{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "901b134b-7510-4d9e-ae95-a01a4c33274e",
   "metadata": {},
   "source": [
    "# Palmer Penguins\n",
    "\n",
    "This notebook is inspired by an example [Radar chart with ggradar](https://r-graph-gallery.com/web-radar-chart-with-R.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "09f8f3a0-478a-4f0a-945d-8354860919b6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:42.160207Z",
     "iopub.status.busy": "2024-04-26T12:19:42.160207Z",
     "iopub.status.idle": "2024-04-26T12:19:43.055517Z",
     "shell.execute_reply": "2024-04-26T12:19:43.055517Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from lets_plot import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f67a85a2-c3a9-4009-a5bf-0feea37e6658",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:43.055517Z",
     "iopub.status.busy": "2024-04-26T12:19:43.055517Z",
     "iopub.status.idle": "2024-04-26T12:19:43.071589Z",
     "shell.execute_reply": "2024-04-26T12:19:43.071589Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "            <div id=\"cAF54A\"></div>\n",
       "            <script type=\"text/javascript\" data-lets-plot-script=\"library\">\n",
       "                if(!window.letsPlotCallQueue) {\n",
       "                    window.letsPlotCallQueue = [];\n",
       "                }; \n",
       "                window.letsPlotCall = function(f) {\n",
       "                    window.letsPlotCallQueue.push(f);\n",
       "                };\n",
       "                (function() {\n",
       "                    var script = document.createElement(\"script\");\n",
       "                    script.type = \"text/javascript\";\n",
       "                    script.src = \"https://cdn.jsdelivr.net/gh/JetBrains/lets-plot@v4.3.2/js-package/distr/lets-plot.min.js\";\n",
       "                    script.onload = function() {\n",
       "                        window.letsPlotCall = function(f) {f();};\n",
       "                        window.letsPlotCallQueue.forEach(function(f) {f();});\n",
       "                        window.letsPlotCallQueue = [];\n",
       "                        \n",
       "                    };\n",
       "                    script.onerror = function(event) {\n",
       "                        window.letsPlotCall = function(f) {};    // noop\n",
       "                        window.letsPlotCallQueue = [];\n",
       "                        var div = document.createElement(\"div\");\n",
       "                        div.style.color = 'darkred';\n",
       "                        div.textContent = 'Error loading Lets-Plot JS';\n",
       "                        document.getElementById(\"cAF54A\").appendChild(div);\n",
       "                    };\n",
       "                    var e = document.getElementById(\"cAF54A\");\n",
       "                    e.appendChild(script);\n",
       "                })()\n",
       "            </script>\n",
       "            "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "LetsPlot.setup_html()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "93b26d2e-123d-40b5-af22-c48464271312",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:43.071589Z",
     "iopub.status.busy": "2024-04-26T12:19:43.071589Z",
     "iopub.status.idle": "2024-04-26T12:19:43.087260Z",
     "shell.execute_reply": "2024-04-26T12:19:43.087260Z"
    }
   },
   "outputs": [],
   "source": [
    "def rescale_in_group_df(df, value_col, group_col, rescaled_col=None):\n",
    "    if rescaled_col is None:\n",
    "        rescaled_col = \"rescaled_{0}\".format(value_col)\n",
