{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#6204640087"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exam Instruction EE522 Fall 2022:\n",
    "    \n",
    "1. Answer all of the following questions. Each answer should be thorough, complete, and relevant. Points will be deducted for irrelevant details. Use the back of the pages if you need more room for your answer.\n",
    "\n",
    "2. The points are a clue about how much time you should spend on each question. Plan your time accordingly.\n",
    "\n",
    "3. There are 3 questions. The total score is 100 points accounted for 25 percent of the total scores.\n",
    "\n",
    "4. Exam Date and time: October 1, 2022 from 1-4 pm. \n",
    "\n",
    "\n",
    "5. You have to submit (1) the Jupiter Notebook code (.ipynp) with the name: your student id.ipynp i.e 6504610069.ipynp \n",
    "\n",
    "6. You have to submit your code on BE-moodle.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1 [50 points]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Set Information:\n",
    "\n",
    "Bike sharing systems are new generation of traditional bike rentals where whole process from membership, rental and return back has become automatic. Through these systems, user is able to easily rent a bike from a particular position and return back at another position. Currently, there are about over 500 bike-sharing programs around the world which is composed of over 500 thousands bicycles. Today, there exists great interest in these systems due to their important role in traffic, environmental and health issues. \n",
    "\n",
    "Apart from interesting real world applications of bike sharing systems, the characteristics of data being generated by these systems make them attractive for the research. Opposed to other transport services such as bus or subway, the duration of travel, departure and arrival position is explicitly recorded in these systems. This feature turns bike sharing system into a virtual sensor network that can be used for sensing mobility in the city. Hence, it is expected that most of important events in the city could be detected via monitoring these data."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dataset characteristics"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\t\n",
    "=========================================\n",
    "Dataset characteristics\n",
    "======================\t\n",
    "hour.csv has the following fields:\n",
    "\t\n",
    "\t- instant: record index\n",
    "\t- dteday : date\n",
    "\t- season : season (1:springer, 2:summer, 3:fall, 4:winter)\n",
    "\t- yr : year (0: 2011, 1:2012)\n",
    "\t- mnth : month ( 1 to 12)\n",
    "\t- hr : hour (0 to 23)\n",
    "\t- holiday : weather day is holiday or not (extracted from http://dchr.dc.gov/page/holiday-schedule)\n",
    "\t- weekday : day of the week\n",
    "\t- workingday : if day is neither weekend nor holiday is 1, otherwise is 0.\n",
    "\t+ weathersit : \n",
    "\t\t- 1: Clear, Few clouds, Partly cloudy, Partly cloudy\n",
    "\t\t- 2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist\n",
    "\t\t- 3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds\n",
    "\t\t- 4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog\n",
    "\t- temp : Normalized temperature in Celsius. The values are divided to 41 (max)\n",
    "\t- atemp: Normalized feeling temperature in Celsius. The values are divided to 50 (max)\n",
    "\t- hum: Normalized humidity. The values are divided to 100 (max)\n",
    "\t- windspeed: Normalized wind speed. The values are divided to 67 (max)\n",
    "\t- casual: count of casual users\n",
    "\t- registered: count of registered users\n",
    "\t- cnt: count of total rental bikes including both casual and registered"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1.1 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot the scatter plots to visualize the relationship between temp and target values (cnt). Then, plot the heatmap to represent the correlation matrix between features and target values.\n",
    "\n",
    "Also, calculate the median of cout of total bikes (cnt) separated by weathersit, season ,and holiday. Is there any interesting thing you found? Explain carefully.\n",
    "\n",
    "\n",
    "[20 Points]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import the necessary libraries and the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 17379 entries, 0 to 17378\n",
      "Data columns (total 17 columns):\n",
      " #   Column      Non-Null Count  Dtype  \n",
      "---  ------      --------------  -----  \n",
      " 0   instant     17379 non-null  int64  \n",
      " 1   dteday      17379 non-null  object \n",
      " 2   season      17379 non-null  int64  \n",
      " 3   yr          17379 non-null  int64  \n",
      " 4   mnth        17379 non-null  int64  \n",
      " 5   hr          17379 non-null  int64  \n",
      " 6   holiday     17379 non-null  int64  \n",
      " 7   weekday     17379 non-null  int64  \n",
      " 8   workingday  17379 non-null  int64  \n",
      " 9   weathersit  17379 non-null  int64  \n",
      " 10  temp        17379 non-null  float64\n",
      " 11  atemp       17379 non-null  float64\n",
      " 12  hum         17379 non-null  float64\n",
      " 13  windspeed   17379 non-null  float64\n",
      " 14  casual      17379 non-null  int64  \n",
      " 15  registered  17379 non-null  int64  \n",
      " 16  cnt         17379 non-null  int64  \n",
      "dtypes: float64(4), int64(12), object(1)\n",
      "memory usage: 2.3+ MB\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline\n",
    "# activate plot theme\n",
    "import qeds\n",
    "\n",
    "qeds.themes.mpl_style();\n",
    "plotly_template = qeds.themes.plotly_template()\n",
    "colors = qeds.themes.COLOR_CYCLE\n",
    "\n",
    "# We will import all these here to ensure that they are loaded, but\n",
    "# will usually re-import close to where they are used to make clear\n",
    "# where the functions come from\n",
    "from sklearn import (linear_model, metrics, model_selection)\n",
    "\n",
    "df = pd.read_csv(\"hour.csv\")\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>hr</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>casual</th>\n",
       "      <th>registered</th>\n",
       "      <th>cnt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.81</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8</td>\n",
       "      <td>32</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5</td>\n",
       "      <td>27</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   instant      dteday  season  yr  mnth  hr  holiday  weekday  workingday  \\\n",
       "0        1  2011-01-01       1   0     1   0        0        6           0   \n",
       "1        2  2011-01-01       1   0     1   1        0        6           0   \n",
       "2        3  2011-01-01       1   0     1   2        0        6           0   \n",
       "3        4  2011-01-01       1   0     1   3        0        6           0   \n",
       "4        5  2011-01-01       1   0     1   4        0        6           0   \n",
       "\n",
       "   weathersit  temp   atemp   hum  windspeed  casual  registered  cnt  \n",
       "0           1  0.24  0.2879  0.81        0.0       3          13   16  \n",
       "1           1  0.22  0.2727  0.80        0.0       8          32   40  \n",
       "2           1  0.22  0.2727  0.80        0.0       5          27   32  \n",
       "3           1  0.24  0.2879  0.75        0.0       3          10   13  \n",
       "4           1  0.24  0.2879  0.75        0.0       0           1    1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Create the scatter plot.\n",
    "def var_scatter(df, ax=None, var=\"temp\"):\n",
    "    if ax is None:\n",
    "        _, ax = plt.subplots(figsize=(8, 6))\n",
    "    df.plot.scatter(x=var , y=\"cnt\",alpha=0.3, s=10, ax=ax)\n",
    "\n",
    "    return ax\n",
    "\n",
    "var_scatter(df);\n",
    "plt.savefig(\"EE522-Thanakrit-Midterm-Scatter01.jpeg\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Create the heat map.\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set()\n",
    "_,ax=plt.subplots(figsize=(15,10))\n",
    "colormap=sns.diverging_palette(220,10,as_cmap=True)\n",
    "sns.heatmap(df.corr(),annot=True,cmap=colormap)\n",
    "plt.savefig(\"EE522-Thanakrit-Midterm-Heatmap.jpeg\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "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>cnt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weathersit</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>159.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>133.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              cnt\n",
       "weathersit       \n",
       "1           159.0\n",
       "2           133.0\n",
       "3            63.0\n",
       "4            36.0"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('weathersit')[['cnt']].median()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The median of the count of rental bikes has the highest value on the \"good\" weather condition (weathersit == 1) and lower; plus, it hits the lowest point on the \"bad\" weather condition (weathersit == 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>cnt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>season</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>76.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>165.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>199.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>155.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          cnt\n",
       "season       \n",
       "1        76.0\n",
       "2       165.0\n",
       "3       199.0\n",
