{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "09118d7a",
   "metadata": {},
   "source": [
    "# Bivariate data - Models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "840c0733",
   "metadata": {},
   "source": [
    "This tutorial focuses on fitting simple regression models to bivariate data using `plans`, and assessing them with the model panel and fit metrics.\n",
    "\n",
    "```{seealso}\n",
    "Check out the {doc}`Bivariate data - Basics <bivar_01>` tutorial first.\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46dad7a5",
   "metadata": {},
   "source": [
    "## Notebook setup\n",
    "\n",
    "For users running this tutorial as a Jupyter Notebook, this cell must be executed first:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8bed0e4e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:12.310257Z",
     "iopub.status.busy": "2026-10-30T22:23:12.309815Z",
     "iopub.status.idle": "2026-10-30T22:23:12.756463Z",
     "shell.execute_reply": "2026-10-30T22:23:12.755851Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Outputs will be saved to: ./outputs\\bivariate\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "from pathlib import Path\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "# Install `plans` in `google.colab`.\n",
    "# Use `pip install plans` for other environments.\n",
    "\n",
    "if \"google.colab\" in sys.modules:\n",
    "    import os\n",
    "    os.system(f\"{sys.executable} -m pip install -q plans\")\n",
    "\n",
    "# This avoids warnings related to uninstalled fonts\n",
    "import logging\n",
    "# Set the matplotlib font manager logger to only show errors (hides warnings)\n",
    "logging.getLogger('matplotlib.font_manager').setLevel(logging.ERROR)\n",
    "\n",
    "# define output folder\n",
    "OUTPUT_DIR = Path(\"outputs/bivariate\")\n",
    "OUTPUT_DIR.mkdir(parents=True, exist_ok=True)\n",
    "print(f\"Outputs will be saved to: ./{OUTPUT_DIR}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "014822c0",
   "metadata": {},
   "source": [
    "## Create synthetic rating curve\n",
    "\n",
    "Stage-discharge relations (rating curves) are a classic case for model fitting in hydrology. Discharge usually starts at a stage offset (the gauge zero is below the channel bottom), so lets make one with $h_0 = 0.2$ m plus gaussian noise. Stages are drawn from a skewed (gamma) distribution, since low flows are far more frequent than floods in a real gauging record:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0396d96a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:12.760291Z",
     "iopub.status.busy": "2026-10-30T22:23:12.759860Z",
     "iopub.status.idle": "2026-10-30T22:23:13.356751Z",
     "shell.execute_reply": "2026-10-30T22:23:13.355891Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 478.346x472.441 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from plans.datasets.analyst import Bivar\n",
    "\n",
    "# make synthetic power-law data with a stage offset\n",
    "rng = np.random.default_rng(seed=42)  # ensure reproducibility\n",
    "h = 0.3 + rng.gamma(shape=1.5, scale=0.4, size=200)  # skewed to low stages\n",
    "q = 5 * np.power(h - 0.2, 1.6) + rng.normal(loc=0, scale=0.5, size=len(h))\n",
    "\n",
    "bv = Bivar(name=\"Rating Curve\", alias=\"RC\")\n",
    "bv.xname = \"Stage\"\n",
    "bv.xunits = \"m\"\n",
    "bv.yname = \"Discharge\"\n",
    "bv.yunits = \"m3/s\"\n",
    "bv.set_data(x=h, y=q)\n",
    "bv.view()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27fa1866",
   "metadata": {},
   "source": [
    "## Available models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10acbdc2",
   "metadata": {},
   "source": [
    "Models are stored in the `.models` dictionary. Each entry holds the function, its formula, a `Setup` table of parameters (initial guesses before fitting) and, once computed, the model `Data` and `Metrics`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ca2bee0f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:13.359743Z",
     "iopub.status.busy": "2026-10-30T22:23:13.359261Z",
     "iopub.status.idle": "2026-10-30T22:23:13.364743Z",
     "shell.execute_reply": "2026-10-30T22:23:13.363896Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Linear       f(x) = c0 + c1 * x\n",
      "Power        f(x) =  c2 * ((x + c0)^c1)\n",
      "Power_zero   f(x) =  c1 * (x^c0)\n"
     ]
    }
   ],
   "source": [
    "for model_type, model in bv.models.items():\n",
    "    print(f\"{model_type:<12} {model['Formula']}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd43df5f",
   "metadata": {},
   "source": [
    "## Fitting models\n",
    "\n",
