merge icml_push into main --squash

.github/workflows/test.yml

@@ -16,8 +16,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
-        os: ["ubuntu-latest"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        os: ["ubuntu-latest", "macos-latest"] #,"windows-latest"
 
     runs-on: ${{ matrix.os }}
     timeout-minutes: 30
@@ -53,5 +53,5 @@ jobs:
       - name: Run tests
         run: python -m pytest
 
-      #- name: Test building the doc
-      #  run: mkdocs build
+      - name: Test building the doc
+        run: mkdocs build

.gitignore

@@ -149,3 +149,6 @@ cookie.txt
 *.txt
 *.sh
 .DS_Store
+*.zarr/
+scripts/
+notebooks/

docs/API/basedataset.md

@@ -0,0 +1 @@
+::: openqdc.datasets.base

docs/API/datasets/alchemy.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.alchemy

docs/API/datasets/ani.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.ani

docs/API/datasets/comp6.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.comp6

docs/API/datasets/des.md

@@ -0,0 +1 @@
+::: openqdc.datasets.interaction.des

docs/API/datasets/gdml.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.gdml

docs/API/datasets/geom.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.geom.GEOM

docs/API/datasets/iso_17.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.iso_17

docs/API/datasets/l7.md

@@ -0,0 +1 @@
+::: openqdc.datasets.interaction.l7

docs/API/datasets/md22.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.md22

docs/API/datasets/metcalf.md

@@ -0,0 +1 @@
+::: openqdc.datasets.interaction.metcalf

docs/API/datasets/molecule3d.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.molecule3d

docs/API/datasets/multixcqm9.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.multixcqm9

docs/API/datasets/nabladft.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.nabladft

docs/API/datasets/orbnet_denali.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.orbnet_denali

docs/API/datasets/pcqm.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.pcqm

docs/API/datasets/proteinfragments.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.proteinfragments

docs/API/datasets/qm1b.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.qm1b

docs/API/datasets/qm7x.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.qm7x

docs/API/datasets/qmugs.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.qmugs

docs/API/datasets/qmx.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.qmx

docs/API/datasets/revmd17.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.revmd17

docs/API/datasets/sn2_rxn.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.sn2_rxn

docs/API/datasets/solvated_peptides.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.solvated_peptides

docs/API/datasets/spice.md

@@ -0,0 +1,2 @@
+
+::: openqdc.datasets.potential.spice

docs/API/datasets/splinter.md

@@ -0,0 +1 @@
+::: openqdc.datasets.interaction.splinter

docs/API/datasets/tmqm.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.tmqm

docs/API/datasets/transition1x.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.transition1x

docs/API/datasets/vqm24.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.vqm24

docs/API/datasets/waterclusters.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.waterclusters

docs/API/datasets/waterclusters3_30.md

@@ -0,0 +1 @@
+::: openqdc.datasets.potential.waterclusters3_30

docs/API/datasets/x40.md

@@ -0,0 +1 @@
+::: openqdc.datasets.interaction.x40

docs/API/formats.md

@@ -0,0 +1 @@
+::: openqdc.datasets.structure

docs/API/methods.md

@@ -1,3 +1,7 @@
 # QM Methods
 
-::: openqdc.methods
+::: openqdc.methods.enums
+
+# Isolated Atom Energies
+
+::: openqdc.methods.atom_energies

