Add GitHub workflows

.github/workflows/pylint.yaml

@@ -0,0 +1,19 @@
+name: PyLint
+
+on: push
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pylint
+      - name: Run pylint
+        run: pylint src/aidsorb/

.github/workflows/unittest.yaml

@@ -0,0 +1,15 @@
+name: Unittest
+
+on: push
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Run unit tests
+        run: python -m unittest

README.md

@@ -1,39 +1,67 @@
-AIdsorb is a Python package for processing molecular point clouds.
+<h1 align="center">
+  <img alt="Logo" src="https://raw.githubusercontent.com/adosar/trial/master/docs/source/images/aidsorb_logo_light.svg"/>
+</h1>
 
-Currently, only the `PointNet`  [^1] architecture is implemented and can be
-found under `src/aidsorb/models.py`. In this implementation, the input `T-Net`
-transformation from the original paper is not applied, *since is it is not
-guaranteed to be a rigid one*.
+<h4 align="center">
+
+![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue?style=for-the-badge&logo=python&logoColor=white&labelColor=black)
+![License GPL-3.0-only](https://img.shields.io/badge/license-GPL--3.0--only-gold?style=for-the-badge&logo=license&logoColor=cyan&labelColor=black)
+![Linux](https://img.shields.io/badge/linux-black?style=for-the-badge&logo=linux&logoColor=cyan)
+
+</h4>
+
+
+**AIdsorb** is a Python package for **deep learning on molecular point clouds**.
+
+**AIdsorb** aims to provide a **fast, easy-to-use and reproduce** interface for:
+
+-   📥 **Creating molecular point clouds**
+
+-   🤖 **Training DL algorithms on molecular point clouds**
+
+
+<p align="center">
+  <img alt="Point cloud" src="https://raw.githubusercontent.com/adosar/aidsorb/master/docs/source/images/pcd.gif" width="25%"/>
+</p>
 
 ## ⚙️  Installation
-> Currently not available in PyPI.
+> [!IMPORTANT] 
+> It is strongly recommended to **perform the installation inside a virtual environment**.
 
-**It is strongly recommended to perform the installation inside a virtual environment**.
+Assuming an activated virtual environment:
 ```bash
-git clone https://github.com/adosar/aidsorb && cd aidsorb
-(venvir) pip install -e .
+pip install aidsorb
 ```
 
-## 📖 Usage
-You can create molecular point clouds form a directory containing molecular
-files and save them in a `.npz` file.
+## 🚀 Usage
+> [!NOTE] 
+> Refer to the 📚 Documentation for more information.
 
-```python
-from aidsorb.utils import pcd_from_dir
-pcd_from_dir('/path/to/dir', file='point_clouds.npz')
-```
+Here is a summary of what you can do from the command line:
 
-## 📇 TODO
-* Add atoms featurization
-* Add more architectures
+1. Visualize a molecular point cloud:
+	```bash
+	aidsorb visualize path/to/structure
+	```
+
+2.  Create and prepare point clouds:
+	```bash
+	aidsorb create path/to/inp path/to/out  # Create point clouds
+	aidsorb prepare path/to/out  # Split point clouds to train, val and test
+	```
+	where `path/to/inp` is a directory containing molecular structures.
+
+3. Train and test a model:
+	```bash
+	aidsorb-lit fit --config=path/to/config.yaml
+	aidsorb-lit test --config=path/to/config.yaml --ckpt_path=path/to/ckpt
+	```
+	Currently, only [PointNet](https://arxiv.org/abs/1612.00593) is supported.
 
 ## 📰 Citing AIdsorb
-> Currently N/A.
+If you use AIdsorb in your research, please consider citing the following work:
+
+	Currently, not available.
 