       "4       155.5"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('season')[['cnt']].median()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The median of the count of rental bikes on the spring (season == 1) is the lowest significantly compared to any other season."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>cnt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>holiday</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>144.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>97.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           cnt\n",
       "holiday       \n",
       "0        144.0\n",
       "1         97.0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('holiday')[['cnt']].median()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The median of the count of rental bikes is higher on the working day compared to the that of holiday."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1.2 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will start by training our data. Please split the dataset into 80 % train data and 20 % test data. Then, use two features which are atemp and weatherlist to train the Regression algorithm and make predictions. What is the MAE and RMSE of train and test data in this model? Interpret the coefficients of these tow variables carefully.[10 Points]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Since weathersit is the dummy variable, I generate the dummy variable first."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>cnt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       cnt\n",
       "0       16\n",
       "1       40\n",
       "2       32\n",
       "3       13\n",
       "4        1\n",
       "...    ...\n",
       "17374  119\n",
       "17375   89\n",
       "17376   90\n",
       "17377   61\n",
       "17378   49\n",
       "\n",
       "[17379 rows x 1 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = df[['cnt']]\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "scrolled": true
   },
   "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>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       1  2  3  4\n",
       "0      1  0  0  0\n",
       "1      1  0  0  0\n",
       "2      1  0  0  0\n",
       "3      1  0  0  0\n",
       "4      1  0  0  0\n",
       "...   .. .. .. ..\n",
       "17374  0  1  0  0\n",
       "17375  0  1  0  0\n",
       "17376  1  0  0  0\n",
       "17377  1  0  0  0\n",
       "17378  1  0  0  0\n",
       "\n",
       "[17379 rows x 4 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weathersit_dummy = pd.get_dummies(df['weathersit'])\n",
    "weathersit_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "scrolled": true
   },
   "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>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "      <th>weathersit_4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       weathersit_1  weathersit_2  weathersit_3  weathersit_4\n",
       "0                 1             0             0             0\n",
       "1                 1             0             0             0\n",
       "2                 1             0             0             0\n",
       "3                 1             0             0             0\n",
       "4                 1             0             0             0\n",
       "...             ...           ...           ...           ...\n",
       "17374             0             1             0             0\n",
       "17375             0             1             0             0\n",
       "17376             1             0             0             0\n",
       "17377             1             0             0             0\n",
       "17378             1             0             0             0\n",
       "\n",
       "[17379 rows x 4 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weathersit_dummy.columns = ['weathersit_1','weathersit_2','weathersit_3','weathersit_4']\n",
    "weathersit_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>atemp</th>\n",
       "      <th>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "      <th>weathersit_4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        atemp  weathersit_1  weathersit_2  weathersit_3  weathersit_4\n",
       "0      0.2879             1             0             0             0\n",
       "1      0.2727             1             0             0             0\n",
       "2      0.2727             1             0             0             0\n",
       "3      0.2879             1             0             0             0\n",
       "4      0.2879             1             0             0             0\n",
       "...       ...           ...           ...           ...           ...\n",
       "17374  0.2576             0             1             0             0\n",
       "17375  0.2576             0             1             0             0\n",
       "17376  0.2576             1             0             0             0\n",
       "17377  0.2727             1             0             0             0\n",
       "17378  0.2727             1             0             0             0\n",
       "\n",
       "[17379 rows x 5 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = pd.concat([df[['atemp']],weathersit_dummy],axis=1)\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>atemp</th>\n",
       "      <th>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.2879</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0.2576</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0.2727</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        atemp  weathersit_1  weathersit_2  weathersit_3\n",
       "0      0.2879             1             0             0\n",
       "1      0.2727             1             0             0\n",
       "2      0.2727             1             0             0\n",
       "3      0.2879             1             0             0\n",
       "4      0.2879             1             0             0\n",
       "...       ...           ...           ...           ...\n",
       "17374  0.2576             0             1             0\n",
       "17375  0.2576             0             1             0\n",
       "17376  0.2576             1             0             0\n",
       "17377  0.2727             1             0             0\n",
       "17378  0.2727             1             0             0\n",
       "\n",
       "[17379 rows x 4 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Drop one dummy out\n",
    "X.drop(columns=['weathersit_4'], axis = 1, inplace = True)\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Split the data into train and test set.\n",
    "from sklearn import (linear_model, metrics, model_selection)\n",
    "X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size = 0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fit model: cnt = -2.7683 + 412.5286 atemp + 6.1641 weathersit_1 + -10.4229 weathersit_2+ -65.6742 weathersit_3\n"
     ]
    }
   ],
   "source": [
    "# Regression\n",
    "from sklearn import linear_model\n",
    "\n",
    "# construct the model instance\n",
    "lr_model_1 = linear_model.LinearRegression()\n",
    "\n",
    "# fit the model\n",
    "model1 = lr_model_1.fit(X, y) # be careful\n",
    "\n",
    "# print the coefficients\n",
    "beta_0 = lr_model_1.intercept_[0]\n",
    "beta_1 = lr_model_1.coef_[0][0]\n",
    "delta_1 = lr_model_1.coef_[0][1]\n",
    "delta_2 = lr_model_1.coef_[0][2]\n",
    "delta_3 = lr_model_1.coef_[0][3]\n",
    "\n",
    "print(f\"Fit model: cnt = {beta_0:.4f} + {beta_1:.4f} atemp + {delta_1:.4f} weathersit_1 + {delta_2:.4f} weathersit_2\\\n",
    "+ {delta_3:.4f} weathersit_3\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "On average, if the atemp (Normalized feeling temperature in Celsius) increases by one unit, the cnt (total number of rental bikes) will increase by 412.5286 units, holding other being constant.\n",
    "\n",
    "On average, the cnt will increase 6.1641 units when the weather condition is clear (weathersit == 1) compared to the case when the weather condition is extreme (weathersit == 4), holding other being constant.\n",
    "\n",
    "On average, the cnt will fall by 10.4229 units when weathersit == 2 compared to the case when the weather condition is extreme (weathersit == 4), holding other being constant.\n",
    "\n",
    "On average, the cnt will fall by 65.6742 units when weathersit == 3 compared to the case when the weather condition is extreme (weathersit == 4), holding other being constant."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The mean absolute error of the train data is 124.0787, while that of the test data is 126.7071\n",
      "The RMSE of the train data is 164.5640, while that of the test data is 166.7370\n"
     ]
    }
   ],
   "source": [
    "# Compare MAE and RMSE\n",
    "mae_test = metrics.mean_absolute_error(y_test, model1.predict(X_test))\n",
    "mae_train = metrics.mean_absolute_error(y_train, model1.predict(X_train))\n",
    "\n",
    "rmse_test = metrics.mean_squared_error(y_test, model1.predict(X_test), squared = False)\n",
    "rmse_train = metrics.mean_squared_error(y_train, model1.predict(X_train), squared = False)\n",
    "\n",
    "print(f'The mean absolute error of the train data is {mae_train:.4f}, while that of the test data is {mae_test:.4f}')\n",
    "print(f'The RMSE of the train data is {rmse_train:.4f}, while that of the test data is {rmse_test:.4f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1.3 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Perform the cross-varidation by spliting the dataset into 10 folds and train the model with Regression algorithm by using the two features as in question 1.2. What is the MAE and RMSE in model?.[10 Points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import KFold"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X.to_numpy()\n",