    "    def rescale_subdf(subdf):\n",
    "        rescaler = lambda s: (s - s.min()) / (s.max() - s.min())\n",
    "        return subdf.assign(**{rescaled_col: rescaler(subdf[value_col])})\n",
    "    return pd.concat([rescale_subdf(df[df[group_col] == g]) for g in df[group_col].unique()])\n",
    "\n",
    "def get_data():\n",
    "    df = pd.read_csv(\"https://raw.githubusercontent.com/JetBrains/lets-plot-docs/master/data/penguins.csv\")\n",
    "\n",
    "    grouped_df = df.dropna().groupby(\"species\")[[\"bill_length_mm\", \"bill_depth_mm\", \"flipper_length_mm\", \"body_mass_g\"]].mean().reset_index()\n",
    "    grouped_df.columns = [\"species\", \"avg. bill length\", \"avg. bill depth\", \"avg. flipper length\", \"avg. body mass\"]\n",
    "\n",
    "    melted_df = pd.melt(grouped_df, id_vars=\"species\")\n",
    "    avg_body_mass_filter = melted_df[\"variable\"] == \"avg. body mass\"\n",
    "    melted_df.loc[avg_body_mass_filter, \"value\"] /= 1000\n",
    "    melted_df = melted_df.assign(units=np.where(avg_body_mass_filter, \"kg\", \"mm\"))\n",
    "\n",
    "    rescaled_df = rescale_in_group_df(melted_df, \"value\", \"variable\")\n",
    "    rescaled_df.loc[:, \"rescaled_value_pct\"] = (100 * rescaled_df[\"rescaled_value\"]).astype(int)\n",
    "    return rescaled_df.sort_values(by=\"species\").reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7c4336eb-7356-4830-ab61-4c233815f071",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:43.087260Z",
     "iopub.status.busy": "2024-04-26T12:19:43.087260Z",
     "iopub.status.idle": "2024-04-26T12:19:43.405669Z",
     "shell.execute_reply": "2024-04-26T12:19:43.405669Z"
    }
   },
   "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>species</th>\n",
       "      <th>variable</th>\n",
       "      <th>value</th>\n",
       "      <th>units</th>\n",
       "      <th>rescaled_value</th>\n",
       "      <th>rescaled_value_pct</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>avg. bill length</td>\n",
       "      <td>38.823973</td>\n",
       "      <td>mm</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>avg. bill depth</td>\n",
       "      <td>18.347260</td>\n",
       "      <td>mm</td>\n",
       "      <td>0.978584</td>\n",
       "      <td>97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>avg. flipper length</td>\n",
       "      <td>190.102740</td>\n",
       "      <td>mm</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>avg. body mass</td>\n",
       "      <td>3.706164</td>\n",
       "      <td>kg</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  species             variable       value units  rescaled_value  \\\n",
       "0  Adelie     avg. bill length   38.823973    mm        0.000000   \n",
       "1  Adelie      avg. bill depth   18.347260    mm        0.978584   \n",
       "2  Adelie  avg. flipper length  190.102740    mm        0.000000   \n",
       "3  Adelie       avg. body mass    3.706164    kg        0.000000   \n",
       "\n",
       "   rescaled_value_pct  \n",
       "0                   0  \n",
       "1                  97  \n",
       "2                   0  \n",
       "3                   0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "penguins_df = get_data()\n",
    "penguins_df.head(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3145b502-08cb-4395-81f0-581746adecf3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:43.405669Z",
     "iopub.status.busy": "2024-04-26T12:19:43.405669Z",
     "iopub.status.idle": "2024-04-26T12:19:43.421374Z",
     "shell.execute_reply": "2024-04-26T12:19:43.421374Z"
    }
   },
   "outputs": [],
