Graph, DB and IR module update (#162)

* Wannier update (#136)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Increase coverage. (#137)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* Wannier TB for phonons (#138)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* QAlgo

* Create CODE_OF_CONDUCT.md (#139)

* Update README.rst

* Atoms POSCAR Order update.

* Qiskit tests.

* Lint fix.

* Wien2K extra test, ene file.

* WT.

* WT added.

* Qiskit depedendence.

* Qiskit version.

* Qiskit version.

* Qiskit version.

* Update requirements-ci.txt

* Update requirements-ci.txt

* Update action_build.yml

* Update shell.nix

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Ignore QAlgo tests.

* Make qiskit work.

* Make qiskit work.

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Delete __init__.py

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Pennylane fix attempt.

* Update test_hermsolver.py

* Test ham.

* Test ham.

* Update inputs.py

* Test ham.

* Update action_build.yml

* Update inputs.py

* Create __init__.py

* Test ham.

* Update test_hermsolver.py

* Update test_hermsolver.py

* Test Circuit.

* Update test_hermsolver.py

* Update action_build.yml

* Aer

* Aer .

* Var circuit added.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Fix POSCAR order issue.

* Version change.

* Poscar write fix, CIF reader fix.

* Develop (#141)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* QAlgo

* Atoms POSCAR Order update.

* Qiskit tests.

* Lint fix.

* Wien2K extra test, ene file.

* WT.

* WT added.

* Qiskit depedendence.

* Qiskit version.

* Qiskit version.

* Qiskit version.

* Update requirements-ci.txt

* Update requirements-ci.txt

* Update action_build.yml

* Update shell.nix

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Ignore QAlgo tests.

* Make qiskit work.

* Make qiskit work.

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Delete __init__.py

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Pennylane fix attempt.

* Update test_hermsolver.py

* Test ham.

* Test ham.

* Update inputs.py

* Test ham.

* Update action_build.yml

* Update inputs.py

* Create __init__.py

* Test ham.

* Update test_hermsolver.py

* Update test_hermsolver.py

* Test Circuit.

* Update test_hermsolver.py

* Update action_build.yml

* Aer

* Aer .

* Var circuit added.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Ready for master branch.

* Update shell.nix

* Update __init__.py

* Version change.

* Poscar format fix. (#142)

* Fix POSCAR order issue.

* Version change.

* Poscar write fix, CIF reader fix.

* Develop (#141)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* QAlgo

* Atoms POSCAR Order update.

* Qiskit tests.

* Lint fix.

* Wien2K extra test, ene file.

* WT.

* WT added.

* Qiskit depedendence.

* Qiskit version.

* Qiskit version.

* Qiskit version.

* Update requirements-ci.txt

* Update requirements-ci.txt

* Update action_build.yml

* Update shell.nix

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Ignore QAlgo tests.

* Make qiskit work.

* Make qiskit work.

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Delete __init__.py

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Pennylane fix attempt.

* Update test_hermsolver.py

* Test ham.

* Test ham.

* Update inputs.py

* Test ham.

* Update action_build.yml

* Update inputs.py

* Create __init__.py

* Test ham.

* Update test_hermsolver.py

* Update test_hermsolver.py

* Test Circuit.

* Update test_hermsolver.py

* Update action_build.yml

* Aer

* Aer .

* Var circuit added.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Ready for master branch.

* Update shell.nix

* Update __init__.py

* Minor fix in figshare and spectrum.

* Minor fix in figshare and spectrum.

* Update README.rst

* Lint fix.

* Minor fix in figshare and spectrum. (#143)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* QAlgo

* Atoms POSCAR Order update.

* Qiskit tests.

* Lint fix.

* Wien2K extra test, ene file.

* WT.

* WT added.

* Qiskit depedendence.

* Qiskit version.

* Qiskit version.

* Qiskit version.

* Update requirements-ci.txt

* Update requirements-ci.txt

* Update action_build.yml

* Update shell.nix

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Ignore QAlgo tests.

* Make qiskit work.

* Make qiskit work.

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Delete __init__.py

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Pennylane fix attempt.