    "y = y.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KFold(n_splits=10, random_state=None, shuffle=False)"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kf = KFold(n_splits=10,shuffle=False)\n",
    "kf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE on 10-fold CV on the train: 164.73969989621293\n",
      "RMSE on 10-fold CV on the test: 160.97629932453293\n"
     ]
    }
   ],
   "source": [
    "err_train = 0\n",
    "err_test =0\n",
    "for train,test in kf.split(X):\n",
    "    lr=linear_model.LinearRegression()\n",
    "    reg=lr.fit(X[train],y[train])\n",
    "    y_pred_train =reg.predict(X[train])\n",
    "    y_pred_test =reg.predict(X[test])\n",
    "    e_train= y[train]-y_pred_train\n",
    "    e_test = y[test]-y_pred_test\n",
    "    err_train += np.sqrt(np.mean(e_train*e_train)) # compute rmse for the estimation rmse test data\n",
    "    err_test += np.sqrt(np.mean(e_test*e_test))\n",
    "rmse_10cv_train = err_train/10              #average the rmse\n",
    "rmse_10cv_test = err_test/10  \n",
    "print('RMSE on 10-fold CV on the train: {}'.format(rmse_10cv_train))\n",
    "print('RMSE on 10-fold CV on the test: {}'.format(rmse_10cv_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE on 10-fold CV on the train: 124.48695397199273\n",
      "MAE on 10-fold CV on the test: 127.40382721279045\n"
     ]
    }
   ],
   "source": [
    "err_train = 0\n",
    "err_test =0\n",
    "for train,test in kf.split(X):\n",
    "    lr=linear_model.LinearRegression()\n",
    "    reg=lr.fit(X[train],y[train])\n",
    "    y_pred_train =reg.predict(X[train])\n",
    "    y_pred_test =reg.predict(X[test])\n",
    "    e_train= y[train]-y_pred_train\n",
    "    e_test = y[test]-y_pred_test\n",
    "    err_train += np.mean(np.abs(e_train)) # compute rmse for the estimation rmse test data\n",
    "    err_test += np.mean(np.abs(e_test))\n",
    "mae_10cv_train = err_train/10              #average the rmse\n",
    "mae_10cv_test = err_test/10  \n",
    "print('MAE on 10-fold CV on the train: {}'.format(mae_10cv_train))\n",
    "print('MAE on 10-fold CV on the test: {}'.format(mae_10cv_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The last excercise, using all features which are\n",
    "- holiday : weather day is holiday or not \n",
    "- weekday : day of the week\n",
    "- workingday : if day is neither weekend nor holiday is 1, otherwise is 0.\n",
    "+ weathersit : \n",
    "    - 1: Clear, Few clouds, Partly cloudy, Partly cloudy\n",
    "    - 2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist\n",
    "    - 3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds\n",
    "    - 4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog\n",
    "- temp : Normalized temperature in Celsius. The values are divided to 41 (max)\n",
    "- atemp: Normalized feeling temperature in Celsius. The values are divided to 50 (max)\n",
    "- hum: Normalized humidity. The values are divided to 100 (max)\n",
    "- windspeed: Normalized wind speed. The values are divided to 67 (max)\n",
    "\n",
    "to train the model with the same process in question 1.2 What is the MAE and RMSE in this model? Interpret the results carefully"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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>cnt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       cnt\n",
       "0       16\n",
       "1       40\n",
       "2       32\n",
       "3       13\n",
       "4        1\n",
       "...    ...\n",
       "17374  119\n",
       "17375   89\n",
       "17376   90\n",
       "17377   61\n",
       "17378   49\n",
       "\n",
       "[17379 rows x 1 columns]"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_all = df[['cnt']]\n",
    "y_all"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "      <th>weathersit_4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       weathersit_1  weathersit_2  weathersit_3  weathersit_4\n",
       "0                 1             0             0             0\n",
       "1                 1             0             0             0\n",
       "2                 1             0             0             0\n",
       "3                 1             0             0             0\n",
       "4                 1             0             0             0\n",
       "...             ...           ...           ...           ...\n",
       "17374             0             1             0             0\n",
       "17375             0             1             0             0\n",
       "17376             1             0             0             0\n",
       "17377             1             0             0             0\n",
       "17378             1             0             0             0\n",
       "\n",
       "[17379 rows x 4 columns]"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weathersit_dummy = pd.get_dummies(df['weathersit'])\n",
    "weathersit_dummy.columns = ['weathersit_1','weathersit_2','weathersit_3','weathersit_4']\n",
    "weathersit_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "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>holiday_no</th>\n",
       "      <th>holiday_yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       holiday_no  holiday_yes\n",
       "0               1            0\n",
       "1               1            0\n",
       "2               1            0\n",
       "3               1            0\n",
       "4               1            0\n",
       "...           ...          ...\n",
       "17374           1            0\n",
       "17375           1            0\n",
       "17376           1            0\n",
       "17377           1            0\n",
       "17378           1            0\n",
       "\n",
       "[17379 rows x 2 columns]"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holiday_dummy = pd.get_dummies(df['holiday'])\n",
    "holiday_dummy.columns = ['holiday_no','holiday_yes']\n",
    "holiday_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "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>workingday_no</th>\n",
       "      <th>workingday_yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       workingday_no  workingday_yes\n",
       "0                  1               0\n",
       "1                  1               0\n",
       "2                  1               0\n",
       "3                  1               0\n",
       "4                  1               0\n",
       "...              ...             ...\n",
       "17374              0               1\n",
       "17375              0               1\n",
       "17376              0               1\n",
       "17377              0               1\n",
       "17378              0               1\n",
       "\n",
       "[17379 rows x 2 columns]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "workingday_dummy = pd.get_dummies(df['workingday'])\n",
    "workingday_dummy.columns = ['workingday_no','workingday_yes']\n",
    "workingday_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "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>Sun</th>\n",
       "      <th>Mon</th>\n",
       "      <th>Tue</th>\n",
       "      <th>Wed</th>\n",
       "      <th>Thurs</th>\n",
       "      <th>Fri</th>\n",
       "      <th>Sat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Sun  Mon  Tue  Wed  Thurs  Fri  Sat\n",
       "0        0    0    0    0      0    0    1\n",
       "1        0    0    0    0      0    0    1\n",
       "2        0    0    0    0      0    0    1\n",
       "3        0    0    0    0      0    0    1\n",
       "4        0    0    0    0      0    0    1\n",
       "...    ...  ...  ...  ...    ...  ...  ...\n",
       "17374    0    1    0    0      0    0    0\n",
       "17375    0    1    0    0      0    0    0\n",
       "17376    0    1    0    0      0    0    0\n",
       "17377    0    1    0    0      0    0    0\n",
       "17378    0    1    0    0      0    0    0\n",
       "\n",
       "[17379 rows x 7 columns]"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weekday_dummy = pd.get_dummies(df['weekday'])\n",
    "weekday_dummy.columns = ['Sun', 'Mon', 'Tue', 'Wed', 'Thurs', 'Fri', 'Sat']\n",
    "weekday_dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "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>temp</th>\n",
       "      <th>atemp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "      <th>weathersit_4</th>\n",
       "      <th>holiday_no</th>\n",
       "      <th>holiday_yes</th>\n",
       "      <th>workingday_no</th>\n",
       "      <th>workingday_yes</th>\n",
       "      <th>Sun</th>\n",
       "      <th>Mon</th>\n",
       "      <th>Tue</th>\n",
       "      <th>Wed</th>\n",
       "      <th>Thurs</th>\n",
       "      <th>Fri</th>\n",
       "      <th>Sat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.81</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.1343</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.65</td>\n",
       "      <td>0.1343</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       temp   atemp   hum  windspeed  weathersit_1  weathersit_2  \\\n",
       "0      0.24  0.2879  0.81     0.0000             1             0   \n",
       "1      0.22  0.2727  0.80     0.0000             1             0   \n",
       "2      0.22  0.2727  0.80     0.0000             1             0   \n",
       "3      0.24  0.2879  0.75     0.0000             1             0   \n",
       "4      0.24  0.2879  0.75     0.0000             1             0   \n",
       "...     ...     ...   ...        ...           ...           ...   \n",
       "17374  0.26  0.2576  0.60     0.1642             0             1   \n",
       "17375  0.26  0.2576  0.60     0.1642             0             1   \n",
       "17376  0.26  0.2576  0.60     0.1642             1             0   \n",