   "source": [
    "font_family = \"roboto\"\n",
    "axis_color = \"lightgray\"\n",
    "axis_text_data = {\"x\": [\"avg. bill length\"]*3, \\\n",
    "                  \"y\": [0, 50, 100], \\\n",
    "                  \"text\": [\"0%\", \"50%\", \"100%\"]}\n",
    "\n",
    "penguins_colors = {\"Adelie\": \"#ff5a5f\", \"Chinstrap\": \"#ffb400\", \"Gentoo\": \"#007a87\"}\n",
    "penguins_tooltips = layer_tooltips().title(\"@species\")\\\n",
    "                                    .line(\"@variable (@units): @value\").format(\"@value\", \".2~f\")\n",
    "penguins_theme = theme(\n",
    "    text=element_text(family=font_family, size=18),\n",
    "    plot_title=element_text(size=28, hjust=.5, face='bold'),\n",
    "    axis_title='blank', axis_text_y='blank', axis_line_x='blank', \\\n",
    "    axis_ticks=element_line(color=axis_color), \\\n",
    "    panel_grid=element_line(color=axis_color), \\\n",
    "    panel_inset=[0, 80], \\\n",
    "    legend_position=[1, 0], legend_justification=[1, 0],\n",
    "    tooltip=element_rect(),\n",
    "    axis_tooltip='blank',\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1cef4685-588c-4c5d-bf3a-576f9933cda9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-26T12:19:43.421374Z",
     "iopub.status.busy": "2024-04-26T12:19:43.421374Z",
     "iopub.status.idle": "2024-04-26T12:19:43.533166Z",
     "shell.execute_reply": "2024-04-26T12:19:43.531172Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "   <div id=\"JaeFXk\"></div>\n",
       "   <script type=\"text/javascript\" data-lets-plot-script=\"plot\">\n",
       "       (function() {\n",
       "           var plotSpec={\n",
       "\"data\":{\n",
       "\"species\":[\"Adelie\",\"Adelie\",\"Adelie\",\"Adelie\",\"Chinstrap\",\"Chinstrap\",\"Chinstrap\",\"Chinstrap\",\"Gentoo\",\"Gentoo\",\"Gentoo\",\"Gentoo\"],\n",
       "\"variable\":[\"avg. bill length\",\"avg. bill depth\",\"avg. flipper length\",\"avg. body mass\",\"avg. bill length\",\"avg. bill depth\",\"avg. flipper length\",\"avg. body mass\",\"avg. bill length\",\"avg. bill depth\",\"avg. flipper length\",\"avg. body mass\"],\n",
       "\"value\":[38.82397260273973,18.3472602739726,190.1027397260274,3.7061643835616436,48.83382352941176,18.420588235294115,195.8235294117647,3.7330882352941175,47.56806722689076,14.996638655462185,217.23529411764707,5.0924369747899165],\n",
       "\"units\":[\"mm\",\"mm\",\"mm\",\"kg\",\"mm\",\"mm\",\"mm\",\"kg\",\"mm\",\"mm\",\"mm\",\"kg\"],\n",
       "\"rescaled_value_pct\":[0.0,97.0,0.0,0.0,100.0,100.0,21.0,1.0,87.0,0.0,100.0,100.0]\n",
       "},\n",
       "\"mapping\":{\n",
       "},\n",
       "\"data_meta\":{\n",
       "},\n",
       "\"coord\":{\n",
       "\"name\":\"polar\",\n",
       "\"ylim\":[-15.0,100.0]\n",
       "},\n",
       "\"ggsize\":{\n",
       "\"width\":800.0,\n",
       "\"height\":600.0\n",
       "},\n",
       "\"ggtitle\":{\n",
       "\"text\":\"Penguins species\"\n",
       "},\n",
       "\"theme\":{\n",
       "\"text\":{\n",
       "\"family\":\"roboto\",\n",
       "\"size\":18.0,\n",
       "\"blank\":false\n",
       "},\n",
       "\"axis_title\":\"blank\",\n",
       "\"axis_text_y\":\"blank\",\n",
       "\"axis_ticks\":{\n",
       "\"color\":\"lightgray\",\n",
       "\"blank\":false\n",
       "},\n",
       "\"axis_line_x\":\"blank\",\n",
       "\"legend_position\":[1.0,0.0],\n",
       "\"legend_justification\":[1.0,0.0],\n",
       "\"panel_grid\":{\n",
       "\"color\":\"lightgray\",\n",
       "\"blank\":false\n",
       "},\n",
       "\"panel_inset\":[0.0,80.0],\n",
       "\"plot_title\":{\n",
       "\"face\":\"bold\",\n",