* Update test_hermsolver.py

* Test ham.

* Test ham.

* Update inputs.py

* Test ham.

* Update action_build.yml

* Update inputs.py

* Create __init__.py

* Test ham.

* Update test_hermsolver.py

* Update test_hermsolver.py

* Test Circuit.

* Update test_hermsolver.py

* Update action_build.yml

* Aer

* Aer .

* Var circuit added.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Fix POSCAR order issue.

* Version change.

* Poscar write fix, CIF reader fix.

* Develop (#141)

* Added OQMD, MP, QM9 CFID datasets.

* Added OQMD, MP, QM9 CFID datasets.

* vasp2xml schema update.

* Update config.yml

* XRD DB making bug fix, scattering.json update.

* Minor bug fix in vasp_to_xml.py

* Add license.

* Add license, pin versions

* Remove circle.

* Update shell.nix

* Vasprun single element bug fix.

* Minor updates.

* DB XML and VASP Workflow fix.

* AFLOW CFID added, VASP_PSP_DIR fix.

* Linting fix, new version release.

* Wannier update.

* Version update.

* VASP task update.

* Tempfile for downloading zipfiles.

* Pypi fix.

* Pypi fix.

* Updated wannier, vasp2xml, increased tests.

* Update setup.py

* Update action_build.yml

* Speed up test.

* Update DatasetSummary.rst

* Update outputs.py

* Enforce nk1==nk2 in spillage.

* Update test_spillage.py

* Multiple updates.

* Magtest update.

* Version update.

* Update README.rst

* Update README.rst

* WannierTB Phonons.

* phonopy TB.

* phonopy TB.

* Versionupdate.

* QAlgo

* Atoms POSCAR Order update.

* Qiskit tests.

* Lint fix.

* Wien2K extra test, ene file.

* WT.

* WT added.

* Qiskit depedendence.

* Qiskit version.

* Qiskit version.

* Qiskit version.

* Update requirements-ci.txt

* Update requirements-ci.txt

* Update action_build.yml

* Update shell.nix

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Ignore QAlgo tests.

* Make qiskit work.

* Make qiskit work.

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Update action_build.yml

* Delete __init__.py

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Qiskit fix attempt.

* Pennylane fix attempt.

* Update test_hermsolver.py

* Test ham.

* Test ham.

* Update inputs.py

* Test ham.

* Update action_build.yml

* Update inputs.py

* Create __init__.py

* Test ham.

* Update test_hermsolver.py

* Update test_hermsolver.py

* Test Circuit.

* Update test_hermsolver.py

* Update action_build.yml

* Aer

* Aer .

* Var circuit added.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Increase test coverage, ASE, Tequila, Qiskit.

* Ready for master branch.

* Update shell.nix

* Update __init__.py

* Version change.

* Minor fix in figshare and spectrum.

* Update README.rst

* Lint fix.

* Minor update.

* Update figshare.py

* Fix build.

* Update README.rst

* docs update.

* Setup requirement change.

* Update version tag. (#145)

* Minor fix in figshare and spectrum.

* Setup requirement change.

* Cleanup graph (#146)

* revert jarvis.core.graph adjacency matrix weights to interatomic distances

* remove jarvis.core.graph.Graph edges with bond length past threshold max_cut

* fix jarvis.core.graph.Graph.adjacency_matrix to support sparse graphs (with no self edges), and update test file to reflect removal of self edges as well

* Update README.rst

* Update README.rst

* develop (#147)

* Update version tag. (#145)

* Minor fix in figshare and spectrum.

* Setup requirement change.

* Cleanup graph (#146)

* revert jarvis.core.graph adjacency matrix weights to interatomic distances

* remove jarvis.core.graph.Graph edges with bond length past threshold max_cut

* fix jarvis.core.graph.Graph.adjacency_matrix to support sparse graphs (with no self edges), and update test file to reflect removal of self edges as well

* Update README.rst

Co-authored-by: Brian DeCost <[email protected]>

* develop (#147)

* Update version tag. (#145)

* Minor fix in figshare and spectrum.

