diff --git a/30_Deployment/30.6 Practic work/pipeline_learning.ipynb b/30_Deployment/30.6 Practic work/pipeline_learning.ipynb
new file mode 100644
index 0000000..d5dad8f
--- /dev/null
+++ b/30_Deployment/30.6 Practic work/pipeline_learning.ipynb	
@@ -0,0 +1,1061 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "45219139-b9ef-42ed-a2d6-54da92eeb1b5",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Пошаговое руководство по созданию простейшего pipeline из Sci-kit Learn"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7219263d-0d78-41db-a3fd-1b656e2f20c0",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### Большинство проектов по науке о данных требуют определенного уровня очистки и предварительной обработки данных, чтобы максимально использовать модели машинного обучения. Вот некоторые распространенные предварительные обработки или преобразования:\n",
+    "\n",
+    "а. Заполнение пропущенных значений\n",
+    "\n",
+    "б. Удаление выбросов\n",
+    "\n",
+    "в. Нормализация или стандартизация числовых признаков\n",
+    "\n",
+    "д. Кодирование категориальных признаков\n",
+    "\n",
+    "В научном наборе есть набор функций, поддерживающих такого рода преобразование, таких как StandardScaler, SimpleImputer и т. д., в пакете предварительной обработки.\n",
+    "\n",
+    "Типичный и упрощенный рабочий процесс науки о данных примерно выглядит так:\n",
+    "\n",
+    "-Получить данные для тренировки\n",
+    "\n",
+    "-Очистить/предварительно обработать/преобразовать данные\n",
+    "\n",
+    "-Обучить модель машинного обучения\n",
+    "\n",
+    "-Оценить и оптимизировать модель\n",
+    "\n",
+    "-Очистить/предварительно обработать/преобразовать новые данные\n",
+    "\n",
+    "-Дать модели новые данным, чтобы делать прогнозы.\n",
+    "\n",
+    "Вы можете заметить, что предварительная обработка данных должна выполняться как минимум дважды в рабочем процессе. Каким бы утомительным и трудоемким ни был этот шаг, было бы здорово, если бы мы могли автоматизировать этот процесс и применить его ко всем будущим новым наборам данных.\n",
+    "\n",
+    "С конвейером обучения scikit мы можем легко систематизировать процесс и, следовательно, сделать его максимально воспроизводимым. Далее я проведу вас через процесс использования конвейера обучения scikit, чтобы облегчить вашу жизнь."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "446d1565-8b4f-4955-a9b5-3158094dc018",
+   "metadata": {},
+   "source": [
+    "#### Чтение данных\n",
+    "Мы будем использовать данные «ежедневного проката велосипедов» из фантастического учебного материала Microsoft по машинному обучению ."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a700bcb1-7c92-4157-be8f-8fe50311aa6d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "instant         int64\n",
+       "dteday         object\n",
+       "season          int64\n",
+       "yr              int64\n",
+       "mnth            int64\n",
+       "holiday         int64\n",
+       "weekday         int64\n",
+       "workingday      int64\n",
+       "weathersit      int64\n",
+       "temp          float64\n",
+       "atemp         float64\n",
+       "hum           float64\n",
+       "windspeed     float64\n",
+       "rentals         int64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "data = pd.read_csv('https://raw.githubusercontent.com/MicrosoftDocs/ml-basics/master/data/daily-bike-share.csv')\n",
+    "data.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fd52b4e1-9d03-416d-989a-ee6a978c04c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "instant       0\n",
+       "dteday        0\n",
+       "season        0\n",
+       "yr            0\n",
+       "mnth          0\n",
+       "holiday       0\n",
+       "weekday       0\n",
+       "workingday    0\n",
+       "weathersit    0\n",
+       "temp          0\n",
+       "atemp         0\n",
+       "hum           0\n",
+       "windspeed     0\n",
+       "rentals       0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba5c3bef-ae5a-4e40-b67b-e24bd2ae06f4",
+   "metadata": {},
+   "source": [
+    " К счастью, в этом наборе данных нет пропущенных значений. Хотя кажется, что все функции являются числовыми, на самом деле есть некоторые категориальные функции, которые нам необходимо идентифицировать."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a8492763-ac30-4426-b10c-ec6e644f1b0b",
+   "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>instant</th>\n",
+       "      <th>dteday</th>\n",
