{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualize correlation from heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import os\n",
    "import pandas as pd\n",
    "import matplotlib.pylab as plt\n",
    "\n",
    "from osdyn.utils.plot.heatmap import heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def corrplot(\n",
    "    data,\n",
    "    size_scale=500,\n",
    "    marker=\"s\",\n",
    "    size_range=[0, 1],\n",
    "    color_range=[-1, 1],\n",
    "):\n",
    "    \"\"\"\n",
    "    Dedicated to correlation plots but can be used for other purposes.\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    data : pandas.Dataframe\n",
    "        data containing the x axes, y axes, values.\n",
    "    size_scale : int, optional\n",
    "        multiplicator of data value. The default is 500.\n",
    "    marker : str, optional\n",
    "        \"s\" \"c\" \"t\"... The default is \"s\".\n",
    "    size_range : list of 2 int or float, optional\n",
    "        Values to anchor the sizes. The default is [0, 1].\n",
    "    color_range : list of 2 int or float, optional\n",
    "        Values to anchor the color. The default is [-1, 1].\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    Call heatmap\n",
    "\n",
    "    \"\"\"\n",
    "    corr = pd.melt(data.reset_index(), id_vars=\"index\").replace(np.nan, 0)\n",
    "    corr.columns = [\"x\", \"y\", \"value\"]\n",
    "    heatmap(\n",
    "        corr[\"x\"],\n",
    "        corr[\"y\"],\n",
    "        color=corr[\"value\"],\n",
    "        color_range=color_range,\n",
    "        palette=plt.get_cmap(\"seismic_r\", lut=256),\n",
    "        size=corr[\"value\"].abs(),\n",
    "        size_range=size_range,\n",
    "        marker=marker,\n",
    "        x_ticklabel=data.columns,\n",
    "        y_ticklabel=data.columns[::-1],\n",
    "        size_scale=size_scale,\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the Automobile dataset.\n",
    "# This gets a cleaned version of UCI dataset\n",
    "# found at http://archive.ics.uci.edu/ml/datasets/automobile\n",
    "#data = pd.read_csv(\"https://raw.githubusercontent.com/drazenz/heatmap/master/autos.clean.csv\")\n",
    "data = pd.read_csv(os.path.join(os.environ[\"INPUT_DATA_PATH\"],\"autos.clean.csv\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "nbsphinx-thumbnail"
    ]
   },
   "outputs": [],
   "source": [
    "plt.figure(figsize=(8, 8))\n",
    "corrplot(data.corr(), size_scale=300)"
   ]
  }
 ],
 "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"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}