* Setup requirement change.

* Cleanup graph (#146)

* revert jarvis.core.graph adjacency matrix weights to interatomic distances

* remove jarvis.core.graph.Graph edges with bond length past threshold max_cut

* fix jarvis.core.graph.Graph.adjacency_matrix to support sparse graphs (with no self edges), and update test file to reflect removal of self edges as well

* Update README.rst

Co-authored-by: Brian DeCost <[email protected]>

* Travis update.

* Travis update.

* Travis update.

* Travis update.

* Travis update.

* Travis update.

* Travis update.

* Travis update.

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Update requirements-for-ci-only.txt

* Adding Qiskit.

* Adding Qiskit.

* Adding Qiskit.

* Adding Qiskit.

* Version update.

* Version update.

* Adding Qiskit.

* Adding Qiskit.

* Fix travis.

* Fix travis.

* Fix travis.

* Fix travis.

* VASP outputs bug fix.

* Optics module and Dos module of VASP fixed.

* Fixing commit.

* Lint fix.

* Update inputs.py

* Version update.

* README update.

* Graph and dataset update.

* Graph and dataset update.

* Graph and dataset update.

* Graph module update.

* More datasets added.

* Update .travis.yml

* Update .travis.yml

* Exclude tequila tests.

* Exclude tequila tests.

* Extra tests.

* Pytest-cov added.

* Update action_build.yml

* Update action_build.yml

* Covergae update.

* Covergae update.

* StructureDataset test added.

* Graph tests fixed.

* Figshare update.

* STM image links added.

* Update test_figshare.py

* Update test_figshare.py

* Update .travis.yml

* Update .travis.yml

* Cache github action attempt.

* DB update.

* Update action.

* DB update.

* Figshare test update.

* JARVIS-FF DB added.

* Try to increase coverage.

* Polymer genome added.

* Graph update.

* Graph update.

* Graph update.

* Figshare update.

* Version update.

* Figshare update.

* Hot encoded species.

* STEM with Convolution and Pyprismatic added.

* STEM Conv update.

* Atoms module update.

* Lorentzian fix.

* Digitized features added.

* Graph angle,prdf added. QE parser update.

* Update outputs.py

* Graph angle update and cif2cell added.

* Reduced formula fix and linting fix.

* Test minor fix.

* Graph tests update.

* Pytestfix.

* See also check url in xml

* See also check url in xml

* Phonopy run update.

* Graph update with torch angle.

* Get all neighbors routine bug fix.

* Figshare lint fix.

* Version update, IR extended, graph torch fix.

* Fix IR pytest.

* IR test fix.

* Cache graph dataset (#161)

* modify graph StructureDataset to enable/disable computation of atomistic line graph.

* fix line length setting in black configuration and fix jarvis.core.specie and jarvis.core.graphs

* pin pennylane version to 0.14.1 in GH build action.

* update graph dataloader test.

* fix pennylane version pinning and fix missing pandas.DataFrame in dataloader test.

* bump version number.

Co-authored-by: Brian DeCost <[email protected]>

.github/workflows/action_build.yml

@@ -19,20 +19,20 @@ jobs:
       with:
         path: ${{ env.pythonLocation }}
         key: ${{ env.pythonLocation }}-${{ hashFiles('setup.py') }}-${{ hashFiles('dev-requirements.txt') }}
-        
+
     - name: Install requirements
       run: |
         python setup.py develop
         pip install --upgrade --upgrade-strategy eager -r dev-requirements.txt -e .
 
         echo 'CONDA LIST'
         conda list
-        
+
         echo 'PIP FREEZE'
         pip freeze
 
         #echo 'PYTEST-COV'
-        #pytest --cov-config=.coveragerc --cov=jarvis -n 2 
+        #pytest --cov-config=.coveragerc --cov=jarvis -n 2
 
 
         coverage run -m pytest
@@ -44,7 +44,7 @@ jobs:
         # ./configure
         # make pw
 
