurization.tests.test_base":{TestAutoFeaturizer:[6,1,1,""]},"automatminer.featurization.tests.test_base.TestAutoFeaturizer":{test_fsets:[6,2,1,""]},"automatminer.featurization.tests.test_core":{TestAutoFeaturizer:[6,1,1,""]},"automatminer.featurization.tests.test_core.TestAutoFeaturizer":{setUp:[6,2,1,""],tearDown:[6,2,1,""],test_StructureFeaturizers_needs_fitting:[6,2,1,""],test_caching:[6,2,1,""],test_column_attr:[6,2,1,""],test_exclude_by_users:[6,2,1,""],test_featurize_bsdos:[6,2,1,""],test_featurize_composition:[6,2,1,""],test_featurize_structure:[6,2,1,""],test_featurizers_by_users:[6,2,1,""],test_functionalization:[6,2,1,""],test_prechecking:[6,2,1,""],test_presets:[6,2,1,""],test_sanity:[6,2,1,""],test_transferability:[6,2,1,""]},"automatminer.featurization.tests.test_sets":{TestAllFeaturizers:[6,1,1,""],TestFeaturizerSets:[6,1,1,""]},"automatminer.featurization.tests.test_sets.TestAllFeaturizers":{get_featurizers:[6,2,1,""],setUp:[6,2,1,""],test_bandstructure_featurizers:[6,2,1,""],test_composition_featurizers:[6,2,1,""],test_dos_featurizers:[6,2,1,""],test_structure_featurizers:[6,2,1,""]},"automatminer.featurization.tests.test_sets.TestFeaturizerSets":{setUp:[6,2,1,""],test_sets_not_empty:[6,2,1,""]},"automatminer.pipeline":{MatPipe:[1,1,1,""]},"automatminer.pipeline.MatPipe":{benchmark:[1,2,1,""],fit:[1,2,1,""],from_preset:[1,2,1,""],inspect:[1,2,1,""],load:[1,2,1,""],ml_type:[1,3,1,""],post_fit_df:[1,3,1,""],pre_fit_df:[1,3,1,""],predict:[1,2,1,""],save:[1,2,1,""],summarize:[1,2,1,""],target:[1,3,1,""],transform:[1,2,1,""],version:[1,3,1,""]},"automatminer.preprocessing":{core:[7,0,0,"-"],feature_selection:[7,0,0,"-"],tests:[8,0,0,"-"]},"automatminer.preprocessing.core":{DataCleaner:[7,1,1,""],FeatureReducer:[7,1,1,""]},"automatminer.preprocessing.core.DataCleaner":{dropped_features:[7,3,1,""],dropped_samples:[7,3,1,""],fit:[7,2,1,""],fit_transform:[7,2,1,""],fitted_df:[7,3,1,""],fitted_target:[7,3,1,""],handle_na:[7,2,1,""],max_problem_col_warning_threshold:[7,3,1,""],number_cols:[7,3,1,""],object_cols:[7,3,1,""],retained_features:[7,2,1,""],to_numerical:[7,2,1,""],transform:[7,2,1,""],warnings:[7,3,1,""]},"automatminer.preprocessing.core.FeatureReducer":{fit:[7,2,1,""],reducer_params:[7,3,1,""],removed_features:[7,3,1,""],retained_features:[7,3,1,""],rm_correlated:[7,2,1,""],transform:[7,2,1,""]},"automatminer.preprocessing.feature_selection":{TreeFeatureReducer:[7,1,1,""],lower_corr_clf:[7,4,1,""],rebate:[7,4,1,""]},"automatminer.preprocessing.feature_selection.TreeFeatureReducer":{fit:[7,2,1,""],get_reduced_features:[7,2,1,""],get_top_features:[7,2,1,""],transform:[7,2,1,""]},"automatminer.preprocessing.tests":{test_core:[8,0,0,"-"]},"automatminer.preprocessing.tests.test_core":{TestFeatureReduction:[8,1,1,""],TestPreprocess:[8,1,1,""]},"automatminer.preprocessing.tests.test_core.TestFeatureReduction":{setUp:[8,2,1,""],test_TreeBasedFeatureReduction:[8,2,1,""],test_lower_corr_clf:[8,2,1,""],test_rebate:[8,2,1,""]},"automatminer.preprocessing.tests.test_core.TestPreprocess":{setUp:[8,2,1,""],test_DataCleaner:[8,2,1,""],test_DataCleaner_big_nan_handler_warning:[8,2,1,""],test_DataCleaner_emergency_na_transform_imputation:[8,2,1,""],test_DataCleaner_feature_na_method:[8,2,1,""],test_DataCleaner_na_method_feature_sample_interaction:[8,2,1,""],test_DataCleaner_sample_na_method:[8,2,1,""],test_FeatureReducer_advanced:[8,2,1,""],test_FeatureReducer_basic:[8,2,1,""],test_FeatureReducer_classification:[8,2,1,""],test_FeatureReducer_combinations:[8,2,1,""],test_FeatureReducer_pca:[8,2,1,""],test_FeatureReducer_transferability:[8,2,1,""],test_df:[8,2,1,""],test_manual_feature_reduction:[8,2,1,""],test_saving_feature_from_removal:[8,2,1,""]},"automatminer.presets":{get_available_presets:[1,4,1,""],get_preset_config:[1,4,1,""]},"automatminer.tests":{test_base:[9,0,0,"-"],test_pipeline:[9,0,0,"-"],test_presets:[9,0,0,"-"]},"automatminer.tests.test_base":{TestBaseTransformers:[9,1,1,""],TestTransformerBad:[9,1,1,""],TestTransformerGood:[9,1,1,""]},"automatminer.tests.test_base.TestBaseTransformers":{setUp:[9,2,1,""],test_DFTransformer:[9,2,1,""],test_DFTransformer_BaseEstimator_behavior:[9,2,1,""]},"automatminer.tests.test_base.TestTransformerGood":{fit:[9,2,1,""],transform:[9,2,1,""]},"automatminer.tests.test_pipeline":{MatPipeDebugSingleTest:[9,1,1,""],MatPipeDebugTest:[9,1,1,""],TestMatPipeSetup:[9,1,1,""],make_matpipe_test:[9,4,1,""]},"automatminer.tests.test_pipeline.TestMatPipeSetup":{setUp:[9,2,1,""],test_from_preset:[9,2,1,""],test_instantiation:[9,2,1,""]},"automatminer.tests.test_presets":{TestMatPipePresets:[9,1,1,""]},"automatminer.tests.test_presets.TestMatPipePresets":{test_caching_powerup:[9,2,1,""],test_debug:[9,2,1,""],test_debug_single:[9,2,1,""],test_express:[9,2,1,""],test_express_single:[9,2,1,""],test_heavy:[9,2,1,""],test_missing:[9,2,1,""],test_n_jobs_powerup:[9,2,1,""],test_production:[9,2,1,""]},"automatminer.utils":{log:[10,0,0,"-"],ml:[10,0,0,"-"],pkg:[10,0,0,"-"],tests:[11,0,0,"-"]},"automatminer.utils.log":{initialize_logger:[10,4,1,""],initialize_null_logger:[10,4,1,""],log_progress:[10,4,1,""]},"automatminer.utils.ml":{is_greater_better:[10,4,1,""],regression_or_classification:[10,4,1,""]},"automatminer.utils.pkg":{AutomatminerError:[10,5,1,""],VersionError:[10,5,1,""],check_fitted:[10,4,1,""],compare_columns:[10,4,1,""],get_version:[10,4,1,""],return_attrs_recursively:[10,4,1,""],save_dict_to_file:[10,4,1,""],set_fitted:[10,4,1,""]},"automatminer.utils.tests":{test_log:[11,0,0,"-"],test_ml:[11,0,0,"-"],test_pkg:[11,0,0,"-"]},"automatminer.utils.tests.test_log":{TestLogTools:[11,1,1,""]},"automatminer.utils.tests.test_log.TestLogTools":{tearDown:[11,2,1,""],test_logger_initialization:[11,2,1,""]},"automatminer.utils.tests.test_ml":{TestMLTools:[11,1,1,""]},"automatminer.utils.tests.test_ml.TestMLTools":{test_is_greater_better:[11,2,1,""],test_regression_or_classification:[11,2,1,""]},"automatminer.utils.tests.test_pkg":{MyTransformer:[11,1,1,""],TestPackageTools:[11,1,1,""]},"automatminer.utils.tests.test_pkg.MyTransformer":{fit:[11,2,1,""],transform:[11,2,1,""]},"automatminer.utils.tests.test_pkg.TestPackageTools":{setUp:[11,2,1,""],tearDown:[11,2,1,""],test_compare_columns:[11,2,1,""],test_fitting_decorations:[11,2,1,""],test_get_version:[11,2,1,""],test_save_dict_to_file:[11,2,1,""]},automatminer:{automl:[2,0,0,"-"],base:[1,0,0,"-"],featurization:[5,0,0,"-"],pipeline:[1,0,0,"-"],preprocessing:[7,0,0,"-"],presets:[1,0,0,"-"],tests:[9,0,0,"-"],utils:[10,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","attribute","Python attribute"],"4":["py","function","Python function"],"5":["py","exception","Python exception"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:attribute","4":"py:function","5":"py:exception"},terms:{"100k":14,"abstract":[1,2,5],"case":[0,4,6,8,9,11],"catch":6,"class":[0,1,2,3,4,5,6,7,8,9,11,12],"default":[0,3,5,7,10,12],"final":[6,7],"float":[5,7],"function":[0,1,5,7,10,12,13,16],"import":[0,1,7,10,12,13,14],"int":[1,5,6,7,10],"long":12,"new":[1,5,6,7,12],"null":7,"public":[13,14],"return":[0,1,2,4,5,6,7,8,9,10,11,12],"static":[1,6,12],"throw":[1,8],"true":[0,1,2,4,5,6,7,12],"try":[5,12,15],"while":[6,7,13],AND:16,ARE:16,Adding:12,And:14,BUT:16,DOS:[1,5,12],FOR:16,For:[0,2,3,5,8,10,12,13,14],NOT:[7,16],Not:5,SUCH:16,THE:16,Thats:0,The:[0,1,2,4,5,7,10,12,13,14,16],There:18,These:[0,5],USE:16,Use:[0,5,12],Used:1,Useful:9,Uses:2,Using:14,__init__:[0,10],_feature_import:7,abc:[1,5,6],abl:[2,6,12,15],about:[10,13],abov:[12,13,16],abs:14,absolut:5,accept:[2,7,12,13],access:[0,1,14],accident:8,accord:7,accumul:7,accur:14,accuraci:[1,12,14],across:14,actual:[1,5,7],adapt:2,adaptor:[0,1,4,17],add:[0,2,3],added:14,addit:[5,7,12],advanc:[12,14],advantag:0,advis:16,after:[5,6,7,10,11,12,13],agreement:16,algorithm:[0,2,3,4,7,14],all:[0,1,2,5,6,7,8,9,10,12,13,14,16,18],allfeatur:[5,6],allow:[1,5,7],alon:13,alreadi:[0,7],also:[0,13],altern:7,although:0,amm_clf_nam:2,amm_reg_nam:2,analag:[0,2],analog:12,analyi:10,analysi:7,ani:[0,2,4,5,7,8,14,16,18],anoth:[0,1,6],anyon:16,anywher:7,appli:[1,5,6,7,10],applic:[5,13],approv:16,arang:2,area:14,arg:[5,6,9],argument:[0,1,5,7,12,13],aris:16,arxiv:14,assign:[0,12],associ:0,assort:11,assum:0,attr:[7,9,10],attrdict:10,attribut:[1,2,5,6,7,10,12],auto:[1,7,10],auto_featur:5,autofeatur:[0,1,5,6,10,12],autofeaturix:1,autogener:14,automat:[0,1,5,6,7,12,14],automatmin:[0,12,15,16,18],automatminererror:10,automl:[0,1,14,17],avail:[1,2,5,6,13,16],backend:[0,2,4,14],bagofbond:5,balanc:1,band:[5,14],bandgap:14,bandstruct_col:6,bandstructur:[0,1,5,12,14],bandstructure_col:5,base:[4,6,7,8,9,10,11,12,17],baseestim:[0,1,2,4],baseexcept:10,basefeatur:5,basic:[8,14],been:[0,1,10,14],befor:[4,5,6,7,8,9,10,11],begin:[10,13],behavior:[0,6],being:[0,2,4,5,10,13],below:[10,16],benchmark:[1,12,14],berkelei:16,best:[1,2,4],best_featur:5,best_model:2,best_pipelin:[2,4],better:[5,10],between:[1,7],bewar:14,bfill:7,bias:0,bibtex:13,binari:16,bolt:12,bool:[1,2,5,6,7,10],bootstrap:2,both:[0,12,14],brave:14,brief:13,bs_featur:5,bsd:16,bsfeatur:5,bug:16,buggier:1,busi:16,cach:1,cache_src:[0,1,5],calcul:[7,13],california:16,call:[0,2,4,5,7,12],can:[0,1,2,3,4,5,8,9,10,12,13,14,15,18],cannot:5,care:3,castabl:10,categor:[7,10],categori:7,caus:16,cell:7,central:13,certain:[5,9,14],chang:[0,1,14],changelog:14,check:[3,6,9,10,13],check_fit:[1,2,10],check_valid:5,chemic:13,choic:[0,5],choos:[0,7,16],circular:10,citat:13,citrin:13,classif:[0,1,2,7,10,13],classifi:[0,2],clean:[0,1,7,12,13],cleaner:[0,1],clone:15,close:[2,4,12],code:[12,14,16,18],coeffici:7,coerce_mismatch:7,column:[0,1,5,7,10,12,13],com:[2,13,15],combin:[1,7],come:[12,13],command:10,comment:3,common:0,compar:[0,10,14],compare_column:10,comparison:13,compat:[2,4],complet:[5,14],compon:[1,7],composit:[0,1,5,6,12,13,14],composition_col:[5,6],composition_featur:5,compositionfeatur:5,comprehens:12,comput:[1,14,16],computation:0,conda:15,condit:16,config:[0,1,2,12],config_attr:[4,9],config_dict:[2,3],config_preset:9,configur:[0,1,9,12],consequenti:16,consid:[3,6,10,14],consist:7,constitu:[1,9,12],construct:12,contain:[0,1,3,5,7,10,12,13,14],content:17,contract:16,contrast:12,contributor:[14,16],convers:12,convert:5,converted_input_df:5,copyright:16,core:[1,17],corr:[0,7],corr_threshold:7,correct:[5,12],correctli:[4,6,8,9],correl:[7,12],correspond:5,could:5,cpu:12,craft:7,creat:[0,1,7,9,14],creation:1,critic:12,cross:[0,7,12],crossvalid:7,crystal:[12,13],crystallin:14,curat:0,current:[1,2,3,7,8,9,12],custom:[3,6,10,12,14],damag:16,data:[0,1,2,5,7,12,14,16],dataclean:[0,1,7,8,12],datafram:[0,1,2,5,7,8,10,12,13,14],dataframetransform:[1,10],dataset:[0,1,5,6,12,14],deal:7,deatafram:8,debug:[1,5,9,10,12],debug_singl:1,decid:[7,10],deconstruct:[6,11],decor:[1,5,10,14],dedupl:13,deepcopi:8,defin:[0,1,5,6,7],degre:12,densiti:[5,14],depend:0,deploy:13,dept:16,deriv:16,descend:7,descript:13,descriptor:[1,12,14],deseri:[1,2],design:14,desir:[1,7],detail:[12,13],determin:[5,7,10,12],determinist:7,develop:[6,16,18],df1:10,df1_not_in_df2:10,df2:10,df2_not_in_df1:10,dfmladaptor:[0,1,2,4],dfpt:13,dftransform:[1,2,5,7,9,11,14],dict:[1,3,5,7,10,12],dictat:8,dictionari:[5,10],differ:14,difficult:[1,14],digest:12,direct:16,directli:[2,7,16],directori:12,disclaim:16,discrtet:5,disk:14,distribut:16,divers:0,do_precheck:5,document:[3,5,16],doe:[2,4,5,7],doing:0,domain:13,don:[0,14],dopp:14,dos:[0,5,12],dos_col:[5,6],dos_featur:5,dosfeatur:5,down:14,download:13,drop:[0,5,7,12],drop_input:5,drop_na_target:7,dropped_featur:7,dropped_sampl:7,due:[2,12],dummi:10,dunn:14,duplic:12,dure:[0,1,2,5,7],e_form:13,each:[0,1,5,7,12],easi:[1,14],easiest:[0,12],eigendecomposit:7,either:[2,16],electron:14,electronic_structur:12,elementproperti:5,emerg:8,enabl:1,encod:[0,7],encode_categori:7,end:12,endors:16,energi:16,enhanc:16,ensembl:2,ensur:[0,6,8,9,10],entir:[0,1,5],entri:[6,13],environ:15,epistasislab:2,equival:[0,12],error:[0,1,5,7,8,10,12],establish:1,estim:0,etc:[0,5,7,12,13],evalu:0,even:[1,16],event:[6,16],everyon:14,everyth:12,ewaldenergi:[0,5],exactli:[6,12],examin:[2,4,14],exampl:[0,1,2,5,7,10,12,13,14,18],