+       "      <th>season</th>\n",
+       "      <th>yr</th>\n",
+       "      <th>mnth</th>\n",
+       "      <th>holiday</th>\n",
+       "      <th>weekday</th>\n",
+       "      <th>workingday</th>\n",
+       "      <th>weathersit</th>\n",
+       "      <th>temp</th>\n",
+       "      <th>atemp</th>\n",
+       "      <th>hum</th>\n",
+       "      <th>windspeed</th>\n",
+       "      <th>rentals</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1/1/2011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.344167</td>\n",
+       "      <td>0.363625</td>\n",
+       "      <td>0.805833</td>\n",
+       "      <td>0.160446</td>\n",
+       "      <td>331</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>1/2/2011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.363478</td>\n",
+       "      <td>0.353739</td>\n",
+       "      <td>0.696087</td>\n",
+       "      <td>0.248539</td>\n",
+       "      <td>131</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>1/3/2011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.196364</td>\n",
+       "      <td>0.189405</td>\n",
+       "      <td>0.437273</td>\n",
+       "      <td>0.248309</td>\n",
+       "      <td>120</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>1/4/2011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.200000</td>\n",
+       "      <td>0.212122</td>\n",
+       "      <td>0.590435</td>\n",
+       "      <td>0.160296</td>\n",
+       "      <td>108</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>1/5/2011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.226957</td>\n",
+       "      <td>0.229270</td>\n",
+       "      <td>0.436957</td>\n",
+       "      <td>0.186900</td>\n",
+       "      <td>82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>726</th>\n",
+       "      <td>727</td>\n",
+       "      <td>12/27/2012</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.254167</td>\n",
+       "      <td>0.226642</td>\n",
+       "      <td>0.652917</td>\n",
+       "      <td>0.350133</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>727</th>\n",
+       "      <td>728</td>\n",
+       "      <td>12/28/2012</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.253333</td>\n",
+       "      <td>0.255046</td>\n",
+       "      <td>0.590000</td>\n",
+       "      <td>0.155471</td>\n",
+       "      <td>644</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>728</th>\n",
+       "      <td>729</td>\n",
+       "      <td>12/29/2012</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.253333</td>\n",
+       "      <td>0.242400</td>\n",
+       "      <td>0.752917</td>\n",
+       "      <td>0.124383</td>\n",
+       "      <td>159</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>729</th>\n",
+       "      <td>730</td>\n",
+       "      <td>12/30/2012</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.255833</td>\n",
+       "      <td>0.231700</td>\n",
+       "      <td>0.483333</td>\n",
+       "      <td>0.350754</td>\n",
+       "      <td>364</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>730</th>\n",
+       "      <td>731</td>\n",
+       "      <td>12/31/2012</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.215833</td>\n",
+       "      <td>0.223487</td>\n",
+       "      <td>0.577500</td>\n",
+       "      <td>0.154846</td>\n",
+       "      <td>439</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>731 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     instant      dteday  season  yr  mnth  holiday  weekday  workingday  \\\n",
+       "0          1    1/1/2011       1   0     1        0        6           0   \n",
+       "1          2    1/2/2011       1   0     1        0        0           0   \n",
+       "2          3    1/3/2011       1   0     1        0        1           1   \n",
+       "3          4    1/4/2011       1   0     1        0        2           1   \n",
+       "4          5    1/5/2011       1   0     1        0        3           1   \n",
+       "..       ...         ...     ...  ..   ...      ...      ...         ...   \n",
+       "726      727  12/27/2012       1   1    12        0        4           1   \n",
+       "727      728  12/28/2012       1   1    12        0        5           1   \n",
+       "728      729  12/29/2012       1   1    12        0        6           0   \n",
+       "729      730  12/30/2012       1   1    12        0        0           0   \n",
