Skip to content

Commit 11b37bb

Browse files
ychoi-krychoi-kr
committed
Create examples for 2.3.1
1 parent fbf38fb commit 11b37bb

File tree

3 files changed

+799
-0
lines changed

3 files changed

+799
-0
lines changed

‎2.NLP_PREP/2.3.1.1.nltk.ipynb

Lines changed: 339 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,339 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {},
7+
"outputs": [
8+
{
9+
"name": "stderr",
10+
"output_type": "stream",
11+
"text": [
12+
"[nltk_data] Downloading collection 'all-corpora'\n",
13+
"[nltk_data] | \n",
14+
"[nltk_data] | Downloading package abc to\n",
15+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
16+
"[nltk_data] | Package abc is already up-to-date!\n",
17+
"[nltk_data] | Downloading package alpino to\n",
18+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
19+
"[nltk_data] | Package alpino is already up-to-date!\n",
20+
"[nltk_data] | Downloading package biocreative_ppi to\n",
21+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
22+
"[nltk_data] | Package biocreative_ppi is already up-to-date!\n",
23+
"[nltk_data] | Downloading package brown to\n",
24+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
25+
"[nltk_data] | Package brown is already up-to-date!\n",
26+
"[nltk_data] | Downloading package brown_tei to\n",
27+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
28+
"[nltk_data] | Package brown_tei is already up-to-date!\n",
29+
"[nltk_data] | Downloading package cess_cat to\n",
30+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
31+
"[nltk_data] | Package cess_cat is already up-to-date!\n",
32+
"[nltk_data] | Downloading package cess_esp to\n",
33+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
34+
"[nltk_data] | Package cess_esp is already up-to-date!\n",
35+
"[nltk_data] | Downloading package chat80 to\n",
36+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
37+
"[nltk_data] | Package chat80 is already up-to-date!\n",
38+
"[nltk_data] | Downloading package city_database to\n",
39+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
40+
"[nltk_data] | Package city_database is already up-to-date!\n",
41+
"[nltk_data] | Downloading package cmudict to\n",
42+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
43+
"[nltk_data] | Package cmudict is already up-to-date!\n",
44+
"[nltk_data] | Downloading package comtrans to\n",
45+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
46+
"[nltk_data] | Package comtrans is already up-to-date!\n",
47+
"[nltk_data] | Downloading package conll2000 to\n",
48+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
49+
"[nltk_data] | Package conll2000 is already up-to-date!\n",
50+
"[nltk_data] | Downloading package conll2002 to\n",
51+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
52+
"[nltk_data] | Package conll2002 is already up-to-date!\n",
53+
"[nltk_data] | Downloading package conll2007 to\n",
54+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
55+
"[nltk_data] | Package conll2007 is already up-to-date!\n",
56+
"[nltk_data] | Downloading package crubadan to\n",
57+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
58+
"[nltk_data] | Package crubadan is already up-to-date!\n",
59+
"[nltk_data] | Downloading package dependency_treebank to\n",
60+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
61+
"[nltk_data] | Package dependency_treebank is already up-to-date!\n",
62+
"[nltk_data] | Downloading package dolch to\n",
63+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
64+
"[nltk_data] | Package dolch is already up-to-date!\n",
65+
"[nltk_data] | Downloading package floresta to\n",
66+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
67+
"[nltk_data] | Package floresta is already up-to-date!\n",
68+
"[nltk_data] | Downloading package framenet_v15 to\n",
69+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
70+
"[nltk_data] | Package framenet_v15 is already up-to-date!\n",
71+
"[nltk_data] | Downloading package framenet_v17 to\n",
72+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
73+
"[nltk_data] | Package framenet_v17 is already up-to-date!\n",
74+
"[nltk_data] | Downloading package gazetteers to\n",
75+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
76+
"[nltk_data] | Package gazetteers is already up-to-date!\n",
77+
"[nltk_data] | Downloading package genesis to\n",
78+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
79+
"[nltk_data] | Package genesis is already up-to-date!\n",
80+
"[nltk_data] | Downloading package gutenberg to\n",
81+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