except:10,exclud:[0,5],exclus:16,execut:[5,10,12],exemplari:16,exercis:[4,6,8,9,11],exfoliation_en:13,exist:5,expens:[0,5],experi:1,experiment:[13,14],explor:2,express:[0,1,5,12,16],express_singl:1,expt:13,extend:14,extens:[2,10],fail:0,fair:13,fals:[1,2,5,6,7],far:0,fashion:[0,2,12],fast:5,faster:6,favor:10,feat_import:7,featur:[0,1,2,4,7,8,10,12,14,16,17],feature_importances_:7,feature_na_method:7,feature_select:[1,17],featurereduc:[0,1,7,12],featuris:5,featurize_bandstructur:6,featurize_do:6,featurizerset:[5,6],fed:7,feedback:14,few:[0,2],fewer:7,ffill:7,figshar:13,file:[1,3,5,6,10,12,13,14],filenam:[1,10,12],fill:7,fillna:7,find:[0,14],finish:[10,12],first:[5,7,10,13,15],fit:[0,1,2,4,5,6,7,8,9,10,11,12,14,16],fit_and_transform:6,fit_kwarg:[1,7],fit_transform:[0,1,7],fitted_df:[7,8],fitted_input_df:5,fitted_pipeline_:[2,4],fitted_target:[2,4,7],fix:16,fixtur:[4,6,8,9,11],flexibl:0,focus:5,fold:0,folder:[10,13],follow:[1,2,7,16],forest:[2,7],fork:14,form:[1,2,4,12,16],format:[1,5,10,13],formatt:10,formula:[6,13],forum:[14,15,18],forward:14,found:[2,4,5,18],four:[0,5],fraction:[5,7,8],free:16,friendli:7,from:[0,1,2,3,5,7,8,12,13,14,16],from_preset:[0,1,5,12],from_seri:2,full:[2,9,13,14],fulli:0,func:10,futur:3,g_vrh:13,ganos:14,gap:[13,14],gener:[0,1,5,12],genet:3,get:[0,1,6,10,12,14],get_all_dataset_info:13,get_available_preset:1,get_featur:6,get_preeset_config:1,get_preset_config:[0,1],get_reduced_featur:7,get_top_featur:7,get_vers:10,gfa:13,git:15,github:[2,14,15,18],give:[7,12],given:[1,5,7],globalsymmetryfeatur:5,gone:8,good:[1,16],got:14,gpa:13,grant:16,greater:[7,10],grow:14,guess_oxist:5,guidelin:14,hackingmateri:15,half:7,hand:14,handl:[0,7,8,12],handle_na:7,handler:10,happen:12,has:[0,1,7,8,10,12,14],have:[0,1,5,7,12,13,14,18],heavi:[1,5,12],heirarchi:12,held:1,help:[10,14,15],here:[0,12,13,14],herebi:16,high:[1,7,8],higher:[2,4,7],highest:1,highli:[5,7],hold:[0,5],holder:16,hook:[4,6,8,9,11],horribl:8,host:18,hot:7,hour:0,hous:7,how:[0,1,7,12],howev:[5,16],http:[2,13,14,15],human:[1,12],hundr:14,hyperparamet:0,idea:0,ident:0,identifi:[0,7],ignor:[0,5,6,7,10],ignore_col:5,ignore_error:5,imagenet:13,implement:[0,1,2,4,5,7,8,9],implementor:5,impli:16,importance_percentil:7,impos:16,improv:14,imput:[0,8,12],incident:16,includ:[0,1,5,8,12,14,16],incompat:5,incomplet:0,incorpor:16,incorrectli:[4,9],independ:6,index:[13,14],indexwis:5,indirect:16,individu:[7,14],infer:[6,12],info:[5,10,12,14],inform:[1,3,5,10,12],informat:13,inherit:1,initi:[0,9,10,14],initialize_logg:10,initialize_null_logg:10,inner:0,inorgan:13,input:[0,5,7,10,12],insid:[6,15],inspect:[1,5,12,14],instal:[14,16],instanc:[2,3,10],instanti:7,instead:[1,2,3,4,5],integ:10,intellig:13,intend:[0,5,12],intens:12,interest:12,interfac:[0,2,9],intermedi:12,intern:12,interpret:12,interrupt:16,introduct:0,involv:14,irrelev:5,is_greater_bett:10,is_met:13,issu:7,item:5,iter:7,its:[12,13,14,16],jain:14,job:[0,5],joint:12,json:[0,5,10,12,13],jupyt:[12,18],just:[5,7,12],k_vrh:13,keep:0,keep_featur:7,kei:[5,7],keyword:[1,2],kfold:0,kind:14,know:14,known:[1,14],kwarg:[1,2,4,5,7,9,11],label:[2,4,7,10],laboratori:16,larger:[7,10,13],last:13,later:[5,14],latest:15,lawrenc:16,learn:[0,1,2,4,5,7,10,11,12,13,14],learner:[0,1],least:5,let:[0,14],level:[0,1,2,4,7,9,10,12],liabil:16,liabl:16,librari:[3,10,14],licens:14,like:[0,1,2,12,14],limit:[2,6,16],line:14,linear:7,link:13,linux:15,list:[0,1,5,6,7,9,13,14,16],load:[0,1,2,12,14],load_dataset:13,loc:5,local:13,locat:1,log10:13,log:[1,2,5,7,11,14,17],log_dir:10,log_progress:10,logger:[9,10],logger_nam:10,longer:12,look:[0,12,14],loss:16,lower:7,lower_corr_clf:7,machin:[0,1,2,4,7,10,11,12,14],maco:15,made:[0,1,13],mai:[0,1,3,5,6,7,8,15,16],mainli:9,make:[0,1,2,5,6,8,14,16],make_matpipe_test:9,manag:13,mani:[5,14],manual:5,matbench:[0,2],matbench_:13,matbench_dielectr:13,matbench_expt_gap:13,matbench_expt_is_met:13,matbench_glass:13,matbench_jdft2d:13,matbench_log_gvrh:13,matbench_log_kvrh:13,matbench_mp_e_form:13,matbench_mp_gap:13,matbench_mp_is_met:13,matbench_perovskit:13,matbench_phonon:13,matbench_steel:13,match:[6,7],materi:[0,1,12,13,14,16],materialsproject:13,matmin:[0,5,6,13,14,18],matminer_exampl:12,matpip:[0,1,2,4,5,9,12,14],matpipedebugsingletest:9,matpipedebugtest:9,matric:5,matrix:7,max:[7,12],max_featur:2,max_na_frac:[0,7],max_problem_col_warning_threshold:7,max_time_min:0,maximum:[6,7],mean:[7,8,13],meant:6,measur:13,mechan:[13,14],median:7,memori:8,merchant:16,met:16,method:[0,1,2,4,5,6,7,8,9,10,11,12,13,14],methodnam:[4,6,8,9,11],metric:10,might:[12,18],min_precheck_frac:5,min_samples_leaf:2,min_samples_split:2,minim:5,minimum:5,minut:13,misc:13,misconfigur:12,mismatch:[1,7,10],mistak:6,mitig:0,mixin:1,ml_type:1,mode:[2,7],model:[0,1,2,4,7,12,14],model_evalu:0,moder:[1,12,14],modif:[1,16],modifi:[0,3,16],modul:[14,17],monitor:14,more:[0,1,2,4,5,7,10,12,13,14],most:[1,7,14],mpcontrib:13,mprester:6,msg:10,much:[0,15],multiiindex:5,multiindex:5,multipl:[0,5],multiprocess:0,multisurf:7,must:[2,4,7,8,16],my_detail:12,my_df:0,my_input_df:0,my_pipelin:12,my_properti:[0,12],my_summari:12,my_target_properti:0,mydict:10,mytransform:11,n_core:5,n_estim:[0,2],n_featur:7,n_job:[0,1,5],n_pca_featur:7,n_rebate_featur:7,n_split:0,na_method:7,na_method_fit:7,na_method_transform:7,name:[0,1,2,5,6,7,9,10,12,13,16],nan:[0,5,7,8],nation:16,nativ:10,ndarrai:7,necessari:[1,2,7],necessarili:5,need:[0,2,4,6,7,12,15],need_fit:5,neglig:16,neither:16,nest:0,nhowpublish:13,non:[5,7,16],none:[1,2,4,5,6,7,8,9,10,11],nor:16,normal:5,notat:7,note:[0,1,2,7,12,13],notebook:[12,18],noth:7,notic:16,now:[0,5,12,13,14],ntitl:13,num:13,number:[0,1,5,6,7,8,12,13],number_col:7,numer:[7,8,10],numpi:[7,10],obejct:5,obj:10,object:[0,1,2,4,5,6,7,10,12,13,14],object_col:7,oblig:16,occurr:7,offici:15,often:0,onc:[0,7,12,14],one:[0,1,6,7,12],onehot:7,onli:[0,1,2,5,6,9,10,12,14],onlin:18,open:16,oper:[0,2,3,5,7,10,12],optim:3,option:[0,5,6,7,12],order:7,ordereddict:2,org:[13,14],other:[0,1,5,7,12,14,16],otherwis:[6,7,16],our:[0,12,13,14,18],out:[0,1,3,12,13,14,16],outer:0,output:[0,2,5,7,10,12],outsid:[0,10],overridden:[2,4],overview:[0,12],overwrit:8,own:[0,1],owner:16,oxid:5,packag:17,pad:7,page:[12,13,14],panda:[1,2,7,8,10,12,14],parallel:[0,1,5],param:10,paramet:[0,1,2,5,6,7,9,10,12],paramt:[1,2],part:[0,9],particular:[9,16],particularli:1,pass:[0,5,7,9],patch:16,path:[1,5,10],pbe:13,pca:7,peak:13,per:5,percentil:7,perform:[0,7,16],permiss:16,permit:16,perpetu:16,persist:10,phase:14,phdo:13,pick:14,pickl:[1,2,12],pip:14,pipe:[0,1,12,14],pipelin:[2,4,14,17],pkg:[1,17],place:18,placehold:7,pleas:[10,14],plu:12,plumb:12,point:14,portabl:14,possibl:[2,4,15,16],post:14,post_fit_df:1,power:[1,12],powerup:1,practic:14,pre_fit_df:1,precheck:[0,5],predict:[0,1,2,4,13,14],predicted_df:[0,14],predicted_fold:0,prediction_df:12,prefer:[2,4],prepar:[0,16],preprint:[13,14],preprocess:[1,3,17],preprocessor:3,present:[2,4,5,7],preset:[0,5,9,14,17],pretti:10,prevent:[0,8],previou:2,primit:[12,13],princip:7,print:[10,13],prior:16,problem:[0,1,2,8,10,12,18],problemat:[0,7,12],procedur:[0,3,13],process:[1,14],procur:16,product:[0,1,16],profit:16,progress:10,project:[2,13],promot:16,prone:5,properli:10,properti:[1,2,4,5,7,8,12,13,14],provid:[0,5,10,12,13,16],publicli:[13,16],publish:0,pull:14,pump:12,purpos:[5,16],put:14,pymatgen:[12,13],pypi:14,python:[6,10,15],question:7,quick:[1,14],quicker:12,quit:0,r_max:7,rais:7,random:[2,7],random_st:7,randomforestregressor:2,rang:2,rate:7,raw:2,read:5,readabl:[1,12],readi:[0,1,7],real:[0,12],reason:5,rebat:7,receipt:16,recogn:5,recommend:[0,1,5,12,13],recurs:[7,10],redistribut:16,reduc:[0,1,7],reducer_param:7,reduct:[0,7,12,14],refer:[13,14],refract:13,refresh_df_init:6,regardless:[0,1,7],regent:16,regress:[0,1,2,7,10,12,13],regression_or_classif:10,regressor:[0,2,3],rel:[7,12],relat:[3,11],releas:15,relev:7,relief:7,relieff:7,remain:[1,7],remind:14,remov:[0,3,5,7,12],remove_featur:7,removed_featur:[5,7],renam:7,replac:[0,7],repositori:[12,13,15,18],reproduc:[14,16],request:14,requir:[0,1,5,12,14,16],research:14,reserv:16,resolv:8,resourc:1,restrict:0,result:[1,2,5,7,12],retain:[7,16],retained_featur:7,retriev:13,return_attrs_recurs:10,right:16,rm_correl:7,robustli:13,rough:0,routin:12,row:13,royalti:16,rtype:[2,4],run:[1,2,7,9,12,14],runtest:[4,6,8,9,11],sai:0,same:[0,1,2,5,7,12],sampl:[0,7,8,12,13,14],save:[1,2,4,5,10,14],save_dict_to_fil:10,saver:14,scheme:[0,2,7],scienc:[13,14],scikit:12,score:[0,2,7,10],scoring_funct:10,search:[13,14],second:[7,10],section:[0,12,13],see:[0,1,5,10,12,13,14],select:[1,5,7],selected_featur:7,selector:3,self:[1,5],separ:[14,16],sequenti:7,seri:[7,10],serial:[1,2],serializ:[2,4],servic:16,set:[0,1,2,4,6,7,8,9,11,12,13,14,17],set_fit:[1,2,10],setup:[4,6,8,9,11,14],sever:13,shall:16,should:[1,2,4,5,7,8,10,12],show:0,shuffl:0,shy:14,similar:[2,5,12],simpl:7,simpli:0,sinc:7,singl:[1,2,5],singlepipelineadaptor:[0,1,2,4],site:5,sitedo:5,size:14,skip:9,skippabl:9,sklearn:[0,1,2,7,10],skrebat:7,small:14,smaller:10,softwar:[16,18],some:[1,3,9,10,12,13,14],someth:[8,12,14],soon:13,sort:7,sourc:[1,14,16],span:13,special:16,specif:[1,5,9,10,16],specifi:[0,1,2,5,7,12,15],split:0,standard:[0,5],start:[0,12],state:[5,14],statist:0,stdout:[10,12],steel:13,step:1,still:[7,13],stop:10,store:[1,12,13],str:[1,2,4,5,6,7,9,10],straightforward:[2,4],stratifiedkfold:0,strength:13,strict:16,string:[1,2,4,5,7,8,10,12],structur:[0,1,3,5,6,12,13],structure_col:[5,6],structurefeatur:5,stuck:14,style:[2,16],subject:16,sublicens:16,sublist:5,submiss:14,submit:[13,14],submodul:17,subpackag:17,subset:[5,7],substitut:16,successfulli:12,suit:[0,9],summar:[1,12,14],summari:[12,13],superced:0,supervis:13,support:[10,15],suppress:1,supress_version_mismatch:1,sure:[1,2,12],swallow:10,syntax:[0,2,12],system:12,tabl:14,take:[6,7,13],taken:3,target:[0,1,2,4,7,8,10,12,13,14],target_kei:7,target_properti:1,task:13,teardown:[6,11],techniqu:[0,7,14],tell:[12,14],test:[0,1,2,5,7,10,14,17],test_adaptor:[1,2],test_bandstructure_featur:6,test_bas:[1,2,5,17],test_baseestim:4,test_baseestimator_classif:4,test_cach:6,test_caching_powerup:9,test_classif:4,test_column_attr:6,test_compare_column:11,test_composition_featur:6,test_cor:[1,5,7],test_dataclean:8,test_datacleaner_big_nan_handler_warn:8,test_datacleaner_emergency_na_transform_imput:8,test_datacleaner_feature_na_method:8,test_datacleaner_na_method_feature_sample_interact:8,test_datacleaner_sample_na_method:8,test_debug:9,test_debug_singl:9,test_df:[0,8],test_dfmladaptor:4,test_dftransform:9,test_dftransformer_baseestimator_behavior:9,test_dos_featur:6,test_exclude_by_us:6,test_express:9,test_express_singl:9,test_feature_mismatch:4,test_featurereducer_advanc:8,test_featurereducer_bas:8,test_featurereducer_classif:8,test_featurereducer_combin:8,test_featurereducer_pca:8,test_featurereducer_transfer:8,test_featurize_bsdo:6,test_featurize_composit:6,test_featurize_structur:6,test_featurizers_by_us:6,test_fitting_decor:11,test_from_preset:9,test_fset:6,test_function:6,test_get_vers:11,test_heavi:9,test_instanti:9,test_is_greater_bett:11,test_log:[1,10],test_logger_initi:11,test_lower_corr_clf:8,test_manual_feature_reduct:8,test_miss:9,test_ml:[1,10],test_n_jobs_powerup:9,test_pipelin:[1,4,17],test_pkg:[1,10],test_precheck:6,test_predict:1,test_preset:[1,6,17],test_product:9,test_reb:8,test_regress:4,test_regression_or_classif:11,test_san:6,test_save_dict_to_fil:11,test_saving_feature_from_remov:8,test_set:[1,5],test_sets_not_empti:6,test_structure_featur:6,test_structurefeaturizers_needs_fit:6,test_training_onli:4,test_transfer:6,test_treebasedfeaturereduct:8,testadaptorbad:4,testadaptorgood:4,testallfeatur:6,testautofeatur:6,testbaseautomltransform:4,testbasetransform:9,testcas:[4,6,8,9,11],testfeaturereduct:8,testfeaturizerset:6,testlogtool:11,testmatpip:9,testmatpipepreset:9,testmatpipesetup:9,testmltool:11,testpackagetool:11,testpreprocess:8,testsinglepipelineadaptor:4,testtpotadaptor:4,testtransformerbad:9,testtransformergood:9,text:[10,12,14],than:[1,5,7,12],thei:[0,5],them:[0,7],theori:16,thereof:16,thermodynam:14,thi:[0,1,2,3,5,6,7,8,10,12,13,14,16,18],thing:0,those:[6,7],though:[2,4,5,12],thousand:5,threshold:[7,12],through:[0,7,13,14,15,16],time:[7,12,13,14],timeli:1,timestamp:12,to_numer:7,too:0,tool:[7,10,12,13,14],top:[0,7,9,12],tort:16,total:7,tpot:[0,1,2,3,10],tpot_config:[1,2],tpot_kwarg:2,tpotadaptor:[0,1,2,12],tpotbas:2,tpotclassifi:[2,4],tpotregressor:2,track:14,train:[0,1,2,7,14],train_df:[12,14],training_df:1,transferr:1,transform:[0,1,2,5,7,8,9,10,11,12],transform_kwarg:[1,2],transformermixin:1,tree:[1,7,12],tree_importance_percentil:7,tree_model:7,treefeaturereduc:[7,12],troubleshoot:18,troublesom:7,tune:[0,14],tupl:7,tutori:[12,14],two:7,txt:10,type:[1,2,4,5,6,7,8,9,10,11,12,13],typic:12,ultra:5,unabl:8,uncommon:7,under:[14,16],undergo:5,understand:14,unfair:0,uniqu:2,unittest:[4,6,8,9,11],univers:16,unknown:[12,14],unknown_df:[1,14],unless:[2,4],updat:6,upgrad:[1,16],url:13,usag:[5,14],use:[0,1,2,3,5,6,7,12,14,15,16],used:[0,1,2,4,5,7,10,12,14,16],useful:[5,14],user:[0,1,5,15],uses:[0,1,14],using:[0,1,2,3,7,12,13,14],util:[1,17],valid:[0,5,7],valu:[1,5,7,12],valv:12,variabl:[7,13],variou:[1,7],vector:5,veri:[0,1,12],version:[1,5,10,15],versionerror:10,via:[1,5,7,13,15],view:13,virtual:15,wai:[0,1,12,14,16],wang:14,want:[0,1,2,3,5,9,10,12,14],warn:[0,7,8,12],warranti:16,were:[0,7,12],what:12,whatsoev:16,when:[0,1,2,6,8,10,12],where:[0,1,8,9,10,12,14],whether:[1,2,5,7,10,16],which:[0,1,2,4,5,7,8,10,12,14],wide:13,window:15,within:12,without:[0,7,10,16],work:[0,1,5,6,7,12,16],worri:10,wors:7,would:12,wrapper:[2,5,7,10],write:[0,12],written:[10,16],wrong:8,xgb:1,xgbclassifi:0,xgboost:[0,1],xgbregressor:0,yaml:[10,12],yield:13,yml:10,you:[0,1,2,5,9,10,12,13,14,15,16,18],your:[0,14,16],zero:7,zip:13},titles:["Advanced