    "The `.fit()` method runs a least squares fit and stores the mean and standard deviation of parameters in the `Setup` table. The `model` layout shows the fitted curve, how the error variance evolves along `x`, the errors, their histogram and a Q-Q plot against the normal distribution."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aab46a71",
   "metadata": {},
   "source": [
    "### Linear model\n",
    "\n",
    "The simplest model. A straight line can not follow the curvature, so errors show a clear pattern along `x`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "107495d7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:13.368842Z",
     "iopub.status.busy": "2026-10-30T22:23:13.368340Z",
     "iopub.status.idle": "2026-10-30T22:23:13.910613Z",
     "shell.execute_reply": "2026-10-30T22:23:13.909920Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "f(x) = c0 + c1 * x\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Parameters</th>\n",
       "      <th>Mean</th>\n",
       "      <th>SD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>c0</td>\n",
       "      <td>-4.373973</td>\n",
       "      <td>0.181619</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>c1</td>\n",
       "      <td>8.632297</td>\n",
       "      <td>0.171988</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Parameters      Mean        SD\n",
       "0         c0 -4.373973  0.181619\n",
       "1         c1  8.632297  0.171988"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.fit(model_type=\"Linear\")\n",
    "print(bv.models[\"Linear\"][\"Formula\"])\n",
    "bv.models[\"Linear\"][\"Setup\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f280838",
   "metadata": {},
   "source": [
    "Fit metrics:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fd7996ea",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:13.914365Z",
     "iopub.status.busy": "2026-10-30T22:23:13.914138Z",
     "iopub.status.idle": "2026-10-30T22:23:13.919101Z",
     "shell.execute_reply": "2026-10-30T22:23:13.917952Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'r': 0.9628756752076764,\n",
       " 'rho': 0.9634260856521415,\n",
       " 'R2': 0.9271295659066388,\n",
       " 'RMSE': 1.2349857669571258,\n",
       " 'MAE': 0.919012840087451,\n",
       " 'Bias': 2.4696790784111732e-08}"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.models[\"Linear\"][\"Metrics\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b590639d",
   "metadata": {},
   "source": [
    "Model panel:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ffd17861",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:13.921635Z",
     "iopub.status.busy": "2026-10-30T22:23:13.921393Z",
     "iopub.status.idle": "2026-10-30T22:23:14.802849Z",
     "shell.execute_reply": "2026-10-30T22:23:14.801151Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 708.661x708.661 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bv.view_specs[\"layout\"] = \"model\"\n",
    "bv.view_specs[\"model_type\"] = \"Linear\"\n",
    "bv.view_specs[\"title\"] = \"Linear model\"\n",
    "bv.view()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37ba3e1c",
   "metadata": {},
   "source": [
    "The model `Data` holds the predictions (`y_Mean`) and the errors (`e_Mean`, model minus observed):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c4005ed2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:14.806593Z",
     "iopub.status.busy": "2026-10-30T22:23:14.806069Z",
     "iopub.status.idle": "2026-10-30T22:23:14.822863Z",
     "shell.execute_reply": "2026-10-30T22:23:14.821838Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>y_Mean</th>\n",
       "      <th>e_Mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.317913</td>\n",
       "      <td>-0.180704</td>\n",
       "      <td>-1.629649</td>\n",
       "      <td>-1.448945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.318673</td>\n",
       "      <td>-0.315874</td>\n",
       "      <td>-1.623089</td>\n",
       "      <td>-1.307215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.323125</td>\n",
       "      <td>0.857127</td>\n",
       "      <td>-1.584662</td>\n",
       "      <td>-2.441789</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.325952</td>\n",
       "      <td>0.987234</td>\n",
       "      <td>-1.560258</td>\n",
       "      <td>-2.547492</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.344702</td>\n",
       "      <td>-0.217002</td>\n",
       "      <td>-1.398398</td>\n",
       "      <td>-1.181397</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          x         y    y_Mean    e_Mean\n",
       "0  0.317913 -0.180704 -1.629649 -1.448945\n",
       "1  0.318673 -0.315874 -1.623089 -1.307215\n",
       "2  0.323125  0.857127 -1.584662 -2.441789\n",