+       "730      731  12/31/2012       1   1    12        0        1           1   \n",
+       "\n",
+       "     weathersit      temp     atemp       hum  windspeed  rentals  \n",
+       "0             2  0.344167  0.363625  0.805833   0.160446      331  \n",
+       "1             2  0.363478  0.353739  0.696087   0.248539      131  \n",
+       "2             1  0.196364  0.189405  0.437273   0.248309      120  \n",
+       "3             1  0.200000  0.212122  0.590435   0.160296      108  \n",
+       "4             1  0.226957  0.229270  0.436957   0.186900       82  \n",
+       "..          ...       ...       ...       ...        ...      ...  \n",
+       "726           2  0.254167  0.226642  0.652917   0.350133      247  \n",
+       "727           2  0.253333  0.255046  0.590000   0.155471      644  \n",
+       "728           2  0.253333  0.242400  0.752917   0.124383      159  \n",
+       "729           1  0.255833  0.231700  0.483333   0.350754      364  \n",
+       "730           2  0.215833  0.223487  0.577500   0.154846      439  \n",
+       "\n",
+       "[731 rows x 14 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "610e2d94-6882-43a0-9739-841b5258591a",
+   "metadata": {},
+   "source": [
+    "Давайте сначала отфильтруем некоторые явно бесполезные функции."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "96c106b3-cbca-4c33-97e7-96190889fa09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = data[['season'\n",
+    "             , 'mnth'\n",
+    "             , 'holiday'\n",
+    "             , 'weekday'\n",
+    "             , 'workingday'\n",
+    "             , 'weathersit'\n",
+    "             , 'temp'\n",
+    "             , 'atemp'\n",
+    "             , 'hum'\n",
+    "             , 'windspeed'\n",
+    "             , 'rentals']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "137f5661-b2f3-4c07-9f34-ad9709c1fbf0",
+   "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>season</th>\n",
+       "      <th>mnth</th>\n",
+       "      <th>holiday</th>\n",
+       "      <th>weekday</th>\n",
+       "      <th>workingday</th>\n",
+       "      <th>weathersit</th>\n",
+       "      <th>temp</th>\n",
+       "      <th>atemp</th>\n",
+       "      <th>hum</th>\n",
+       "      <th>windspeed</th>\n",
+       "      <th>rentals</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.344167</td>\n",
+       "      <td>0.363625</td>\n",
+       "      <td>0.805833</td>\n",
+       "      <td>0.160446</td>\n",
+       "      <td>331</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.363478</td>\n",
+       "      <td>0.353739</td>\n",
+       "      <td>0.696087</td>\n",
+       "      <td>0.248539</td>\n",
+       "      <td>131</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.196364</td>\n",
+       "      <td>0.189405</td>\n",
+       "      <td>0.437273</td>\n",
+       "      <td>0.248309</td>\n",
+       "      <td>120</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.200000</td>\n",
+       "      <td>0.212122</td>\n",
+       "      <td>0.590435</td>\n",
+       "      <td>0.160296</td>\n",
+       "      <td>108</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.226957</td>\n",
+       "      <td>0.229270</td>\n",
+       "      <td>0.436957</td>\n",
+       "      <td>0.186900</td>\n",
+       "      <td>82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>726</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.254167</td>\n",
+       "      <td>0.226642</td>\n",
+       "      <td>0.652917</td>\n",
+       "      <td>0.350133</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>727</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.253333</td>\n",
+       "      <td>0.255046</td>\n",
+       "      <td>0.590000</td>\n",
+       "      <td>0.155471</td>\n",
+       "      <td>644</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>728</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.253333</td>\n",
+       "      <td>0.242400</td>\n",
+       "      <td>0.752917</td>\n",
+       "      <td>0.124383</td>\n",
+       "      <td>159</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>729</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.255833</td>\n",
+       "      <td>0.231700</td>\n",
+       "      <td>0.483333</td>\n",
+       "      <td>0.350754</td>\n",
+       "      <td>364</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>730</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.215833</td>\n",
+       "      <td>0.223487</td>\n",
