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.
241 lines
6.5 KiB
241 lines
6.5 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import SentSeg\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[[['Die', 'Frau', 'von', 'den', 'Bergen', 'ist', 'eine', 'gute', 'Partie.']], [['Es', 'war', 'die', 'Frau', 'mit', 'den', 'Klauen,', 'die', 'ein', 'größeres', 'Problem', 'mit', 'der', 'Geschichte', 'hatte.']]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"sent_seg = SentSeg.SentSeg('de')\n",
|
|
"\n",
|
|
" \n",
|
|
"sentences = sent_seg.ReadDoc2Sent('atest1')\n",
|
|
"print(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'done'"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"sent_seg.LoadSentGlueSGDandGSUtils()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"creating array of comma or not..\n",
|
|
"done\n",
|
|
"[[['Hallo', 'was', 'gehe', 'denn', 'hier', 'so.'], [0, ['Hallo']], [0, ['Hallo']], [0, ['Hallo']]], [['Ich', 'habe', 'echt', 'keine', 'Ahnung', 'verdammt.'], [0, ['Ich']], [0, ['Ich']], [0, ['Ich']]], [['I.', 'd.', 'R.', 'gibt', 'es', 'keine', 'Abschiebungen.'], [0, ['I.']], [0, ['I.']], [0, ['I.']]], [['Ende', 'd.', 'J.', 'wird', 'alles', 'problematisch.'], [0, ['Ende']], [0, ['Ende']], [0, ['Ende']]], [['Sie', 'gingen', 'nach', 'Hause,', 'weil', 'es', 'in', 'Strömen', 'regnete.'], [1, ['Sie', 'weil']], [1, ['Sie', 'weil']], [1, ['Sie', 'weil']]], [['Heute', 'war', 'die', 'Straße', 'blau', 'angemalt,', 'damit', 'der', 'Marathon', 'funktionierte.'], [1, ['Heute', 'damit']], [1, ['Heute', 'damit']], [1, ['Heute', 'damit']]], [['Er', 'habe', 'es', 'sehr', 'schwer.'], [0, ['Er']], [0, ['Er']], [0, ['Er']]], [['Es', 'war', 'die', 'Hose', 'des', 'Gauners.'], [0, ['Es']], [0, ['Es']], [0, ['Es']]], [['Bliblablub.'], [0, ['Bliblablub']], [0, ['Bliblablub']], [0, ['Bliblablub']]], [['Sie', 'ist', 'nicht', 'schön', 'heute.'], [0, ['Sie']], [0, ['Sie']], [0, ['Sie']]], [['Oleoleole.'], [0, ['Oleoleole']], [0, ['Oleoleole']], [0, ['Oleoleole']]], [['Mannoman.'], [0, ['Mannoman']], [0, ['Mannoman']], [0, ['Mannoman']]], [['Er', 'ginge', 'nicht', 'schnell.'], [0, ['Er']], [0, ['Er']], [0, ['Er']]], [['Die', 'Hühner', 'lieben', 'sich', 'nicht.'], [0, ['Die']], [0, ['Die']], [0, ['Die']]]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"sentences = sent_seg.putAppendixesIntoOwnSentences(sentences, punctuations)\n",
|
|
"print(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"sentences = sent_seg.GetUtteranceNumber(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"sentences = sent_seg.GetQuestionOrNot(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"importing spacy..\n",
|
|
"done\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"sentences1 = sent_seg.SplitSentencesIntoHauptNebenTuple(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"['es', 'regnete', 'in Strömen']\n",
|
|
"['deswegen', 'Sie', 'gingen', 'nach Hause']\n",
|
|
"['Heute', 'war', 'blau', 'angemalt', 'die Straße']\n",
|
|
"100\n",
|
|
"['dann', 'funktionierte', 'der Marathon']\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"outsentences = sent_seg.SplitCommatas(sentences1)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[['Hallo', 'was', 'gehe', 'denn', 'hier', 'so'], ['Ich', 'habe', 'echt', 'keine', 'Ahnung', 'verdammt'], ['I.', 'd.', 'R.', 'gibt', 'es', 'keine', 'Abschiebungen'], ['Ende', 'd.', 'J.', 'wird', 'alles', 'problematisch'], ['in', 'Strömen', 'regnete', 'e'], ['deswegen', 'gingen', 'Sie', 'nach', 'Haus'], ['angemalt', 'war', 'die', 'Straße', 'blau', 'Heut'], ['dann', 'der', 'Marathon', 'funktioniert'], ['Er', 'habe', 'es', 'sehr', 'schwer'], ['Es', 'war', 'die', 'Hose', 'des', 'Gauners'], ['Bliblablub'], ['Oleoleole'], ['Mannoman'], ['Er', 'ginge', 'nicht', 'schnell'], ['Der', 'Satz', 'davor', 'funktioniert', 'nicht', 'im', 'Modul', 'Konjunktsolve'], ['Weil', 'er', 'zu', 'viele', 'verben', 'hat']]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(outsentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 19,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"punctuations = []\n",
|
|
"for n in range(len(outsentences)):\n",
|
|
" punctuations.append('.')\n",
|
|
" if outsentences[n][-1][-1] == '.':\n",
|
|
" outsentences[n][-1] = outsentences[n][-1][:-1]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from oi import *\n",
|
|
"oi = oi()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'OK'"
|
|
]
|
|
},
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"oi.PrintSplitSentencesToTextFile(punctuations, outsentences, 'test1out')\n"
|
|
]
|
|
},
|
|
{
|
|
"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
|
|
}
|