docs/API/regressor.md

@@ -0,0 +1 @@
+::: openqdc.utils.regressor

docs/API/units.md

@@ -0,0 +1,3 @@
+# UNITS
+
+::: openqdc.utils.units

docs/API/utils.md

@@ -0,0 +1 @@
+::: openqdc.utils

docs/cli.md

@@ -0,0 +1,113 @@
+# CLI for dataset downloading and uploading
+You can quickly download, fetch, preprocess and upload openQDC datasets using the command line interface (CLI).
+
+## Datasets
+Print a formatted table of the available openQDC datasets and some informations.
+
+Usage:
+
+    openqdc datasets [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+
+## Cache
+Get the current local cache path of openQDC
+
+Usage:
+
+    openqdc cache [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+
+
+## Download
+Download preprocessed ml-ready datasets from the main openQDC hub.
+
+Usage:
+
+    openqdc download DATASETS... [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+    --overwrite     Whether to force the re-download of the datasets and overwrite the current cached dataset. [default: no-overwrite]
+    --cache-dir     Path to the cache. If not provided, the default cache directory (.cache/openqdc/) will be used. [default: None]
+    --as-zarr       Whether to use a zarr format for the datasets instead of memmap. [default: no-as-zarr]
+    --gs            Whether source to use for downloading. If True, Google Storage will be used.Otherwise, AWS S3 will be used [default: no-gs]
+
+Example:
+
+    openqdc download Spice
+
+## Fetch
+Download the raw datasets files from the main openQDC hub
+
+Note:
+
+    Special case: if the dataset is "all", "potential", "interaction".
+
+Usage:
+
+    openqdc fetch DATASETS... [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+    --overwrite     Whether to overwrite or force the re-download of the raw files. [default: no-overwrite]
+    --cache-dir     Path to the cache. If not provided, the default cache directory (.cache/openqdc/) will be used. [default: None]
+
+Example:
+
+    openqdc fetch Spice
+
+## Preprocess
+Preprocess a raw dataset (previously fetched) into a openqdc dataset and optionally push it to remote.
+
+Usage:
+
+    openqdc preprocess DATASETS... [OPTIONS]
+
+Options:
+
+    --help         Show this message and exit.
+    --overwrite    Whether to overwrite the current cached datasets. [default: overwrite]
+    --upload       Whether to attempt the upload to the remote storage. Must have write permissions. [default: no-upload]
+    --as-zarr      Whether to preprocess as a zarr format or a memmap format. [default: no-as-zarr]
+
+Example:
+
+    openqdc preprocess Spice QMugs
+
+## Upload
+Upload a preprocessed dataset to the remote storage
+
+Usage:
+
+    openqdc upload DATASETS... [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+    --overwrite     Whether to overwrite the remote files if they are present. [default: overwrite]
+    --as-zarr       Whether to upload the zarr files if available. [default: no-as-zarr]
+
+Example:
+
+    openqdc upload Spice --overwrite
+
+## Convert
+Convert a preprocessed dataset from a memmap dataset to a zarr dataset.
+
+Usage:
+
+    openqdc convert DATASETS... [OPTIONS]
+
+Options:
+
+    --help          Show this message and exit.
+    --overwrite     Whether to overwrite the current zarr cached datasets. [default: no-overwrite]
+    --download      Whether to force the re-download of the memmap datasets. [default: no-download]

docs/contribute.md

@@ -0,0 +1,59 @@
+# Contribute
+
+The below documents the development lifecycle of OpenQDC.
+
+## Setup a dev environment
+
+```bash
+mamba env create -n openqdc -f env.yml
+mamba activate datamol
+pip install -e .
+```
+
+## Pre commit installation
+
+```bash
+pre-commit install
+pre-commit run --all-files
+```
+
+## Continuous Integration
+
+OpenQDC uses Github Actions to:
+
+- **Build and test** `openQDC`.
+  - Multiple combinations of OS and Python versions are tested.
+- **Check** the code:
+  - Formatting with `black`.
+  - Static type check with `mypy`.
+  - Modules import formatting with `isort`.
+  - Pre-commit hooks.
+- **Documentation**:
+  - Google docstring format.
+  - build and deploy the documentation on `main` and for every new git tag.
+
+
+## Run tests
+
+```bash
+pytest
+```
+
+## Build the documentation
+
+You can build and serve the documentation locally with:
+
+```bash
+# Build and serve the doc
+mike serve
+```
+
+or with
+
+```bash
+mkdocs serve
+```
+
+### Multi-versionning
+
+The doc is built for eash push on `main` and every git tags using [mike](https://github.com/jimporter/mike). Everything is automated using Github Actions. Please refer to the official mike's documentation for the details.