{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b0a9c779-31d4-4589-9f8f-083b589d4d56",
   "metadata": {
    "tags": []
   },
   "source": [
    "## Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "fddba659-9cec-451e-a7fd-2052da65c77d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting pydotplus\n",
      "  Downloading pydotplus-2.0.2.tar.gz (278 kB)\n",
      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25hCollecting graphviz\n",
      "  Downloading graphviz-0.21-py3-none-any.whl.metadata (12 kB)\n",
      "Requirement already satisfied: seaborn in /opt/conda/lib/python3.11/site-packages (0.13.2)\n",
      "Requirement already satisfied: pyparsing>=2.0.1 in /opt/conda/lib/python3.11/site-packages (from pydotplus) (3.2.3)\n",
      "Requirement already satisfied: numpy!=1.24.0,>=1.20 in /opt/conda/lib/python3.11/site-packages (from seaborn) (1.24.4)\n",
      "Requirement already satisfied: pandas>=1.2 in /opt/conda/lib/python3.11/site-packages (from seaborn) (2.1.4)\n",
      "Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in /opt/conda/lib/python3.11/site-packages (from seaborn) (3.8.4)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.3.1)\n",
      "Requirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (4.57.0)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.4.7)\n",
      "Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (24.2)\n",
      "Requirement already satisfied: pillow>=8 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (11.1.0)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.11/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.11/site-packages (from pandas>=1.2->seaborn) (2025.2)\n",
      "Requirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.11/site-packages (from pandas>=1.2->seaborn) (2025.2)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.11/site-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3.4->seaborn) (1.17.0)\n",
      "Downloading graphviz-0.21-py3-none-any.whl (47 kB)\n",
      "Building wheels for collected packages: pydotplus\n",
      "  Building wheel for pydotplus (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for pydotplus: filename=pydotplus-2.0.2-py3-none-any.whl size=24635 sha256=a224ec7847f67379faacc9423010758780f43906b518f0c1aff05cb5770092c5\n",
      "  Stored in directory: /home/krista.klinger-hpe.com/.cache/pip/wheels/bd/ce/e8/ff9d9c699514922f57caa22fbd55b0a32761114b4c4acc9e03\n",
      "Successfully built pydotplus\n",
      "Installing collected packages: pydotplus, graphviz\n",
      "Successfully installed graphviz-0.21 pydotplus-2.0.2\n"
     ]
    }
   ],
   "source": [
    "#!pip3 install --proxy <PROXY> pydotplus graphviz seaborn\n",
    "!pip3 install pydotplus graphviz seaborn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b518aac5-850a-479e-a0b2-427194384aa3",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Key backend: 'inline' is not a valid value for backend; supported values are ['GTK3Agg', 'GTK3Cairo', 'GTK4Agg', 'GTK4Cairo', 'MacOSX', 'nbAgg', 'QtAgg', 'QtCairo', 'Qt5Agg', 'Qt5Cairo', 'TkAgg', 'TkCairo', 'WebAgg', 'WX', 'WXAgg', 'WXCairo', 'agg', 'cairo', 'pdf', 'pgf', 'ps', 'svg', 'template']",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[2], line 54\u001b[0m\n\u001b[1;32m     50\u001b[0m pd\u001b[38;5;241m.\u001b[39mplotting\u001b[38;5;241m.\u001b[39mregister_matplotlib_converters()\n\u001b[1;32m     52\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mrandom\u001b[39;00m\n\u001b[0;32m---> 54\u001b[0m \u001b[43mget_ipython\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun_line_magic\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mmatplotlib\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43minline\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     56\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mwarnings\u001b[39;00m\n\u001b[1;32m     57\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/IPython/core/interactiveshell.py:2482\u001b[0m, in \u001b[0;36mInteractiveShell.run_line_magic\u001b[0;34m(self, magic_name, line, _stack_depth)\u001b[0m\n\u001b[1;32m   2480\u001b[0m     kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlocal_ns\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_local_scope(stack_depth)\n\u001b[1;32m   2481\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuiltin_trap:\n\u001b[0;32m-> 2482\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2484\u001b[0m \u001b[38;5;66;03m# The code below prevents the output from being displayed\u001b[39;00m\n\u001b[1;32m   2485\u001b[0m \u001b[38;5;66;03m# when using magics with decorator @output_can_be_silenced\u001b[39;00m\n\u001b[1;32m   2486\u001b[0m \u001b[38;5;66;03m# when the last Python token in the expression is a ';'.\u001b[39;00m\n\u001b[1;32m   2487\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(fn, magic\u001b[38;5;241m.\u001b[39mMAGIC_OUTPUT_CAN_BE_SILENCED, \u001b[38;5;28;01mFalse\u001b[39;00m):\n",
