diff --git a/dz_les_2.ipynb b/dz_les_2.ipynb
new file mode 100644
index 0000000..ad88fc3
--- /dev/null
+++ b/dz_les_2.ipynb
@@ -0,0 +1,968 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "baa39400",
+   "metadata": {},
+   "source": [
+    "## Тема “Вычисления с помощью Numpy”"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75a7d1fa",
+   "metadata": {},
+   "source": [
+    "###### Задание 1\n",
+    "Импортируйте библиотеку Numpy и дайте ей псевдоним np.\n",
+    "Создайте массив Numpy под названием a размером 5x2, то есть состоящий из 5 строк и 2 столбцов. Первый столбец должен содержать числа 1, 2, 3, 3, 1, а второй - числа 6, 8, 11, 10, 7. Будем считать, что каждый столбец - это признак, а строка - наблюдение. Затем найдите среднее значение по каждому признаку, используя метод mean массива Numpy. Результат запишите в массив mean_a, в нем должно быть 2 элемента.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 249,
+   "id": "b3f3cb0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 250,
+   "id": "b65b9485",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1,  6],\n",
+       "       [ 2,  8],\n",
+       "       [ 3, 11],\n",
+       "       [ 3, 10],\n",
+       "       [ 1,  7]])"
+      ]
+     },
+     "execution_count": 250,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a = np.array([[1, 2, 3, 3, 1],[ 6, 8, 11, 10, 7]]).T\n",
+    "a"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 251,
+   "id": "e1817a21",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([2. , 8.4])"
+      ]
+     },
+     "execution_count": 251,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_a = np.mean(a, axis=0)\n",
+    "mean_a"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "271e69f8",
+   "metadata": {},
+   "source": [
+    "###### Задание 2\n",
+    "Вычислите массив a_centered, отняв от значений массива “а” средние значения соответствующих признаков, содержащиеся в массиве mean_a. Вычисление должно производиться в одно действие. Получившийся массив должен иметь размер 5x2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 252,
+   "id": "1d09ae5f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[-1. , -2.4],\n",
+       "       [ 0. , -0.4],\n",
+       "       [ 1. ,  2.6],\n",
+       "       [ 1. ,  1.6],\n",
+       "       [-1. , -1.4]])"
+      ]
+     },
+     "execution_count": 252,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a_centered = np.vstack((a[:,0]-mean_a[0], a[:,1]-mean_a[1])).T\n",
+    "a_centered"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 253,
+   "id": "cf26e417",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5, 2)"
+      ]
+     },
+     "execution_count": 253,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a_centered.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0bcbea7c",
+   "metadata": {},
+   "source": [
+    "###### Задание 3\n",
+    "Найдите скалярное произведение столбцов массива a_centered. В результате должна получиться величина a_centered_sp. Затем поделите a_centered_sp на N-1, где N - число наблюдений."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 254,
+   "id": "8b12bc90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8.0"
+      ]
+     },
+     "execution_count": 254,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a_centered_sp = a_centered[:,0] @ a_centered[:,1]\n",
+    "a_centered_sp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 255,
+   "id": "953391c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2.0"
+      ]
+     },
+     "execution_count": 255,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a_centered_sp / (a.shape[0] - 1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "563f5e2a",
+   "metadata": {},
+   "source": [
+    "###### Задание 4**\n",
+    "Число, которое мы получили в конце задания 3 является ковариацией двух признаков, содержащихся в массиве “а”. В задании 4 мы делили сумму произведений центрированных признаков на N-1, а не на N, поэтому полученная нами величина является несмещенной оценкой ковариации."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90994e3c",
+   "metadata": {},
+   "source": [
+    "В этом задании проверьте получившееся число, вычислив ковариацию еще одним способом - с помощью функции np.cov. В качестве аргумента m функция np.cov должна принимать транспонированный массив “a”. В получившейся ковариационной матрице (массив Numpy размером 2x2) искомое значение ковариации будет равно элементу в строке с индексом 0 и столбце с индексом "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 256,
+   "id": "924e4167",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2.0"
