basabuuka_prototyp/Prototyp/Use_Fremd_WB.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from FremdWB import *\n",
    "\n",
    "\n",
    "\n",
    "fwb = FremdWB(None,None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n",
      "2000\n",
      "creating the hkl dump of Fremd_WBDBAll\n",
      "done..\n",
      "Creating the hkl dump of Fremd_WBDB 1\n",
      "Creating the hkl dump of Fremd_WBDB 2\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'done'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fwb.create_hklDB_from_csv('HurrakiWoerterbuch_nodoubles.txt', 'None')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Creating the bag of words...\n",
      "\n",
      "dumping the data to hkl format..\n",
      "done\n",
      "Creating the bag of words...\n",
      "\n",
      "dumping the data to hkl format..\n",
      "done\n"
     ]
    }
   ],
   "source": [
    "fwb.load_DB_into_FASTsearch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "sentences = [['das', 'ist', 'Abfall'],['er', 'ging', 'über', 'die', 'Straße'], ['halt', 'ab', 'hier']]\n",
    "punctuations = ['.', '!', '.']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "outsentences, punctuations = fwb.fremdEintragAppend(sentences, punctuations)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[['das', 'ist', 'Abfall'], ['Abfall', 'sind', 'Sachen', 'die', 'wir', 'nicht', 'mehr', 'brauchen'], ['er', 'ging', 'über', 'die', 'Straße'], ['halt', 'ab', 'hier']] ['.', '.', '!', '.']\n"
     ]
    }
   ],
   "source": [
    "print(outsentences, punctuations)"
   ]
  },
  {
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}