Linear_Simples.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>tempo</th>\n",
       "      <th>vendas</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tempo  vendas\n",
       "0      1      91\n",
       "1      3     110\n",
       "2      4     106\n",
       "3      4     116\n",
       "4      6     119"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset = {\"tempo\":[1,3,4,4,6,8,10,10,11,13],\n",
    "           \"vendas\":[91,110,106,116,119,129,139,143,138,159]}\n",
    "\n",
    "dataset = pd.DataFrame(dataset)\n",
    "dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from pandas.io.sql import DatabaseError\n",
    "ax = sns.lineplot(data=dataset, x='tempo', y='vendas')\n",
    "ax.figure.set_size_inches(12,6)\n",
    "ax.figure.suptitle('Reta de regressão - Tempo X Vendas', fontsize=16, y=1.02)\n",
    "ax.set_xlabel('Tempo de experiência', fontsize=14)\n",
    "ax.set_ylabel('Vendas', fontsize=14)\n",
    "ax;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>tempo</th>\n",
       "      <th>vendas</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>tempo</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.976883</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>vendas</th>\n",
       "      <td>0.976883</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           tempo    vendas\n",
       "tempo   1.000000  0.976883\n",
       "vendas  0.976883  1.000000"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import statsmodels.api as sm\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = dataset.vendas\n",
    "x = sm.add_constant(dataset.tempo)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "rr = sm.OLS(y,x).fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 vendas   R-squared:                       0.954\n",
      "Model:                            OLS   Adj. R-squared:                  0.949\n",
      "Method:                 Least Squares   F-statistic:                     167.1\n",
      "Date:                Fri, 07 Jun 2024   Prob (F-statistic):           1.22e-06\n",
      "Time:                        15:12:40   Log-Likelihood:                -28.355\n",
      "No. Observations:                  10   AIC:                             60.71\n",
      "Df Residuals:                       8   BIC:                             61.32\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         90.0000      3.075     29.265      0.000      82.908      97.092\n",
      "tempo          5.0000      0.387     12.925      0.000       4.108       5.892\n",
      "==============================================================================\n",
      "Omnibus:                        0.928   Durbin-Watson:                   3.224\n",
      "Prob(Omnibus):                  0.629   Jarque-Bera (JB):                0.616\n",
      "Skew:                          -0.060   Prob(JB):                        0.735\n",
      "Kurtosis:                       1.790   Cond. No.                         17.0\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Usuario\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\scipy\\stats\\_axis_nan_policy.py:531: UserWarning: kurtosistest only valid for n>=20 ... continuing anyway, n=10\n",
      "  res = hypotest_fun_out(*samples, **kwds)\n"
     ]
    }
   ],
   "source": [
    "print(rr.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>tempo</th>\n",
       "      <th>vendas</th>\n",
       "      <th>y_previsto</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>91</td>\n",
       "      <td>95.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>110</td>\n",
       "      <td>105.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>106</td>\n",
       "      <td>110.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>116</td>\n",
       "      <td>110.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>119</td>\n",
       "      <td>120.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tempo  vendas  y_previsto\n",
       "0      1      91        95.0\n",
       "1      3     110       105.0\n",
       "2      4     106       110.0\n",
       "3      4     116       110.0\n",
       "4      6     119       120.0"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset['y_previsto'] = rr.predict()\n",
    "dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>tempo</th>\n",
       "      <th>vendas</th>\n",
       "      <th>y_previsto</th>\n",
       "      <th>erro</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>91</td>\n",
       "      <td>95.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>110</td>\n",
       "      <td>105.0</td>\n",
       "      <td>-5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>106</td>\n",
       "      <td>110.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>116</td>\n",
       "      <td>110.0</td>\n",
       "      <td>-6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>119</td>\n",
       "      <td>120.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tempo  vendas  y_previsto  erro\n",
       "0      1      91        95.0   4.0\n",
       "1      3     110       105.0  -5.0\n",
       "2      4     106       110.0   4.0\n",
       "3      4     116       110.0  -6.0\n",
       "4      6     119       120.0   1.0"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset['erro'] = dataset['y_previsto'] - dataset['vendas']\n",
    "dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}