+       "      <td>0.577500</td>\n",
+       "      <td>0.154846</td>\n",
+       "      <td>439</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>731 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     season  mnth  holiday  weekday  workingday  weathersit      temp  \\\n",
+       "0         1     1        0        6           0           2  0.344167   \n",
+       "1         1     1        0        0           0           2  0.363478   \n",
+       "2         1     1        0        1           1           1  0.196364   \n",
+       "3         1     1        0        2           1           1  0.200000   \n",
+       "4         1     1        0        3           1           1  0.226957   \n",
+       "..      ...   ...      ...      ...         ...         ...       ...   \n",
+       "726       1    12        0        4           1           2  0.254167   \n",
+       "727       1    12        0        5           1           2  0.253333   \n",
+       "728       1    12        0        6           0           2  0.253333   \n",
+       "729       1    12        0        0           0           1  0.255833   \n",
+       "730       1    12        0        1           1           2  0.215833   \n",
+       "\n",
+       "        atemp       hum  windspeed  rentals  \n",
+       "0    0.363625  0.805833   0.160446      331  \n",
+       "1    0.353739  0.696087   0.248539      131  \n",
+       "2    0.189405  0.437273   0.248309      120  \n",
+       "3    0.212122  0.590435   0.160296      108  \n",
+       "4    0.229270  0.436957   0.186900       82  \n",
+       "..        ...       ...        ...      ...  \n",
+       "726  0.226642  0.652917   0.350133      247  \n",
+       "727  0.255046  0.590000   0.155471      644  \n",
+       "728  0.242400  0.752917   0.124383      159  \n",
+       "729  0.231700  0.483333   0.350754      364  \n",
+       "730  0.223487  0.577500   0.154846      439  \n",
+       "\n",
+       "[731 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "28c56084-4cae-49ec-a410-627b3917fb8d",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### Разделим данные\n",
+    "Перед созданием конвейера нам нужно сначала разделить данные на обучающий набор и тестовый набор."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "912fe504-9905-4a2d-a248-60ba6dbb09c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "X = data.drop('rentals',axis=1)\n",
+    "y = data['rentals']\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb532c1d-a1a2-417e-b4b1-7f6de586ec36",
+   "metadata": {},
+   "source": [
+    "#### Создадим конвейер (pipeline)\n",
+    "Основным параметром пайплайна, над которым мы будем работать, являются « шаги ». Легче просто взглянуть на то, как должен выглядеть конвейер:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c5199aec-a6f8-40b5-ad14-39e19b619c3d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Pipeline(steps=[('name_of_preprocessor', препроцессор), \n",
+    "                #('name_of_ml_model', ml_model())])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df6d7c3c-4594-4b16-a9ee-397d03b7a672",
+   "metadata": {},
+   "source": [
+    "Импортируем нужные библиотеки"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "89df662a-51a2-4747-8936-32636adb475b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import StandardScaler, OrdinalEncoder\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "from sklearn.compose import ColumnTransformer\n",
+    "from sklearn.pipeline import Pipeline"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c41046dd-77cc-460c-a355-fdd7a2428a17",
+   "metadata": {},
+   "source": [
+    "Во-первых, нам нужно определить преобразователи как для числовых, так и для категориальных признаков. Шаг преобразования представлен кортежем. В этом кортеже вы сначала определяете имя преобразователя, а затем функцию, которую хотите применить. Порядок кортежа будет порядком, в котором конвейер применяет преобразования. Здесь мы сначала имеем дело с пропущенными значениями, затем стандартизируем числовые признаки и кодируем категориальные признаки."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d10e4cae-c3f8-4a87-8e54-8fcb9b11c3b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "numeric_transformer = Pipeline(steps=[\n",
+    "       ('imputer', SimpleImputer(strategy='mean'))\n",
+    "      ,('scaler', StandardScaler())\n",
+    "])\n",
+    "categorical_transformer = Pipeline(steps=[\n",
+    "       ('imputer', SimpleImputer(strategy='constant'))\n",