       "17377  0.26  0.2727  0.56     0.1343             1             0   \n",
       "17378  0.26  0.2727  0.65     0.1343             1             0   \n",
       "\n",
       "       weathersit_3  weathersit_4  holiday_no  holiday_yes  workingday_no  \\\n",
       "0                 0             0           1            0              1   \n",
       "1                 0             0           1            0              1   \n",
       "2                 0             0           1            0              1   \n",
       "3                 0             0           1            0              1   \n",
       "4                 0             0           1            0              1   \n",
       "...             ...           ...         ...          ...            ...   \n",
       "17374             0             0           1            0              0   \n",
       "17375             0             0           1            0              0   \n",
       "17376             0             0           1            0              0   \n",
       "17377             0             0           1            0              0   \n",
       "17378             0             0           1            0              0   \n",
       "\n",
       "       workingday_yes  Sun  Mon  Tue  Wed  Thurs  Fri  Sat  \n",
       "0                   0    0    0    0    0      0    0    1  \n",
       "1                   0    0    0    0    0      0    0    1  \n",
       "2                   0    0    0    0    0      0    0    1  \n",
       "3                   0    0    0    0    0      0    0    1  \n",
       "4                   0    0    0    0    0      0    0    1  \n",
       "...               ...  ...  ...  ...  ...    ...  ...  ...  \n",
       "17374               1    0    1    0    0      0    0    0  \n",
       "17375               1    0    1    0    0      0    0    0  \n",
       "17376               1    0    1    0    0      0    0    0  \n",
       "17377               1    0    1    0    0      0    0    0  \n",
       "17378               1    0    1    0    0      0    0    0  \n",
       "\n",
       "[17379 rows x 19 columns]"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_all = pd.concat([df[['temp', 'atemp', 'hum', 'windspeed']],weathersit_dummy, holiday_dummy, workingday_dummy, weekday_dummy],axis=1)\n",
    "X_all"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "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>temp</th>\n",
       "      <th>atemp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>weathersit_1</th>\n",
       "      <th>weathersit_2</th>\n",
       "      <th>weathersit_3</th>\n",
       "      <th>holiday_yes</th>\n",
       "      <th>workingday_yes</th>\n",
       "      <th>Mon</th>\n",
       "      <th>Tue</th>\n",
       "      <th>Wed</th>\n",
       "      <th>Thurs</th>\n",
       "      <th>Fri</th>\n",
       "      <th>Sat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.81</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17374</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17375</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17376</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2576</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.1642</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17377</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.1343</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17378</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.65</td>\n",
       "      <td>0.1343</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17379 rows × 15 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       temp   atemp   hum  windspeed  weathersit_1  weathersit_2  \\\n",
       "0      0.24  0.2879  0.81     0.0000             1             0   \n",
       "1      0.22  0.2727  0.80     0.0000             1             0   \n",
       "2      0.22  0.2727  0.80     0.0000             1             0   \n",
       "3      0.24  0.2879  0.75     0.0000             1             0   \n",
       "4      0.24  0.2879  0.75     0.0000             1             0   \n",
       "...     ...     ...   ...        ...           ...           ...   \n",
       "17374  0.26  0.2576  0.60     0.1642             0             1   \n",
       "17375  0.26  0.2576  0.60     0.1642             0             1   \n",
       "17376  0.26  0.2576  0.60     0.1642             1             0   \n",
       "17377  0.26  0.2727  0.56     0.1343             1             0   \n",
       "17378  0.26  0.2727  0.65     0.1343             1             0   \n",
       "\n",
       "       weathersit_3  holiday_yes  workingday_yes  Mon  Tue  Wed  Thurs  Fri  \\\n",
       "0                 0            0               0    0    0    0      0    0   \n",
       "1                 0            0               0    0    0    0      0    0   \n",
       "2                 0            0               0    0    0    0      0    0   \n",
       "3                 0            0               0    0    0    0      0    0   \n",
       "4                 0            0               0    0    0    0      0    0   \n",
       "...             ...          ...             ...  ...  ...  ...    ...  ...   \n",
       "17374             0            0               1    1    0    0      0    0   \n",
       "17375             0            0               1    1    0    0      0    0   \n",
       "17376             0            0               1    1    0    0      0    0   \n",
       "17377             0            0               1    1    0    0      0    0   \n",
       "17378             0            0               1    1    0    0      0    0   \n",
       "\n",
       "       Sat  \n",
       "0        1  \n",
       "1        1  \n",
       "2        1  \n",
       "3        1  \n",
       "4        1  \n",
       "...    ...  \n",
       "17374    0  \n",
       "17375    0  \n",
       "17376    0  \n",
       "17377    0  \n",
       "17378    0  \n",
       "\n",
       "[17379 rows x 15 columns]"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_all.drop(columns = ['weathersit_4', 'holiday_no', 'workingday_no', 'Sun'], axis=1, inplace= True)\n",
    "X_all"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Split the data into train and test set.\n",
    "from sklearn import (linear_model, metrics, model_selection)\n",
    "X_all_train, X_all_test, y_all_train, y_all_test = model_selection.train_test_split(X_all, y_all, test_size = 0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Regression\n",
    "from sklearn import linear_model\n",
    "\n",
    "# construct the model instance\n",
    "lr_model_2 = linear_model.LinearRegression()\n",
    "\n",
    "# fit the model\n",
    "model2 = lr_model_2.fit(X_all, y_all) # be careful"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The mean absolute error of the train data is 116.5281, while that of the test data is 117.2382\n",
      "The RMSE of the train data is 156.3693, while that of the test data is 156.5068\n"
     ]
    }
   ],
   "source": [
    "# Compare MAE and RMSE\n",
    "mae_all_test = metrics.mean_absolute_error(y_all_test, model2.predict(X_all_test))\n",
    "mae_all_train = metrics.mean_absolute_error(y_all_train, model2.predict(X_all_train))\n",
    "\n",
    "rmse_all_test = metrics.mean_squared_error(y_all_test, model2.predict(X_all_test), squared = False)\n",
    "rmse_all_train = metrics.mean_squared_error(y_all_train, model2.predict(X_all_train), squared = False)\n",
    "\n",
    "print(f'The mean absolute error of the train data is {mae_all_train:.4f}, while that of the test data is {mae_all_test:.4f}')\n",
    "print(f'The RMSE of the train data is {rmse_all_train:.4f}, while that of the test data is {rmse_all_test:.4f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1.4 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Should we use all features or only the two features? Why? Is there the problem of overfitting in the model you select? Why? [10 Points]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We should employ the all features model, according to my result, since the RMSE of all-features-model of the test data is smaller than that of the two-variables model. Moreover, the result of all features model is good in such a way that the error of the train data is smaller than that of the test data which shows the sign of not having the overfitting problem."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1.5 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using the model you selcted in 1.4 to create the dataframe that contains three columns which are : Actual value, Predicted value, and the error/residual. Then fill in these values from the test data.[10 Points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 209,
   "metadata": {},
   "outputs": [],
   "source": [
    "#yhat\n",
    "predict = model2.predict(X_all_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "13903"
      ]
     },