       "3  0.325952  0.987234 -1.560258 -2.547492\n",
       "4  0.344702 -0.217002 -1.398398 -1.181397"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.models[\"Linear\"][\"Data\"].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb07eb30",
   "metadata": {},
   "source": [
    "### Power_zero model\n",
    "\n",
    "A power law with root at zero. It follows the curvature, but can not represent the stage offset:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "f89f65ec",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:14.827158Z",
     "iopub.status.busy": "2026-10-30T22:23:14.826670Z",
     "iopub.status.idle": "2026-10-30T22:23:14.851006Z",
     "shell.execute_reply": "2026-10-30T22:23:14.849501Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "f(x) =  c1 * (x^c0)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Parameters</th>\n",
       "      <th>Mean</th>\n",
       "      <th>SD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>c0</td>\n",
       "      <td>1.873139</td>\n",
       "      <td>0.014986</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>c1</td>\n",
       "      <td>3.431515</td>\n",
       "      <td>0.043597</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Parameters      Mean        SD\n",
       "0         c0  1.873139  0.014986\n",
       "1         c1  3.431515  0.043597"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.fit(model_type=\"Power_zero\")\n",
    "print(bv.models[\"Power_zero\"][\"Formula\"])\n",
    "bv.models[\"Power_zero\"][\"Setup\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a79812a3",
   "metadata": {},
   "source": [
    "Fit metrics:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e2547f16",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:14.855254Z",
     "iopub.status.busy": "2026-10-30T22:23:14.854770Z",
     "iopub.status.idle": "2026-10-30T22:23:14.862281Z",
     "shell.execute_reply": "2026-10-30T22:23:14.860707Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'r': 0.9935712183494392,\n",
       " 'rho': 0.9634260856521415,\n",
       " 'R2': 0.9867430899580296,\n",
       " 'RMSE': 0.5267534985525234,\n",
       " 'MAE': 0.4079012884384201,\n",
       " 'Bias': 2.0582720823796645}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.models[\"Power_zero\"][\"Metrics\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a3d5979",
   "metadata": {},
   "source": [
    "Model panel:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0170d7e4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:14.866724Z",
     "iopub.status.busy": "2026-10-30T22:23:14.866221Z",
     "iopub.status.idle": "2026-10-30T22:23:15.628155Z",
     "shell.execute_reply": "2026-10-30T22:23:15.626483Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 708.661x708.661 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bv.view_specs[\"layout\"] = \"model\"\n",
    "bv.view_specs[\"model_type\"] = \"Power_zero\"\n",
    "bv.view_specs[\"title\"] = \"Power_zero model\"\n",
    "bv.view()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec393ffb",
   "metadata": {},
   "source": [
    "### Power model\n",
    "\n",
    "A power law with a translational parameter `c0`, which captures the stage offset ($c_0 \\approx -h_0$):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9feceb72",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:15.633041Z",
     "iopub.status.busy": "2026-10-30T22:23:15.632197Z",
     "iopub.status.idle": "2026-10-30T22:23:15.656907Z",
     "shell.execute_reply": "2026-10-30T22:23:15.655121Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "f(x) =  c2 * ((x + c0)^c1)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Parameters</th>\n",
       "      <th>Mean</th>\n",
       "      <th>SD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>c0</td>\n",
       "      <td>-0.184590</td>\n",
       "      <td>0.030121</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>c1</td>\n",
       "      <td>1.655100</td>\n",
       "      <td>0.038360</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>c2</td>\n",
       "      <td>4.789241</td>\n",
       "      <td>0.257472</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Parameters      Mean        SD\n",
       "0         c0 -0.184590  0.030121\n",
       "1         c1  1.655100  0.038360\n",
       "2         c2  4.789241  0.257472"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.fit(model_type=\"Power\")\n",
    "print(bv.models[\"Power\"][\"Formula\"])\n",
    "bv.models[\"Power\"][\"Setup\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed948c7f",
   "metadata": {},
   "source": [
    "Fit metrics:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "626f3006",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:15.660833Z",
