{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Installation Guide for SpaCon\n",
    "\n",
    "This guide will walk you through setting up an isolated Python environment using `conda` and installing the necessary packages, including `spacon`, `torch`, and `torch_geometric`.\n",
    "\n",
    "\n",
    "---\n",
    "\n",
    "\n",
    "> **Prerequisites**  \n",
    "   \n",
    "   \n",
    "\n",
    "\n",
    "Before you begin, ensure you have Anaconda or Miniconda installed on your system. If not, you can download it from the [official Anaconda website](https://www.anaconda.com/products/distribution).\n",
    "\n",
    "You will also need an NVIDIA GPU with a driver that supports the version of CUDA you intend to use.\n",
    "\n",
    "> **Step 1: Create a Conda Virtual Environment**\n",
    "\n",
    "First, create a new virtual environment to isolate our project dependencies. We will name this environment `spacon-env`. Open your terminal or Anaconda Prompt and execute the following command:\n",
    "\n",
    "```bash\n",
    "conda create --name spacon-env python=3.10\n",
    "```\n",
    "\n",
    "This command creates a new environment with Python 3.10. When prompted to proceed, type `y` and press Enter.\n",
    " \n",
    "Once the environment is created, activate it:\n",
    "\n",
    "```bash\n",
    "conda activate spacon-env\n",
    "```\n",
    "\n",
    "Your terminal prompt should now be prefixed with `(spacon-env)`.\n",
    "\n",
    "> **Step 2: Install spacon**\n",
    "\n",
    "With the `spacon-env` environment activated, the first package we will install is `spacon`.\n",
    "\n",
    "```bash\n",
    "pip install spacon\n",
    "```\n",
    "\n",
    "> **Step 3: Install PyTorch**\n",
    "\n",
    "Next, we will install PyTorch.\n",
    "\n",
    "**Note:** The PyTorch installation command depends on your Operating System, package manager (pip, conda), and desired CUDA version. The command below is just an example for `torch==2.5.0` with `CUDA 12.4`.\n",
    "\n",
    "It is highly recommended that you visit the [official PyTorch website (previous versions)](https://pytorch.org/get-started/previous-versions/) to find the correct installation command for your specific setup.\n",
    "\n",
    "Example installation command:\n",
    "\n",
    "```bash\n",
    "pip install torch==2.5.0 torchvision==0.20.0 torchaudio==2.5.0 --index-url https://download.pytorch.org/whl/cu124\n",
    "```\n",
    "\n",
    "> **Step 4: Install torch_geometric**\n",
    "\n",
    "After successfully installing PyTorch, you can install `torch_geometric`.\n",
    "\n",
    "```bash\n",
    "pip install torch_geometric\n",
    "```\n",
    "\n",
    "> **Step 5: Install torch_geometric Dependencies**\n",
    "\n",
    "Finally, we need to install the necessary dependencies for `torch_geometric` that are compatible with our specific PyTorch and CUDA versions.\n",
    "\n",
    "**Note:** The URL specified with the `-f` flag must match your version of `torch` and CUDA.\n",
    "\n",
    "Please refer to the [official PyTorch Geometric installation documentation](https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html) to find the correct URL for your build.\n",
    "\n",
    "The URL `https://data.pyg.org/whl/torch-2.5.0+cu124.html` in the command below corresponds to `torch-2.5.0` and `cu124`. You must adjust this URL according to your versions.\n",
    "\n",
    "```bash\n",
    "pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.5.0+cu124.html\n",
    "```\n",
    "\n",
    "> **Verification**\n",
    "\n",
    "To ensure that all packages have been installed correctly, you can run the following Python script:\n",
    "\n",
    "```python\n",
    "import spacon\n",
    "import torch\n",
    "import torch_geometric\n",
    "\n",
    "print(f\"PyTorch version: {torch.__version__}\")\n",
    "print(f\"CUDA available: {torch.cuda.is_available()}\")\n",
    "if torch.cuda.is_available():\n",
    "    print(f\"CUDA version: {torch.version.cuda}\")\n",
    "print(f\"torch_geometric version: {torch_geometric.__version__}\")\n",
    "```\n",
    "\n",
    "You have now successfully set up your Python environment with all the required packages."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}