You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
154 lines
4.5 KiB
154 lines
4.5 KiB
{
|
|
"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": [],
|
|
"source": [
|
|
"#fwb.create_hklDB_from_csv('HurrakiWoerterbuch_nodoubles.txt', 'None')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"generating BoW Model 1..\n",
|
|
"Creating the bag of words...\n",
|
|
"\n",
|
|
"dumping the data to hkl format..\n",
|
|
"done\n",
|
|
"generating BoW Model 2..\n",
|
|
"Creating the bag of words...\n",
|
|
"\n",
|
|
"dumping the data to hkl format..\n",
|
|
"done\n",
|
|
"loading the bow model 1\n",
|
|
"loading the bow model 2\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": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"something\n",
|
|
"sentence ['das', 'ist', 'Abfall']\n",
|
|
"['ist', 'Abfall']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"['Abfall']\n",
|
|
"fremdeintrag ['Abfall', 'sind', 'Sachen', 'die', 'wir', 'nicht', 'mehr', 'brauchen.']\n",
|
|
"fremdeintraege [['Abfall', 'sind', 'Sachen', 'die', 'wir', 'nicht', 'mehr', 'brauchen.']]\n",
|
|
"sentence ['er', 'ging', 'über', 'die', 'Straße']\n",
|
|
"['ging', 'über', 'die', 'Straße']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"['Enzyklopädie']\n",
|
|
"fremdeintrag ['Enzyklopädie', 'ist', 'ein', 'anderes', 'Wort', 'für', 'Lexikon.', 'In', 'einer', 'Enzyklopädie', 'findet', 'man', 'Informationen.']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"fremdeintraege []\n",
|
|
"sentence ['halt', 'ab', 'hier']\n",
|
|
"['halt', 'ab', 'hier']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"['Zyprer']\n",
|
|
"fremdeintrag ['Ein', 'Zyprer', 'oder', 'eine', 'Zyprerin', 'ist', 'ein', 'Mensch.', 'Dieser', 'Mensch', 'lebt', 'auf', 'der', 'Insel', 'Zypern.']\n",
|
|
"fremdeintraege []\n"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|