 ## 📑 License
-MOXελ is released under the [GNU General Public License v3.0 only](https://spdx.org/licenses/GPL-3.0-only.html).
-
-[^1]: R. Q. Charles, H. Su, M. Kaichun and L. J. Guibas, "PointNet: Deep
-Learning on Point Sets for 3D Classification and Segmentation," 2017 IEEE
-Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI,USA,
-2017, pp. 77-85, doi: 10.1109/CVPR.2017.16.
+AIdosrb is released under the [GNU General Public License v3.0 only](https://spdx.org/licenses/GPL-3.0-only.html).

docs/source/conf.py

@@ -6,7 +6,6 @@
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
-from urllib.parse import quote
 import sys, os
 import subprocess
 from plotly.io._sg_scraper import plotly_sg_scraper

docs/source/index.rst

@@ -12,7 +12,7 @@
 About
 =====
 
-**AIdsorb** is a :fa:`python; fa-fade` Python package for **Deep Learning on
+**AIdsorb** is a :fa:`python; fa-fade` Python package for **deep learning on
 molecular point clouds**.
 
 .. grid:: 4

docs/source/tutorial.rst

@@ -58,6 +58,14 @@ Introduction
     4:]`` any **additional features**. If ``C == 0``, then the only features are the
     atomic numbers.
 
+
+.. tip::
+    You can visualize a molecular point cloud with:
+
+    .. code-block:: console
+
+        $ aidsorb visualize path/to/structure
+
 Deep learning on molecular point clouds
 ---------------------------------------
 
@@ -66,7 +74,7 @@ AIdsorb, the following components are needed:
 
 * A directory containing files of **molecular structures**.
 * A ``.csv`` file containing the **labels of the molecular structures**.
-* A ``.yaml`` **configuration file** for orchestrating the ML part.
+* A ``.yaml`` **configuration file** for orchestrating the DL part.
 
 .. note::
     You are solely responsible for these 3 components.

pyproject.toml

@@ -7,6 +7,11 @@ where = ["src"]
 
 [tool.setuptools_scm]
 
+[tool.pylint.main]
+jobs = 0
+disable = ["C"]
+fail-under = 8
+
 [project]
 name = "aidsorb"
 dynamic = ["version"]

src/aidsorb/__init__.py

@@ -15,7 +15,7 @@
 # along with this program. If not, see <http://www.gnu.org/licenses/>.
 
 r"""
-**AIdsorb** is a :fa:`python; fa-fade` Python package for **Deep Learning on
+**AIdsorb** is a :fa:`python; fa-fade` Python package for **deep learning on
 molecular point clouds**.
 
 

src/aidsorb/models.py

@@ -37,9 +37,6 @@
 .. todo::
     Add more architectures for point cloud processing.
 
-.. danger::
-    Check all docstrings.
-
 References
 ----------
 
@@ -429,7 +426,8 @@ def forward(self, x):
 
 class PointNet(nn.Module):
     r"""
-    A deep learning architecture for processing point clouds.
+    Vanilla version from the [PointNet]_ paper where :class:`TNet`'s have been
+    removed.
 
     ``PointNet`` takes as input a point cloud and produces one or more outputs.
     *The type of the task is determined by* ``head``.

tests/test_data.py

@@ -31,7 +31,6 @@
 import pandas as pd
 from torch.utils.data import DataLoader
 from aidsorb import data
-from aidsorb._internal import _check_shape
 from aidsorb.utils import pcd_from_dir
 from aidsorb.transforms import Centering
 from aidsorb.data import (

tests/test_datamodules.py

@@ -24,7 +24,7 @@
 import os
 import unittest
 import tempfile
-from itertools import combinations, product
+from itertools import combinations
 from torch.utils.data import RandomSampler, SequentialSampler
 from aidsorb.utils import pcd_from_dir
 from aidsorb.data import prepare_data, Collator

tests/test_litmodels.py

@@ -22,7 +22,6 @@
 """
 
 import doctest
-import unittest
 from aidsorb import litmodels
 
 

tests/test_models.py

@@ -22,7 +22,6 @@
 """
 
 import doctest
-import unittest
 from aidsorb import models
 
 

tests/test_transforms.py

@@ -22,7 +22,6 @@
 """
 
 import doctest
-import unittest
 from aidsorb import transforms