     "execution_count": 249,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 222,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "If using all scalar values, you must pass an index",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_13688/3777349714.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m{\u001b[0m\u001b[1;34m'predicted'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'actual'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0my_all_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'residual'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0my_all_train\u001b[0m\u001b[1;33m-\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[0;32m    612\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    613\u001b[0m             \u001b[1;31m# GH#38939 de facto copy defaults to False only in non-dict cases\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 614\u001b[1;33m             \u001b[0mmgr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict_to_mgr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtyp\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmanager\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    615\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mMaskedArray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    616\u001b[0m             \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmrecords\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mmrecords\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36mdict_to_mgr\u001b[1;34m(data, index, columns, dtype, typ, copy)\u001b[0m\n\u001b[0;32m    462\u001b[0m         \u001b[1;31m# TODO: can we get rid of the dt64tz special case above?\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    463\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 464\u001b[1;33m     return arrays_to_mgr(\n\u001b[0m\u001b[0;32m    465\u001b[0m         \u001b[0marrays\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata_names\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtyp\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtyp\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconsolidate\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    466\u001b[0m     )\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36marrays_to_mgr\u001b[1;34m(arrays, arr_names, index, columns, dtype, verify_integrity, typ, consolidate)\u001b[0m\n\u001b[0;32m    117\u001b[0m         \u001b[1;31m# figure out the index, if necessary\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    118\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mindex\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 119\u001b[1;33m             \u001b[0mindex\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_extract_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marrays\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    120\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    121\u001b[0m             \u001b[0mindex\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mensure_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36m_extract_index\u001b[1;34m(data)\u001b[0m\n\u001b[0;32m    623\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    624\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mindexes\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mraw_lengths\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 625\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"If using all scalar values, you must pass an index\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    626\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    627\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mhave_series\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: If using all scalar values, you must pass an index"
     ]
    }
   ],
   "source": [
    "result = pd.DataFrame({'predicted':predict, 'actual':y_all_train, 'residual':y_all_train-predict})\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "metadata": {},
   "outputs": [],
   "source": [
    "tab1 = pd.DataFrame()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Cannot set a frame with no defined index and a value that cannot be converted to a Series",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m_ensure_valid_index\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m   3845\u001b[0m                 \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3846\u001b[1;33m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mSeries\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   3847\u001b[0m                 \u001b[1;32mexcept\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mValueError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mNotImplementedError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, data, index, dtype, name, copy, fastpath)\u001b[0m\n\u001b[0;32m    438\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 439\u001b[1;33m                 \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msanitize_array\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    440\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\construction.py\u001b[0m in \u001b[0;36msanitize_array\u001b[1;34m(data, index, dtype, copy, raise_cast_failure, allow_2d)\u001b[0m\n\u001b[0;32m    575\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 576\u001b[1;33m     \u001b[0msubarr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_sanitize_ndim\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msubarr\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mallow_2d\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mallow_2d\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    577\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\construction.py\u001b[0m in \u001b[0;36m_sanitize_ndim\u001b[1;34m(result, data, dtype, index, allow_2d)\u001b[0m\n\u001b[0;32m    626\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 627\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Data must be 1-dimensional\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    628\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mis_object_dtype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mExtensionDtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Data must be 1-dimensional",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_13688/1170655134.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtab1\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Predicted'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m=\u001b[0m \u001b[0mpredict\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__setitem__\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m   3610\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3611\u001b[0m             \u001b[1;31m# set column\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3612\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_set_item\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   3613\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3614\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_setitem_slice\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mslice\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m_set_item\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m   3782\u001b[0m         \u001b[0mensure\u001b[0m \u001b[0mhomogeneity\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3783\u001b[0m         \"\"\"\n\u001b[1;32m-> 3784\u001b[1;33m         \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sanitize_column\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   3785\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3786\u001b[0m         if (\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m_sanitize_column\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m   4500\u001b[0m         \u001b[0mnumpy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndarray\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mExtensionArray\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4501\u001b[0m         \"\"\"\n\u001b[1;32m-> 4502\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_ensure_valid_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   4503\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4504\u001b[0m         \u001b[1;31m# We should never get here with DataFrame value\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m_ensure_valid_index\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m   3846\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mSeries\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3847\u001b[0m                 \u001b[1;32mexcept\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mValueError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mNotImplementedError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3848\u001b[1;33m                     raise ValueError(\n\u001b[0m\u001b[0;32m   3849\u001b[0m                         \u001b[1;34m\"Cannot set a frame with no defined index \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3850\u001b[0m                         \u001b[1;34m\"and a value that cannot be converted to a Series\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Cannot set a frame with no defined index and a value that cannot be converted to a Series"
     ]
    }
   ],
   "source": [