Usage","automatminer package","automatminer.automl package","automatminer.automl.config package","automatminer.automl.tests package","automatminer.featurization package","automatminer.featurization.tests package","automatminer.preprocessing package","automatminer.preprocessing.tests package","automatminer.tests package","automatminer.utils package","automatminer.utils.tests package","Basic Usage","MatBench benchmark","automatminer documentation","Installation","License","automatminer","Tutorials and Support"],titleterms:{"new":14,Using:[0,12],access:13,adaptor:2,advanc:0,api:14,automatmin:[1,2,3,4,5,6,7,8,9,10,11,14,17],automl:[2,3,4],base:[1,2,5],basic:12,benchmark:[0,13],cite:14,config:3,contact:14,content:[1,2,3,4,5,6,7,8,9,10,11],contribut:14,core:[5,7],custom:0,dataset:13,dftransform:0,differ:12,document:14,down:13,examin:12,featur:[5,6],feature_select:7,from:15,get:13,how:14,individu:0,info:13,initi:12,instal:15,later:12,licens:16,load:13,log:[10,12],make:12,manual:14,matbench:[13,14],modul:[1,2,3,4,5,6,7,8,9,10,11],monitor:12,overview:[13,14],packag:[1,2,3,4,5,6,7,8,9,10,11],pip:15,pipelin:[0,1,12],pkg:10,practic:0,predict:12,preprocess:[7,8],preset:[1,12],pypi:15,quick:12,remind:12,run:0,save:12,saver:0,set:5,sourc:15,submodul:[1,2,3,4,5,6,7,8,9,10,11],subpackag:[1,2,5,7,10],support:[14,18],test:[4,6,8,9,11],test_adaptor:4,test_bas:[4,6,9],test_cor:[6,8],test_log:11,test_ml:11,test_pipelin:9,test_pkg:11,test_preset:9,test_set:6,time:0,tool:0,tpot_config:3,train:12,tutori:18,usag:[0,12],user:14,using:15,util:[10,11],what:14,work:14,your:12}})
\ No newline at end of file
+Search.setIndex({docnames:["advanced","automatminer","automatminer.automl","automatminer.automl.config","automatminer.automl.tests","automatminer.featurization","automatminer.featurization.tests","automatminer.preprocessing","automatminer.preprocessing.tests","automatminer.tests","automatminer.utils","automatminer.utils.tests","basic","datasets","index","installation","license","modules","tutorials"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.intersphinx":1,sphinx:56},filenames:["advanced.rst","automatminer.rst","automatminer.automl.rst","automatminer.automl.config.rst","automatminer.automl.tests.rst","automatminer.featurization.rst","automatminer.featurization.tests.rst","automatminer.preprocessing.rst","automatminer.preprocessing.tests.rst","automatminer.tests.rst","automatminer.utils.rst","automatminer.utils.tests.rst","basic.rst","datasets.rst","index.rst","installation.rst","license.rst","modules.rst","tutorials.rst"],objects:{"":{automatminer:[1,0,0,"-"]},"automatminer.automl":{adaptors:[2,0,0,"-"],base:[2,0,0,"-"],config:[3,0,0,"-"],tests:[4,0,0,"-"]},"automatminer.automl.adaptors":{SinglePipelineAdaptor:[2,1,1,""],TPOTAdaptor:[2,1,1,""]},"automatminer.automl.adaptors.SinglePipelineAdaptor":{backend:[2,2,1,""],best_pipeline:[2,2,1,""],features:[2,2,1,""],fit:[2,2,1,""],fitted_target:[2,2,1,""],mode:[2,3,1,""]},"automatminer.automl.adaptors.TPOTAdaptor":{backend:[2,3,1,""],best_models:[2,3,1,""],best_pipeline:[2,2,1,""],deserialize:[2,2,1,""],features:[2,2,1,""],fit:[2,2,1,""],fitted_target:[2,2,1,""],from_serialized:[2,3,1,""],mode:[2,3,1,""],models:[2,3,1,""],serialize:[2,2,1,""]},"automatminer.automl.base":{DFMLAdaptor:[2,1,1,""]},"automatminer.automl.base.DFMLAdaptor":{backend:[2,2,1,""],best_pipeline:[2,2,1,""],deserialize:[2,2,1,""],features:[2,2,1,""],fitted_target:[2,2,1,""],predict:[2,2,1,""],serialize:[2,2,1,""],transform:[2,2,1,""]},"automatminer.automl.config":{tpot_configs:[3,0,0,"-"]},"automatminer.automl.tests":{test_adaptors:[4,0,0,"-"],test_base:[4,0,0,"-"]},"automatminer.automl.tests.test_adaptors":{TestSinglePipelineAdaptor:[4,1,1,""],TestTPOTAdaptor:[4,1,1,""]},"automatminer.automl.tests.test_adaptors.TestSinglePipelineAdaptor":{setUp:[4,2,1,""],test_BaseEstimator:[4,2,1,""],test_BaseEstimator_classification:[4,2,1,""],test_Pipeline:[4,2,1,""],test_feature_mismatching:[4,2,1,""]},"automatminer.automl.tests.test_adaptors.TestTPOTAdaptor":{setUp:[4,2,1,""],test_classification:[4,2,1,""],test_feature_mismatching:[4,2,1,""],test_regression:[4,2,1,""],test_training_only:[4,2,1,""]},"automatminer.automl.tests.test_base":{TestAdaptorBad:[4,1,1,""],TestAdaptorGood:[4,1,1,""],TestBaseAutoMLTransformers:[4,1,1,""]},"automatminer.automl.tests.test_base.TestAdaptorGood":{backend:[4,2,1,""],best_pipeline:[4,2,1,""],features:[4,2,1,""],fit:[4,2,1,""],fitted_target:[4,2,1,""],predict:[4,2,1,""]},"automatminer.automl.tests.test_base.TestBaseAutoMLTransformers":{setUp:[4,2,1,""],test_DFMLAdaptor:[4,2,1,""]},"automatminer.base":{DFTransformer:[1,1,1,""]},"automatminer.base.DFTransformer":{fit:[1,2,1,""],fit_transform:[1,2,1,""],transform:[1,2,1,""]},"automatminer.featurization":{base:[5,0,0,"-"],core:[5,0,0,"-"],sets:[5,0,0,"-"],tests:[6,0,0,"-"]},"automatminer.featurization.base":{FeaturizerSet:[5,1,1,""]},"automatminer.featurization.base.FeaturizerSet":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.core":{AutoFeaturizer:[5,1,1,""]},"automatminer.featurization.core.AutoFeaturizer":{auto_featurizer:[5,3,1,""],converted_input_df:[5,3,1,""],features:[5,3,1,""],featurizers:[5,3,1,""],fit:[5,2,1,""],fitted_input_df:[5,3,1,""],min_precheck_frac:[5,3,1,""],removed_featurizers:[5,3,1,""],transform:[5,2,1,""]},"automatminer.featurization.sets":{AllFeaturizers:[5,1,1,""],BSFeaturizers:[5,1,1,""],CompositionFeaturizers:[5,1,1,""],DOSFeaturizers:[5,1,1,""],StructureFeaturizers:[5,1,1,""]},"automatminer.featurization.sets.AllFeaturizers":{all:[5,2,1,""],bandstructure:[5,2,1,""],composition:[5,2,1,""],debug:[5,2,1,""],dos:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""],structure:[5,2,1,""]},"automatminer.featurization.sets.BSFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.CompositionFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.DOSFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""]},"automatminer.featurization.sets.StructureFeaturizers":{all:[5,2,1,""],debug:[5,2,1,""],express:[5,2,1,""],heavy:[5,2,1,""],need_fit:[5,2,1,""]},"automatminer.featurization.tests":{test_base:[6,0,0,"-"],test_core:[6,0,0,"-"],test_sets:[6,0,0,"-"]},"automatminer.featurization.tests.test_base":{TestAutoFeaturizer:[6,1,1,""]},"automatminer.featurization.tests.test_base.TestAutoFeaturizer":{test_fsets:[6,2,1,""]},"automatminer.featurization.tests.test_core":{TestAutoFeaturizer:[6,1,1,""]},"automatminer.featurization.tests.test_core.TestAutoFeaturizer":{setUp:[6,2,1,""],tearDown:[6,2,1,""],test_StructureFeaturizers_needs_fitting:[6,2,1,""],test_caching:[6,2,1,""],test_column_attr:[6,2,1,""],test_exclude_by_users:[6,2,1,""],test_featurize_bsdos:[6,2,1,""],test_featurize_composition:[6,2,1,""],test_featurize_structure:[6,2,1,""],test_featurizers_by_users:[6,2,1,""],test_functionalization:[6,2,1,""],test_prechecking:[6,2,1,""],test_presets:[6,2,1,""],test_sanity:[6,2,1,""],test_transferability:[6,2,1,""]},"automatminer.featurization.tests.test_sets":{TestAllFeaturizers:[6,1,1,""],TestFeaturizerSets:[6,1,1,""]},"automatminer.featurization.tests.test_sets.TestAllFeaturizers":{get_featurizers:[6,2,1,""],setUp:[6,2,1,""],test_bandstructure_featurizers:[6,2,1,""],test_composition_featurizers:[6,2,1,""],test_dos_featurizers:[6,2,1,""],test_structure_featurizers:[6,2,1,""]},"automatminer.featurization.tests.test_sets.TestFeaturizerSets":{setUp:[6,2,1,""],test_sets_not_empty:[6,2,1,""]},"automatminer.pipeline":{MatPipe:[1,1,1,""]},"automatminer.pipeline.MatPipe":{benchmark:[1,2,1,""],fit:[1,2,1,""],from_preset:[1,2,1,""],inspect:[1,2,1,""],load:[1,2,1,""],ml_type:[1,3,1,""],post_fit_df:[1,3,1,""],pre_fit_df:[1,3,1,""],predict:[1,2,1,""],save:[1,2,1,""],summarize:[1,2,1,""],target:[1,3,1,""],transform:[1,2,1,""],version:[1,3,1,""]},"automatminer.preprocessing":{core:[7,0,0,"-"],feature_selection:[7,0,0,"-"],tests:[8,0,0,"-"]},"automatminer.preprocessing.core":{DataCleaner:[7,1,1,""],FeatureReducer:[7,1,1,""]},"automatminer.preprocessing.core.DataCleaner":{dropped_features:[7,3,1,""],dropped_samples:[7,3,1,""],fit:[7,2,1,""],fit_transform:[7,2,1,""],fitted_df:[7,3,1,""],fitted_target:[7,3,1,""],handle_na:[7,2,1,""],max_problem_col_warning_threshold:[7,3,1,""],number_cols:[7,3,1,""],object_cols:[7,3,1,""],retained_features:[7,2,1,""],to_numerical:[7,2,1,""],transform:[7,2,1,""],warnings:[7,3,1,""]},"automatminer.preprocessing.core.FeatureReducer":{fit:[7,2,1,""],reducer_params:[7,3,1,""],removed_features:[7,3,1,""],retained_features:[7,3,1,""],rm_correlated:[7,2,1,""],transform:[7,2,1,""]},"automatminer.preprocessing.feature_selection":{TreeFeatureReducer:[7,1,1,""],lower_corr_clf:[7,4,1,""],rebate:[7,4,1,""]},"automatminer.preprocessing.feature_selection.TreeFeatureReducer":{fit:[7,2,1,""],get_reduced_features:[7,2,1,""],get_top_features:[7,2,1,""],transform:[7,2,1,""]},"automatminer.preprocessing.tests":{test_core:[8,0,0,"-"]},"automatminer.preprocessing.tests.test_core":{TestFeatureReduction:[8,1,1,""],TestPreprocess:[8,1,1,""]},"automatminer.preprocessing.tests.test_core.TestFeatureReduction":{setUp:[8,2,1,""],test_TreeBasedFeatureReduction:[8,2,1,""],test_lower_corr_clf:[8,2,1,""],test_rebate:[8,2,1,""]},"automatminer.preprocessing.tests.test_core.TestPreprocess":{setUp:[8,2,1,""],test_DataCleaner:[8,2,1,""],test_DataCleaner_big_nan_handler_warning:[8,2,1,""],test_DataCleaner_emergency_na_transform_imputation:[8,2,1,""],test_DataCleaner_feature_na_method:[8,2,1,""],test_DataCleaner_na_method_feature_sample_interaction:[8,2,1,""],test_DataCleaner_sample_na_method:[8,2,1,""],test_FeatureReducer_advanced:[8,2,1,""],test_FeatureReducer_basic:[8,2,1,""],test_FeatureReducer_classification:[8,2,1,""],test_FeatureReducer_combinations:[8,2,1,""],test_FeatureReducer_pca:[8,2,1,""],test_FeatureReducer_transferability:[8,2,1,""],test_df:[8,2,1,""],test_manual_feature_reduction:[8,2,1,""],test_saving_feature_from_removal:[8,2,1,""]},"automatminer.presets":{get_available_presets:[1,4,1,""],get_preset_config:[1,4,1,""]},"automatminer.tests":{test_base:[9,0,0,"-"],test_pipeline:[9,0,0,"-"],test_presets:[9,0,0,"-"]},"automatminer.tests.test_base":{TestBaseTransformers:[9,1,1,""],TestTransformerBad:[9,1,1,""],TestTransformerGood:[9,1,1,""]},"automatminer.tests.test_base.TestBaseTransformers":{setUp:[9,2,1,""],test_DFTransformer:[9,2,1,""],test_DFTransformer_BaseEstimator_behavior:[9,2,1,""]},"automatminer.tests.test_base.TestTransformerGood":{fit