+      ]
+     },
+     "execution_count": 256,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np.cov(a.T)[0][1]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "312dd388",
+   "metadata": {},
+   "source": [
+    "## Тема “Работа с данными в Pandas”"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9425e353",
+   "metadata": {},
+   "source": [
+    "###### Задание 1\n",
+    "Импортируйте библиотеку Pandas и дайте ей псевдоним pd. Создайте датафрейм authors со столбцами author_id и author_name, в которых соответственно содержатся данные: [1, 2, 3] и ['Тургенев', 'Чехов', 'Островский'].\n",
+    "Затем создайте датафрейм book cо столбцами author_id, book_title и price, в которых соответственно содержатся данные:  \n",
+    "[1, 1, 1, 2, 2, 3, 3],\n",
+    "['Отцы и дети', 'Рудин', 'Дворянское гнездо', 'Толстый и тонкий', 'Дама с собачкой', 'Гроза', 'Таланты и поклонники'],\n",
+    "[450, 300, 350, 500, 450, 370, 290]."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 257,
+   "id": "85849927",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 258,
+   "id": "8a7e4edf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "authors = pd.DataFrame({\n",
+    "    \"author_id\": [1, 2, 3],\n",
+    "    \"author_name\": ['Тургенев', 'Чехов', 'Островский']\n",
+    "})\n",
+    "book = pd.DataFrame({\n",
+    "    \"author_id\": [1, 1, 1, 2, 2, 3, 3],\n",
+    "    \"book_title\": ['Отцы и дети', 'Рудин', 'Дворянское гнездо', 'Толстый и тонкий', 'Дама с собачкой', 'Гроза', 'Таланты и поклонники'],\n",
+    "    \"price\": [450, 300, 350, 500, 450, 370, 290]\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "62a21149",
+   "metadata": {},
+   "source": [
+    "###### Задание 2\n",
+    "Получите датафрейм authors_price, соединив датафреймы authors и books по полю author_id."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 259,
+   "id": "8e657295",
+   "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>author_id</th>\n",
+       "      <th>author_name</th>\n",
+       "      <th>book_title</th>\n",
+       "      <th>price</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Отцы и дети</td>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Рудин</td>\n",
+       "      <td>300</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Дворянское гнездо</td>\n",
+       "      <td>350</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Толстый и тонкий</td>\n",
+       "      <td>500</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Дама с собачкой</td>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Островский</td>\n",
+       "      <td>Гроза</td>\n",
+       "      <td>370</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Островский</td>\n",
+       "      <td>Таланты и поклонники</td>\n",
+       "      <td>290</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   author_id author_name            book_title  price\n",
+       "0          1    Тургенев           Отцы и дети    450\n",
+       "1          1    Тургенев                 Рудин    300\n",
+       "2          1    Тургенев     Дворянское гнездо    350\n",
+       "3          2       Чехов      Толстый и тонкий    500\n",
+       "4          2       Чехов       Дама с собачкой    450\n",
+       "5          3  Островский                 Гроза    370\n",
+       "6          3  Островский  Таланты и поклонники    290"
+      ]
+     },
+     "execution_count": 259,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "authors_price = pd.merge(authors, book, on='author_id', how='inner')\n",
+    "authors_price"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b15da2c2",
+   "metadata": {},
+   "source": [
+    "###### Задание 3\n",
+    "Создайте датафрейм top5, в котором содержатся строки из authors_price с пятью самыми дорогими книгами."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 260,
+   "id": "031356ce",
+   "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>author_id</th>\n",
+       "      <th>author_name</th>\n",
+       "      <th>book_title</th>\n",
+       "      <th>price</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Дворянское гнездо</td>\n",
+       "      <td>350</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Островский</td>\n",
+       "      <td>Гроза</td>\n",
+       "      <td>370</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Отцы и дети</td>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Дама с собачкой</td>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Толстый и тонкий</td>\n",
+       "      <td>500</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   author_id author_name         book_title  price\n",
