Merge branch 'main' into solvents

.github/workflows/lint.yml

@@ -0,0 +1,25 @@
+name: lint
+
+on:
+  push:
+  workflow_dispatch:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 6
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e .[dev]
+      - name: black
+        run: |
+          black --color ocdata

.github/workflows/test.yml

@@ -0,0 +1,50 @@
+name: test
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_call:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 10
+      matrix:
+        python_version: ['3.9', '3.10', '3.11']
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python_version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version:  ${{ matrix.python_version }}
+
+      - name: Cache pip
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+            ${{ runner.os }}-
+
+      - name: Install dependencies and package
+        # this can be added along with a dependabot config to run tests with latest versions
+        # pip install -r requirements.txt
+        # pip install -r requirements-optional.txt
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e .[dev]
+      - name: Test with pytest
+        run: |
+          pytest tests -vv --cov-report=xml --cov=ocpdata
+
+      - if: ${{ matrix.python_version == '3.11' }}
+        name: codecov-report
+        uses: codecov/codecov-action@v4
+        with:
+          fail_ci_if_error: false # optional (default = false)
+          files: ./coverage.xml
+          token: ${{ secrets.CODECOV_TOKEN }} # required
+          verbose: true # optional (default = false)

README.md

@@ -1,3 +1,5 @@
+# THIS REPOSITORY HAS BEEN MOVED TO [http://github.com/fair-chem/fairchem/tree/main/src/fairchem/data/oc](http://github.com/fair-chem/fairchem/tree/main/src/fairchem/data/oc) 
+
 [![CircleCI](https://dl.circleci.com/status-badge/img/gh/Open-Catalyst-Project/Open-Catalyst-Dataset/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/Open-Catalyst-Project/Open-Catalyst-Dataset/tree/main)
 [![codecov](https://codecov.io/gh/Open-Catalyst-Project/Open-Catalyst-Dataset/branch/main/graph/badge.svg?token=IZ7J729L6S)](https://codecov.io/gh/Open-Catalyst-Project/Open-Catalyst-Dataset/tree/main)
 

codecov.yml

@@ -0,0 +1,9 @@
+coverage:
+  status:
+    project:
+      default:
+        informational: true
+    patch:
+      default:
+        informational: true
+github_checks: false

ocdata/core/adsorbate.py

@@ -1,11 +1,11 @@
 import pickle
-from typing import Any, Dict, Tuple
 import warnings
+from typing import Any, Dict, Tuple
 
 import ase
 import numpy as np
 
-from ocdata.configs.paths import ADSORBATES_PKL_PATH
+from ocdata.databases.pkls import ADSORBATES_PKL_PATH
 
 
 class Adsorbate:

ocdata/core/bulk.py

@@ -1,13 +1,13 @@
 import os
 import pickle
-from typing import Any, Dict, List
 import warnings
+from typing import Any, Dict, List
 
 import ase
 import numpy as np
 
-from ocdata.configs.paths import BULK_PKL_PATH
 from ocdata.core.slab import Slab
+from ocdata.databases.pkls import BULK_PKL_PATH
 
 
 class Bulk:

ocdata/core/slab.py

@@ -21,8 +21,8 @@ class Slab:
     """
     Initializes a slab object, i.e. a particular slab tiled along xyz, in
     one of 2 ways:
-    - Pass in a Bulk object and a slab 4-tuple containing
-    (atoms, miller, shift, top).
+    - Pass in a Bulk object and a slab 5-tuple containing
+    (atoms, miller, shift, top, oriented bulk).
     - Pass in a Bulk object and randomly sample a slab.
 
     Arguments
@@ -48,6 +48,7 @@ def __init__(
         millers: tuple = None,
         shift: float = None,
         top: bool = None,
+        oriented_bulk: Structure = None,
         min_ab: float = 0.8,
     ):
         assert bulk is not None
@@ -57,6 +58,7 @@ def __init__(
         self.millers = millers
         self.shift = shift
         self.top = top
+        self.oriented_bulk = oriented_bulk
 
         assert (
             Composition(self.atoms.get_chemical_formula()).reduced_formula
@@ -87,10 +89,12 @@ def from_bulk_get_random_slab(
                 max_miller=max_miller,
             )
             slab_idx = np.random.randint(len(untiled_slabs))
-            unit_slab_struct, millers, shift, top = untiled_slabs[slab_idx]
+            unit_slab_struct, millers, shift, top, oriented_bulk = untiled_slabs[
+                slab_idx
+            ]
             slab_atoms = tile_and_tag_atoms(unit_slab_struct, bulk.atoms, min_ab=min_ab)
 