     "iopub.status.busy": "2026-10-30T22:23:15.660422Z",
     "iopub.status.idle": "2026-10-30T22:23:15.669320Z",
     "shell.execute_reply": "2026-10-30T22:23:15.668015Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'r': 0.9941759516647759,\n",
       " 'rho': 0.9634260856521415,\n",
       " 'R2': 0.9883855277023155,\n",
       " 'RMSE': 0.49304438285530766,\n",
       " 'MAE': 0.3951174168161138,\n",
       " 'Bias': -0.054016609030506244}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.models[\"Power\"][\"Metrics\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b6e87ed",
   "metadata": {},
   "source": [
    "Model panel:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "0d0e37cc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:15.672849Z",
     "iopub.status.busy": "2026-10-30T22:23:15.672404Z",
     "iopub.status.idle": "2026-10-30T22:23:16.554624Z",
     "shell.execute_reply": "2026-10-30T22:23:16.551688Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 708.661x708.661 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bv.view_specs[\"layout\"] = \"model\"\n",
    "bv.view_specs[\"model_type\"] = \"Power\"\n",
    "bv.view_specs[\"title\"] = \"Power model\"\n",
    "bv.view()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a174ad4c",
   "metadata": {},
   "source": [
    "## Comparing models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88a665ca",
   "metadata": {},
   "source": [
    "Collect the metrics of all models in a table:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c51417ce",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:16.566410Z",
     "iopub.status.busy": "2026-10-30T22:23:16.563429Z",
     "iopub.status.idle": "2026-10-30T22:23:16.604545Z",
     "shell.execute_reply": "2026-10-30T22:23:16.602486Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>r</th>\n",
       "      <th>rho</th>\n",
       "      <th>R2</th>\n",
       "      <th>RMSE</th>\n",
       "      <th>MAE</th>\n",
       "      <th>Bias</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Linear</th>\n",
       "      <td>0.962876</td>\n",
       "      <td>0.963426</td>\n",
       "      <td>0.927130</td>\n",
       "      <td>1.234986</td>\n",
       "      <td>0.919013</td>\n",
       "      <td>2.469679e-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Power</th>\n",
       "      <td>0.994176</td>\n",
       "      <td>0.963426</td>\n",
       "      <td>0.988386</td>\n",
       "      <td>0.493044</td>\n",
       "      <td>0.395117</td>\n",
       "      <td>-5.401661e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Power_zero</th>\n",
       "      <td>0.993571</td>\n",
       "      <td>0.963426</td>\n",
       "      <td>0.986743</td>\n",
       "      <td>0.526753</td>\n",
       "      <td>0.407901</td>\n",
       "      <td>2.058272e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   r       rho        R2      RMSE       MAE          Bias\n",
       "Linear      0.962876  0.963426  0.927130  1.234986  0.919013  2.469679e-08\n",
       "Power       0.994176  0.963426  0.988386  0.493044  0.395117 -5.401661e-02\n",
       "Power_zero  0.993571  0.963426  0.986743  0.526753  0.407901  2.058272e+00"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dc_metrics = {}\n",
    "for model_type in bv.models:\n",
    "    dc_metrics[model_type] = bv.models[model_type][\"Metrics\"]\n",
    "\n",
    "df_metrics = pd.DataFrame(dc_metrics).T\n",
    "df_metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc31eb8c",
   "metadata": {},
   "source": [
    "Note that $\\rho$ is the same for all models: they are all increasing curves, so they rank the predictions in the same order. Here $r$, $R^2$ and the errors are what separate the models. Also, $R^2$ equals $r^2$ only for the least-squares linear model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "88247e1b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:16.614462Z",
     "iopub.status.busy": "2026-10-30T22:23:16.610894Z",
     "iopub.status.idle": "2026-10-30T22:23:16.629990Z",
     "shell.execute_reply": "2026-10-30T22:23:16.628335Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Linear R2: 0.9271\n",
      "Linear r^2: 0.9271\n"
     ]
    }
   ],
   "source": [
    "print(f\"Linear R2: {df_metrics.loc['Linear', 'R2']:.4f}\")\n",
    "print(f\"Linear r^2: {df_metrics.loc['Linear', 'r'] ** 2:.4f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c2e3d017",
   "metadata": {},
   "source": [
    "### Error normality\n",
    "\n",
    "Assess if model errors are normal via the `.get_error_normality()` method:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "a26ea7ae",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:16.638943Z",