-        
+
 
 #jobs:
 #   miniconda:
@@ -77,7 +77,7 @@ jobs:
 #         run: |
 #             python setup.py develop
 #             #pip uninstall qiskit
-#             # pip install qiskit ase  numpy==1.18.5 scipy==1.4.1 matplotlib>=3.0.0 phonopy==2.8.1 coverage lightgbm==2.1.0  flask joblib networkx scikit-learn pandas pennylane dgl tqdm  codecov torch keras tensorflow==2.3.0  pytest pytest-cov bokeh pytest-xdist
+#             # pip install qiskit ase  numpy==1.18.5 scipy==1.4.1 matplotlib>=3.0.0 phonopy==2.8.1 coverage lightgbm==2.1.0  flask joblib networkx scikit-learn pandas pennylane==0.14.1 dgl tqdm  codecov torch keras tensorflow==2.3.0  pytest pytest-cov bokeh pytest-xdist
 #             # pip install git+https://github.com/aspuru-guzik-group/tequila.git
 #             # pip install -r requirements-for-ci-only.txt
 #             # pip install -r dev-requirements.txt
@@ -97,4 +97,3 @@ jobs:
 #             # cd q-e
 #             # ./configure
 #             # make pw
-

dev-requirements.txt

@@ -1,24 +1,24 @@
 wheel
 qiskit >= 0.24.0
-ase>=3.21.1   
-numpy>=1.18.5 
-scipy>=1.4.1 
-matplotlib>=3.0.0 
-phonopy>=2.8.1 
-coverage>=5.5 
-lightgbm>=2.1.0  
+ase>=3.21.1
+numpy>=1.18.5
+scipy>=1.4.1
+matplotlib>=3.0.0
+phonopy>=2.8.1
+coverage>=5.5
+lightgbm>=2.1.0
 flask >=1.1.2
 joblib >=1.0.1
-networkx >=2.5 
+networkx >=2.5
 scikit-learn >=0.24.1
 pandas >=1.2.3
 dgl>=0.6.0.post1
-tqdm>=4.59.0 
-pennylane>=0.14.1   
+tqdm>=4.59.0
+pennylane==0.14.1
 codecov >=2.1.11
 torch >=1.8.0
 keras >=2.4.3
-tensorflow>=2.4.0  
+tensorflow>=2.4.0
 cif2cell
 pytest >=6.2.2
 pytest-cov >=2.11.1

jarvis/__init__.py

@@ -1,2 +1,2 @@
 """Version number."""
-__version__ = "2021.4.19"
+__version__ = "2021.4.21"

jarvis/core/graphs.py

@@ -3,11 +3,13 @@
 from jarvis.core.specie import Specie
 from jarvis.core.utils import random_colors
 import numpy as np
+import pandas as pd
 from collections import OrderedDict
 from jarvis.analysis.structure.neighbors import NeighborsAnalysis
-from jarvis.core.specie import get_node_attributes
+from jarvis.core.specie import chem_data, get_node_attributes
 from jarvis.core.atoms import Atoms
 from collections import defaultdict
+from typing import List, Tuple, Sequence, Optional
 
 try:
     import torch
@@ -190,7 +192,8 @@ def atom_dgl_multigraph(
         max_neighbors=12,
         atom_features="cgcnn",
         max_attempts=3,
-        id="JVASP-6172",
+        id: Optional[str] = None,
+        compute_line_graph: bool = True,
     ):
         """Obtain a DGLGraph for Atoms object."""
         if neighbor_strategy == "k-nearest":
@@ -208,9 +211,8 @@ def atom_dgl_multigraph(
         u, v, r = build_undirected_edgedata(atoms, edges)
 
         # build up atom attribute tensor
-        species = atoms.elements
         sps_features = []
-        for ii, s in enumerate(species):
+        for ii, s in enumerate(atoms.elements):
             feat = list(get_node_attributes(s, atom_features=atom_features))
             # if include_prdf_angles:
             #    feat=feat+list(prdf[ii])+list(adf[ii])
@@ -222,10 +224,16 @@ def atom_dgl_multigraph(
         g = dgl.graph((u, v))
         g.ndata["atom_features"] = node_features
         g.edata["r"] = r
-        lg = g.line_graph(shared=True)
-        lg.apply_edges(compute_bond_cosines)
 