-            return cls(bulk, slab_atoms, millers, shift, top)
+            return cls(bulk, slab_atoms, millers, shift, top, oriented_bulk)
 
     @classmethod
     def from_bulk_get_specific_millers(
@@ -123,10 +127,11 @@ def from_bulk_get_specific_millers(
                         s[1],
                         s[2],
                         s[3],
+                        s[4],
                     )
                 )
 
-            return [cls(bulk, s[0], s[1], s[2], s[3]) for s in slabs]
+            return [cls(bulk, s[0], s[1], s[2], s[3], s[4]) for s in slabs]
 
     @classmethod
     def from_bulk_get_all_slabs(
@@ -141,7 +146,13 @@ def from_bulk_get_all_slabs(
         slabs = []
         for s in untiled_slabs:
             slabs.append(
-                (tile_and_tag_atoms(s[0], bulk.atoms, min_ab=min_ab), s[1], s[2], s[3])
+                (
+                    tile_and_tag_atoms(s[0], bulk.atoms, min_ab=min_ab),
+                    s[1],
+                    s[2],
+                    s[3],
+                    s[4],
+                )
             )
 
         # if path is provided, save out the pkl
@@ -150,7 +161,7 @@ def from_bulk_get_all_slabs(
             with open(save_path, "wb") as f:
                 pickle.dump(slabs, f)
 
-        return [cls(bulk, s[0], s[1], s[2], s[3]) for s in slabs]
+        return [cls(bulk, s[0], s[1], s[2], s[3], s[4]) for s in slabs]
 
     @classmethod
     def from_precomputed_slabs_pkl(
@@ -173,7 +184,7 @@ def from_precomputed_slabs_pkl(
             return slabs
         else:
             assert np.all(np.array([s[1] for s in slabs]) <= max_miller)
-            return [cls(bulk, s[0], s[1], s[2], s[3]) for s in slabs]
+            return [cls(bulk, s[0], s[1], s[2], s[3], s[4]) for s in slabs]
 
     @classmethod
     def from_atoms(cls, atoms: ase.Atoms = None, bulk=None, **kwargs):
@@ -193,6 +204,7 @@ def get_metadata_dict(self):
                 "millers": self.millers,
                 "shift": self.shift,
                 "top": self.top,
+                "oriented_bulk": self.oriented_bulk,
             },
         }
 
@@ -211,6 +223,7 @@ def __eq__(self, other):
             and self.millers == other.millers
             and self.shift == other.shift
             and self.top == other.top
+            and self.oriented_bulk == other.oriented_bulk
         )
 
 
@@ -496,8 +509,9 @@ def compute_slabs(
     Returns
     -------
     all_slabs_info: list
-        A list of 4-tuples containing pymatgen structure objects for enumerated
-        slabs, the Miller indices, floats for the shifts, and booleans for top.
+        A list of 5-tuples containing pymatgen structure objects for enumerated
+        slabs, the Miller indices, floats for the shifts, booleans for top, and
+        the oriented bulk structure.
     """
     assert bulk_atoms is not None
     bulk_struct = standardize_bulk(bulk_atoms)
@@ -527,13 +541,16 @@ def compute_slabs(
         # want to consider them too.
         if len(slabs) != 0:
             flipped_slabs_info = [
-                (flip_struct(slab), millers, slab.shift, False)
+                (flip_struct(slab), millers, slab.shift, False, slab.oriented_unit_cell)
                 for slab in slabs
                 if is_structure_invertible(slab) is False
             ]
 
             # Concatenate all the results together
-            slabs_info = [(slab, millers, slab.shift, True) for slab in slabs]
+            slabs_info = [
+                (slab, millers, slab.shift, True, slab.oriented_unit_cell)
+                for slab in slabs
+            ]
             all_slabs_info.extend(slabs_info + flipped_slabs_info)
 
     return all_slabs_info

ocdata/databases/pkls/__init__.py

@@ -1,4 +1,4 @@
 import os
 
-BULK_PKL = os.path.join(__path__[0], "bulks.pkl")
-ADSORBATE_PKL = os.path.join(__path__[0], "adsorbates.pkl")
+BULK_PKL_PATH = os.path.join(__path__[0], "bulks.pkl")
+ADSORBATES_PKL_PATH = os.path.join(__path__[0], "adsorbates.pkl")

ocdata/databases/update.py

@@ -2,10 +2,7 @@
 Script for updating ase pkl and db files from v3.19 to v3.21.
 Run it with ase v3.19.
 """
-
-
 import pickle
-from collections import defaultdict
 
 import ase.io
 from ase.atoms import Atoms