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.
251 lines
4.7 KiB
251 lines
4.7 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "raw",
|
|
"metadata": {},
|
|
"source": [
|
|
" Zuerst wird die Klasse SayYes importiert und initialisiert"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"loading the german spacy model..\n",
|
|
"done\n",
|
|
"loading the stemmer..\n",
|
|
"done\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from SayYes import *\n",
|
|
"\n",
|
|
"sy = SayYes(None, None)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "raw",
|
|
"metadata": {},
|
|
"source": [
|
|
"Nun werden die Datenbanken in den Arbeitsspeicher geladen."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Loading the hklDB1..\n",
|
|
"done\n",
|
|
"Loading the hklDB2\n",
|
|
"done\n",
|
|
"loading hkldbOpposites 1..\n",
|
|
"done\n",
|
|
"loading hkldbOpposites 2..\n",
|
|
"done\n",
|
|
"loading the bow model 1\n",
|
|
"done\n",
|
|
"loading the bow model 2\n",
|
|
"done\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"\n",
|
|
"#sy.create_hklDB_from_csv('Gegenwoerter.csv')\n",
|
|
"\n",
|
|
"#print(sy.hkldbOpposites1)\n",
|
|
"\n",
|
|
"sy.load_DB_into_FASTsearch()\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "raw",
|
|
"metadata": {},
|
|
"source": [
|
|
"Hier wird die Datei atest1 eingeladen, Output der Funktion ReadDoc2Sent sind die Sätze in Listen. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from oi import *\n",
|
|
"oi = oi()\n",
|
|
"sentences, punctuations = oi.ReadDoc2Sent('atest1')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "raw",
|
|
"metadata": {},
|
|
"source": [
|
|
"Hier werden nun die Sätze nach den Wörtern 'nicht' oder 'kein/keine' durchsucht, diesess dann entfernt und das entsprechende Wort durch dessen Gegenteil ersetzt."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"wenigstens etwas\n",
|
|
"oloa\n",
|
|
"processing sentence 1\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 2\n",
|
|
"ola\n",
|
|
"thetheone\n",
|
|
"oloa\n",
|
|
"processing sentence 3\n",
|
|
"ola\n",
|
|
"thetheone\n",
|
|
"oloa\n",
|
|
"processing sentence 4\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 5\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 6\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 7\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 8\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 9\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 10\n",
|
|
"ola\n",
|
|
"thetheone\n",
|
|
"theone\n",
|
|
"1\n",
|
|
"2\n",
|
|
"2\n",
|
|
"oloa\n",
|
|
"processing sentence 11\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 12\n",
|
|
"ola\n",
|
|
"oloa\n",
|
|
"processing sentence 13\n",
|
|
"ola\n",
|
|
"thetheone\n",
|
|
"theone\n",
|
|
"1\n",
|
|
"2\n",
|
|
"2\n",
|
|
"oloa\n",
|
|
"processing sentence 14\n",
|
|
"ola\n",
|
|
"thetheone\n",
|
|
"theone\n",
|
|
"1\n",
|
|
"4\n",
|
|
"2\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"outsentences = sy.replaceOpposites(sentences)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "raw",
|
|
"metadata": {},
|
|
"source": [
|
|
"Das Ergebnis der vorherigen Funktion wird in der folgenden Zeile in das Dokument atest1out geschrieben."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n",
|
|
".\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'OK'"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"oi.PrintSplitSentencesToTextFile(punctuations, outsentences, 'atest1out')"
|
|
]
|
|
},
|
|
{
|
|
"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": 4
|
|
}
|