:[9,2,1,""],transform:[9,2,1,""]},"automatminer.tests.test_pipeline":{MatPipeDebugSingleTest:[9,1,1,""],MatPipeDebugTest:[9,1,1,""],TestMatPipeSetup:[9,1,1,""],make_matpipe_test:[9,4,1,""]},"automatminer.tests.test_pipeline.TestMatPipeSetup":{setUp:[9,2,1,""],test_from_preset:[9,2,1,""],test_instantiation:[9,2,1,""]},"automatminer.tests.test_presets":{TestMatPipePresets:[9,1,1,""]},"automatminer.tests.test_presets.TestMatPipePresets":{test_caching_powerup:[9,2,1,""],test_debug:[9,2,1,""],test_debug_single:[9,2,1,""],test_express:[9,2,1,""],test_express_single:[9,2,1,""],test_heavy:[9,2,1,""],test_missing:[9,2,1,""],test_n_jobs_powerup:[9,2,1,""],test_production:[9,2,1,""]},"automatminer.utils":{log:[10,0,0,"-"],ml:[10,0,0,"-"],pkg:[10,0,0,"-"],tests:[11,0,0,"-"]},"automatminer.utils.log":{initialize_logger:[10,4,1,""],initialize_null_logger:[10,4,1,""],log_progress:[10,4,1,""]},"automatminer.utils.ml":{is_greater_better:[10,4,1,""],regression_or_classification:[10,4,1,""]},"automatminer.utils.pkg":{AutomatminerError:[10,5,1,""],VersionError:[10,5,1,""],check_fitted:[10,4,1,""],compare_columns:[10,4,1,""],get_version:[10,4,1,""],return_attrs_recursively:[10,4,1,""],save_dict_to_file:[10,4,1,""],set_fitted:[10,4,1,""]},"automatminer.utils.tests":{test_log:[11,0,0,"-"],test_ml:[11,0,0,"-"],test_pkg:[11,0,0,"-"]},"automatminer.utils.tests.test_log":{TestLogTools:[11,1,1,""]},"automatminer.utils.tests.test_log.TestLogTools":{tearDown:[11,2,1,""],test_logger_initialization:[11,2,1,""]},"automatminer.utils.tests.test_ml":{TestMLTools:[11,1,1,""]},"automatminer.utils.tests.test_ml.TestMLTools":{test_is_greater_better:[11,2,1,""],test_regression_or_classification:[11,2,1,""]},"automatminer.utils.tests.test_pkg":{MyTransformer:[11,1,1,""],TestPackageTools:[11,1,1,""]},"automatminer.utils.tests.test_pkg.MyTransformer":{fit:[11,2,1,""],transform:[11,2,1,""]},"automatminer.utils.tests.test_pkg.TestPackageTools":{setUp:[11,2,1,""],tearDown:[11,2,1,""],test_compare_columns:[11,2,1,""],test_fitting_decorations:[11,2,1,""],test_get_version:[11,2,1,""],test_save_dict_to_file:[11,2,1,""]},automatminer:{automl:[2,0,0,"-"],base:[1,0,0,"-"],featurization:[5,0,0,"-"],pipeline:[1,0,0,"-"],preprocessing:[7,0,0,"-"],presets:[1,0,0,"-"],tests:[9,0,0,"-"],utils:[10,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","attribute","Python attribute"],"4":["py","function","Python function"],"5":["py","exception","Python exception"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:attribute","4":"py:function","5":"py:exception"},terms:{"100k":14,"abstract":[1,2,5],"case":[0,4,6,8,9,11],"catch":6,"class":[0,1,2,3,4,5,6,7,8,9,11,12],"default":[0,3,5,7,10,12],"final":[6,7],"float":[5,7],"function":[0,1,5,7,10,12,13,16],"import":[0,1,7,10,12,13,14],"int":[1,5,6,7,10],"long":12,"new":[1,5,6,7,12],"null":7,"public":[13,14],"return":[0,1,2,4,5,6,7,8,9,10,11,12],"static":[1,6,12],"throw":[1,8],"true":[0,1,2,4,5,6,7,12],"try":[5,12,15],"while":[6,7,13],AND:16,ARE:16,Adding:12,And:14,BUT:16,DOS:[1,5,12],FOR:16,For:[0,2,3,5,8,10,12,13,14],NOT:[7,16],Not:5,SUCH:16,THE:16,Thats:0,The:[0,1,2,4,5,7,10,12,13,14,16],There:18,These:[0,5],USE:16,Use:[0,5,12],Used:1,Useful:9,Uses:2,Using:14,__init__:[0,10],_feature_import:7,abc:[1,5,6],abl:[2,6,12,15],about:[10,13],abov:[12,13,16],abs:14,absolut:5,accept:[2,7,12,13],access:[0,1,14],accident:8,accord:7,accumul:7,accur:14,accuraci:[1,12,14],across:14,actual:[1,5,7],adapt:2,adaptor:[0,1,4,17],add:[0,2,3],added:14,addit:[5,7,12],advanc:[12,14],advantag:0,advis:16,after:[5,6,7,10,11,12,13],agreement:16,algorithm:[0,2,3,4,7,14],all:[0,1,2,5,6,7,8,9,10,12,13,14,16,18],allfeatur:[5,6],allow:[1,5,7],alon:13,alreadi:[0,7],also:[0,13],altern:7,although:0,amm_clf_nam:2,amm_reg_nam:2,analag:[0,2],analog:12,analyi:10,analysi:7,ani:[0,2,4,5,7,8,14,16,18],anoth:[0,1,6],anyon:16,anywher:7,appli:[1,5,6,7,10],applic:[5,13],approv:16,arang:2,area:14,arg:[5,6,9],argument:[0,1,5,7,12,13],aris:16,arxiv:14,assign:[0,12],associ:0,assort:11,assum:0,attr:[7,9,10],attrdict:10,attribut:[1,2,5,6,7,10,12],auto:[1,7,10],auto_featur:5,autofeatur:[0,1,5,6,10,12],autofeaturix:1,autogener:14,automat:[0,1,5,6,7,12,14],automatmin:[0,12,15,16,18],automatminererror:10,automl:[0,1,14,17],avail:[1,2,5,6,13,16],backend:[0,2,4,14],bagofbond:5,balanc:1,band:[5,14],bandgap:14,bandstruct_col:6,bandstructur:[0,1,5,12,14],bandstructure_col:5,base:[4,6,7,8,9,10,11,12,17],baseestim:[0,1,2,4],baseexcept:10,basefeatur:5,basic:[8,14],been:[0,1,10,14],befor:[4,5,6,7,8,9,10,11],begin:[10,13],behavior:[0,6],being:[0,2,4,5,10,13],below:[10,16],benchmark:[1,12,14],berkelei:16,best:[1,2,4],best_featur:5,best_model:2,best_pipelin:[2,4],better:[5,10],between:[1,7],bewar:14,bfill:7,bias:0,bibtex:13,binari:16,bolt:12,bool:[1,2,5,6,7,10],bootstrap:2,both:[0,12,14],brave:14,brief:13,bs_featur:5,bsd:16,bsfeatur:5,bug:16,buggier:1,busi:16,cach:1,cache_src:[0,1,5],calcul:[7,13],california:16,call:[0,2,4,5,7,12],can:[0,1,2,3,4,5,8,9,10,12,13,14,15,18],cannot:5,care:3,castabl:10,categor:[7,10],categori:7,caus:16,cell:7,central:13,certain:[5,9,14],chang:[0,1,14],changelog:14,check:[3,6,9,10,13],check_fit:[1,2,10],check_valid:5,chemic:13,choic:[0,5],choos:[0,7,16],circular:10,citat:13,citrin:13,classif:[0,1,2,7,10,13],classifi:[0,2],clean:[0,1,7,12,13],cleaner:[0,1],clone:15,close:[2,4,12],code:[12,14,16,18],coeffici:7,coerce_mismatch:7,column:[0,1,5,7,10,12,13],com:[2,13,15],combin:[1,7],come:[12,13],command:10,comment:3,common:0,compar:[0,10,14],compare_column:10,comparison:13,compat:[2,4],complet:[5,14],compon:[1,7],composit:[0,1,5,6,12,13,14],composition_col:[5,6],composition_featur:5,compositionfeatur:5,comprehens:12,comput:[1,14,16],computation:0,conda:15,condit:16,config:[0,1,2,12],config_attr:[4,9],config_dict:[2,3],config_preset:9,configur:[0,1,9,12],consequenti:16,consid:[3,6,10,14],consist:7,constitu:[1,9,12],construct:12,contain:[0,1,3,5,7,10,12,13,14],content:17,contract:16,contrast:12,contributor:[14,16],convers:12,convert:5,converted_input_df:5,copyright:16,core:[1,17],corr:[0,7],corr_threshold:7,correct:[5,12],correctli:[4,6,8,9],correl:[7,12],correspond:5,could:5,cpu:12,craft:7,creat:[0,1,7,9,14],creation:1,critic:12,cross:[0,7,12],crossvalid:7,crystal:[12,13],crystallin:14,curat:0,current:[1,2,3,7,8,9,12],custom:[3,6,10,12,14],damag:16,data:[0,1,2,5,7,12,14,16],dataclean:[0,1,7,8,12],datafram:[0,1,2,5,7,8,10,12,13,14],dataframetransform:[1,10],dataset:[0,1,5,6,12,14],deal:7,deatafram:8,debug:[1,5,9,10,12],debug_singl:1,decid:[7,10],deconstruct:[6,11],decor:[1,5,10,14],dedupl:13,deepcopi:8,defin:[0,1,5,6,7],degre:12,densiti:[5,14],depend:0,deploy:13,dept:16,deriv:16,descend:7,descript:13,descriptor:[1,12,14],deseri:[1,2],design:14,desir:[1,7],detail:[12,13],determin:[5,7,10,12],determinist:7,develop:[6,16,18],df1:10,df1_not_in_df2:10,df2:10,df2_not_in_df1:10,dfmladaptor:[0,1,2,4],dfpt:13,dftransform:[1,2,5,7,9,11,14],dict:[1,3,5,7,10,12],dictat:8,dictionari:[5,10],differ:14,difficult:[1,14],digest:12,direct:16,directli:[2,7,16],directori:12,disclaim:16,discrtet:5,disk:14,distribut:16,divers:0,do_precheck:5,document:[3,5,16],doe:[2,4,5,7],doing:0,domain:13,don:[0,14],dopp:14,dos:[0,5,12],dos_col:[5,6],dos_featur:5,dosfeatur:5,down:14,download:13,drop:[0,5,7,12],drop_input:5,drop_na_target:7,dropped_featur:7,dropped_sampl:7,due:[2,12],dummi:10,dunn:14,duplic:12,dure:[0,1,2,5,7],e_form:13,each:[0,1,5,7,12],easi:[1,14],easiest:[0,12],eigendecomposit:7,either:[2,16],electron:14,electronic_structur:12,elementproperti:5,emerg:8,enabl:1,encod:[0,7],encode_categori:7,end:12,endors:16,energi:16,enhanc:16,ensembl:2,ensur:[0,6,8,9,10],entir:[0,1,5],entri:[6,13],environ:15,epistasislab:2,equival:[0,12],error:[0,1,5,7,8,10,12],establish:1,estim:0,etc:[0,5,7,12,13],evalu:0,even:[1,16],event:[6,16],everyon:14,everyth:12,ewaldenergi:[0,5],exactli:[6,12],examin:[2,4,14],exampl:[0,1,2,5,7,10,12,13,14,18],except:10,exclud:[0,5],exclus:16,execut:[5,10,12],exemplari:16,exercis:[4,6,8,9,11],exfoliation_en:13,exist:5,expens:[0,5],experi:1,experiment:[13,14],explor:2,express:[0,1,5,12,16],express_singl:1,expt:13,extend:14,extens:[2,10],fail:0,fair:13,fals:[1,2,5,6,7],far:0,fashion:[0,2,12],fast:5,faster:6,favor:10,feat_import:7,featur:[0,1,2,4,7,8,10,12,14,16,17],feature_importances_:7,feature_na_method:7,feature_select:[1,17],featurereduc:[0,1,7,12],featuris:5,featurize_bandstructur:6,featurize_do:6,featurizerset:[5,6],fed:7,feedback:14,few:[0,2],fewer:7,ffill:7,figshar:13,file:[1,3,5,6,10,12,13,14],filenam:[1,10,12],fill:7,fillna:7,find:[0,14],finish:[10,12],first:[5,7,10,13,15],fit:[0,1,2,4,5,6,7,8,9,10,11,12,14,16],fit_and_transform:6,fit_kwarg:[1,7],fit_transform:[0,1,7],fitted_df:[7,8],fitted_input_df:5,fitted_pipeline_:[2,4],fitted_target:[2,4,7],fix:16,fixtur:[4,6,8,9,11],flexibl:0,focus:5,fold:0,folder:[10,13],follow:[1,2,7,16],forest:[2,7],fork:14,form:[1,2,4,12,16],format:[1,5,10,13],formatt:10,formula:[6,13],forum:[14,15,18],forward:14,found:[2,4,5,18],four:[0,5],fraction:[5,7,8],free:16,friendli:7,from:[0,1,2,3,5,7,8,12,13,14,16],from_preset:[0,1,5,12],from_seri:2,full:[2,9,13,14],fulli:0,func:10,futur:3,g_vrh:13,ganos:14,gap:[13,14],gener:[0,1,5,12],genet:3,get:[0,1,6,10,12,14],get_all_dataset_info:13,get_available_preset:1,get_featur:6,get_preeset_config:1,get_preset_config:[0,1],get_reduced_featur:7,get_top_featur:7,get_vers:10,gfa:13,git:15,github:[2,14,15,18],give:[7,12],given:[1,5,7],globalsymmetryfeatur:5,gone:8,good:[1,16],got:14,grant:16,greater:[7,10],grow:14,guess_oxist:5,guidelin:14,hackingmateri:15,half:7,hand:14,handl:[0,7,8,12],handle_na:7,handler:10,happen:12,has:[0,1,7,8,10,12,14],have:[0,1,5,7,12,13,14,18],heavi:[1,5,12],heirarchi:12,held:1,help:[10,14,15],here:[0,12,13,14],herebi:16,high:[1,7,8],higher:[2,4,7],highest:1,highli:[5,7],hold:[0,5],holder:16,hook:[4,6,8,9,11],horribl:8,host:18,hot:7,hour:0,hous:7,how:[0,1,7,12],howev:[5,16],http:[2,13,14,15],human:[1,12],hundr:14,hyperparamet:0,idea:0,ident:0,identifi:[0,7],ignor:[0,5,6,7,10],ignore_col:5,ignore_error:5,imagenet:13,implement:[0,1,2,4,5,7,8,9],implementor:5,impli:16,importance_percentil:7,impos:16,improv:14,imput:[0,8,12],incident:16,includ:[0,1,5,8,12,14,16],incompat:5,incomplet:0,incorpor:16,incorrectli:[4,9],independ:6,index:[13,14],indexwis:5,indirect:16,individu:[7,14],infer:[6,12],info:[5,10,12,14],inform:[1,3,5,10,12],informat:13,inherit:1,initi:[0,9,10,14],initialize_logg:10,initialize_null_logg:10,inner:0,inorgan:13,input:[0,5,7,10,12],insid:[6,15],inspect:[1,5,12,14],instal:[14,16],instanc:[2,3,10],instanti:7,instead:[1,2,3,4,5],integ:10,intellig:13,intend:[0,5,12],intens:12,interest:12,interfac:[0,2,9],intermedi:12,intern:12,interpret:12,interrupt:16,introduct:0,involv:14,irrelev:5,is_greater_bett:10,is_met:13,issu:7,item:5,iter:7,its:[12,13,14,16],jain:14,job:[0,5],joint:12,json:[0,5,10,12,13],jupyt:[12,18],just:[5,7,12],k_vrh:13,keep:0,keep_featur:7,kei:[5,7],keyword:[1,2],kfold:0,kind:14,know:14,known:[1,14],kwarg:[1,2,4,5,7,9,11],label:[2,4,7,10],laboratori:16,larger:[7,10,13],last:13,later:[5,14],latest:15,lawrenc:16,learn:[0,1,2,4,5,7,10,11,12,13,14],learner:[0,1],least:5,let:[0,14],level:[0,1,2,4,7,9,10,12],liabil:16,liabl:16,librari:[3,10,14],licens:14,like:[0,1,2,12,14],limit:[2,6,16],line:14,linear:7,link:13,linux:15,list:[0,1,5,6,7,9,13,14,16],load:[0,1,2,12,14],load_dataset:13,loc:5,local:13,locat:1,log10:13,log:[1,2,5,7,11,14,17],log_dir:10,log_progress:10,logger:[9,10],logger_nam:10,longer:12,look:[0,12,14],loss:16,lower:7,lower_corr_clf:7,machin:[0,1,2,4,7,10,11,12,14],maco:15,made:[0,1,13],mai:[0,1,3,5,6,7,8,15,16],mainli:9,make:[0,1,2,5,6,8,14,16],make_matpipe_test:9,manag:13,mani:[5,14],manual:5,matbench:[0,2],matbench_:13,matbench_dielectr:13,matbench_expt_gap:13,matbench_expt_is_met:13,matbench_glass:13,matbench_jdft2d:13,matbench_log_gvrh:13,matbench_log_kvrh:13,matbench_mp_e_form:13,matbench_mp_gap:13,matbench_mp_is_met:13,matbench_perovskit:13,matbench_phonon:13,matbench_steel:13,match:[6,7],materi:[0,1,12,13,14,16],materialsproject:13,matmin:[0,5,6,13,14,18],matminer_exampl:12,matpip:[0,1,2,4,5,9,12,14],matpipedebugsingletest:9,matpipedebugtest:9,matric:5,matrix:7,max:[7,12],max_featur:2,max_na_frac:[0,7],max_problem_col_warning_threshold:7,max_time_min:0,maximum:[6,7],mean:[7,8,13],meant:6,measur:13,mechan:[13,14],median:7,memori:8,merchant:16,met:16,method:[0,1,2,4,5,6,7,8,9,10,11,12,13,14],methodnam:[4,6,8,9,11],metric:10,might:[12,18],min_precheck_frac:5,min_samples_leaf:2,min_samples_split:2,minim:5,minimum:5,minut:13,misc:13,misconfigur:12,mismatch:[1,7,10],mistak:6,mitig:0,mixin:1,ml_type:1,mode:[2,7],model:[0,1,2,4,7,12,14],model_evalu:0,moder:[1,12,14],modif:[1,16],modifi:[0,3,16],modul:[14,17],monitor:14,more:[0,1,2,4,5,7,10,12,13,14],most:[1,7,14],mpa:13,mpcontrib:13,mprester:6,msg:10,much:[0,15],multiiindex:5,multiindex:5,multipl:[0,5],multiprocess:0,multisurf:7,must:[2,4,7,8,16],my_detail:12,my_df:0,my_input_df:0,my_pipelin:12,my_properti:[0,12],my_summari:12,my_target_properti:0,mydict:10,mytransform:11,n_core:5,n_estim:[0,2],n_featur:7,n_job:[0,1,5],n_pca_featur:7,n_rebate_featur:7,n_split:0,na_method:7,na_method_fit:7,na_method_transform:7,name:[0,1,2,5,6,7,9,10,12,13,16],nan:[0,5,7,8],nation:16,nativ:10,ndarrai:7,necessari:[1,2,7],necessarili:5,need:[0,2,4,6,7,12,15],need_fit:5,neglig:16,neither:16,nest:0,nhowpublish:13,non:[5,7,16],none:[1,2,4,5,6,7,8,9,10,11],nor:16,normal:5,notat:7,note:[0,1,2,7,12,13],notebook:[12,18],noth:7,notic:16,now:[0,5,12,13,14],ntitl:13,num:13,number:[0,1,5,6,7,8,12,13],number_col:7,numer:[7,8,10],numpi:[7,10],obejct:5,obj:10,object:[0,1,2,4,5,6,7,10,12,13,14],object_col:7,oblig:16,occurr:7,offici:15,often:0,onc:[0,7,12,14],one:[0,1,6,7,12],onehot:7,onli:[0,1,2,5,6,9,10,12,14],onlin:18,open:16,oper:[0,2,3,5,7,10,12],optim:3,option:[0,5,6,7,12],order:7,ordereddict:2,org:[13,14],other:[0,1,5,7,12,14,16],otherwis:[6,7,16],our:[0,12,13,14,18],out:[0,1,3,12,13,14,16],outer:0,output:[0,2,5,7,10,12],outsid:[0,10],overridden:[2,4],overview:[0,12],overwrit:8,own:[0,1],owner:16,oxid:5,packag:17,pad:7,page:[12,13,14],panda:[1,2,7,8,10,12,14],parallel:[0,1,5],param:10,paramet:[0,1,2,5,6,7,9,10,12],paramt:[1,2],part:[0,9],particular:[9,16],particularli:1,pass:[0,5,7,9],patch:16,path:[1,5,10],pbe:13,pca:7,peak:13,per:5,percentil:7,perform:[0,7,16],permiss:16,permit:16,perpetu:16,persist:10,phase:14,phdo:13,pick:14,pickl:[1,2,12],pip:14,pipe:[0,1,12,14],pipelin:[2,4,14,17],pkg:[1,17],place:18,placehold:7,pleas:[10,14],plu:12,plumb:12,point:14,portabl:14,possibl:[2,4,15,16],post:14,post_fit_df:1,power:[1,12],powerup:1,practic:14,pre_fit_df:1,precheck:[0,5],predict:[0,1,2,4,13,14],predicted_df:[0,14],predicted_fold:0,prediction_df:12,prefer:[2,4],prepar:[0,16],preprint:[13,14],preprocess:[1,3,17],preprocessor:3,present:[2,4,5,7],preset:[0,5,9,14,17],pretti:10,prevent:[0,8],previou:2,primit:[12,13],princip:7,print:[10,13],prior:16,problem:[0,1,2,8,10,12,18],problemat:[0,7,12],procedur:[0,3,13],process:[1,14],procur:16,product:[0,1,16],profit:16,progress:10,project:[2,13],promot:16,prone:5,properli:10,properti:[1,2,4,5,7,8,12,13,14],provid:[0,5,10,12,13,16],publicli:[13,16],publish:0,pull:14,pump:12,purpos:[5,16],put:14,pymatgen:[12,13],pypi:14,python:[6,10,15],question:7,quick:[1,14],quicker:12,quit:0,r_max:7,rais:7,random:[2,7],random_st:7,randomforestregressor:2,rang:2,rate:7,raw:2,read:5,readabl:[1,12],readi:[0,1,7],real:[0,12],reason:5,rebat:7,receipt:16,recogn:5,recommend:[0,1,5,12,13],recurs:[7,10],redistribut:16,reduc:[0,1,7],reducer_param:7,reduct:[0,7,12,14],refer:[13,14],refract:13,refresh_df_init:6,regardless:[0,1,7],regent:16,regress:[0,1,2,7,10,12,13],regression_or_classif:10,regressor:[0,2,3],rel:[7,12],relat:[3,11],releas:15,relev:7,relief:7,relieff:7,remain:[1,7],remind:14,remov:[0,3,5,7,12],remove_featur:7,removed_featur:[5,7],renam:7,replac:[0,7],repositori:[12,13,15,18],reproduc:[14,16],request:14,requir:[0,1,5,12,14,16],research:14,reserv:16,resolv:8,resourc:1,restrict:0,result:[1,2,5,7,12],retain:[7,16],retained_featur:7,retriev:13,return_attrs_recurs:10,right:16,rm_correl:7,robustli:13,rough:0,routin:12,row:13,royalti:16,rtype:[2,4],run:[1,2,7,9,12,14],runtest:[4,6,8,9,11],sai:0,same:[0,1,2,5,7,12],sampl:[0,7,8,12,13,14],save:[1,2,4,5,10,14],save_dict_to_fil:10,saver:14,scheme:[0,2,7],scienc:[13,14],scikit:12,score:[0,2,7,10],scoring_funct:10,search:[13,14],second:[7,10],section:[0,12,13],see:[0,1,5,10,12,13,14],select:[1,5,7],selected_featur:7,selector:3,self:[1,5],separ:[14,16],sequenti:7,seri:[7,10],serial:[1,2],serializ:[2,4],servic:16,set:[0,1,2,4,6,7,8,9,11,12,13,14,17],set_fit:[1,2,10],setup:[4,6,8,9,11,14],sever:13,shall:16,should:[1,2,4,5,7,8,10,12],show:0,shuffl:0,shy:14,similar:[2,5,12],simpl:7,simpli:0,sinc:7,singl:[1,2,5],singlepipelineadaptor:[0,1,2,4],site:5,sitedo:5,size:14,skip:9,skippabl:9,sklearn:[0,1,2,7,10],skrebat:7,small:14,smaller:10,softwar:[16,18],some:[1,3,9,10,12,13,14],someth:[8,12,14],soon:13,sort:7,sourc:[1,14,16],span:13,special:16,specif:[1,5,9,10,16],specifi:[0,1,2,5,7,12,15],split:0,standard:[0,5],start:[0,12],state:[5,14],statist:0,stdout:[10,12],steel:13,step:1,still:[7,13],stop:10,store:[1,12,13],str:[1,2,4,5,6,7,9,10],straightforward:[2,4],stratifiedkfold:0,strength:13,strict:16,string:[1,2,4,5,7,8,10,12],structur:[0,1,3,5,6,12,13],structure_col:[5,6],structurefeatur:5,stuck:14,style:[2,16],subject:16,sublicens:16,sublist:5,submiss:14,submit:[13,14],submodul:17,subpackag:17,subset:[5,7],substitut:16,successfulli:12,suit:[0,9],summar:[1,12,14],summari:[12,13],superced:0,supervis:13,support:[10,15],suppress:1,supress_version_mismatch:1,sure:[1,2,12],swallow:10,syntax:[0,2,12],system:12,tabl:14,take:[6,7,13],taken:3,target:[0,1,2,4,7,8,10,12,13,14],target_kei:7,target_properti:1,task:13,teardown:[6,11],techniqu:[0,7,14],tell:[12,14],test:[0,1,2,5,7,10,14,17],test_adaptor:[1,2],test_bandstructure_featur:6,test_bas:[1,2,5,17],test_baseestim:4,test_baseestimator_classif:4,test_cach:6,test_caching_powerup:9,test_classif:4,test_column_attr:6,test_compare_column:11,test_composition_featur:6,test_cor:[1,5,7],test_dataclean:8,test_datacleaner_big_nan_handler_warn:8,test_datacleaner_emergency_na_transform_imput:8,test_datacleaner_feature_na_method:8,test_datacleaner_na_method_feature_sample_interact:8,test_datacleaner_sample_na_method:8,test_debug:9,test_debug_singl:9,test_df:[0,8],test_dfmladaptor:4,test_dftransform:9,test_dftransformer_baseestimator_behavior:9,test_dos_featur:6,test_exclude_by_us:6,test_express:9,test_express_singl:9,test_feature_mismatch:4,test_featurereducer_advanc:8,test_featurereducer_bas:8,test_featurereducer_classif:8,test_featurereducer_combin:8,test_featurereducer_pca:8,test_featurereducer_transfer:8,test_featurize_bsdo:6,test_featurize_composit:6,test_featurize_structur:6,test_featurizers_by_us:6,test_fitting_decor:11,test_from_preset:9,test_fset:6,test_function:6,test_get_vers:11,test_heavi:9,test_instanti:9,test_is_greater_bett:11,test_log:[1,10],test_logger_initi:11,test_lower_corr_clf:8,test_manual_feature_reduct:8,test_miss:9,test_ml:[1,10],test_n_jobs_powerup:9,test_pipelin:[1,4,17],test_pkg:[1,10],test_precheck:6,test_predict:1,test_preset:[1,6,17],test_product:9,test_reb:8,test_regress:4,test_regression_or_classif:11,test_san:6,test_save_dict_to_fil:11,test_saving_feature_from_remov:8,test_set:[1,5],test_sets_not_empti:6,test_structure_featur:6,test_structurefeaturizers_needs_fit:6,test_training_onli:4,test_transfer:6,test_treebasedfeaturereduct:8,testadaptorbad:4,testadaptorgood:4,testallfeatur:6,testautofeatur:6,testbaseautomltransform:4,testbasetransform:9,testcas:[4,6,8,9,11],testfeaturereduct:8,testfeaturizerset:6,testlogtool:11,testmatpip:9,testmatpipepreset:9,testmatpipesetup:9,testmltool:11,testpackagetool:11,testpreprocess:8,testsinglepipelineadaptor:4,testtpotadaptor:4,testtransformerbad:9,testtransformergood:9,text:[10,12,14],than:[1,5,7,12],thei:[0,5],them:[0,7],theori:16,thereof:16,thermodynam:14,thi:[0,1,2,3,5,6,7,8,10,12,13,14,16,18],thing:0,those:[6,7],though:[2,4,5,12],thousand:5,threshold:[7,12],through:[0,7,13,14,15,16],time:[7,12,13,14],timeli:1,timestamp:12,to_numer:7,too:0,tool:[7,10,12,13,14],top:[0,7,9,12],tort:16,total:7,tpot:[0,1,2,3,10],tpot_config:[1,2],tpot_kwarg:2,tpotadaptor:[0,1,2,12],tpotbas:2,tpotclassifi:[2,4],tpotregressor:2,track:14,train:[0,1,2,7,14],train_df:[12,14],training_df:1,transferr:1,transform:[0,1,2,5,7,8,9,10,11,12],transform_kwarg:[1,2],transformermixin:1,tree:[1,7,12],tree_importance_percentil:7,tree_model:7,treefeaturereduc:[7,12],troubleshoot:18,troublesom:7,tune:[0,14],tupl:7,tutori:[12,14],two:7,txt:10,type:[1,2,4,5,6,7,8,9,10,11,12,13],typic:12,ultra:5,unabl:8,uncommon:7,under:[14,16],undergo:5,understand:14,unfair:0,uniqu:2,unittest:[4,6,8,9,11],univers:16,unknown:[12,14],unknown_df:[1,14],unless:[2,4],updat:6,upgrad:[1,16],url:13,usag:[5,14],use:[0,1,2,3,5,6,7,12,14,15,16],used:[0,1,2,4,5,7,10,12,14,16],useful:[5,14],user:[0,1,5,15],uses:[0,1,14],using:[0,1,2,3,7,12,13,14],util:[1,17],valid:[0,5,7],valu:[1,5,7,12],valv:12,variabl:[7,13],variou:[1,7],vector:5,veri:[0,1,12],version:[1,5,10,15],versionerror:10,via:[1,5,7,13,15],view:13,virtual:15,wai:[0,1,12,14,16],wang:14,want:[0,1,2,3,5,9,10,12,14],warn:[0,7,8,12],warranti:16,were:[0,7,12],what:12,whatsoev:16,when:[0,1,2,6,8,10,12],where:[0,1,8,9,10,12,14],whether:[1,2,5,7,10,16],which:[0,1,2,4,5,7,8,10,12,14],wide:13,window:15,within:12,without:[0,7,10,16],work:[0,1,5,6,7,12,16],worri:10,wors:7,would:12,wrapper:[2,5,7,10],write:[0,12],written:[10,16],wrong:8,xgb:1,xgbclassifi:0,xgboost:[0,1],xgbregressor:0,yaml:[10,12],yield:13,yml:10,you:[0,1,2,5,9,10,12,13,14,15,16,18],your:[0,14,16],zero:7,zip:13},titles:["Advanced Usage","automatminer package","automatminer.automl package","automatminer.automl.config package","automatminer.automl.tests package","automatminer.featurization package","automatminer.featurization.tests package","automatminer.preprocessing package","automatminer.preprocessing.tests package","automatminer.tests package","automatminer.utils package","automatminer.utils.tests package","Basic Usage","MatBench benchmark","automatminer documentation","Installation","License","automatminer","Tutorials and Support"],titleterms:{"new":14,Using:[0,12],access:13,adaptor:2,advanc:0,api:14,automatmin:[1,2,3,4,5,6,7,8,9,10,11,14,17],automl:[2,3,4],base:[1,2,5],basic:12,benchmark:[0,13],cite:14,config:3,contact:14,content:[1,2,3,4,5,6,7,8,9,10,11],contribut:14,core:[5,7],custom:0,dataset:13,dftransform:0,differ:12,document:14,down:13,examin:12,featur:[5,6],feature_select:7,from:15,get:13,how:14,individu:0,info:13,initi:12,instal:15,later:12,licens:16,load:13,log:[10,12],make:12,manual:14,matbench:[13,14],modul:[1,2,3,4,5,6,7,8,9,10,11],monitor:12,overview:[13,14],packag:[1,2,3,4,5,6,7,8,9,10,11],pip:15,pipelin:[0,1,12],pkg:10,practic:0,predict:12,preprocess:[7,8],preset:[1,12],pypi:15,quick:12,remind:12,run:0,save:12,saver:0,set:5,sourc:15,submodul:[1,2,3,4,5,6,7,8,9,10,11],subpackag:[1,2,5,7,10],support:[14,18],test:[4,6,8,9,11],test_adaptor:4,test_bas:[4,6,9],test_cor:[6,8],test_log:11,test_ml:11,test_pipelin:9,test_pkg:11,test_preset:9,test_set:6,time:0,tool:0,tpot_config:3,train:12,tutori:18,usag:[0,12],user:14,using:15,util:[10,11],what:14,work:14,your:12}})
\ No newline at end of file
diff --git a/docs/source/datasets.rst b/docs/source/datasets.rst
index 6f52dcd9..c74ec98a 100644
--- a/docs/source/datasets.rst
+++ b/docs/source/datasets.rst
@@ -131,7 +131,7 @@ procedures, etc.) on a dataset with :code:`matminer.datasets.get_all_dataset_inf
     Description: Matbench v0.1 dataset for predicting steel yield strengths from chemical composition alone. Retrieved from Citrine informatics. Deduplicated.
     Columns:
         composition: Chemical formula.
-        yield strength: Target variable. Experimentally measured steel yield strengths, in GPa.
+        yield strength: Target variable. Experimentally measured steel yield strengths, in MPa.
     Num Entries: 312
     Reference: https://citrination.com/datasets/153092/
     Bibtex citations: ['@misc{Citrine Informatics,\ntitle = {Mechanical properties of some steels},\nhowpublished = {\\url{https://citrination.com/datasets/153092/},\n}']