     "iopub.status.busy": "2026-10-30T22:23:16.637390Z",
     "iopub.status.idle": "2026-10-30T22:23:16.777714Z",
     "shell.execute_reply": "2026-10-30T22:23:16.775973Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Model</th>\n",
       "      <th>Test</th>\n",
       "      <th>Statistic</th>\n",
       "      <th>p-value</th>\n",
       "      <th>is_normal</th>\n",
       "      <th>Confidence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Linear</td>\n",
       "      <td>Kolmogorov-Smirnov</td>\n",
       "      <td>0.084378</td>\n",
       "      <td>1.094225e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Linear</td>\n",
       "      <td>Shapiro-Wilk</td>\n",
       "      <td>0.876952</td>\n",
       "      <td>1.074658e-11</td>\n",
       "      <td>False</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Linear</td>\n",
       "      <td>D'Agostino-Pearson</td>\n",
       "      <td>113.712185</td>\n",
       "      <td>2.031013e-25</td>\n",
       "      <td>False</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Power</td>\n",
       "      <td>Kolmogorov-Smirnov</td>\n",
       "      <td>0.039072</td>\n",
       "      <td>9.083111e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Power</td>\n",
       "      <td>Shapiro-Wilk</td>\n",
       "      <td>0.997095</td>\n",
       "      <td>9.728016e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Power</td>\n",
       "      <td>D'Agostino-Pearson</td>\n",
       "      <td>0.095267</td>\n",
       "      <td>9.534831e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Power_zero</td>\n",
       "      <td>Kolmogorov-Smirnov</td>\n",
       "      <td>0.061591</td>\n",
       "      <td>4.172193e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Power_zero</td>\n",
       "      <td>Shapiro-Wilk</td>\n",
       "      <td>0.990347</td>\n",
       "      <td>2.006875e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Power_zero</td>\n",
       "      <td>D'Agostino-Pearson</td>\n",
       "      <td>0.870901</td>\n",
       "      <td>6.469732e-01</td>\n",
       "      <td>True</td>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Model                Test   Statistic       p-value  is_normal  \\\n",
       "0      Linear  Kolmogorov-Smirnov    0.084378  1.094225e-01       True   \n",
       "1      Linear        Shapiro-Wilk    0.876952  1.074658e-11      False   \n",
       "2      Linear  D'Agostino-Pearson  113.712185  2.031013e-25      False   \n",
       "3       Power  Kolmogorov-Smirnov    0.039072  9.083111e-01       True   \n",
       "4       Power        Shapiro-Wilk    0.997095  9.728016e-01       True   \n",
       "5       Power  D'Agostino-Pearson    0.095267  9.534831e-01       True   \n",
       "6  Power_zero  Kolmogorov-Smirnov    0.061591  4.172193e-01       True   \n",
       "7  Power_zero        Shapiro-Wilk    0.990347  2.006875e-01       True   \n",
       "8  Power_zero  D'Agostino-Pearson    0.870901  6.469732e-01       True   \n",
       "\n",
       "   Confidence  \n",
       "0        0.95  \n",
       "1        0.95  \n",
       "2        0.95  \n",
       "3        0.95  \n",
       "4        0.95  \n",
       "5        0.95  \n",
       "6        0.95  \n",
       "7        0.95  \n",
       "8        0.95  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ls_dfs = []\n",
    "for model_type in bv.models:\n",
    "    df = bv.get_error_normality(model_type=model_type, clevel=0.95)\n",
    "    df.insert(0, \"Model\", model_type)\n",
    "    ls_dfs.append(df)\n",
    "pd.concat(ls_dfs, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e70e3f4",
   "metadata": {},
   "source": [
    "## Set parameters manually\n",
    "\n",
    "Parameters can also be set by hand with `.update_model()`, for instance to test a known reference curve. Metrics and the model data are updated accordingly:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c444a524",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T22:23:16.786826Z",
     "iopub.status.busy": "2026-10-30T22:23:16.783729Z",
     "iopub.status.idle": "2026-10-30T22:23:16.813063Z",
     "shell.execute_reply": "2026-10-30T22:23:16.811153Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'r': 0.994033909930358,\n",
       " 'rho': 0.9634260856521415,\n",
       " 'R2': 0.9878227099891589,\n",
       " 'RMSE': 0.5048491143405004,\n",
       " 'MAE': 0.40285840445680393,\n",
       " 'Bias': 0.8702160614684503}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bv.update_model(params_mean=[-0.2, 1.6, 5.0], model_type=\"Power\")\n",
    "bv.models[\"Power\"][\"Metrics\"]"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}