{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "72fffd8e-9cbd-4701-ad0e-8b22c882ddbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0663334a-73dc-4be0-8a65-1040e4b5acf0",
   "metadata": {},
   "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>interface</th>\n",
       "      <th>scenario</th>\n",
       "      <th>successful_orders</th>\n",
       "      <th>total_orders</th>\n",
       "      <th>conversion</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Новый интерфейс</td>\n",
       "      <td>Простой</td>\n",
       "      <td>90</td>\n",
       "      <td>100</td>\n",
       "      <td>0.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Новый интерфейс</td>\n",
       "      <td>Сложный</td>\n",
       "      <td>18</td>\n",
       "      <td>100</td>\n",
       "      <td>0.180000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Старый интерфейс</td>\n",
       "      <td>Простой</td>\n",
       "      <td>19</td>\n",
       "      <td>22</td>\n",
       "      <td>0.863636</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Старый интерфейс</td>\n",
       "      <td>Сложный</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>0.100000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          interface scenario  successful_orders  total_orders  conversion\n",
       "0   Новый интерфейс  Простой                 90           100    0.900000\n",
       "1   Новый интерфейс  Сложный                 18           100    0.180000\n",
       "2  Старый интерфейс  Простой                 19            22    0.863636\n",
       "3  Старый интерфейс  Сложный                  1            10    0.100000"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.DataFrame({\n",
    "    'interface': [\n",
    "        'Новый интерфейс',\n",
    "        'Новый интерфейс',\n",
    "        'Старый интерфейс',\n",
    "        'Старый интерфейс'\n",
    "    ],\n",
    "    'scenario': [\n",
    "        'Простой',\n",
    "        'Сложный',\n",
    "        'Простой',\n",
    "        'Сложный'\n",
    "    ],\n",
    "    'successful_orders': [90, 18, 19, 1],\n",
    "    'total_orders': [100, 100, 22, 10]\n",
    "})\n",
    "\n",
    "data['conversion'] = (\n",
    "    data['successful_orders'] / data['total_orders']\n",
    ")\n",
    "\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b1cfb563-dd85-4e47-b449-f0431b586b52",
   "metadata": {},
   "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>interface</th>\n",
       "      <th>Новый интерфейс</th>\n",
       "      <th>Старый интерфейс</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>scenario</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Простой</th>\n",
       "      <td>90.0</td>\n",
       "      <td>86.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Сложный</th>\n",
       "      <td>18.0</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "interface  Новый интерфейс  Старый интерфейс\n",
       "scenario                                    \n",
       "Простой               90.0              86.4\n",
       "Сложный               18.0              10.0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "segment_conversion = data.pivot(\n",
    "    index='scenario',\n",
    "    columns='interface',\n",
    "    values='conversion'\n",
    ")\n",
    "\n",
    "(segment_conversion * 100).round(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6841246c-acef-41ac-8170-ca51c8edbe17",
   "metadata": {},
   "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>interface</th>\n",
       "      <th>successful_orders</th>\n",
       "      <th>total_orders</th>\n",
       "      <th>conversion</th>\n",
       "      <th>conversion_percent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Новый интерфейс</td>\n",
       "      <td>108</td>\n",
       "      <td>200</td>\n",
       "      <td>0.540</td>\n",
       "      <td>54.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Старый интерфейс</td>\n",
       "      <td>20</td>\n",
       "      <td>32</td>\n",
       "      <td>0.625</td>\n",
       "      <td>62.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          interface  successful_orders  total_orders  conversion  \\\n",
       "0   Новый интерфейс                108           200       0.540   \n",
       "1  Старый интерфейс                 20            32       0.625   \n",
       "\n",
       "   conversion_percent  \n",
       "0                54.0  \n",
       "1                62.5  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "overall = data.groupby('interface', as_index=False).agg(\n",
    "    successful_orders=('successful_orders', 'sum'),\n",
    "    total_orders=('total_orders', 'sum')\n",
    ")\n",
    "\n",
    "overall['conversion'] = (\n",
    "    overall['successful_orders'] / overall['total_orders']\n",
    ")\n",
    "\n",
    "overall['conversion_percent'] = (\n",
    "    overall['conversion'] * 100\n",
    ").round(1)\n",
    "\n",
    "overall"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "93fa8c0f-2b45-48bf-bcf1-3d901a616ffb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_theme(style='whitegrid')\n",
    "\n",
    "plot_data = data.copy()\n",
    "plot_data['conversion_percent'] = plot_data['conversion'] * 100\n",
    "\n",
    "plt.figure(figsize=(10, 5))\n",
    "\n",
    "sns.barplot(\n",
    "    data=plot_data,\n",
    "    x='scenario',\n",
    "    y='conversion_percent',\n",
    "    hue='interface',\n",
    "    palette=['#4C78A8', '#E45756']\n",
    ")\n",
    "\n",
    "plt.title('Конверсия интерфейсов по сложности сценария')\n",
    "plt.xlabel('Сценарий')\n",
    "plt.ylabel('Конверсия, %')\n",
    "plt.legend(title='Интерфейс')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:base] *",
   "language": "python",
   "name": "conda-base-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}