       "\"size\":28.0,\n",
       "\"hjust\":0.5,\n",
       "\"blank\":false\n",
       "},\n",
       "\"axis_tooltip\":\"blank\",\n",
       "\"tooltip\":{\n",
       "\"blank\":false\n",
       "},\n",
       "\"flavor\":\"solarized_light\"\n",
       "},\n",
       "\"kind\":\"plot\",\n",
       "\"scales\":[{\n",
       "\"aesthetic\":\"x\",\n",
       "\"discrete\":true,\n",
       "\"reverse\":false\n",
       "},{\n",
       "\"name\":\"\",\n",
       "\"aesthetic\":\"paint_a\",\n",
       "\"breaks\":[\"Adelie\",\"Chinstrap\",\"Gentoo\"],\n",
       "\"values\":[\"#ff5a5f\",\"#ffb400\",\"#007a87\"]\n",
       "}],\n",
       "\"layers\":[{\n",
       "\"geom\":\"area\",\n",
       "\"mapping\":{\n",
       "\"x\":\"variable\",\n",
       "\"y\":\"rescaled_value_pct\",\n",
       "\"paint_a\":\"species\"\n",
       "},\n",
       "\"position\":\"identity\",\n",
       "\"data_meta\":{\n",
       "},\n",
       "\"flat\":true,\n",
       "\"color_by\":\"paint_a\",\n",
       "\"fill_by\":\"paint_a\",\n",
       "\"size\":2.5,\n",
       "\"alpha\":0.2,\n",
       "\"data\":{\n",
       "}\n",
       "},{\n",
       "\"geom\":\"point\",\n",
       "\"mapping\":{\n",
       "\"x\":\"variable\",\n",
       "\"y\":\"rescaled_value_pct\",\n",
       "\"paint_a\":\"species\"\n",
       "},\n",
       "\"tooltips\":{\n",
       "\"formats\":[{\n",
       "\"field\":\"@value\",\n",
       "\"format\":\".2~f\"\n",
       "}],\n",
       "\"lines\":[\"@variable (@units): @value\"],\n",
       "\"title\":\"@species\"\n",
       "},\n",
       "\"data_meta\":{\n",
       "},\n",
       "\"color_by\":\"paint_a\",\n",
       "\"size\":6.0,\n",
       "\"data\":{\n",
       "}\n",
       "},{\n",
       "\"geom\":\"text\",\n",
       "\"data\":{\n",
       "\"x\":[\"avg. bill length\",\"avg. bill length\",\"avg. bill length\"],\n",
       "\"y\":[0.0,50.0,100.0],\n",
       "\"text\":[\"0%\",\"50%\",\"100%\"]\n",
       "},\n",
       "\"mapping\":{\n",
       "\"x\":\"x\",\n",
       "\"y\":\"y\",\n",
       "\"label\":\"text\"\n",
       "},\n",
       "\"data_meta\":{\n",
       "},\n",
       "\"hjust\":1.0,\n",
       "\"fontface\":\"bold\",\n",
       "\"family\":\"roboto\",\n",
       "\"size\":10.0\n",
       "}],\n",
       "\"metainfo_list\":[]\n",
       "};\n",
       "           var plotContainer = document.getElementById(\"JaeFXk\");\n",
       "           window.letsPlotCall(function() {{\n",
       "               LetsPlot.buildPlotFromProcessedSpecs(plotSpec, -1, -1, plotContainer);\n",
       "           }});\n",
       "       })();\n",
       "   </script>"
      ],
      "text/plain": [
       "<lets_plot.plot.core.PlotSpec at 0x1af725949a0>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ggplot(penguins_df) + \\\n",
    "    geom_area(aes(\"variable\", \"rescaled_value_pct\", paint_a=\"species\"), position='identity', flat=True, \\\n",
    "              size=2.5, color_by='paint_a', fill_by='paint_a', alpha=.2) + \\\n",
    "    geom_point(aes(\"variable\", \"rescaled_value_pct\", paint_a=\"species\"), size=6, color_by='paint_a', tooltips=penguins_tooltips) + \\\n",
    "    geom_text(aes(\"x\", \"y\", label=\"text\"), data=axis_text_data, hjust=1, fontface='bold', family=font_family, size=10) + \\\n",
    "    scale_x_discrete() + \\\n",
    "    scale_manual('paint_a', name='', values=penguins_colors) + \\\n",
    "    coord_polar(ylim=[-15, 100]) + \\\n",
    "    ggsize(800, 600) + \\\n",
    "    ggtitle(\"Penguins species\") + \\\n",
    "    penguins_theme + flavor_solarized_light()"
   ]
  }
 ],
 "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}