{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# STDM Quick Start Tutorial\n",
        "\n",
        "This notebook demonstrates the basic usage of the STDM package for tensor decomposition of gene expression data.\n",
        "\n",
        "## Overview\n",
        "\n",
        "We'll cover:\n",
        "1. Loading and preprocessing gene expression data\n",
        "2. Building multi-dimensional tensors\n",
        "3. Fitting CP decomposition\n",
        "4. Visualizing results\n",
        "5. Interpreting biological patterns\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Import required packages\n",
        "import sys\n",
        "from pathlib import Path\n",
        "\n",
        "# Add src to path if running from examples directory\n",
        "sys.path.insert(0, str(Path.cwd().parent / \"src\"))\n",
        "\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "from stdm import (\n",
        "    DataLoader,\n",
        "    TensorBuilder,\n",
        "    CPDecomposition,\n",
        "    plot_components,\n",
        "    plot_temporal_patterns,\n",
        "    plot_species_comparison,\n",
        "    plot_gene_loadings\n",
        ")\n",
        "from stdm.utils import compute_explained_variance\n",
        "\n",
        "%matplotlib inline\n",
        "sns.set_style('whitegrid')\n",
        "print(\"Imports successful!\")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 1. Load Gene Expression Data\n",
        "\n",
        "First, let's load the merged gene expression data containing all species.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Set up paths\n",
        "data_dir = Path.cwd().parent / \"data\" / \"merge-vst\"\n",
        "\n",
        "# Load data\n",
        "loader = DataLoader(data_dir)\n",
        "data = loader.load_merged_data()\n",
        "\n",
        "print(f\"Data shape: {data.shape}\")\n",
        "print(f\"Genes: {data.shape[0]}\")\n",
        "print(f\"Samples: {data.shape[1]}\")\n",
        "print(f\"\\nFirst few rows:\")\n",
        "data.head()\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Summary\n",
        "\n",
        "In this tutorial, we completed a full tensor decomposition analysis of gene expression data. The STDM package provides powerful tools for:\n",
        "- Multi-species gene expression analysis\n",
        "- Temporal pattern discovery\n",
        "- Species comparison\n",
        "- Marker gene identification\n",
        "\n",
        "For more examples and advanced usage, see the `examples/` directory and the comprehensive README.\n"
      ]
    }
  ],
  "metadata": {
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}