+       "2          1    Тургенев  Дворянское гнездо    350\n",
+       "5          3  Островский              Гроза    370\n",
+       "0          1    Тургенев        Отцы и дети    450\n",
+       "4          2       Чехов    Дама с собачкой    450\n",
+       "3          2       Чехов   Толстый и тонкий    500"
+      ]
+     },
+     "execution_count": 260,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "top5  = (authors_price.sort_values('price')).tail(5)\n",
+    "top5"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "665695cd",
+   "metadata": {},
+   "source": [
+    "###### Задание 4\n",
+    "Создайте датафрейм authors_stat на основе информации из authors_price. В датафрейме authors_stat должны быть четыре столбца:\n",
+    "author_name, min_price, max_price и mean_price,\n",
+    "в которых должны содержаться соответственно имя автора, минимальная, максимальная и средняя цена на книги этого автора"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 261,
+   "id": "91b9e649",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "authors_stat = authors_price.groupby(\"author_name\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 262,
+   "id": "fb2028b0",
+   "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>min_price</th>\n",
+       "      <th>max_price</th>\n",
+       "      <th>mean_price</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>author_name</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Островский</th>\n",
+       "      <td>370</td>\n",
+       "      <td>290</td>\n",
+       "      <td>330.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Тургенев</th>\n",
+       "      <td>450</td>\n",
+       "      <td>300</td>\n",
+       "      <td>366.666667</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Чехов</th>\n",
+       "      <td>500</td>\n",
+       "      <td>450</td>\n",
+       "      <td>475.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             min_price  max_price  mean_price\n",
+       "author_name                                  \n",
+       "Островский         370        290  330.000000\n",
+       "Тургенев           450        300  366.666667\n",
+       "Чехов              500        450  475.000000"
+      ]
+     },
+     "execution_count": 262,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "authors_stat_price = pd.concat([authors_stat.agg({\"price\": \"max\" }), authors_stat.agg({\"price\": \"min\" }), authors_stat.agg({\"price\": \"mean\" })], axis=1, ignore_index=True);\n",
+    "authors_stat_price.columns= [\"min_price\",\"max_price\",\"mean_price\"]\n",
+    "authors_stat_price"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e10a3e72",
+   "metadata": {},
+   "source": [
+    "###### Задание 5**\n",
+    "Создайте новый столбец в датафрейме authors_price под названием cover, в нем будут располагаться данные о том, какая обложка у данной книги - твердая или мягкая. В этот столбец поместите данные из следующего списка:\n",
+    "['твердая', 'мягкая', 'мягкая', 'твердая', 'твердая', 'мягкая', 'мягкая'].\n",
+    "Просмотрите документацию по функции pd.pivot_table с помощью вопросительного знака.\n",
+    "\n",
+    "Для каждого автора посчитайте суммарную стоимость книг в твердой и мягкой обложке. Используйте для этого функцию pd.pivot_table. При этом столбцы должны называться \"твердая\" и \"мягкая\", а индексами должны быть фамилии авторов. Пропущенные значения стоимостей заполните нулями, при необходимости загрузите библиотеку Numpy.\n",
+    "Назовите полученный датасет book_info и сохраните его в формат pickle под названием \"book_info.pkl\". Затем загрузите из этого файла датафрейм и назовите его book_info2. Удостоверьтесь, что датафреймы book_info и book_info2 идентичны."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 263,
+   "id": "d3ed614c",
+   "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>author_id</th>\n",
+       "      <th>author_name</th>\n",
+       "      <th>book_title</th>\n",
+       "      <th>price</th>\n",
+       "      <th>cover</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Отцы и дети</td>\n",
+       "      <td>450</td>\n",
+       "      <td>твердая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Рудин</td>\n",
+       "      <td>300</td>\n",
+       "      <td>мягкая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Тургенев</td>\n",
+       "      <td>Дворянское гнездо</td>\n",
+       "      <td>350</td>\n",
+       "      <td>мягкая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Толстый и тонкий</td>\n",
+       "      <td>500</td>\n",
+       "      <td>твердая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Чехов</td>\n",
