multiple-csv-merge.ipynb

multiple-csv-merge.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# imports\n",
    "import os\n",
    "import glob\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# create dataframes\n",
    "df1 = pd.DataFrame([['a', 1], ['b', 2]], columns=['letter', 'number'])\n",
    "df2 = pd.DataFrame([['c', 3], ['d', 4]], columns=['letter', 'number'])\n",
    "df3 = pd.DataFrame([['c', 3, 'cat'], ['d', 4, 'dog']], columns=['letter', 'number', 'animal'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# save dataframes to csv\n",
    "df1.to_csv('df1.csv', index=False)\n",
    "df2.to_csv('df2.csv', index=False)\n",
    "df3.to_csv('df3.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['./df1.csv', './df2.csv', './df3.csv']\n"
     ]
    }
   ],
   "source": [
    "# set path and get csv files\n",
    "path = r'.'\n",
    "all_files = glob.glob(os.path.join(path, \"*.csv\"))\n",
    "print(all_files)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   number  number  number animal\n",
      "a     1.0     NaN     NaN    NaN\n",
      "b     2.0     NaN     NaN    NaN\n",
      "c     NaN     3.0     3.0    cat\n",
      "d     NaN     4.0     4.0    dog\n"
     ]
    }
   ],
   "source": [
    "# read each csv file, set index, and concatenate based on index\n",
    "df_from_each_file = (pd.read_csv(f, index_col='letter') for f in all_files)\n",
    "concatenated_df = pd.concat(df_from_each_file, axis=1)\n",
    "print(concatenated_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.6",
   "language": "python",
   "name": "python36"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}