82+
"[nltk_data] | Package gutenberg is already up-to-date!\n",
83+
"[nltk_data] | Downloading package ieer to\n",
84+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
85+
"[nltk_data] | Package ieer is already up-to-date!\n",
86+
"[nltk_data] | Downloading package inaugural to\n",
87+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
88+
"[nltk_data] | Package inaugural is already up-to-date!\n",
89+
"[nltk_data] | Downloading package indian to\n",
90+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
91+
"[nltk_data] | Package indian is already up-to-date!\n",
92+
"[nltk_data] | Downloading package jeita to\n",
93+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
94+
"[nltk_data] | Package jeita is already up-to-date!\n",
95+
"[nltk_data] | Downloading package kimmo to\n",
96+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
97+
"[nltk_data] | Package kimmo is already up-to-date!\n",
98+
"[nltk_data] | Downloading package knbc to\n",
99+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
100+
"[nltk_data] | Package knbc is already up-to-date!\n",
101+
"[nltk_data] | Downloading package lin_thesaurus to\n",
102+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
103+
"[nltk_data] | Package lin_thesaurus is already up-to-date!\n",
104+
"[nltk_data] | Downloading package mac_morpho to\n",
105+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
106+
"[nltk_data] | Package mac_morpho is already up-to-date!\n",
107+
"[nltk_data] | Downloading package machado to\n",
108+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
109+
"[nltk_data] | Package machado is already up-to-date!\n",
110+
"[nltk_data] | Downloading package masc_tagged to\n",
111+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
112+
"[nltk_data] | Package masc_tagged is already up-to-date!\n",
113+
"[nltk_data] | Downloading package movie_reviews to\n",
114+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
115+
"[nltk_data] | Package movie_reviews is already up-to-date!\n",
116+
"[nltk_data] | Downloading package names to\n",
117+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
118+
"[nltk_data] | Package names is already up-to-date!\n",
119+
"[nltk_data] | Downloading package nombank.1.0 to\n",
120+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
121+
"[nltk_data] | Package nombank.1.0 is already up-to-date!\n",
122+
"[nltk_data] | Downloading package nps_chat to\n",
123+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
124+
"[nltk_data] | Package nps_chat is already up-to-date!\n",
125+
"[nltk_data] | Downloading package omw to\n",
126+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
127+
"[nltk_data] | Package omw is already up-to-date!\n",
128+
"[nltk_data] | Downloading package paradigms to\n",
129+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
130+
"[nltk_data] | Package paradigms is already up-to-date!\n",
131+
"[nltk_data] | Downloading package pil to\n",
132+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
133+
"[nltk_data] | Package pil is already up-to-date!\n",
134+
"[nltk_data] | Downloading package pl196x to\n",
135+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
136+
"[nltk_data] | Package pl196x is already up-to-date!\n",
137+
"[nltk_data] | Downloading package ppattach to\n",
138+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
139+
"[nltk_data] | Package ppattach is already up-to-date!\n",
140+
"[nltk_data] | Downloading package problem_reports to\n",
141+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
142+
"[nltk_data] | Package problem_reports is already up-to-date!\n",
143+
"[nltk_data] | Downloading package propbank to\n",
144+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
145+
"[nltk_data] | Package propbank is already up-to-date!\n",
146+
"[nltk_data] | Downloading package ptb to\n",
147+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
148+
"[nltk_data] | Package ptb is already up-to-date!\n",
149+
"[nltk_data] | Downloading package qc to\n",
150+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
151+
"[nltk_data] | Package qc is already up-to-date!\n",
152+
"[nltk_data] | Downloading package reuters to\n",
153+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
154+
"[nltk_data] | Package reuters is already up-to-date!\n",
155+
"[nltk_data] | Downloading package rte to\n",
156+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
157+
"[nltk_data] | Package rte is already up-to-date!\n",
158+
"[nltk_data] | Downloading package semcor to\n",
159+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