    "tab1['Predicted']= predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "If using all scalar values, you must pass an index",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_13688/813689020.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;31m#yhat\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[0mpredict2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_all_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mresult2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m{\u001b[0m\u001b[1;34m'predicted'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mpredict2\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'actual'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0my_all_test\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'residual'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0my_all_test\u001b[0m\u001b[1;33m-\u001b[0m\u001b[0mpredict2\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m \u001b[0mresult2\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[0;32m    612\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    613\u001b[0m             \u001b[1;31m# GH#38939 de facto copy defaults to False only in non-dict cases\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 614\u001b[1;33m             \u001b[0mmgr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict_to_mgr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtyp\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmanager\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    615\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mMaskedArray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    616\u001b[0m             \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmrecords\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mmrecords\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36mdict_to_mgr\u001b[1;34m(data, index, columns, dtype, typ, copy)\u001b[0m\n\u001b[0;32m    462\u001b[0m         \u001b[1;31m# TODO: can we get rid of the dt64tz special case above?\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    463\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 464\u001b[1;33m     return arrays_to_mgr(\n\u001b[0m\u001b[0;32m    465\u001b[0m         \u001b[0marrays\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata_names\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtyp\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtyp\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconsolidate\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    466\u001b[0m     )\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36marrays_to_mgr\u001b[1;34m(arrays, arr_names, index, columns, dtype, verify_integrity, typ, consolidate)\u001b[0m\n\u001b[0;32m    117\u001b[0m         \u001b[1;31m# figure out the index, if necessary\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    118\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mindex\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 119\u001b[1;33m             \u001b[0mindex\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_extract_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marrays\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    120\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    121\u001b[0m             \u001b[0mindex\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mensure_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36m_extract_index\u001b[1;34m(data)\u001b[0m\n\u001b[0;32m    623\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    624\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mindexes\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mraw_lengths\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 625\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"If using all scalar values, you must pass an index\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    626\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    627\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mhave_series\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: If using all scalar values, you must pass an index"
     ]
    }
   ],
   "source": [
    "#yhat\n",
    "predict2 = model2.predict(X_all_test)\n",
    "result2 = pd.DataFrame({'predicted':predict2, 'actual':y_all_test, 'residual':y_all_test-predict2})\n",
    "result2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 2 [20 points]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 2.1:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2.1 The below information shows the U.S unemployment rate (unemp)in 2010 from January-December \n",
    "\n",
    "\n",
    "Task: write down the python code using control flow  \"if\" to print the message ONLY the months that have the unemployment rate above 8% i.e.\n",
    "\n",
    "\n",
    "- The umemployment rate in Apr is 14.8%\n",
    "\n",
    "- The unemployment rate in May is 13.3%\n",
    "\n",
    "\n",
    "\n",
    "[10 Points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "unemp= [3.5,\n",
    "3.5,\n",
    "4.4,\n",
    "14.8,\n",
    "13.3,\n",
    "11.1,\n",
    "10.2,\n",
    "8.4,\n",
    "7.8,\n",
    "6.9,\n",
    "6.7,\n",
    "6.7]\n",
    "month =['Jan','Feb','Mar','Apr','May','June','July','Aug','Sep','Oct','Nov','Dec']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The umemployment rate in Apr is 14.8%\n",
      "The umemployment rate in May is 13.3%\n",
      "The umemployment rate in June is 11.1%\n",
      "The umemployment rate in July is 10.2%\n",
      "The umemployment rate in Aug is 8.4%\n"
     ]
    }
   ],
   "source": [
    "for val, mon in list(zip(unemp,month)):\n",
    "    if val > 8:\n",
    "        print(f\"The umemployment rate in {mon} is {val}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 2.2 :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2.2 write the list [.] of even numbers from 2-500. Then using control flow to find out the summation of the log of even numbers from 2-100. i.e. log(2)+log(4)+....log(100) \n",
    "[10 Points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_even = []\n",
    "\n",
    "for number in range(2,501):\n",
    "      if(number % 2 == 0):\n",
    "        num_even.append(number)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "int"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(num_even[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[2,\n",
       " 4,\n",
       " 6,\n",
       " 8,\n",
       " 10,\n",
       " 12,\n",
       " 14,\n",
       " 16,\n",
       " 18,\n",
       " 20,\n",
       " 22,\n",
       " 24,\n",
       " 26,\n",
       " 28,\n",
       " 30,\n",
       " 32,\n",
       " 34,\n",
       " 36,\n",
       " 38,\n",
       " 40,\n",
       " 42,\n",
       " 44,\n",
       " 46,\n",
       " 48,\n",
       " 50,\n",
       " 52,\n",
       " 54,\n",
       " 56,\n",
       " 58,\n",
       " 60,\n",
       " 62,\n",
       " 64,\n",
       " 66,\n",
       " 68,\n",
       " 70,\n",
       " 72,\n",
       " 74,\n",
       " 76,\n",
       " 78,\n",
       " 80,\n",
       " 82,\n",
       " 84,\n",
       " 86,\n",
       " 88,\n",
       " 90,\n",
       " 92,\n",
       " 94,\n",
       " 96,\n",
       " 98,\n",
       " 100]"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_even[0:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.69314718, 1.38629436, 1.79175947, 2.07944154, 2.30258509,\n",
       "       2.48490665, 2.63905733, 2.77258872, 2.89037176, 2.99573227,\n",
       "       3.09104245, 3.17805383, 3.25809654, 3.33220451, 3.40119738,\n",
       "       3.4657359 , 3.52636052, 3.58351894, 3.63758616, 3.68887945,\n",
       "       3.73766962, 3.78418963, 3.8286414 , 3.87120101, 3.91202301,\n",
       "       3.95124372, 3.98898405, 4.02535169, 4.06044301, 4.09434456,\n",
       "       4.12713439, 4.15888308, 4.18965474, 4.21950771, 4.24849524,\n",
       "       4.27666612, 4.30406509, 4.33073334, 4.35670883, 4.38202663,\n",
       "       4.40671925, 4.4308168 , 4.4543473 , 4.47733681, 4.49980967,\n",
       "       4.52178858, 4.54329478, 4.56434819, 4.58496748, 4.60517019])"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "log_num_even=np.log(num_even)\n",
    "log_num_even[0:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " The summation of the log of even numbers from 2-100 is 187.7600987930546\n"
     ]
    }
   ],
   "source": [
    "total = 0\n",
    "for index in list(range(0,51)):\n",
    "    total = total + log_num_even[index]\n",
    "    \n",
    "print(f\" The summation of the log of even numbers from 2-100 is {total}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 3 [20 point]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3.1 Consider the stock prices: TESLA (TSLA) stock.from June 29, 2010 to Sept 30, 2022. The data are downloadable from Yahoo Finance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams[\"figure.figsize\"] = [10,8]  # Set default figure size\n",
    "import requests #To get the data from the online database.\n",
    "import datetime\n",
    "import pandas_datareader.data as web "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot (1) the TESLA prices and (2) TESLA log returns. Then, check the stationarity condition of these two series. [10 points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [],
   "source": [
    "start = datetime.datetime(2010,6,29)\n",
    "end = datetime.datetime(2022,9,30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "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>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Open</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>Adj Close</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2010-06-29</th>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.169333</td>\n",
       "      <td>1.266667</td>\n",
       "      <td>1.592667</td>\n",
       "      <td>281494500.0</td>\n",
       "      <td>1.592667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-06-30</th>\n",
       "      <td>2.028000</td>\n",
       "      <td>1.553333</td>\n",
       "      <td>1.719333</td>\n",
       "      <td>1.588667</td>\n",
       "      <td>257806500.0</td>\n",
       "      <td>1.588667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-01</th>\n",
       "      <td>1.728000</td>\n",
       "      <td>1.351333</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.464000</td>\n",
       "      <td>123282000.0</td>\n",
       "      <td>1.464000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-02</th>\n",
       "      <td>1.540000</td>\n",
       "      <td>1.247333</td>\n",
       "      <td>1.533333</td>\n",
       "      <td>1.280000</td>\n",
       "      <td>77097000.0</td>\n",
       "      <td>1.280000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-06</th>\n",
       "      <td>1.333333</td>\n",
       "      <td>1.055333</td>\n",
       "      <td>1.333333</td>\n",
       "      <td>1.074000</td>\n",
       "      <td>103003500.0</td>\n",
       "      <td>1.074000</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-26</th>\n",
       "      <td>284.089996</td>\n",
       "      <td>270.309998</td>\n",
       "      <td>271.829987</td>\n",
       "      <td>276.010010</td>\n",
       "      <td>58076900.0</td>\n",
       "      <td>276.010010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-27</th>\n",
