{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "607a7ec5-4509-4512-94f9-908899963604",
   "metadata": {},
   "source": [
    "# Metric Lists Comparison\n",
    "\n",
    "The metric lists comparison is used to facilitate element-wise comparisons\n",
    "between metrics logged as lists. Users can dynamically choose between available\n",
    "list metrics to visualize.\n",
    "\n",
    "The plot itself is a Plotly annotated heatmap. More information can be found\n",
    "in [the Plotly documentation](https://plotly.com/python/annotated-heatmap/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8aad3d90-949e-4efa-a648-ac31689bdfb0",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "from rubicon_ml import Rubicon\n",
    "from rubicon_ml.viz import MetricListsComparison"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e1026b2-d42b-447b-97e5-221d6d619935",
   "metadata": {},
   "source": [
    "First, we'll create a few experiments and log some list metrics to them."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "51c7e3fc-ac37-4766-be79-21057199aeee",
   "metadata": {},
   "outputs": [],
   "source": [
    "rubicon = Rubicon(persistence=\"memory\", auto_git_enabled=True)\n",
    "project = rubicon.get_or_create_project(\"list metric comparison\")\n",
    "\n",
    "for i in range(0, 10):\n",
    "    experiment = project.log_experiment()\n",
    "    experiment.log_metric(\n",
    "        name=\"coefficients\",\n",
    "        value=[random.random() for _ in range(0, 25)],\n",
    "    )\n",
    "    experiment.log_metric(\n",
    "        name=\"p-values\",\n",
    "        value=[random.random() for _ in range(0, 25)],\n",
    "    )\n",
    "    experiment.log_metric(\n",
    "        name=\"stderr\",\n",
    "        value=[random.random() for _ in range(0, 25)],\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "94d2e5b0-5828-4aff-ab59-a4351f7164a1",
   "metadata": {},
   "source": [
    "Now, we can instantiate the `MetricListsComparison` object with the experiments we\n",
    "just logged. Optionally, provide a list of column names as `column_names` to add the\n",
    "names as a header to each column in the visualization.\n",
    "\n",
    "We can view the plot right in the notebook with `show`. The Dash application\n",
    "itself will be running on http://127.0.0.1:8050/ when running locally. Use the\n",
    "`serve` command to launch the server directly without rendering the widget in the\n",
    "current Python interpreter."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "68c4321a-6e41-4597-98b6-4921dcedd3aa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dash is running on http://127.0.0.1:8050/\n"
     ]
    }
   ],
   "source": [
    "MetricListsComparison(\n",
    "    experiments=project.experiments(),\n",
    "    column_names=[\"intercept\"] + [f\"var_{i:03}\" for i in range(1, 25)],\n",
    ").show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "194fa6a5-12d1-48ce-b13d-ef0605970d09",
   "metadata": {},
   "source": [
    "![metric-lists-comparisons](metric-lists-comparisons.png \"metric lists comparisons\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}