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.
149 lines
3.5 KiB
149 lines
3.5 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from Medio import *\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"medi = Medio(None,None)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#medi.create_hklDB_from_csv('mediowords.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": [
|
|
"medi.load_DB_into_FASTsearch()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"sentences = [['das', 'ist', 'Kindersprache'],['er', 'ging', 'über', 'die', 'Straße'], ['halt', 'ab', 'hier']]\n",
|
|
"punctuations = ['.', '!', '.']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"mediosofsentence ['das', 'ist', 'Kindersprache']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Kindersprache']\n",
|
|
"medioeintrag ['Kinder·sprache']\n",
|
|
"medioeintraege [['Kindersprache', ['Kinder·sprache']]]\n",
|
|
"mediosofsentence ['er', 'ging', 'über', 'die', 'Straße']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"medioeintraege []\n",
|
|
"mediosofsentence ['halt', 'ab', 'hier']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"['Oberbuergermeister']\n",
|
|
"medioeintrag ['Ober·buerger·meister']\n",
|
|
"medioeintraege []\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"outsentences, punctuations = medi.Medioreplace(sentences, punctuations)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[['das', 'ist', ['Kinder·sprache']], ['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
|
|
}
|