-        return g, lg
+        if compute_line_graph:
+            # construct atomistic line graph
+            # (nodes are bonds, edges are bond pairs)
+            # and add bond angle cosines as edge features
+            lg = g.line_graph(shared=True)
+            lg.apply_edges(compute_bond_cosines)
+            return g, lg
+        else:
+            return g
 
     @staticmethod
     def from_atoms(
@@ -441,27 +449,43 @@ def forward(self, g: dgl.DGLGraph):
         return g
 
 
-def prepare_dgl_batch(batch, device=None, non_blocking=False):
-    """Send batched dgl graph to device."""
-    g, lg, t = batch
-    batch = ((g.to(device), lg.to(device)), t.to(device))
-    # g, t = batch
-    # batch = (g.to(device), t.to(device))
+def prepare_dgl_batch(
+    batch: Tuple[dgl.DGLGraph, torch.Tensor], device=None, non_blocking=False
+):
+    """Send batched dgl crystal graph to device."""
+    g, t = batch
+    batch = (
+        g.to(device, non_blocking=non_blocking),
+        t.to(device, non_blocking=non_blocking),
+    )
 
     return batch
 
 
-def prepare_line_graph_batch(batch, device=None, non_blocking=False):
-    """Send batched dgl graph to device."""
+def prepare_line_graph_batch(
+    batch: Tuple[Tuple[dgl.DGLGraph, dgl.DGLGraph], torch.Tensor],
+    device=None,
+    non_blocking=False,
+):
+    """Send line graph batch to device.
+
+    Note: the batch is a nested tuple, with the graph and line graph together
+    """
     g, lg, t = batch
-    batch = ((g.to(device), lg.to(device)), t.to(device))
+    batch = (
+        (
+            g.to(device, non_blocking=non_blocking),
+            lg.to(device, non_blocking=non_blocking),
+        ),
+        t.to(device, non_blocking=non_blocking),
+    )
 
     return batch
 
 
-def prepare_batch(batch, device=None):
-    """Send tuple to device, including DGLGraphs."""
-    return tuple(x.to(device) for x in batch)
+# def prepare_batch(batch, device=None):
+#     """Send tuple to device, including DGLGraphs."""
+#     return tuple(x.to(device) for x in batch)
 
 
 def compute_bond_cosines(edges):
@@ -489,51 +513,78 @@ class StructureDataset(torch.utils.data.Dataset):
 
     def __init__(
         self,
-        structures,
-        targets,
-        ids=None,
-        cutoff=8.0,
-        maxrows=np.inf,
-        atom_features="cgcnn",
+        df: pd.DataFrame,
+        graphs: Sequence[dgl.DGLGraph],
+        target: str,
+        atom_features="atomic_number",
         transform=None,
-        enforce_undirected=False,
-        max_neighbors=12,
-        neighbor_strategy="k-nearest",
+        line_graph=False,
         classification=False,
     ):
-        """Initialize the class."""
-        self.graphs = []
-        self.labels = []
-        self.ids = []
-        self.line_graphs = []
-
-        for idx, (structure, target, id) in enumerate(
-            tqdm(zip(structures, targets, ids))
-        ):
-
-            if idx >= maxrows:
-                break
-            a = Atoms.from_dict(structure)
-            g, lg = Graph.atom_dgl_multigraph(
-                a,
-                atom_features=atom_features,
-                cutoff=cutoff,
-                max_neighbors=max_neighbors,
-                id=id,
-            )
+        """Pytorch Dataset for atomistic graphs.
 
