Support por python object CSV serialization in python 2

python2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.7.6 |Continuum Analytics, Inc.| (default, May 27 2014, 14:50:58) \\n[GCC 4.1.2 20080704 (Red Hat 4.1.2-54)]'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import sys\n",
    "sys.version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "INSTALLED VERSIONS\n",
      "------------------\n",
      "commit: None\n",
      "python: 2.7.6.final.0\n",
      "python-bits: 64\n",
      "OS: Linux\n",
      "OS-release: 3.19.0-58-generic\n",
      "machine: x86_64\n",
      "processor: x86_64\n",
      "byteorder: little\n",
      "LC_ALL: None\n",
      "LANG: en_US.UTF-8\n",
      "\n",
      "pandas: 0.17.1\n",
      "nose: 1.3.7\n",
      "pip: 8.0.3\n",
      "setuptools: 20.1.1\n",
      "Cython: 0.23.4\n",
      "numpy: 1.10.4\n",
      "scipy: 0.17.0\n",
      "statsmodels: None\n",
      "IPython: 4.0.2\n",
      "sphinx: None\n",
      "patsy: None\n",
      "dateutil: 2.4.2\n",
      "pytz: 2015.7\n",
      "blosc: 1.2.8\n",
      "bottleneck: None\n",
      "tables: 3.2.2\n",
      "numexpr: 2.5.2\n",
      "matplotlib: 1.5.1\n",
      "openpyxl: None\n",
      "xlrd: 0.9.4\n",
      "xlwt: None\n",
      "xlsxwriter: None\n",
      "lxml: None\n",
      "bs4: 4.4.1\n",
      "html5lib: None\n",
      "httplib2: None\n",
      "apiclient: None\n",
      "sqlalchemy: 1.0.5\n",
      "pymysql: None\n",
      "psycopg2: 2.6.1 (dt dec pq3 ext)\n",
      "Jinja2: None\n"
     ]
    }
   ],
   "source": [
    "pd.show_versions()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Unicode json lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"first_name\":\"Manuel\", \"last_name\":\"Garrido Peña\",\"experience\":[{\"name\":\"Peña Industries\", \"start\":\"May 2014\"}]}\r\n",
      "{\"first_name\":\"Ana\", \"last_name\":\"Cañón\", \"experience\":[{\"name\":\"Cañón technologies\",\"start\":\"April 2016\"}]}\r\n"
     ]
    }
   ],
   "source": [
    "cat test.jl"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We load the jl with pandas, then save to csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>experience</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[{u'start': u'May 2014', u'name': u'Peña Indus...</td>\n",
       "      <td>Manuel</td>\n",
       "      <td>Garrido Peña</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[{u'start': u'April 2016', u'name': u'Cañón te...</td>\n",
       "      <td>Ana</td>\n",
       "      <td>Cañón</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          experience first_name     last_name\n",
       "0  [{u'start': u'May 2014', u'name': u'Peña Indus...     Manuel  Garrido Peña\n",
       "1  [{u'start': u'April 2016', u'name': u'Cañón te...        Ana         Cañón"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with open('test.jl') as fname:\n",
    "    lines = fname.readlines()\n",
    "    df = pd.DataFrame([json.loads(l) for l in lines])\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    [{u'start': u'May 2014', u'name': u'Peña Indus...\n",
       "1    [{u'start': u'April 2016', u'name': u'Cañón te...\n",
       "Name: experience, dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.experience"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df.to_csv('test_p2c.csv',index=False, encoding='utf8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "experience,first_name,last_name\r\n",
      "\"[{u'start': u'May 2014', u'name': u'Peña Industries'}]\",Manuel,Garrido Peña\r\n",
      "\"[{u'start': u'April 2016', u'name': u'Cañón technologies'}]\",Ana,Cañón\r\n"
     ]
    }
   ],
   "source": [
    "cat test_p2c.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/manuel/anaconda3/envs/exporters/lib/python2.7/site-packages/ipykernel/__main__.py:1: FutureWarning: 'engine' keyword is deprecated and will be removed in a future version\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "df.to_csv('test_p2p.csv',index=False, encoding='utf8',engine='python')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "experience,first_name,last_name\r\n",
      "\"[{u'start': u'May 2014', u'name': u'Peña Industries'}]\",Manuel,Garrido Peña\r\n",
      "\"[{u'start': u'April 2016', u'name': u'Cañón technologies'}]\",Ana,Cañón\r\n"
     ]
    }
   ],
   "source": [
    "cat test_p2.csv"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

python3.ipynb

test.jl

{"first_name":"Manuel", "last_name":"Garrido Peña","experience":[{"name":"Peña Industries", "start":"May 2014"}]}
{"first_name":"Ana", "last_name":"Cañón", "experience":[{"name":"Cañón technologies","start":"April 2016"}]}

test_p2.csv

test_p2c.csv

test_p3.csv

test_p3c.csv