       "      <td>288.670013</td>\n",
       "      <td>277.510010</td>\n",
       "      <td>283.839996</td>\n",
       "      <td>282.940002</td>\n",
       "      <td>61925200.0</td>\n",
       "      <td>282.940002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-28</th>\n",
       "      <td>289.000000</td>\n",
       "      <td>277.570007</td>\n",
       "      <td>283.079987</td>\n",
       "      <td>287.809998</td>\n",
       "      <td>54664800.0</td>\n",
       "      <td>287.809998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-29</th>\n",
       "      <td>283.649994</td>\n",
       "      <td>265.779999</td>\n",
       "      <td>282.760010</td>\n",
       "      <td>268.209991</td>\n",
       "      <td>77620600.0</td>\n",
       "      <td>268.209991</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-30</th>\n",
       "      <td>275.570007</td>\n",
       "      <td>262.470001</td>\n",
       "      <td>266.149994</td>\n",
       "      <td>265.250000</td>\n",
       "      <td>67517800.0</td>\n",
       "      <td>265.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3087 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  High         Low        Open       Close       Volume  \\\n",
       "Date                                                                      \n",
       "2010-06-29    1.666667    1.169333    1.266667    1.592667  281494500.0   \n",
       "2010-06-30    2.028000    1.553333    1.719333    1.588667  257806500.0   \n",
       "2010-07-01    1.728000    1.351333    1.666667    1.464000  123282000.0   \n",
       "2010-07-02    1.540000    1.247333    1.533333    1.280000   77097000.0   \n",
       "2010-07-06    1.333333    1.055333    1.333333    1.074000  103003500.0   \n",
       "...                ...         ...         ...         ...          ...   \n",
       "2022-09-26  284.089996  270.309998  271.829987  276.010010   58076900.0   \n",
       "2022-09-27  288.670013  277.510010  283.839996  282.940002   61925200.0   \n",
       "2022-09-28  289.000000  277.570007  283.079987  287.809998   54664800.0   \n",
       "2022-09-29  283.649994  265.779999  282.760010  268.209991   77620600.0   \n",
       "2022-09-30  275.570007  262.470001  266.149994  265.250000   67517800.0   \n",
       "\n",
       "             Adj Close  \n",
       "Date                    \n",
       "2010-06-29    1.592667  \n",
       "2010-06-30    1.588667  \n",
       "2010-07-01    1.464000  \n",
       "2010-07-02    1.280000  \n",
       "2010-07-06    1.074000  \n",
       "...                ...  \n",
       "2022-09-26  276.010010  \n",
       "2022-09-27  282.940002  \n",
       "2022-09-28  287.809998  \n",
       "2022-09-29  268.209991  \n",
       "2022-09-30  265.250000  \n",
       "\n",
       "[3087 rows x 6 columns]"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = web.DataReader('TSLA' , 'yahoo', start = start, end = end)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\thana\\AppData\\Local\\Temp/ipykernel_13688/3293786418.py:3: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  price_tsla['log_price'] = np.log(price_tsla['price'])\n"
     ]
    },
    {
     "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>price</th>\n",
       "      <th>log_price</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2010-06-29</th>\n",
       "      <td>1.592667</td>\n",
       "      <td>0.465410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-06-30</th>\n",
       "      <td>1.588667</td>\n",
       "      <td>0.462895</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-01</th>\n",
       "      <td>1.464000</td>\n",
       "      <td>0.381172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-02</th>\n",
       "      <td>1.280000</td>\n",
       "      <td>0.246860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-06</th>\n",
       "      <td>1.074000</td>\n",
       "      <td>0.071390</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-26</th>\n",
       "      <td>276.010010</td>\n",
       "      <td>5.620437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-27</th>\n",
       "      <td>282.940002</td>\n",
       "      <td>5.645235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-28</th>\n",
       "      <td>287.809998</td>\n",
       "      <td>5.662301</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-29</th>\n",
       "      <td>268.209991</td>\n",
       "      <td>5.591770</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-09-30</th>\n",
       "      <td>265.250000</td>\n",
       "      <td>5.580673</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3087 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 price  log_price\n",
       "Date                             \n",
       "2010-06-29    1.592667   0.465410\n",
       "2010-06-30    1.588667   0.462895\n",
       "2010-07-01    1.464000   0.381172\n",
       "2010-07-02    1.280000   0.246860\n",
       "2010-07-06    1.074000   0.071390\n",
       "...                ...        ...\n",
       "2022-09-26  276.010010   5.620437\n",
       "2022-09-27  282.940002   5.645235\n",
       "2022-09-28  287.809998   5.662301\n",
       "2022-09-29  268.209991   5.591770\n",
       "2022-09-30  265.250000   5.580673\n",
       "\n",
       "[3087 rows x 2 columns]"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "price_tsla = df[['Adj Close']]\n",
    "price_tsla.columns = ['price']\n",
    "price_tsla['log_price'] = np.log(price_tsla['price'])\n",
    "price_tsla"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 152,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Date'>"
      ]
     },
     "execution_count": 152,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "price_tsla['price'].plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\thana\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py:4906: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  return super().drop(\n"
     ]
    }
   ],
   "source": [
    "price_tsla.drop(columns = ['log_return','return'],axis=1, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\thana\\AppData\\Local\\Temp/ipykernel_13688/3831666107.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  price_tsla['log_return'] = price_tsla['log_price'].diff()\n"
     ]
    }
   ],
   "source": [
    "price_tsla['log_return'] = price_tsla['log_price'].diff()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Date'>"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "price_tsla['log_return'].plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "metadata": {},
   "outputs": [],
   "source": [
    "#From the eyeballs, we can see that the log_return is stationary but the price is not.\n",
    "# Augmented Dickey-Fuller test\n",
    "\n",
    "from statsmodels.tsa.stattools import adfuller\n",
    "X1 = price_tsla['price'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ADF Statistic: -0.147295\n",
      "p-value: 0.944519\n",
      "Critical Values:\n",
      "\t1%: -3.432\n",
      "\t5%: -2.862\n",
      "\t10%: -2.567\n"
     ]
    }
   ],
   "source": [
    "result1 = adfuller(X1)\n",
    "print('ADF Statistic: %f' % result1[0])\n",
    "print('p-value: %f' % result1[1])\n",
    "print('Critical Values:')\n",
    "for key, value in result1[4].items():\n",
    "\tprint('\\t%s: %.3f' % (key, value))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since the p-value of ADF test is greater than 0.05, the null hypothesis that the series \"price\" has a unit root problem cannot be rejected. Hence, the \"price\" series has a unit root problem; nonstationary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [
    {
     "ename": "MissingDataError",
     "evalue": "exog contains inf or nans",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mMissingDataError\u001b[0m                          Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_13688/2806702879.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mstatsmodels\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtsa\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstattools\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0madfuller\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[0mX2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mprice_tsla\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'log_return'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mresult2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0madfuller\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'ADF Statistic: %f'\u001b[0m \u001b[1;33m%\u001b[0m \u001b[0mresult2\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'p-value: %f'\u001b[0m \u001b[1;33m%\u001b[0m \u001b[0mresult2\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\tsa\\stattools.py\u001b[0m in \u001b[0;36madfuller\u001b[1;34m(x, maxlag, regression, autolag, store, regresults)\u001b[0m\n\u001b[0;32m    312\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    313\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mregresults\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 314\u001b[1;33m             icbest, bestlag = _autolag(\n\u001b[0m\u001b[0;32m    315\u001b[0m                 \u001b[0mOLS\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mxdshort\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfullRHS\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstartlag\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmaxlag\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mautolag\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    316\u001b[0m             )\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\tsa\\stattools.py\u001b[0m in \u001b[0;36m_autolag\u001b[1;34m(mod, endog, exog, startlag, maxlag, method, modargs, fitargs, regresults)\u001b[0m\n\u001b[0;32m    122\u001b[0m     \u001b[0mmethod\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlower\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    123\u001b[0m     \u001b[1;32mfor\u001b[0m \u001b[0mlag\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstartlag\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstartlag\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mmaxlag\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 124\u001b[1;33m         \u001b[0mmod_instance\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmod\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mlag\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0mmodargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    125\u001b[0m         \u001b[0mresults\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mlag\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmod_instance\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    126\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\regression\\linear_model.