diff --git a/dev-requirements.txt b/dev-requirements.txt index e59d6d61..4ed61886 100644 --- a/dev-requirements.txt +++ b/dev-requirements.txt @@ -15,7 +15,7 @@ cffi==1.15.0 charset-normalizer==2.0.9 cif2cell==2.0.0a3 click==8.0.3 -codecov==2.1.12 +codecov==2.1.13 coverage==6.2 cryptography==36.0.1 cycler==0.11.0 @@ -149,4 +149,4 @@ Werkzeug==2.0.2 wrapt==1.13.3 xmltodict==0.12.0 yfinance==0.1.67 -zipp==3.6.0 \ No newline at end of file +zipp==3.6.0 diff --git a/docs/requirements.txt b/docs/requirements.txt index e60dd07a..3e1cb05b 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -16,7 +16,7 @@ cffi==1.15.0 charset-normalizer==2.0.9 cif2cell==2.0.0a3 click==8.0.3 -codecov==2.1.12 +codecov==2.1.13 coverage==6.2 cryptography==36.0.1 cycler==0.11.0 @@ -151,4 +151,4 @@ Werkzeug==2.0.2 wrapt==1.13.3 xmltodict==0.12.0 yfinance==0.1.67 -zipp==3.6.0 \ No newline at end of file +zipp==3.6.0 diff --git a/docs/source/databases.rst b/docs/source/databases.rst index 7a3d411e..26606c82 100644 --- a/docs/source/databases.rst +++ b/docs/source/databases.rst @@ -45,6 +45,18 @@ Database name Number of data-points Description ``qmof`` 20425 Bandgaps and total energies of metal organic frameowrks in QMOF database ``hmof`` 137651 Hypothetical MOF database +``snumat`` 10481 Bandgaps with hybrid functional +``arXiv`` 12500 arXiv dataset 1.8 million title, abstract and id dataset +``ssub`` 1726 SSUB formation energy for chemical formula dataset +``mlearn`` 1730 Machine learning force-field for elements datasets +``ocp10k`` 59886 Open Catalyst 10000 training, rest validation and test dataset +``ocp100k`` 149886 Open Catalyst 100000 training, rest validation and test dataset +``ocp_all`` 510214 Open Catalyst 460328 training, rest validation and test dataset +``tinnet_N`` 329 TinNet Nitrogen catalyst dataset +``tinnet_O`` 747 TinNet Oxygen catalyst dataset +``tinnet_OH`` 748 TinNet OH group catalyst dataset +``supercon_3d`` 1058 3D superconductor DFT dataset +``supercon_2d`` 161 2D superconductor DFT dataset ``cfid_3d`` 55723 Various 3D materials properties in JARVIS-DFT database computed with OptB88vdW and TBmBJ methods with CFID ``raw_files`` 144895 Figshare links to download raw calculations VASP files diff --git a/jarvis/__init__.py b/jarvis/__init__.py index ba536cfb..115a5935 100644 --- a/jarvis/__init__.py +++ b/jarvis/__init__.py @@ -1,5 +1,5 @@ """Version number.""" -__version__ = "2023.04.06" +__version__ = "2023.05.26" import os diff --git a/jarvis/db/figshare.py b/jarvis/db/figshare.py index f9e4eba7..c91b0025 100644 --- a/jarvis/db/figshare.py +++ b/jarvis/db/figshare.py @@ -256,6 +256,121 @@ def get_db_info(): "Obtaining CORD19 dataset 223k...", "https://github.com/usnistgov/cord19-cdcs-nist", ], + # https://doi.org/10.6084/m9.figshare.22583677 + "ssub": [ + "https://figshare.com/ndownloader/files/40084921", + "ssub.json", + "Obtaining SSUB dataset 1726...", + "https://github.com/wolverton-research-group/qmpy", + ], + # https://doi.org/10.6084/m9.figshare.22721047 + "mlearn": [ + "https://figshare.com/ndownloader/files/40424156", + "mlearn.json", + "Obtaining mlearn dataset 1730...", + "https://github.com/materialsvirtuallab/mlearn", + ], + # https://doi.org/10.6084/m9.figshare.22814318 + "foundry_ml_exp_bandgaps": [ + "https://figshare.com/ndownloader/files/40557743", + "foundry_ml_exp_bandgaps.json", + "Obtaining foundry_ml_exp_bandgaps dataset 2069...", + "https://foundry-ml.org/#/datasets/10.18126/wg3u-g8vu", + ], + # ToFix# https://doi.org/10.6084/m9.figshare.22815926 + # "mat_scholar_ner": [ + # "https://figshare.com/ndownloader/files/40563593", + # "mat_scholar_ner.json", + # "Obtaining mat_scholar_ner dataset XYZ...", + # "https://pubs.acs.org/doi/10.1021/acs.jcim.9b00470", + # ], + # https://doi.org/10.6084/m9.figshare.22817633 + # Contains repeats + "ocp10k": [ + "https://figshare.com/ndownloader/files/40566122", + "ocp10k.json", + "Obtaining OCP 10k train dataset, 59886...", + "https://github.com/Open-Catalyst-Project/ocp", + ], + # https://doi.org/10.6084/m9.figshare.22817651 + "arxiv_summary": [ + "https://figshare.com/ndownloader/files/40566137", + "arxiv_summary.json", + "Obtaining arxiv summary cond.mat dataset 137927...", + "https://github.com/usnistgov/chemnlp", + ], + # TODO:PubChem + # https://doi.org/10.6084/m9.figshare.22975787 + "supercon_chem": [ + "https://figshare.com/ndownloader/files/40719260", + "supercon_chem.json", + "Obtaining supercon chem dataset 16414...", + "https://www.nature.com/articles/s41524-018-0085-8", + ], + # https://doi.org/10.6084/m9.figshare.22976285 + "mag2d_chem": [ + "https://figshare.com/ndownloader/files/40720004", + "mag2d_chem.json", + "Obtaining magnetic 2D chem dataset 226...", + "https://doi.org/10.24435/materialscloud:2019.0020/v1", + ], + # https://doi.org/10.6084/m9.figshare.23000573 + "vacancydb": [ + "https://figshare.com/ndownloader/files/40750811", + "vacancydb.json", + "Obtaining vacancy dataset 464...", + "https://arxiv.org/abs/2205.08366", + ], + # Contains repeats + # https://doi.org/10.6084/m9.figshare.23206193 + "ocp100k": [ + "https://figshare.com/ndownloader/files/40902845", + "ocp100k.json", + "Obtaining OCP100k dataset 149886...", + "https://github.com/Open-Catalyst-Project/ocp", + ], + # https://doi.org/10.6084/m9.figshare.23250629 + "ocp_all": [ + "https://figshare.com/ndownloader/files/40974599", + "ocp_all.json", + "Obtaining OCPall dataset 510214...", + "https://github.com/Open-Catalyst-Project/ocp", + ], + # https://doi.org/10.6084/m9.figshare.23225687 + "tinnet_N": [ + "https://figshare.com/ndownloader/files/40934285", + "tinnet_N.json", + "Obtaining TinNet Nitrogen dataset 329...", + "https://github.com/hlxin/tinnet", + ], + # https://doi.org/10.6084/m9.figshare.23254151 + "tinnet_O": [ + "https://figshare.com/ndownloader/files/40978943", + "tinnet_O.json", + "Obtaining TinNet Oxygen dataset 747...", + "https://github.com/hlxin/tinnet", + ], + # https://doi.org/10.6084/m9.figshare.23254154 + "tinnet_OH": [ + "https://figshare.com/ndownloader/files/40978949", + "tinnet_OH.json", + "Obtaining TinNet OH dataset 748...", + "https://github.com/hlxin/tinnet", + ], + # https://doi.org/10.6084/m9.figshare.21370572 + "supercon_3d": [ + "https://figshare.com/ndownloader/files/38307921", + "jarvis_epc_data_figshare_1058.json", + "Obtaining supercond. Tc dataset 1058...", + "https://www.nature.com/articles/s41524-022-00933-1", + ], + # https://doi.org/10.6084/m9.figshare.21370572 + "supercon_2d": [ + "https://figshare.com/ndownloader/files/38950433", + "jarvis_epc_data_2d.json", + "Obtaining supercond. Tc dataset 161...", + "https://doi.org/10.1021/acs.nanolett.2c04420", + ], # https://doi.org/10.6084/m9.figshare.13154159 "raw_files": [ "https://ndownloader.figshare.com/files/25295732", diff --git a/setup.py b/setup.py index d03ef968..d5949a27 100644 --- a/setup.py +++ b/setup.py @@ -11,7 +11,7 @@ setup( name="jarvis-tools", - version="2023.04.06", + version="2023.05.26", long_description=long_d, install_requires=[ "numpy>=1.19.5",