Geometric_deep_learning.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Install required packages.\n",
    "import os\n",
    "import torch\n",
    "os.environ['TORCH'] = torch.__version__\n",
    "print(torch.__version__)\n",
    "\n",
    "!pip install -q torch-scatter -f https://data.pyg.org/whl/torch-${TORCH}.html\n",
    "!pip install -q torch-sparse -f https://data.pyg.org/whl/torch-${TORCH}.html\n",
    "!pip install -q git+https://github.com/pyg-team/pytorch_geometric.git\n",
    "\n",
    "# Helper function for visualization.\n",
    "%matplotlib inline\n",
    "import networkx as nx\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "def visualize_graph(G, color):\n",
    "    plt.figure(figsize=(7,7))\n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "    nx.draw_networkx(G, pos=nx.spring_layout(G, seed=42), with_labels=False,\n",
    "                     node_color=color, cmap=\"Set2\")\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def visualize_embedding(h, color, epoch=None, loss=None):\n",
    "    plt.figure(figsize=(7,7))\n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "    h = h.detach().cpu().numpy()\n",
    "    plt.scatter(h[:, 0], h[:, 1], s=140, c=color, cmap=\"Set2\")\n",
    "    if epoch is not None and loss is not None:\n",
    "        plt.xlabel(f'Epoch: {epoch}, Loss: {loss.item():.4f}', fontsize=16)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch_geometric.datasets import KarateClub\n",
    "\n",
    "dataset = KarateClub()\n",
    "print(f'Dataset: {dataset}:')\n",
    "print('======================')\n",
    "print(f'Number of graphs: {len(dataset)}')\n",
    "print(f'Number of features: {dataset.num_features}')\n",
    "print(f'Number of classes: {dataset.num_classes}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = dataset[0]  # Get the first graph object.\n",
    "\n",
    "print(data)\n",
    "print('==============================================================')\n",
    "\n",
    "# Gather some statistics about the graph.\n",
    "print(f'Number of nodes: {data.num_nodes}')\n",
    "print(f'Number of edges: {data.num_edges}')\n",
    "print(f'Average node degree: {data.num_edges / data.num_nodes:.2f}')\n",
    "print(f'Number of training nodes: {data.train_mask.sum()}')\n",
    "print(f'Training node label rate: {int(data.train_mask.sum()) / data.num_nodes:.2f}')\n",
    "print(f'Has isolated nodes: {data.has_isolated_nodes()}')\n",
    "print(f'Has self-loops: {data.has_self_loops()}')\n",
    "print(f'Is undirected: {data.is_undirected()}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Data(edge_index=[2, 156], x=[34, 34], y=[34], train_mask=[34])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import Javascript  # Restrict height of output cell.\n",
    "display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 300})'''))\n",
    "\n",
    "edge_index = data.edge_index\n",
    "print(edge_index.t())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch_geometric.utils import to_networkx\n",
    "\n",
    "G = to_networkx(data, to_undirected=True)\n",
    "visualize_graph(G, color=data.y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch.nn import Linear\n",
    "from torch_geometric.nn import GCNConv\n",
    "\n",
    "\n",
    "class GCN(torch.nn.Module):\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        torch.manual_seed(1234)\n",
    "        self.conv1 = GCNConv(dataset.num_features, 4)\n",
    "        self.conv2 = GCNConv(4, 4)\n",
    "        self.conv3 = GCNConv(4, 2)\n",
    "        self.classifier = Linear(2, dataset.num_classes)\n",
    "\n",
    "    def forward(self, x, edge_index):\n",
    "        h = self.conv1(x, edge_index)\n",
    "        h = h.tanh()\n",
    "        h = self.conv2(h, edge_index)\n",
    "        h = h.tanh()\n",
    "        h = self.conv3(h, edge_index)\n",
    "        h = h.tanh()  # Final GNN embedding space.\n",
    "        \n",
    "        # Apply a final (linear) classifier.\n",
    "        out = self.classifier(h)\n",
    "\n",
    "        return out, h\n",
    "\n",
    "model = GCN()\n",
    "print(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = GCN()\n",
    "\n",
    "_, h = model(data.x, data.edge_index)\n",
    "print(f'Embedding shape: {list(h.shape)}')\n",
    "\n",
    "visualize_embedding(h, color=data.y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "loss = criterion(out[data.train_mask], data.y[data.train_mask])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "from IPython.display import Javascript  # Restrict height of output cell.\n",
    "display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 430})'''))\n",
    "\n",
    "model = GCN()\n",
    "criterion = torch.nn.CrossEntropyLoss()  # Define loss criterion.\n",
    "optimizer = torch.optim.Adam(model.parameters(), lr=0.01)  # Define optimizer.\n",
    "\n",
    "def train(data):\n",
    "    optimizer.zero_grad()  # Clear gradients.\n",
    "    out, h = model(data.x, data.edge_index)  # Perform a single forward pass.\n",
    "    loss = criterion(out[data.train_mask], data.y[data.train_mask])  # Compute the loss solely based on the training nodes.\n",
    "    loss.backward()  # Derive gradients.\n",
    "    optimizer.step()  # Update parameters based on gradients.\n",
    "    return loss, h\n",
    "\n",
    "for epoch in range(401):\n",
    "    loss, h = train(data)\n",
    "    if epoch % 10 == 0:\n",
    "        visualize_embedding(h, color=data.y, epoch=epoch, loss=loss)\n",
    "        time.sleep(0.3)"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}