{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Importación de archivos numéricos usando NumPy --- 6:53 min\n",
    "===\n",
    "\n",
    "* 6:53 min | Última modificación: Octubre 13, 2021 | [YouTube](https://youtu.be/3-jElszJ3nU)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting /tmp/numpy_data.txt\n"
     ]
    }
   ],
   "source": [
    "%%writefile /tmp/numpy_data.txt\n",
    "7.318719402026263587e-02 1.775082190597712106e-01 9.205824952147805273e-01\n",
    "4.062207718332084827e-01 6.691909950327930012e-01 4.691625868153078693e-01\n",
    "6.963794427590925817e-01 1.380183788805662282e-01 8.086264398068685466e-01\n",
    "5.893088349077085786e-01 3.899639085394711602e-01 8.655591960123206752e-01"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.07318719, 0.17750822, 0.9205825 ],\n",
       "       [0.40622077, 0.669191  , 0.46916259],\n",
       "       [0.69637944, 0.13801838, 0.80862644],\n",
       "       [0.58930883, 0.38996391, 0.8655592 ]])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Lectura del archivo de texto\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.loadtxt('/tmp/numpy_data.txt')\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cantidad de datos leidos\n",
    "#\n",
    "numpy_data.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting /tmp/comma_delimited_data.txt\n"
     ]
    }
   ],
   "source": [
    "%%writefile /tmp/comma_delimited_data.txt\n",
    "1,2,3\n",
    "4,5,6\n",
    "7,8,9\n",
    "10,11,12"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.,  2.,  3.],\n",
       "       [ 4.,  5.,  6.],\n",
       "       [ 7.,  8.,  9.],\n",
       "       [10., 11., 12.]])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Lectura de un archivo delimitado por comas\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.loadtxt(\n",
    "    \"/tmp/comma_delimited_data.txt\",\n",
    "    delimiter=\",\",\n",
    ")\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.,  3.],\n",
       "       [ 4.,  6.],\n",
       "       [ 7.,  9.],\n",
       "       [10., 12.]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Selección de columnas a leer\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.loadtxt(\n",
    "    \"/tmp/comma_delimited_data.txt\",\n",
    "    delimiter=\",\",\n",
    "    usecols=(0, 2),\n",
    ")\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting /tmp/comma_delimited_data.txt\n"
     ]
    }
   ],
   "source": [
    "%%writefile /tmp/comma_delimited_data.txt\n",
    "col_A,col_B,col_C\n",
    "1,2,3\n",
    "4,5,6\n",
    "7,8,9\n",
    "10,11,12"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.,  2.,  3.],\n",
       "       [ 4.,  5.,  6.],\n",
       "       [ 7.,  8.,  9.],\n",
       "       [10., 11., 12.]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Lectura de un archivo con cabecera\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.loadtxt(\n",
    "    \"/tmp/comma_delimited_data.txt\",\n",
    "    delimiter=\",\",\n",
    "    skiprows=1,\n",
    ")\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3],\n",
       "       [ 4,  5,  6],\n",
       "       [ 7,  8,  9],\n",
       "       [10, 11, 12]], dtype=uint64)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Especificación del tipo de dato\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.loadtxt(\n",
    "    \"/tmp/comma_delimited_data.txt\",\n",
    "    delimiter=\",\",\n",
    "    skiprows=1,\n",
    "    dtype=np.uint,\n",
    ")\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[101,   2,   3],\n",
       "       [104,   5,   6],\n",
       "       [107,   8,   9],\n",
       "       [110,  11,  12]], dtype=uint64)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Aplicación de una función a una columna\n",
    "# ===============================================\n",
    "#\n",
    "\n",
    "\n",
    "def increase(id):\n",
    "    return int(id) + 100\n",
    "\n",
    "\n",
    "numpy_data = np.loadtxt(\n",
    "    \"/tmp/comma_delimited_data.txt\",\n",
    "    delimiter=\",\",\n",
    "    skiprows=1,\n",
    "    dtype=np.uint,\n",
    "    converters={0: increase},\n",
    ")\n",
    "\n",
    "numpy_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting /tmp/missing_data.txt\n"
     ]
    }
   ],
   "source": [
    "%%writefile /tmp/missing_data.txt\n",
    "1,,3\n",
    "4,5,6\n",
    "7,8,\n",
    "10,11,12"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1., nan,  3.],\n",
       "       [ 4.,  5.,  6.],\n",
       "       [ 7.,  8., nan],\n",
       "       [10., 11., 12.]])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Lectura de un archivo con datos faltantes\n",
    "# ===============================================\n",
    "#\n",
    "numpy_data = np.genfromtxt(\n",
    "    '/tmp/missing_data.txt',\n",
    "    delimiter=',',\n",
    ")\n",
    "numpy_data"
   ]
  }
 ],
 "metadata": {
  "kernel_info": {
   "name": "python3"
  },
  "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": "3.6.9"
  },
  "nteract": {
   "version": "0.12.3"
  },
  "toc-autonumbering": false,
  "toc-showcode": false,
  "toc-showmarkdowntxt": false,
  "toc-showtags": false
 },
 "nbformat": 4,
 "nbformat_minor": 4
}