test.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2018-07-19T19:04:58-05:00\n",
      "\n",
      "CPython 3.6.5\n",
      "IPython 6.4.0\n",
      "\n",
      "compiler   : MSC v.1900 64 bit (AMD64)\n",
      "system     : Windows\n",
      "release    : 10\n",
      "machine    : AMD64\n",
      "processor  : AMD64 Family 21 Model 112 Stepping 0, AuthenticAMD\n",
      "CPU cores  : 2\n",
      "interpreter: 64bit\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams['figure.figsize']=(12,12)\n",
    "plt.rcParams['font.size']=16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " El volumen de la unidad C no tiene etiqueta.\n",
      " El número de serie del volumen es: C893-DDFA\n",
      "\n",
      " Directorio de C:\\Users\\jmartinez\\Desktop\\Escritorio2\\AnacondaJC\n",
      "\n",
      "19/07/2018  07:08 p. m.    <DIR>          .\n",
      "19/07/2018  07:08 p. m.    <DIR>          ..\n",
      "19/07/2018  07:04 p. m.    <DIR>          .ipynb_checkpoints\n",
      "07/07/2018  06:59 p. m.    <DIR>          curso_data_science-master\n",
      "17/07/2018  09:22 p. m.            10,557 ejercicio.ipynb\n",
      "12/07/2018  11:54 p. m.             6,603 phyton y numpy.ipynb\n",
      "12/07/2018  11:17 p. m.             2,568 primer programa con jupyter.ipynb\n",
      "13/07/2018  12:06 a. m.             2,963 Untitled.ipynb\n",
      "19/07/2018  07:08 p. m.             1,510 Untitled1.ipynb\n",
      "17/07/2018  02:46 p. m.        16,848,926 vehicles.csv\n",
      "18/07/2018  09:29 a. m.         1,468,901 vehicles.csv.zip\n",
      "17/07/2018  09:15 p. m.         4,269,212 vehiculos-original.csv\n",
      "17/07/2018  09:08 p. m.         1,199,229 watermarrk.ipynb\n",
      "16/07/2018  05:25 p. m.           224,831 wcp.png\n",
      "              10 archivos     24,035,300 bytes\n",
      "               4 dirs  720,719,024,128 bytes libres\n"
     ]
    }
   ],
   "source": [
    "ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "vehiculos=pd.read_csv(\"C:/Users/jmartinez/Desktop/Escritorio2/AnacondaJC/curso_data_science-master/Secciones/Seccion5.Machine_Learning/Regresion_Lineal_practica/data/vehiculos_procesado.csv\",\n",
    "                      usecols=[\"consumo\",\"co2\",\"cilindros\",\"desplazamiento\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "litros_por_galon=3.78541"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "vehiculos[\"consumo_litos_milla\"]=litros_por_galon/vehiculos.consumo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(35539, 5)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vehiculos.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>desplazamiento</th>\n",
       "      <th>cilindros</th>\n",
       "      <th>consumo</th>\n",
       "      <th>co2</th>\n",
       "      <th>consumo_litos_milla</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>17</td>\n",
       "      <td>522.764706</td>\n",
       "      <td>0.222671</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>13</td>\n",
       "      <td>683.615385</td>\n",
       "      <td>0.291185</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>16</td>\n",
       "      <td>555.437500</td>\n",
       "      <td>0.236588</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   desplazamiento  cilindros  consumo         co2  consumo_litos_milla\n",
       "0             2.5        4.0       17  522.764706             0.222671\n",
       "1             4.2        6.0       13  683.615385             0.291185\n",
       "2             2.5        4.0       16  555.437500             0.236588"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vehiculos.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "pct_entrenamiento=0.8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "vehiculos_training=vehiculos.sample(frac=pct_entrenamiento)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "vehiculos_test=vehiculos[~vehiculos.index.isin(vehiculos_training.index)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(28431, 5)\n"
     ]
    }
   ],
   "source": [
    "print(vehiculos_training.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(7108, 5)\n"
     ]
    }
   ],
   "source": [
    "print(vehiculos_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "variables_independientes=[\"desplazamiento\",\"cilindros\",\"consumo_litos_milla\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "variable_dependiente=\"co2\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jmartinez\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "X = vehiculos_training[variables_independientes].as_matrix()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jmartinez\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "Y = vehiculos_training[variable_dependiente].as_matrix()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_T = X.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[3.1       , 6.        , 0.21030056],\n",
       "       [5.        , 8.        , 0.27038643],\n",
       "       [4.3       , 6.        , 0.25236067],\n",
       "       ...,\n",
       "       [3.3       , 6.        , 0.18025762],\n",
       "       [4.3       , 6.        , 0.23658813],\n",
       "       [3.        , 6.        , 0.22267118]])"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "betas = np.linalg.inv(X_T@X)@X_T@Y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 3.74255395e+00, -5.40919129e-01,  2.30466918e+03])"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "betas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "470.6694731294241"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jmartinez\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.36737696715539414"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "alfa=Y.mean()-np.dot(betas,vehiculos_training[variables_independientes].mean().as_matrix())\n",
    "alfa"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predecir(r):\n",
    "    return alfa + np.dot(betas, r.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}