From 7c696df38e5c2dadf40d3be313eabb9de7d4f00f Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Mon, 10 Aug 2020 12:09:21 -0700
Subject: [PATCH 4/7] fix support forum

---
 docs/_sources/index.rst.txt | 2 +-
 docs/index.html             | 2 +-
 docs/source/index.rst       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/docs/_sources/index.rst.txt b/docs/_sources/index.rst.txt
index e460e525..b41163ad 100644
--- a/docs/_sources/index.rst.txt
+++ b/docs/_sources/index.rst.txt
@@ -150,7 +150,7 @@ Want to see something added or changed? Some ways to get involved are:
 - Contribute code! You can do this by forking
   `Automatminer on Github <https://github.com/hackingmaterials/automatminer>`_
   and submitting a pull request.
-- Post to our `support forum <https://hackingmaterials.discourse.group/c/matminer>`_. Don't be shy, we look forward to feedback!
+- Post to our `support forum <https://matsci.org/c/matminer/>`_. Don't be shy, we look forward to feedback!
 
 See our `contribution guidelines
 <https://github.com/hackingmaterials/automatminer/blob/master/CONTRIBUTING.md>`_
diff --git a/docs/index.html b/docs/index.html
index a877f7d8..2cd37dc6 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -210,7 +210,7 @@ <h1>Contributing / Contact / Support<a class="headerlink" href="#contributing-co
 <li><p>Contribute code! You can do this by forking
 <a class="reference external" href="https://github.com/hackingmaterials/automatminer">Automatminer on Github</a>
 and submitting a pull request.</p></li>
-<li><p>Post to our <a class="reference external" href="https://hackingmaterials.discourse.group/c/matminer">support forum</a>. Don’t be shy, we look forward to feedback!</p></li>
+<li><p>Post to our <a class="reference external" href="https://matsci.org/c/matminer/">support forum</a>. Don’t be shy, we look forward to feedback!</p></li>
 </ul>
 <p>See our <a class="reference external" href="https://github.com/hackingmaterials/automatminer/blob/master/CONTRIBUTING.md">contribution guidelines</a>
 for more inspect. For a list of contributors, see our
diff --git a/docs/source/index.rst b/docs/source/index.rst
index e460e525..b41163ad 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -150,7 +150,7 @@ Want to see something added or changed? Some ways to get involved are:
 - Contribute code! You can do this by forking
   `Automatminer on Github <https://github.com/hackingmaterials/automatminer>`_
   and submitting a pull request.
-- Post to our `support forum <https://hackingmaterials.discourse.group/c/matminer>`_. Don't be shy, we look forward to feedback!
+- Post to our `support forum <https://matsci.org/c/matminer/>`_. Don't be shy, we look forward to feedback!
 