      "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/IPython/core/magics/pylab.py:103\u001b[0m, in \u001b[0;36mPylabMagics.matplotlib\u001b[0;34m(self, line)\u001b[0m\n\u001b[1;32m     98\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\n\u001b[1;32m     99\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAvailable matplotlib backends: \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    100\u001b[0m         \u001b[38;5;241m%\u001b[39m _list_matplotlib_backends_and_gui_loops()\n\u001b[1;32m    101\u001b[0m     )\n\u001b[1;32m    102\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 103\u001b[0m     gui, backend \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshell\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43menable_matplotlib\u001b[49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgui\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    104\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_show_matplotlib_backend(args\u001b[38;5;241m.\u001b[39mgui, backend)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/IPython/core/interactiveshell.py:3679\u001b[0m, in \u001b[0;36mInteractiveShell.enable_matplotlib\u001b[0;34m(self, gui)\u001b[0m\n\u001b[1;32m   3675\u001b[0m         \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mWarning: Cannot change to a different GUI toolkit: \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m   3676\u001b[0m                 \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m Using \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m instead.\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m%\u001b[39m (gui, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpylab_gui_select))\n\u001b[1;32m   3677\u001b[0m         gui, backend \u001b[38;5;241m=\u001b[39m pt\u001b[38;5;241m.\u001b[39mfind_gui_and_backend(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpylab_gui_select)\n\u001b[0;32m-> 3679\u001b[0m \u001b[43mpt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mactivate_matplotlib\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbackend\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3681\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mmatplotlib_inline\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mbackend_inline\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m configure_inline_support\n\u001b[1;32m   3683\u001b[0m configure_inline_support(\u001b[38;5;28mself\u001b[39m, backend)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/IPython/core/pylabtools.py:403\u001b[0m, in \u001b[0;36mactivate_matplotlib\u001b[0;34m(backend)\u001b[0m\n\u001b[1;32m    398\u001b[0m matplotlib\u001b[38;5;241m.\u001b[39minteractive(\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m    400\u001b[0m \u001b[38;5;66;03m# Matplotlib had a bug where even switch_backend could not force\u001b[39;00m\n\u001b[1;32m    401\u001b[0m \u001b[38;5;66;03m# the rcParam to update. This needs to be set *before* the module\u001b[39;00m\n\u001b[1;32m    402\u001b[0m \u001b[38;5;66;03m# magic of switch_backend().\u001b[39;00m\n\u001b[0;32m--> 403\u001b[0m \u001b[43mmatplotlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrcParams\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mbackend\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m \u001b[38;5;241m=\u001b[39m backend\n\u001b[1;32m    405\u001b[0m \u001b[38;5;66;03m# Due to circular imports, pyplot may be only partially initialised\u001b[39;00m\n\u001b[1;32m    406\u001b[0m \u001b[38;5;66;03m# when this function runs.\u001b[39;00m\n\u001b[1;32m    407\u001b[0m \u001b[38;5;66;03m# So avoid needing matplotlib attribute-lookup to access pyplot.\u001b[39;00m\n\u001b[1;32m    408\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m pyplot \u001b[38;5;28;01mas\u001b[39;00m plt\n",
      "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/matplotlib/__init__.py:734\u001b[0m, in \u001b[0;36mRcParams.__setitem__\u001b[0;34m(self, key, val)\u001b[0m\n\u001b[1;32m    732\u001b[0m         cval \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvalidate[key](val)\n\u001b[1;32m    733\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m ve:\n\u001b[0;32m--> 734\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mKey \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mkey\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mve\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    735\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_set(key, cval)\n\u001b[1;32m    736\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
      "\u001b[0;31mValueError\u001b[0m: Key backend: 'inline' is not a valid value for backend; supported values are ['GTK3Agg', 'GTK3Cairo', 'GTK4Agg', 'GTK4Cairo', 'MacOSX', 'nbAgg', 'QtAgg', 'QtCairo', 'Qt5Agg', 'Qt5Cairo', 'TkAgg', 'TkCairo', 'WebAgg', 'WX', 'WXAgg', 'WXCairo', 'agg', 'cairo', 'pdf', 'pgf', 'ps', 'svg', 'template']"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from urllib.parse import urlparse\n",
    "\n",
    "from prettytable import PrettyTable\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import statsmodels.api as sm\n",
    "import json, datetime\n",
    "from datetime import datetime, timedelta,date\n",
    "from __future__ import division\n",
    "from sklearn.cluster import KMeans\n",
    "#import mlflow\n",
    "#import mlflow.sklearn\n",
    "#from mlflow import log_metric, log_param, log_artifact\n",
    "#model\n",
    "from sklearn.model_selection import KFold, cross_val_score, train_test_split, RandomizedSearchCV\n",
    "#metrics\n",
    "from sklearn.metrics import mean_squared_error, mean_absolute_error, mean_squared_log_error, classification_report,confusion_matrix\n",
    "#models\n",
    "from sklearn.ensemble import GradientBoostingRegressor\n",
    "from sklearn.ensemble import BaggingRegressor\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "\n",
    "from sklearn.linear_model import Lasso, ElasticNet, Ridge, SGDRegressor\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "from sklearn.svm import SVR, NuSVR, SVC\n",
    "from sklearn.multioutput import MultiOutputClassifier\n",
    "from sklearn.inspection import permutation_importance\n",
    "from mlflow.models.signature import infer_signature\n",
    "from sklearn import tree\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "\n",
    "import xgboost as xgb\n",
    "\n",
    "from pydotplus import graph_from_dot_data\n",
    "import graphviz\n",
    "from IPython.display import Image\n",
    "\n",
    "import itertools, os\n",
    "\n",
    "plt.style.use(\"fivethirtyeight\")\n",
    "pd.plotting.register_matplotlib_converters()\n",
    "\n",
    "import random\n",
    "\n",
    "%matplotlib inline\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "if os.path.exists(\"model_artifacts\"):\n",
    "    os.system(\"rm -rf model_artifacts\")\n",
    "os.mkdir(\"model_artifacts\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "132e7f98-4904-4fd7-a1d2-d91a0600540f",
   "metadata": {
    "tags": []
   },
   "source": [
    "## Load & Explore Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2253b65d-6e82-4227-a1be-069a03223042",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# load input data into pandas dataframe\n",
    "candy_data = pd.read_csv(\"candy.csv\")\n",
    "candy_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7ae94200-7056-4c86-b55c-786b2778fe5e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "print(candy_data.isnull().any())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c7cf24bd-e858-4900-81cb-232710d2f8d5",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#validate no missing values\n",
    "candy_data.info()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bce2f4fe-bdba-4b6e-aa31-d262c73a7f1d",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#validate unique values\n",
    "candy_data.apply(lambda x: len(x.unique()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7dff5fda-04fb-4cc2-9af7-1883b5f52f16",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# view statistical info\n",
    "candy_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5cdb1995-1fcd-452b-96f7-9269f9035ecb",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# use better names\n",
    "candy_data.rename(columns={\n",
    "    'competitorname': \"Candy Name\",\n",
    "    'chocolate': 'Chocolate',\n",
    "    'fruity': 'Fruity Flavor',\n",
    "    'caramel': 'Caramel',\n",
    "    'peanutyalmondy': 'Peanuts & Nuts',\n",
    "    'nougat': 'Nougat',\n",
    "    'crispedricewafer': 'Crispy',\n",
    "    'hard': 'Hard Candy',\n",
    "    'bar': 'Candy bar',\n",
    "    'pluribus': 'Multi-piece',\n",
    "    'sugarpercent': 'Sugar Percentage',\n",
    "    'pricepercent': 'Price Percentage',\n",
    "    'winpercent': 'Win Percentage'\n",
    "})\n",
    "\n",
    "candy_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3f7b88ee-bcf6-4f8f-9132-296f3432843c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "print(candy_data.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a6c719d-e255-4769-bd4b-a1bbc912db9f",
   "metadata": {},
   "source": [
    "## Load & Explore Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "503c1f02-8e34-44c9-af2f-f585c931e8bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Seaborn plot\n",
    "fig, ax = plt.subplots(figsize=(20,10))\n",
    "sns.pointplot(data=candy_data, x='winpercent', y='chocolate', hue= 'month', ax=ax)\n",
    "ax.set(title='Count of bikes during weekdays and weekends')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b7e7231c-ce62-4db5-80a8-b26d101c7197",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "categorical_data = candy_data[['chocolate','fruity','caramel','peanutyalmondy','nougat','crispedricewafer','hard','bar','pluribus']]\n",
    "continuous_data = candy_data[['sugarpercent','pricepercent','winpercent']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "26af47fd-0439-4965-ad41-3980db425be6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#check the distribution on the continuous feature\n",
    "\n",
    "sns.pairplot(data= continuous_data, diag_kind='kde')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8a9760e9-b061-4f29-bf92-32593414f945",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}