SO: Pandas gives an error from str.extractall('#')

Answer

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3.5.1 (default, Dec 26 2015, 18:11:22) \n",
      "[GCC 4.2.1 Compatible Apple LLVM 7.0.2 (clang-700.1.81)]\n",
      "Pandas:  0.18.1\n"
     ]
    }
   ],
   "source": [
    "# Version info\n",
    "import sys\n",
    "print(sys.version)\n",
    "print('Pandas: ', pd.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Sample data\n",
    "data=\"\"\"01, home #sweet home\n",
    "01, #happy #life \n",
    "02, #world peace\n",
    "03, #all are one\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from io import StringIO"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(StringIO(data), \n",
    "                 header=None, \n",
    "                 names=['col1', 'col2'],\n",
    "                 index_col=0)"
   ]
  },
  {
   "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>col2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>col1</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>home #sweet home</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>#happy #life</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>#world peace</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>#all are one</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   col2\n",
       "col1                   \n",
       "1      home #sweet home\n",
       "1         #happy #life \n",
       "2          #world peace\n",
       "3          #all are one"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>col1</th>\n",
       "      <th>match</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>s</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>h</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>l</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>w</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            0\n",
       "col1 match   \n",
       "1    0      s\n",
       "     0      h\n",
       "     1      l\n",
       "2    0      w\n",
       "3    0      a"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This should work (will only output the first character of each match)\n",
    "df['col2'].str.extractall('#(\\S)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "AssertionError",
     "evalue": "1 columns passed, passed data had 6 columns",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-8-4792d3b6c94f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# This won't work due to a bug\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'col2'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'(#\\S+)'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/strings.py\u001b[0m in \u001b[0;36mextractall\u001b[0;34m(self, pat, flags)\u001b[0m\n\u001b[1;32m   1619\u001b[0m     \u001b[0;34m@\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstr_extractall\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1620\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mextractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpat\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1621\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mstr_extractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_orig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpat\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1622\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1623\u001b[0m     _shared_docs['find'] = (\"\"\"\n",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/strings.py\u001b[0m in \u001b[0;36mstr_extractall\u001b[0;34m(arr, pat, flags)\u001b[0m\n\u001b[1;32m    714\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    715\u001b[0m         \u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 716\u001b[0;31m     \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmatch_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    717\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    718\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[1;32m    261\u001b[0m                     \u001b[0;32mif\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_named_tuple\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    262\u001b[0m                         \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_fields\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 263\u001b[0;31m                     \u001b[0marrays\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_to_arrays\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    264\u001b[0m                     \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_ensure_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    265\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_to_arrays\u001b[0;34m(data, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m   5350\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtuple\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5351\u001b[0m         return _list_to_arrays(data, columns, coerce_float=coerce_float,\n\u001b[0;32m-> 5352\u001b[0;31m                                dtype=dtype)\n\u001b[0m\u001b[1;32m   5353\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcollections\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMapping\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5354\u001b[0m         return _list_of_dict_to_arrays(data, columns,\n",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_list_to_arrays\u001b[0;34m(data, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m   5429\u001b[0m         \u001b[0mcontent\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_object_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mT\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5430\u001b[0m     return _convert_object_array(content, columns, dtype=dtype,\n\u001b[0;32m-> 5431\u001b[0;31m                                  coerce_float=coerce_float)\n\u001b[0m\u001b[1;32m   5432\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5433\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_convert_object_array\u001b[0;34m(content, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m   5487\u001b[0m             \u001b[0;31m# caller's responsibility to check for this...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5488\u001b[0m             raise AssertionError('%d columns passed, passed data had %s '\n\u001b[0;32m-> 5489\u001b[0;31m                                  'columns' % (len(columns), len(content)))\n\u001b[0m\u001b[1;32m   5490\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5491\u001b[0m     \u001b[0;31m# provide soft conversion of object dtypes\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mAssertionError\u001b[0m: 1 columns passed, passed data had 6 columns"
     ]
    }
   ],
   "source": [
    "# This won't work due to a bug\n",
    "df['col2'].str.extractall('(#\\S+)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

Notebook viewer link