 See our `contribution guidelines
 <https://github.com/hackingmaterials/automatminer/blob/master/CONTRIBUTING.md>`_

From 4fb77dc0561097d1530611570dcd5009a09027df Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Thu, 10 Sep 2020 20:54:06 -0700
Subject: [PATCH 5/7] update dev

---
 automatminer_dev/config.py                    |  13 ++
 .../matbench/dataset_creation/__init__.py     |   0
 .../{ => dataset_creation}/castelli.py        |   0
 .../{ => dataset_creation}/dielectric.py      |   0
 .../{ => dataset_creation}/expt_gap.py        |   0
 .../{ => dataset_creation}/expt_is_metal.py   |   0
 .../matbench/{ => dataset_creation}/glass.py  |   0
 .../matbench/{ => dataset_creation}/jdft2d.py |   0
 .../{ => dataset_creation}/mp_eform.py        |   0
 .../{ => dataset_creation}/mp_elasticity.py   |   0
 .../{ => dataset_creation}/mp_gaps.py         |   0
 .../{ => dataset_creation}/phonons.py         |   0
 .../matbench/{ => dataset_creation}/steels.py |   0
 automatminer_dev/matbench/docs/__init__.py    |   0
 .../formatting_matbench_table.py}             |   8 +
 .../matbench/mpcontribs/__init__.py           |   0
 .../matbench/mpcontribs/upload.py             | 138 ++++++++++++++++++
 requirements_dev.txt                          |   2 +
 18 files changed, 161 insertions(+)
 create mode 100644 automatminer_dev/matbench/dataset_creation/__init__.py
 rename automatminer_dev/matbench/{ => dataset_creation}/castelli.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/dielectric.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/expt_gap.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/expt_is_metal.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/glass.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/jdft2d.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/mp_eform.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/mp_elasticity.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/mp_gaps.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/phonons.py (100%)
 rename automatminer_dev/matbench/{ => dataset_creation}/steels.py (100%)
 create mode 100644 automatminer_dev/matbench/docs/__init__.py
 rename automatminer_dev/matbench/{get_info.py => docs/formatting_matbench_table.py} (87%)
 create mode 100644 automatminer_dev/matbench/mpcontribs/__init__.py
 create mode 100644 automatminer_dev/matbench/mpcontribs/upload.py

diff --git a/automatminer_dev/config.py b/automatminer_dev/config.py
index 2ce6044b..01d522ed 100644
--- a/automatminer_dev/config.py
+++ b/automatminer_dev/config.py
@@ -29,6 +29,7 @@
     "target": "log10(K_VRH)",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": None,
 }
 
 LOG_GVRH = {
@@ -37,6 +38,7 @@
     "target": "log10(G_VRH)",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": None,
 }
 
 DIELECTRIC = {
@@ -45,6 +47,7 @@
     "target": "n",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": None,
 }
 
 JDFT2D = {
@@ -53,6 +56,7 @@
     "target": "exfoliation_en",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "meV/atom"
 }
 
 MP_GAP = {
@@ -61,6 +65,7 @@
     "target": "gap pbe",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "eV"
 }
 
 MP_IS_METAL = {
@@ -69,6 +74,7 @@
     "target": "is_metal",
     "problem_type": AMM_CLF_NAME,
     "clf_pos_label": True,
+    "unit": None
 }
 
 MP_E_FORM = {
@@ -77,6 +83,7 @@
     "target": "e_form",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "eV/atom"
 }
 
 PEROVSKITES = {
@@ -85,6 +92,7 @@
     "target": "e_form",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "eV"
 }
 
 GLASS = {
@@ -93,6 +101,7 @@
     "target": "gfa",
     "problem_type": AMM_CLF_NAME,
     "clf_pos_label": True,
+    "unit": None
 }
 
 EXPT_IS_METAL = {
@@ -101,6 +110,7 @@
     "target": "is_metal",
     "problem_type": AMM_CLF_NAME,
     "clf_pos_label": True,
+    "unit": None
 }
 
 EXPT_GAP = {
@@ -109,6 +119,7 @@
     "target": "gap expt",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "eV"
 }
 
 PHONONS = {
@@ -117,6 +128,7 @@
     "target": "last phdos peak",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "cm^-1"
 }
 
 STEELS = {
@@ -125,6 +137,7 @@
     "target": "yield strength",
     "problem_type": AMM_REG_NAME,
     "clf_pos_label": None,
+    "unit": "MPa"
 }
 
 BENCHMARK_DEBUG_SET = [JDFT2D, PHONONS, EXPT_IS_METAL, STEELS]
diff --git a/automatminer_dev/matbench/dataset_creation/__init__.py b/automatminer_dev/matbench/dataset_creation/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/automatminer_dev/matbench/castelli.py b/automatminer_dev/matbench/dataset_creation/castelli.py
similarity index 100%
rename from automatminer_dev/matbench/castelli.py
rename to automatminer_dev/matbench/dataset_creation/castelli.py
diff --git a/automatminer_dev/matbench/dielectric.py b/automatminer_dev/matbench/dataset_creation/dielectric.py
similarity index 100%
rename from automatminer_dev/matbench/dielectric.py
rename to automatminer_dev/matbench/dataset_creation/dielectric.py
diff --git a/automatminer_dev/matbench/expt_gap.py b/automatminer_dev/matbench/dataset_creation/expt_gap.py
similarity index 100%
rename from automatminer_dev/matbench/expt_gap.py
rename to automatminer_dev/matbench/dataset_creation/expt_gap.py
diff --git a/automatminer_dev/matbench/expt_is_metal.py b/automatminer_dev/matbench/dataset_creation/expt_is_metal.py
similarity index 100%
rename from automatminer_dev/matbench/expt_is_metal.py
rename to automatminer_dev/matbench/dataset_creation/expt_is_metal.py
diff --git a/automatminer_dev/matbench/glass.py b/automatminer_dev/matbench/dataset_creation/glass.py
similarity index 100%
rename from automatminer_dev/matbench/glass.py
rename to automatminer_dev/matbench/dataset_creation/glass.py
diff --git a/automatminer_dev/matbench/jdft2d.py b/automatminer_dev/matbench/dataset_creation/jdft2d.py
similarity index 100%
rename from automatminer_dev/matbench/jdft2d.py
rename to automatminer_dev/matbench/dataset_creation/jdft2d.py
diff --git a/automatminer_dev/matbench/mp_eform.py b/automatminer_dev/matbench/dataset_creation/mp_eform.py
similarity index 100%
rename from automatminer_dev/matbench/mp_eform.py
rename to automatminer_dev/matbench/dataset_creation/mp_eform.py
diff --git a/automatminer_dev/matbench/mp_elasticity.py b/automatminer_dev/matbench/dataset_creation/mp_elasticity.py
similarity index 100%
rename from automatminer_dev/matbench/mp_elasticity.py
rename to automatminer_dev/matbench/dataset_creation/mp_elasticity.py
diff --git a/automatminer_dev/matbench/mp_gaps.py b/automatminer_dev/matbench/dataset_creation/mp_gaps.py
similarity index 100%
rename from automatminer_dev/matbench/mp_gaps.py
rename to automatminer_dev/matbench/dataset_creation/mp_gaps.py
diff --git a/automatminer_dev/matbench/phonons.py b/automatminer_dev/matbench/dataset_creation/phonons.py
similarity index 100%
rename from automatminer_dev/matbench/phonons.py
rename to automatminer_dev/matbench/dataset_creation/phonons.py
diff --git a/automatminer_dev/matbench/steels.py b/automatminer_dev/matbench/dataset_creation/steels.py
similarity index 100%
rename from automatminer_dev/matbench/steels.py
rename to automatminer_dev/matbench/dataset_creation/steels.py
diff --git a/automatminer_dev/matbench/docs/__init__.py b/automatminer_dev/matbench/docs/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/automatminer_dev/matbench/get_info.py b/automatminer_dev/matbench/docs/formatting_matbench_table.py
similarity index 87%
rename from automatminer_dev/matbench/get_info.py
rename to automatminer_dev/matbench/docs/formatting_matbench_table.py
index 8a14ecfe..bd1ee747 100644
--- a/automatminer_dev/matbench/get_info.py
+++ b/automatminer_dev/matbench/docs/formatting_matbench_table.py
@@ -1,4 +1,12 @@
 from matminer.datasets.dataset_retrieval import load_dataset, get_available_datasets, get_all_dataset_info
+
+
+'''
+
+Helper function to format matbench documentation page.
+'''
+
+
 datasets = get_available_datasets(print_format=None)
 
 for dataset in datasets:
diff --git a/automatminer_dev/matbench/mpcontribs/__init__.py b/automatminer_dev/matbench/mpcontribs/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/automatminer_dev/matbench/mpcontribs/upload.py b/automatminer_dev/matbench/mpcontribs/upload.py
new file mode 100644
index 00000000..fda5d3cc
--- /dev/null
+++ b/automatminer_dev/matbench/mpcontribs/upload.py
@@ -0,0 +1,138 @@
+import wget, json, os
+from string import capwords
+from pybtex.database import parse_string
+import pybtex.errors
+from mpcontribs.client import Client
+from pymatgen import MPRester
+import tqdm
+
+
+# from matminer.datasets.dataset_retrieval import (
+#     get_all_dataset_info,
+#     get_available_datasets,
+#     load_dataset,
+# )
+
+from matminer.datasets import load_dataset
+
+from automatminer_dev.config import DIELECTRIC
+
+
+pybtex.errors.set_strict_mode(False)
+api_key = os.environ["MPCONTRIBS_API_KEY"]
+client = Client(api_key, host='ml-api.materialsproject.cloud')
+mprester = MPRester()
+
+
+# client.get_project("matbench_steels").pretty()
+
+
+fn = 'dataset_metadata.json'
+if not os.path.exists(fn):
+    wget.download(f'https://raw.githubusercontent.com/hackingmaterials/matminer/master/matminer/datasets/{fn}')
+metadata = json.load(open(fn, 'r'))
+metadata = {k: d for k, d in metadata.items() if "matbench" in k}
+
+
+
+# Creating new projects
+#######################
+# todo: might not have access to add new projects
+# for name, info in metadata.items():
+#     if "phonons" not in name:
+#         continue
+#
+#     print(f"Uploading {name}")
+#
+#     columns = {}
+#     for col, text in info['columns'].items():
+#         k = col.replace('_', '|').replace('-', '|').replace('(', ' ').replace(
+#             ')', '')
+#         columns[k] = text
+#
+#     project = {
+#         'is_public': True,
+#         'owner': 'ardunn@lbl.gov',
+#         "name": name,
+#         'title': name,  # TODO update and set long_title
+#         'authors': 'A. Dunn, A. Jain',
+#         'description': info['description'],
+#         'other': {
+#             'columns': columns,
+#             'entries': info['num_entries']
+#         },
+#         'references': []
+#     }
+#
+#     for ref in info['bibtex_refs']:
+#
+#         if name == "matbench_phonons":
+#             ref = ref.replace(
+#                 "petretto_dwaraknath_miranda_winston_giantomassi_rignanese_van setten_gonze_persson_hautier_2018",
+#                 "petretto2018")
+#
+#         bib = parse_string(ref, 'bibtex')
+#         for key, entry in bib.entries.items():
+#             key_is_doi = key.startswith('doi:')
+#             url = 'https://doi.org/' + key.split(':', 1)[
+#                 -1] if key_is_doi else entry.fields.get('url')
+#             k = 'Zhuo2018' if key_is_doi else capwords(key.replace('_', ''))
+#             if k.startswith('C2'):
+#                 k = 'Castelli2012'
+#             elif k.startswith('Landolt'):
+#                 k = 'LB1997'
+#             elif k == 'Citrine':
+#                 url = 'https://www.citrination.com'
+#
+#             if len(k) > 8:
+#                 k = k[:4] + k[-4:]
+#             project['references'].append({"label": k, "url": url})
+#
+#     try:
+#         print(client.projects.create_entry(project=project).result())
+#     except Exception as ex:
+#         print(
+#             ex)  # TODO should use get_entry to check existence -> use update_entry if project exists
+
+
+
+
+# Entering all contributions to projects
+########################################
+
+LIMIT = 100
+
+
+
+ds_config = DIELECTRIC
+name = "matbench_" + ds_config["name"]
+client.delete_contributions(name)
+print(f"Loading {name}")
+df = load_dataset(name)
+target = ds_config["target"]
+unit = f" {ds_config['unit']}" if ds_config["unit"] else ""
+
+
+#todo: PROBLEMATIC ENTRY IS DIELECTRIC INDEX 105
+
+# df = df.iloc[104:]
+
+chunks = (df.shape[0] - 1) // LIMIT + 1
+for j in range(chunks):
+    print(f"\tBatch {j} of {chunks}")
+    batch = df.iloc[j * LIMIT:(j + 1) * LIMIT]
+
+    contributions = []
+
+    for i, row in enumerate(batch.iterrows()):
+        entry = row[1]
+        contrib = {'project': name, 'is_public': True, 'structures': []}
+        s = entry.loc["structure"]
+        c = s.composition.get_integer_formula_and_factor()[0]
+        identifier = f"mb-{ds_config['name']}-{(j - 1) * LIMIT + i}"
+        contrib["identifier"] = identifier
+        contrib["data"] = {target: f"{entry.loc[target]}{unit}"}
+        contrib["formula"] = c
+        contrib["structures"].append(s)
+        contributions.append(contrib)
+    client.submit_contributions(contributions)
\ No newline at end of file
diff --git a/requirements_dev.txt b/requirements_dev.txt
index 19506027..37ca2ad9 100644
--- a/requirements_dev.txt
+++ b/requirements_dev.txt
@@ -7,3 +7,5 @@ isort==4.3.21
 pre-commit==1.18.3
 paramiko==2.6.0
 scp==0.13.2
+pcontribs-client==3.3.0
+wget==3.2
\ No newline at end of file