+    "      ,('encoder', OrdinalEncoder())\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a399dbf7-a2a9-4516-b0e8-6d282b57cda2",
+   "metadata": {},
+   "source": [
+    "#### Preprocessor\n",
+    "Следующее, что нам нужно сделать, это указать, какие столбцы являются числовыми, а какие категориальными, чтобы мы могли соответствующим образом применить преобразователи. Мы применяем преобразователи к функциям с помощью ColumnTransformer. Применение преобразователей к функциям — это наш препроцессор. Подобно конвейеру, мы передаем список кортежей, который состоит из («имя», «трансформер», «функции») , параметру « трансформеры »."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ad374c35-cd2c-42dd-b23d-2996568d86d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "numeric_features = ['temp', 'atemp', 'hum', 'windspeed']\n",
+    "categorical_features = ['season', 'mnth', 'holiday', 'weekday', 'workingday', 'weathersit']\n",
+    "preprocessor = ColumnTransformer(\n",
+    "   transformers=[\n",
+    "    ('numeric', numeric_transformer, numeric_features)\n",
+    "   ,('categorical', categorical_transformer, categorical_features)\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2fed8f72-7bb2-468b-847f-aabbede77a8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Можно создать список числовых/категориальных функций на основе типа данных, например:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "9d067d0e-628b-4242-a63e-a2b415bb9093",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "numeric_features = data.select_dtypes(include=['int64', 'float64']).columns\n",
+    "categorical_features = data.select_dtypes(include=['object']).columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f7ad295d-d484-4e85-b0dd-cb6cf0e1ce2c",
+   "metadata": {},
+   "source": [
+    "Я лично не рекомендую это, потому что если у вас есть категориальные признаки, замаскированные под числовой тип данных, например, этот набор данных, вы не сможете их идентифицировать. Используйте этот метод только в том случае, если вы на 100 % уверены, что только числовые признаки являются числовыми типами данных."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d7f830a3-fbf1-4994-83a8-ca361ad51537",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index([], dtype='object')"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "categorical_features"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df9c6ba4-4650-43ae-82d9-450b3a03ca69",
+   "metadata": {},
+   "source": [
+    "#### Оценщик Estimator\n",
+    "\n",
+    "После сборки нашего препроцессора мы можем добавить оценщик, который представляет собой алгоритм машинного обучения, который вы хотели бы применить, чтобы завершить наш конвейер предварительной обработки и обучения. Поскольку в этом случае целевая переменная непрерывна, я применю здесь модель случайной лесной регрессии."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "49546964-931c-40df-983c-17c7b8e92a83",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "pipeline = Pipeline(steps = [\n",
+    "               ('preprocessor', preprocessor)\n",
+    "              ,('regressor',RandomForestRegressor())\n",
+    "           ])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bd418898-b174-4dbc-8177-519823364401",
+   "metadata": {},
+   "source": [
+    "Чтобы создать модель, аналогичную тому, что мы делали с алгоритмом машинного обучения, мы используем функцию конвейера fit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "01653c3e-5a46-48a2-8fc8-6c1a728f3b15",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pipeline(steps=[('preprocessor',\n",
+      "                 ColumnTransformer(transformers=[('numeric',\n",
+      "                                                  Pipeline(steps=[('imputer',\n",
+      "                                                                   SimpleImputer()),\n",
+      "                                                                  ('scaler',\n",
+      "                                                                   StandardScaler())]),\n",
+      "                                                  ['temp', 'atemp', 'hum',\n",
+      "                                                   'windspeed']),\n",
+      "                                                 ('categorical',\n",
+      "                                                  Pipeline(steps=[('imputer',\n",
+      "                                                                   SimpleImputer(strategy='constant')),\n",
