[Example] Add Pytorch Geometric Example

MANIFEST.in

@@ -24,15 +24,14 @@ include *.md
 include LICENSE
 
 exclude *.sh
-exclude *.toml
 exclude *.svg
 recursive-include pytorch_lightning *.py
 
 # Include marker file for PEP 561
 include pytorch_lightning/py.typed
 
 # include examples
-recursive-include pl_examples *.py *.md *.sh *.txt
+recursive-include pl_examples *.py *.md *.sh *.txt *.toml
 
 # exclude tests from package
 recursive-exclude tests *
@@ -49,6 +48,7 @@ recursive-include docs/source/_images/general/ pl_overview* tf_* tutorial_* PTL1
 recursive-include requirements *.txt
 recursive-exclude requirements *.sh
 include requirements.txt
+include pyproject.toml
 
 # Exclude build configs
 exclude *.yml

docs/source/index.rst

@@ -76,6 +76,7 @@ PyTorch Lightning Documentation
    :name: Examples
    :caption: Examples
 
+   pytorch_ecoystem
    community_examples
    Autoencoder <https://pytorch-lightning-bolts.readthedocs.io/en/latest/autoencoders.html#autoencoders>
    BYOL <https://pytorch-lightning-bolts.readthedocs.io/en/latest/self_supervised_models.html#byol>

docs/source/pytorch_ecoystem.rst

@@ -0,0 +1,4 @@
+Pytorch Ecosystem Examples
+==========================
+
+- `Pytorch Geometric: Deep learning on Graphs and other irregular structures <https://github.com/PyTorchLightning/pytorch-lightning/tree/master/pl_examples/pytorch_ecosystem/pytorch_geometric/README.md>`_.

pl_examples/pytorch_ecosystem/pytorch_geometric/README.md

@@ -0,0 +1,38 @@
+#  [Pytorch Geometric](https://github.com/rusty1s/pytorch_geometric) examples with Lighting
+
+### Introduction
+
+PyTorch Geometric (PyG) is a geometric deep learning extension library for PyTorch. It relies on lower level libraries such as
+
+* PyTorch Cluster: A package consists of a small extension library of highly optimized graph cluster algorithms in Pytorch
+* PyTorch Sparse: A package consists of a small extension library of optimized sparse matrix operations with autograd support in Pytorch
+* PyTorch Scatter: A package consists of a small extension library of highly optimized sparse update (scatter and segment) operations for the use in PyTorch
+
+## Setup
+
+```
+pyenv install 3.7.8
+pyenv local 3.7.8
+python -m venv
+source .venv/bin/activate
+poetry install
+```
+
+Run example
+
+```
+python cora_dna.py
+```
+
+## Current example lists
+
+| `DATASET` | `MODEL` | `TASK` | DATASET DESCRIPTION | MODEL DESCRIPTION                                                                                                                                                                   |                                                                                                                                                                     |
+| :---: | :---: | :---: | :---: | :---: | :---: |
+| Cora | DNA | Node Classification | The citation network datasets "Cora", "CiteSeer" and "PubMed" from the "Revisiting Semi-Supervised Learning with Graph Embeddings" <https://arxiv.org/abs/1603.08861> | The dynamic neighborhood aggregation operator from the "Just Jump: Towards Dynamic Neighborhood Aggregation in Graph Neural Networks"
+
+
+## DATASET SIZES
+
+```
+ 16M    ./cora
+```