From 6c1ce01d0de9e6d6ae2d2d23c0c2ac043ff45c36 Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Thu, 17 Sep 2020 16:51:10 -0700
Subject: [PATCH 6/7] update mpcontribs upload

---
 automatminer_dev/config.py                    |  14 ++
 .../matbench/mpcontribs/upload.py             | 138 ++++++++++++++----
 2 files changed, 126 insertions(+), 26 deletions(-)

diff --git a/automatminer_dev/config.py b/automatminer_dev/config.py
index 01d522ed..945b8c43 100644
--- a/automatminer_dev/config.py
+++ b/automatminer_dev/config.py
@@ -156,3 +156,17 @@
     STEELS,
     PHONONS,
 ]
+
+HAS_STRUCTURE = [
+    LOG_KVRH,
+    LOG_GVRH,
+    DIELECTRIC,
+    JDFT2D,
+    MP_GAP,
+    MP_IS_METAL,
+    MP_E_FORM,
+    PEROVSKITES,
+    PHONONS
+]
+
+BENCHMARK_DICT = {ds["name"]: ds for ds in BENCHMARK_FULL_SET}
\ No newline at end of file
diff --git a/automatminer_dev/matbench/mpcontribs/upload.py b/automatminer_dev/matbench/mpcontribs/upload.py
index fda5d3cc..0d576f4d 100644
--- a/automatminer_dev/matbench/mpcontribs/upload.py
+++ b/automatminer_dev/matbench/mpcontribs/upload.py
@@ -1,11 +1,11 @@
-import wget, json, os
+import wget, json, os, math
 from string import capwords
 from pybtex.database import parse_string
 import pybtex.errors
 from mpcontribs.client import Client
-from pymatgen import MPRester
+from pymatgen import MPRester, Structure
 import tqdm
-
+import pprint
 
 # from matminer.datasets.dataset_retrieval import (
 #     get_all_dataset_info,
@@ -15,7 +15,7 @@
 
 from matminer.datasets import load_dataset
 
-from automatminer_dev.config import DIELECTRIC
+from automatminer_dev.config import DIELECTRIC, JDFT2D, PEROVSKITES, STEELS, BENCHMARK_FULL_SET, BENCHMARK_DICT, HAS_STRUCTURE
 
 
 pybtex.errors.set_strict_mode(False)
@@ -39,8 +39,6 @@
 #######################
 # todo: might not have access to add new projects
 # for name, info in metadata.items():
-#     if "phonons" not in name:
-#         continue
 #
 #     print(f"Uploading {name}")
 #
@@ -97,42 +95,130 @@
 
 
 
+
+# Map of canonical yet non-mpcontribs-compatible tagret nams to compatible (unicode, no punctuation) target names
+target_map = {
+    "yield strength": "σᵧ",
+    "log10(K_VRH)": "log₁₀Kᵛʳʰ",
+    "log10(G_VRH)": "log₁₀Gᵛʳʰ",
+    "n": "𝑛",
+    "exfoliation_en": "Eˣ",
+    "gap pbe": "Eᵍ",
+    "is_metal": "metallic",
+    "e_form": "Eᶠ",
+    "gfa": "glass",
+    "gap expt": "Eᵍ",
+    "last phdos peak": "ωᵐᵃˣ",
+}
+
+
+# # Getting project-level metadata in order
+# #########################################
+#
+# # Add warning to mpcontribs since the results will be stored out of order.
+# # Also, fix columns for new mpcontribs deployment
+# for name, info in metadata.items():
+#     mb_shortname = name.replace("matbench_", "")
+#
+#     description = info["description"] + f" If you are viewing this on MPContribs-ML interactively, please ensure the order of the identifiers is sequential (mb-{mb_shortname}-0001, mb-{mb_shortname}-0002, etc.) before benchmarking."
+#     if "For benchmarking" not in description:
+#         print(name, description)
+#
+#     has_structure = mb_shortname in [ds["name"] for ds in HAS_STRUCTURE]
+#     primitive_key = "structure" if has_structure else "composition"
+#     target = BENCHMARK_DICT[mb_shortname]["target"]
+#
+#     print(client.projects.update_entry(
+#         pk=name,
+#         project={
+#             "description": description,
+#             'other.columns': {
+#                 target_map[target]: metadata[name]["columns"][target],
+#                 primitive_key: metadata[name]["columns"][primitive_key]
+#             }
+#         }).result())
+
+
+
+
 # Entering all contributions to projects
 ########################################
 
-LIMIT = 100
+
+# steels.........X
+# log_kvrh.......
+# log_gvrh.......
+# dielectric.....
+# jdft2d.........X
+# expt_gap.......X
+# expt_is_metal..X
+# phonons........
+# mp_is_metal....
+# mp_gap.........
+# glass..........X
+# mp_e_form......
+# perovskites....
+
 
 
 
-ds_config = DIELECTRIC
+ds_config = BENCHMARK_DICT["jdft2d"]
+
 name = "matbench_" + ds_config["name"]
-client.delete_contributions(name)
 print(f"Loading {name}")
 df = load_dataset(name)
 target = ds_config["target"]
 unit = f" {ds_config['unit']}" if ds_config["unit"] else ""
 
 
-#todo: PROBLEMATIC ENTRY IS DIELECTRIC INDEX 105
+# print(f"Updating 'other' column entries of {name} with unicode.")
+# print(client.projects.update_entry(pk=name, project={
+#     'other.columns': {
+#         target_map[target]: metadata[name]["columns"][target],
+#         "structure": metadata[name]["columns"]["structure"]
+#         # "composition": metadata[name]["columns"]["composition"]
+#     }
+# }).result())
+
+
+
+print(f"Deleting contributions of {name}")
+client.delete_contributions(name)
+
 
-# df = df.iloc[104:]
 
-chunks = (df.shape[0] - 1) // LIMIT + 1
-for j in range(chunks):
-    print(f"\tBatch {j} of {chunks}")
-    batch = df.iloc[j * LIMIT:(j + 1) * LIMIT]
+print(f"Assembling and uploading contributions for {name}")
+structure_filename = "/Users/ardunn/Downloads/outfile.cif"
+contributions = []
+id_prefix = df.shape[0]
 
-    contributions = []
 
-    for i, row in enumerate(batch.iterrows()):
-        entry = row[1]
-        contrib = {'project': name, 'is_public': True, 'structures': []}
+id_n_zeros = math.floor(math.log(df.shape[0], 10)) + 1
+
+df = df.iloc[:2]
+
+for i, row in tqdm.tqdm(enumerate(df.iterrows())):
+    entry = row[1]
+    contrib = {'project': name, 'is_public': True}
+
+    if "structure" in entry.index:
+        structures = []
         s = entry.loc["structure"]
+        s.to("cif", structure_filename)
+        s = Structure.from_file(structure_filename)
         c = s.composition.get_integer_formula_and_factor()[0]
-        identifier = f"mb-{ds_config['name']}-{(j - 1) * LIMIT + i}"
-        contrib["identifier"] = identifier
-        contrib["data"] = {target: f"{entry.loc[target]}{unit}"}
-        contrib["formula"] = c
-        contrib["structures"].append(s)
-        contributions.append(contrib)
-    client.submit_contributions(contributions)
\ No newline at end of file
+        contrib["structures"] = [s]
+
+    else:
+        c = entry["composition"]
+
+    id_number = f"{i+1:0{id_n_zeros}d}"
+    identifier = f"mb-{ds_config['name']}-{id_number}"
+    contrib["identifier"] = identifier
+
+    contrib["data"] = {target_map[target]: f"{entry.loc[target]}{unit}"}
+    contrib["formula"] = c
+    contributions.append(contrib)
+
+pprint.pprint(contributions)
+client.submit_contributions(contributions)
\ No newline at end of file

From 5baa4ef2b355fa31344a8371dc488a4ad05571e4 Mon Sep 17 00:00:00 2001
From: ardunn <ardunn@lbl.gov>
Date: Mon, 21 Sep 2020 20:07:22 -0700
Subject: [PATCH 7/7] update upload to mpcontribs

---
 .../matbench/mpcontribs/upload.py             | 87 +++++++++----------
 1 file changed, 41 insertions(+), 46 deletions(-)

diff --git a/automatminer_dev/matbench/mpcontribs/upload.py b/automatminer_dev/matbench/mpcontribs/upload.py
index 0d576f4d..bca132a7 100644
--- a/automatminer_dev/matbench/mpcontribs/upload.py
+++ b/automatminer_dev/matbench/mpcontribs/upload.py
@@ -160,65 +160,60 @@
 # perovskites....
 
 
+for ds in ["dielectric", "phonons", "mp_gap", "mp_is_metal", "perovskites", "mp_e_form"]:
 
+    ds_config = BENCHMARK_DICT[ds]
 
-ds_config = BENCHMARK_DICT["jdft2d"]
+    name = "matbench_" + ds_config["name"]
+    print(f"Loading {name}")
+    df = load_dataset(name)
+    target = ds_config["target"]
+    unit = f" {ds_config['unit']}" if ds_config["unit"] else ""
 
-name = "matbench_" + ds_config["name"]
-print(f"Loading {name}")
-df = load_dataset(name)
-target = ds_config["target"]
-unit = f" {ds_config['unit']}" if ds_config["unit"] else ""
 
-
-# print(f"Updating 'other' column entries of {name} with unicode.")
-# print(client.projects.update_entry(pk=name, project={
-#     'other.columns': {
-#         target_map[target]: metadata[name]["columns"][target],
-#         "structure": metadata[name]["columns"]["structure"]
-#         # "composition": metadata[name]["columns"]["composition"]
-#     }
-# }).result())
-
-
-
-print(f"Deleting contributions of {name}")
-client.delete_contributions(name)
+    # print(f"Updating 'other' column entries of {name} with unicode.")
+    # print(client.projects.update_entry(pk=name, project={
+    #     'other.columns': {
+    #         target_map[target]: metadata[name]["columns"][target],
+    #         "structure": metadata[name]["columns"]["structure"]
+    #         # "composition": metadata[name]["columns"]["composition"]
+    #     }
+    # }).result())
 
 
 
-print(f"Assembling and uploading contributions for {name}")
-structure_filename = "/Users/ardunn/Downloads/outfile.cif"
-contributions = []
-id_prefix = df.shape[0]
+    # print(f"Deleting contributions of {name}")
+    # client.delete_contributions(name)
 
 
-id_n_zeros = math.floor(math.log(df.shape[0], 10)) + 1
+    print(f"Assembling and uploading contributions for {name}")
+    structure_filename = "/Users/ardunn/Downloads/outfile.cif"
+    contributions = []
+    id_prefix = df.shape[0]
 
-df = df.iloc[:2]
 
-for i, row in tqdm.tqdm(enumerate(df.iterrows())):
-    entry = row[1]
-    contrib = {'project': name, 'is_public': True}
+    id_n_zeros = math.floor(math.log(df.shape[0], 10)) + 1
+    for i, row in tqdm.tqdm(enumerate(df.iterrows())):
+        entry = row[1]
+        contrib = {'project': name, 'is_public': True}
 
-    if "structure" in entry.index:
-        structures = []
-        s = entry.loc["structure"]
-        s.to("cif", structure_filename)
-        s = Structure.from_file(structure_filename)
-        c = s.composition.get_integer_formula_and_factor()[0]
-        contrib["structures"] = [s]
+        if "structure" in entry.index:
+            structures = []
+            s = entry.loc["structure"]
+            s.to("cif", structure_filename)
+            s = Structure.from_file(structure_filename)
+            c = s.composition.get_integer_formula_and_factor()[0]
+            contrib["structures"] = [s]
 
-    else:
-        c = entry["composition"]
+        else:
+            c = entry["composition"]
 
-    id_number = f"{i+1:0{id_n_zeros}d}"
-    identifier = f"mb-{ds_config['name']}-{id_number}"
-    contrib["identifier"] = identifier
+        id_number = f"{i+1:0{id_n_zeros}d}"
+        identifier = f"mb-{ds_config['name']}-{id_number}"
+        contrib["identifier"] = identifier
 
-    contrib["data"] = {target_map[target]: f"{entry.loc[target]}{unit}"}
-    contrib["formula"] = c
-    contributions.append(contrib)
+        contrib["data"] = {target_map[target]: f"{entry.loc[target]}{unit}"}
+        contrib["formula"] = c
+        contributions.append(contrib)
 
-pprint.pprint(contributions)
-client.submit_contributions(contributions)
\ No newline at end of file
+    client.submit_contributions(contributions, per_page=10)
\ No newline at end of file