Remove Input Channel

.github/workflows/black.yml

@@ -0,0 +1,10 @@
+name: Lint
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: psf/black@stable

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# configs/ # commented as new configs can be added as a part of a feature
+
+/.idea
+/data
+/logs
+/results_buffer
+electra_pretrained.ckpt
+.isort.cfg
+/.vscode

.pre-commit-config.yaml

@@ -1,9 +1,25 @@
 repos:
-#-   repo: https://github.com/PyCQA/isort
-#    rev: "5.12.0"
-#    hooks:
-#    -   id: isort
 -   repo: https://github.com/psf/black
-    rev: "22.10.0"
+    rev: "24.2.0"
     hooks:
-    -   id: black
+    -   id: black
+    -   id: black-jupyter # for formatting jupyter-notebook
+
+-   repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile=black"]
+
+-   repo: https://github.com/asottile/seed-isort-config
+    rev: v2.2.0
+    hooks:
+    -   id: seed-isort-config
+
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace

README.md

@@ -2,13 +2,13 @@
 
 ## Installation
 
-Some requirements may not be installed successfully automatically. 
+Some requirements may not be installed successfully automatically.
 To install the `torch-` libraries, use
 
 `pip install torch-${lib} -f https://data.pyg.org/whl/torch-2.1.0+${CUDA}.html`
 
 where `${lib}` is either `scatter`, `geometric`, `sparse` or `cluster`, and
-`${CUDA}` is either `cpu`, `cu118` or `cu121` (depending on your system, see e.g. 
+`${CUDA}` is either `cpu`, `cu118` or `cu121` (depending on your system, see e.g.
 [torch-geometric docs](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html))
 
 
@@ -31,7 +31,7 @@ We recommend the following setup:
 
   If you run the command from the `python-chebai` directory, you can use the same data for both chebai- and chebai-graph-models (e.g., Transformers and GNNs).
   Then you have to use `{path-to-chebai} -> .` and `{path-to-chebai-graph} -> ../python-chebai-graph`.
-      
+
 Pretraining on a atom / bond masking task with PubChem data (feature-branch):
 ```
 python3 -m chebai fit --model={path-to-chebai-graph}/configs/model/gnn_resgated_pretrain.yml --data={path-to-chebai-graph}/configs/data/pubchem_graph.yml --trainer={path-to-chebai}/configs/training/pretraining_trainer.yml

chebai_graph/models/gin_net.py

@@ -1,10 +1,11 @@
+import typing
+
+import torch
+import torch.nn.functional as F
+import torch_geometric
 from torch_scatter import scatter_add
 
 from chebai_graph.models.graph import GraphBaseNet
-import torch_geometric
-import torch.nn.functional as F
-import torch
-import typing
 
 
 class AggregateMLP(torch.nn.Module):

chebai_graph/models/graph.py

@@ -1,5 +1,6 @@
 import logging
 import typing
+from abc import ABC
 
 import torch
 import torch.nn.functional as F
@@ -15,7 +16,7 @@
 logging.getLogger("pysmiles").setLevel(logging.CRITICAL)
 
 
-class GraphBaseNet(ChebaiBaseNet):
+class GraphBaseNet(ChebaiBaseNet, ABC):
     def _get_prediction_and_labels(self, data, labels, output):
         return torch.sigmoid(output), labels.int()
 
@@ -84,8 +85,6 @@ class ResGatedGraphConvNetBase(GraphBaseNet):
 
     def __init__(self, config: typing.Dict, **kwargs):
         super().__init__(**kwargs)
-
-        self.in_length = config["in_length"]
         self.hidden_length = config["hidden_length"]
         self.dropout_rate = config["dropout_rate"]
         self.n_conv_layers = config["n_conv_layers"] if "n_conv_layers" in config else 3
@@ -104,26 +103,26 @@ def __init__(self, config: typing.Dict, **kwargs):
 
         self.activation = F.elu
         self.dropout = nn.Dropout(self.dropout_rate)
-
         self.convs = torch.nn.ModuleList([])
-        for i in range(self.n_conv_layers):
-            if i == 0:
-                self.convs.append(
-                    tgnn.ResGatedGraphConv(
-                        self.n_atom_properties,
-                        self.in_length,
-                        # dropout=self.dropout_rate,
-                        edge_dim=self.n_bond_properties,
-                    )
-                )
+
+        self.convs.append(
+            tgnn.ResGatedGraphConv(
+                self.n_atom_properties,
+                self.hidden_length,
+                # dropout=self.dropout_rate,
+                edge_dim=self.n_bond_properties,
+            )
+        )
+
+        for _ in range(self.n_conv_layers - 1):
             self.convs.append(
                 tgnn.ResGatedGraphConv(
-                    self.in_length, self.in_length, edge_dim=self.n_bond_properties
+                    self.hidden_length,
+                    self.hidden_length,
+                    # dropout=self.dropout_rate,
+                    edge_dim=self.n_bond_properties,
                 )
             )
-        self.final_conv = tgnn.ResGatedGraphConv(
-            self.in_length, self.hidden_length, edge_dim=self.n_bond_properties
-        )
 
     def forward(self, batch):
         graph_data = batch["features"][0]
@@ -136,11 +135,6 @@ def forward(self, batch):
             a = self.activation(
                 conv(a, graph_data.edge_index.long(), edge_attr=graph_data.edge_attr)
             )
-        a = self.activation(
-            self.final_conv(
-                a, graph_data.edge_index.long(), edge_attr=graph_data.edge_attr
-            )
-        )
         return a
 
 

chebai_graph/preprocessing/collate.py

@@ -1,11 +1,11 @@
 from typing import Dict
 
 import torch
+from chebai.preprocessing.collate import RaggedCollator
 from torch_geometric.data import Data as GeomData
 from torch_geometric.data.collate import collate as graph_collate
-from chebai_graph.preprocessing.structures import XYGraphData
 
-from chebai.preprocessing.collate import RaggedCollator
+from chebai_graph.preprocessing.structures import XYGraphData
 
 
 class GraphCollator(RaggedCollator):