+       "      <td>Дама с собачкой</td>\n",
+       "      <td>450</td>\n",
+       "      <td>твердая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Островский</td>\n",
+       "      <td>Гроза</td>\n",
+       "      <td>370</td>\n",
+       "      <td>мягкая</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Островский</td>\n",
+       "      <td>Таланты и поклонники</td>\n",
+       "      <td>290</td>\n",
+       "      <td>мягкая</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   author_id author_name            book_title  price    cover\n",
+       "0          1    Тургенев           Отцы и дети    450  твердая\n",
+       "1          1    Тургенев                 Рудин    300   мягкая\n",
+       "2          1    Тургенев     Дворянское гнездо    350   мягкая\n",
+       "3          2       Чехов      Толстый и тонкий    500  твердая\n",
+       "4          2       Чехов       Дама с собачкой    450  твердая\n",
+       "5          3  Островский                 Гроза    370   мягкая\n",
+       "6          3  Островский  Таланты и поклонники    290   мягкая"
+      ]
+     },
+     "execution_count": 263,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "authors_price[\"cover\"] = ['твердая', 'мягкая', 'мягкая', 'твердая', 'твердая', 'мягкая', 'мягкая']\n",
+    "authors_price"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 264,
+   "id": "18a7b7de",
+   "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></th>\n",
+       "      <th>price</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>author_name</th>\n",
+       "      <th>cover</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Островский</th>\n",
+       "      <th>мягкая</th>\n",
+       "      <td>660</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"2\" valign=\"top\">Тургенев</th>\n",
+       "      <th>мягкая</th>\n",
+       "      <td>650</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>твердая</th>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Чехов</th>\n",
+       "      <th>твердая</th>\n",
+       "      <td>950</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     price\n",
+       "author_name cover         \n",
+       "Островский  мягкая     660\n",
+       "Тургенев    мягкая     650\n",
+       "            твердая    450\n",
+       "Чехов       твердая    950"
+      ]
+     },
+     "execution_count": 264,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "book_info = pd.pivot_table(authors_price, index = [\"author_name\",\"cover\"],  values=[\"price\"], aggfunc=np.sum, fill_value=0)\n",
+    "book_info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 273,
+   "id": "b414ad8f",
+   "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></th>\n",
+       "      <th>price</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>author_name</th>\n",
+       "      <th>cover</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Островский</th>\n",
+       "      <th>мягкая</th>\n",
+       "      <td>660</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"2\" valign=\"top\">Тургенев</th>\n",
+       "      <th>мягкая</th>\n",
+       "      <td>650</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>твердая</th>\n",
+       "      <td>450</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Чехов</th>\n",
+       "      <th>твердая</th>\n",
+       "      <td>950</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     price\n",
+       "author_name cover         \n",
+       "Островский  мягкая     660\n",
+       "Тургенев    мягкая     650\n",
+       "            твердая    450\n",
+       "Чехов       твердая    950"
+      ]
+     },
+     "execution_count": 273,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "book_info.to_pickle(\"book_info.pkl\")\n",
+    "book_info2 = pd.read_pickle(\"book_info.pkl\")\n",
+    "book_info2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86cff9fd",
+   "metadata": {},
+   "source": [
+    "Найдем различие"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 272,
+   "id": "ec9838fe",
+   "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></th>\n",
+       "      <th>price</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>author_name</th>\n",
+       "      <th>cover</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [price]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 272,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "book_info2[ ~book_info2.isin(book_info)].dropna()"
+   ]
+  }
+ ],
+ "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": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}