+      "                                                                  ('encoder',\n",
+      "                                                                   OrdinalEncoder())]),\n",
+      "                                                  ['season', 'mnth', 'holiday',\n",
+      "                                                   'weekday', 'workingday',\n",
+      "                                                   'weathersit'])])),\n",
+      "                ('regressor', RandomForestRegressor())])\n"
+     ]
+    }
+   ],
+   "source": [
+    "rf_model = pipeline.fit(X_train, y_train)\n",
+    "print (rf_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90e3276a-4739-4253-8f72-ec23fb66fb6e",
+   "metadata": {},
+   "source": [
+    "Используем обычные методы для оценки модели."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "7355feec-d7c5-4b7b-b312-c5344f26ca3a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7683677302805014\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import r2_score\n",
+    "predictions = rf_model.predict(X_test)\n",
+    "print (r2_score(y_test, predictions))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48ab9d67-ecc4-47e5-bdf4-52a96aad3499",
+   "metadata": {},
+   "source": [
+    "#### Использование модели\n",
+    "Чтобы максимизировать воспроизводимость, мы хотели бы неоднократно использовать эту модель для наших новых входящих данных. Давайте сохраним модель, используя пакет joblib, чтобы сохранить ее"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "9b89c017-2a90-46e2-a6aa-bbf1f1daab9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['./rf_model.pkl']"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import joblib\n",
+    "joblib.dump(rf_model, './rf_model.pkl')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "957229e8-bb57-454d-8313-e0715bd6a5dc",
+   "metadata": {},
+   "source": [
+    "Теперь мы можем вызвать этот конвейер, который включает в себя все виды предварительной обработки данных, которые нам нужны, и модель обучения, когда нам это нужно."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "50b8cfb4-07f6-484f-a71b-855aecabf04e",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'new_data' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32mC:\\Users\\HPZ2~1\\AppData\\Local\\Temp/ipykernel_12436/1643577056.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mrf_model\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mjoblib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'./rf_model.pkl'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mnew_prediction\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrf_model\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnew_data\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m: name 'new_data' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "rf_model = joblib.load('PATH/TO/rf_model.pkl')\n",
+    "new_prediction = rf_model.predict(new_data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08a09549-7ff9-4109-af85-cc7e4a93c723",
+   "metadata": {},
+   "source": [
+    "#### Заключение\n",
+    "До знакомства с конвейером обучения scikit мне всегда приходилось переделывать всю предварительную обработку и преобразование данных всякий раз, когда я хотел применить одну и ту же модель к разным наборам данных. Это был действительно утомительный процесс. Я попытался написать функцию, выполняющую их все, но результат меня не очень удовлетворил и не избавил меня от большого количества работы.\n",
+    "\n",
+    "Конвейер обучения Scikit действительно делает мои рабочие процессы более плавными и гибкими. Например, вы можете легко сравнить производительность ряда алгоритмов, таких как:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74bef463-7e3d-4941-b588-2703c858aaa2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "regressors = [\n",
+    "    regressor_1()\n",
+    "   ,regressor_2()\n",
+    "   ,regressor_3()\n",
+    "   ....]\n",
+    "for regressor in regressors:\n",
+    "    pipeline = Pipeline(steps = [\n",
+    "               ('preprocessor', preprocessor)\n",
+    "              ,('regressor',regressor)\n",
+    "           ])\n",
+    "    model = pipeline.fit(X_train, y_train)\n",
+    "    predictions = model.predict(X_test)\n",
+    "    print (regressor)\n",
+    "    print (f('Model r2 score:{r2_score(predictions, y_test)}')"
+   ]
+  }
+ ],
+ "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}