-            self.graphs.append(g)
-            self.line_graphs.append(lg)
-            self.labels.append(target)
-            self.ids.append(id)
+        `df`: pandas dataframe from e.g. jarvis.db.figshare.data
+        `graphs`: DGLGraph representations corresponding to rows in `df`
+        `target`: key for label column in `df`
+        """
+        self.df = df
+        self.graphs = graphs
+        self.target = target
+        self.line_graph = line_graph
+
+        self.labels = self.df[target]
+        self.ids = self.df["jid"]
+        self.labels = torch.tensor(self.df[target]).type(
+            torch.get_default_dtype()
+        )
+        self.transform = transform
+
+        features = self._get_attribute_lookup(atom_features)
+
+        # load selected node representation
+        # assume graphs contain atomic number in g.ndata["atom_features"]
+        for g in graphs:
+            z = g.ndata.pop("atom_features")
+            g.ndata["atomic_number"] = z
+            z = z.type(torch.IntTensor).squeeze()
+            f = torch.tensor(features[z]).type(torch.FloatTensor)
+            if g.num_nodes() == 1:
+                f = f.unsqueeze(0)
+            g.ndata["atom_features"] = f
+
+        self.prepare_batch = prepare_dgl_batch
+        if line_graph:
+            self.prepare_batch = prepare_line_graph_batch
+
+            print("building line graphs")
+            self.line_graphs = []
+            for g in tqdm(graphs):
+                lg = g.line_graph(shared=True)
+                lg.apply_edges(compute_bond_cosines)
+                self.line_graphs.append(lg)
 
-        self.labels = torch.tensor(self.labels).type(torch.get_default_dtype())
         if classification:
             self.labels = self.labels.view(-1).long()
             print("Classification dataset.", self.labels)
 
-        self.transform = transform
-        self.prepare_batch = prepare_line_graph_batch
+    @staticmethod
+    def _get_attribute_lookup(atom_features: str = "cgcnn"):
+        """Build a lookup array indexed by atomic number."""
+        max_z = max(v["Z"] for v in chem_data.values())
+
+        # get feature shape (referencing Carbon)
+        template = get_node_attributes("C", atom_features)
+
+        features = np.zeros((1 + max_z, len(template)))
+
+        for element, v in chem_data.items():
+            z = v["Z"]
+            x = get_node_attributes(element, atom_features)
+
+            if x is not None:
+                features[z, :] = x
+
+        return features
 
     def __len__(self):
         """Get length."""
@@ -546,12 +597,21 @@ def __getitem__(self, idx):
 
         if self.transform:
             g = self.transform(g)
-        # return g,  label
-        return g, self.line_graphs[idx], label
 
-    def setup_standardizer(self):
+        if self.line_graph:
+            return g, self.line_graphs[idx], label
+
+        return g, label
+
+    def setup_standardizer(self, ids):
         """Atom-wise feature standardization transform."""
-        x = torch.cat([g.ndata["atom_features"] for g in self.graphs])
+        x = torch.cat(
+            [
+                g.ndata["atom_features"]
+                for idx, g in enumerate(self.graphs)
+                if idx in ids
+            ]
+        )
         self.atom_feature_mean = x.mean(0)
         self.atom_feature_std = x.std(0)
 
@@ -560,21 +620,21 @@ def setup_standardizer(self):
         )
 
     @staticmethod
-    def collate(samples):
+    def collate(samples: List[Tuple[dgl.DGLGraph, torch.Tensor]]):
+        """Dataloader helper to batch graphs cross `samples`."""
+        graphs, labels = map(list, zip(*samples))
+        batched_graph = dgl.batch(graphs)
+        return batched_graph, torch.tensor(labels)
+
+    @staticmethod
+    def collate_line_graph(
+        samples: List[Tuple[dgl.DGLGraph, dgl.DGLGraph, torch.Tensor]]
+    ):
         """Dataloader helper to batch graphs cross `samples`."""
-        # device = "cpu"
-        # if torch.cuda.is_available():
-        #    device = torch.device("cuda")
-        # graphs,  labels = map(list, zip(*samples))
         graphs, line_graphs, labels = map(list, zip(*samples))
         batched_graph = dgl.batch(graphs)
         batched_line_graph = dgl.batch(line_graphs)
-        # return batched_graph.to(device),  torch.tensor(labels).to(device)
-        return (
-            batched_graph,
-            batched_line_graph,
-            torch.tensor(labels),
-        )  # .to(device)
+        return batched_graph, batched_line_graph, torch.tensor(labels)
 
 
 """