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, missing, hasconst, **kwargs)\u001b[0m\n\u001b[0;32m    870\u001b[0m     def __init__(self, endog, exog=None, missing='none', hasconst=None,\n\u001b[0;32m    871\u001b[0m                  **kwargs):\n\u001b[1;32m--> 872\u001b[1;33m         super(OLS, self).__init__(endog, exog, missing=missing,\n\u001b[0m\u001b[0;32m    873\u001b[0m                                   hasconst=hasconst, **kwargs)\n\u001b[0;32m    874\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[1;34m\"weights\"\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_init_keys\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\regression\\linear_model.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, weights, missing, hasconst, **kwargs)\u001b[0m\n\u001b[0;32m    701\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    702\u001b[0m             \u001b[0mweights\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mweights\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msqueeze\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 703\u001b[1;33m         super(WLS, self).__init__(endog, exog, missing=missing,\n\u001b[0m\u001b[0;32m    704\u001b[0m                                   weights=weights, hasconst=hasconst, **kwargs)\n\u001b[0;32m    705\u001b[0m         \u001b[0mnobs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexog\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\regression\\linear_model.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, **kwargs)\u001b[0m\n\u001b[0;32m    188\u001b[0m     \"\"\"\n\u001b[0;32m    189\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 190\u001b[1;33m         \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mRegressionModel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    191\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_data_attr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'pinv_wexog'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'weights'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    192\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\model.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, **kwargs)\u001b[0m\n\u001b[0;32m    235\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    236\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m         \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mLikelihoodModel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    238\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minitialize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    239\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\model.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, **kwargs)\u001b[0m\n\u001b[0;32m     75\u001b[0m         \u001b[0mmissing\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'missing'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'none'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     76\u001b[0m         \u001b[0mhasconst\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'hasconst'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 77\u001b[1;33m         self.data = self._handle_data(endog, exog, missing, hasconst,\n\u001b[0m\u001b[0;32m     78\u001b[0m                                       **kwargs)\n\u001b[0;32m     79\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mk_constant\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mk_constant\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\model.py\u001b[0m in \u001b[0;36m_handle_data\u001b[1;34m(self, endog, exog, missing, hasconst, **kwargs)\u001b[0m\n\u001b[0;32m     99\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    100\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_handle_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmissing\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhasconst\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 101\u001b[1;33m         \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mhandle_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmissing\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhasconst\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    102\u001b[0m         \u001b[1;31m# kwargs arrays could have changed, easier to just attach here\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    103\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\data.py\u001b[0m in \u001b[0;36mhandle_data\u001b[1;34m(endog, exog, missing, hasconst, **kwargs)\u001b[0m\n\u001b[0;32m    670\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    671\u001b[0m     \u001b[0mklass\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mhandle_data_class_factory\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mendog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexog\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 672\u001b[1;33m     return klass(endog, exog=exog, missing=missing, hasconst=hasconst,\n\u001b[0m\u001b[0;32m    673\u001b[0m                  **kwargs)\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\data.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, endog, exog, missing, hasconst, **kwargs)\u001b[0m\n\u001b[0;32m     85\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconst_idx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     86\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mk_constant\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 87\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_handle_constant\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mhasconst\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     88\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_check_integrity\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     89\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_cache\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\statsmodels\\base\\data.py\u001b[0m in \u001b[0;36m_handle_constant\u001b[1;34m(self, hasconst)\u001b[0m\n\u001b[0;32m    131\u001b[0m             \u001b[0mexog_max\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    132\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misfinite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mexog_max\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mall\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 133\u001b[1;33m                 \u001b[1;32mraise\u001b[0m \u001b[0mMissingDataError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'exog contains inf or nans'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    134\u001b[0m             \u001b[0mexog_min\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexog\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    135\u001b[0m             \u001b[0mconst_idx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwhere\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mexog_max\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mexog_min\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msqueeze\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mMissingDataError\u001b[0m: exog contains inf or nans"
     ]
    }
   ],
   "source": [
    "from statsmodels.tsa.stattools import adfuller\n",
    "X2 = price_tsla['log_return'].values\n",
    "result2 = adfuller(X2)\n",
    "print('ADF Statistic: %f' % result2[0])\n",
    "print('p-value: %f' % result2[1])\n",
    "print('Critical Values:')\n",
    "for key, value in result2[4].items():\n",
    "\tprint('\\t%s: %.3f' % (key, value))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "price_tsla['log_return'].isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ADF Statistic: -55.582081\n",
      "p-value: 0.000000\n",
      "Critical Values:\n",
      "\t1%: -3.432\n",
      "\t5%: -2.862\n",
      "\t10%: -2.567\n"
     ]
    }
   ],
   "source": [
    "#Ignore the first value which is null.\n",
    "from statsmodels.tsa.stattools import adfuller\n",
    "X2 = price_tsla['log_return'][1:].values\n",
    "result2 = adfuller(X2)\n",
    "print('ADF Statistic: %f' % result2[0])\n",
    "print('p-value: %f' % result2[1])\n",
    "print('Critical Values:')\n",
    "for key, value in result2[4].items():\n",
    "\tprint('\\t%s: %.3f' % (key, value))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since the p-value of ADF test is less than 0.05, the null hypothesis that the series \"log_return\" has a unit root problem is rejected. Hence, the \"log_return\" series does not have a unit root problem. log_return is stationary."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3.2 Using the library seaborn to plot the distribution of TESLA log returns. [10 points]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x16e396b3a00>"
      ]
     },
     "execution_count": 181,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(price_tsla, x=\"log_return\")"
   ]
  }
 ],
 "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": 4
}