160+
"[nltk_data] | Package semcor is already up-to-date!\n",
161+
"[nltk_data] | Downloading package senseval to\n",
162+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n"
163+
]
164+
},
165+
{
166+
"name": "stderr",
167+
"output_type": "stream",
168+
"text": [
169+
"[nltk_data] | Package senseval is already up-to-date!\n",
170+
"[nltk_data] | Downloading package sentiwordnet to\n",
171+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
172+
"[nltk_data] | Package sentiwordnet is already up-to-date!\n",
173+
"[nltk_data] | Downloading package shakespeare to\n",
174+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
175+
"[nltk_data] | Package shakespeare is already up-to-date!\n",
176+
"[nltk_data] | Downloading package sinica_treebank to\n",
177+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
178+
"[nltk_data] | Package sinica_treebank is already up-to-date!\n",
179+
"[nltk_data] | Downloading package state_union to\n",
180+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
181+
"[nltk_data] | Package state_union is already up-to-date!\n",
182+
"[nltk_data] | Downloading package stopwords to\n",
183+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
184+
"[nltk_data] | Package stopwords is already up-to-date!\n",
185+
"[nltk_data] | Downloading package swadesh to\n",
186+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
187+
"[nltk_data] | Package swadesh is already up-to-date!\n",
188+
"[nltk_data] | Downloading package switchboard to\n",
189+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
190+
"[nltk_data] | Package switchboard is already up-to-date!\n",
191+
"[nltk_data] | Downloading package timit to\n",
192+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
193+
"[nltk_data] | Package timit is already up-to-date!\n",
194+
"[nltk_data] | Downloading package toolbox to\n",
195+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
196+
"[nltk_data] | Package toolbox is already up-to-date!\n",
197+
"[nltk_data] | Downloading package treebank to\n",
198+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
199+
"[nltk_data] | Package treebank is already up-to-date!\n",
200+
"[nltk_data] | Downloading package udhr to\n",
201+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
202+
"[nltk_data] | Package udhr is already up-to-date!\n",
203+
"[nltk_data] | Downloading package udhr2 to\n",
204+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
205+
"[nltk_data] | Package udhr2 is already up-to-date!\n",
206+
"[nltk_data] | Downloading package unicode_samples to\n",
207+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
208+
"[nltk_data] | Package unicode_samples is already up-to-date!\n",
209+
"[nltk_data] | Downloading package universal_treebanks_v20 to\n",
210+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
211+
"[nltk_data] | Package universal_treebanks_v20 is already up-to-\n",
212+
"[nltk_data] | date!\n",
213+
"[nltk_data] | Downloading package verbnet to\n",
214+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
215+
"[nltk_data] | Package verbnet is already up-to-date!\n",
216+
"[nltk_data] | Downloading package verbnet3 to\n",
217+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
218+
"[nltk_data] | Package verbnet3 is already up-to-date!\n",
219+
"[nltk_data] | Downloading package webtext to\n",
220+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
221+
"[nltk_data] | Package webtext is already up-to-date!\n",
222+
"[nltk_data] | Downloading package wordnet to\n",
223+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
224+
"[nltk_data] | Package wordnet is already up-to-date!\n",
225+
"[nltk_data] | Downloading package wordnet_ic to\n",
226+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
227+
"[nltk_data] | Package wordnet_ic is already up-to-date!\n",
228+
"[nltk_data] | Downloading package words to\n",
229+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
230+
"[nltk_data] | Package words is already up-to-date!\n",
231+
"[nltk_data] | Downloading package ycoe to\n",
232+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
233+
"[nltk_data] | Package ycoe is already up-to-date!\n",
234+
"[nltk_data] | Downloading package panlex_swadesh to\n",
235+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
236+
"[nltk_data] | Package panlex_swadesh is already up-to-date!\n",
237+
"[nltk_data] | Downloading package mte_teip5 to\n",
238+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
239+
"[nltk_data] | Package mte_teip5 is already up-to-date!\n",
240+
"[nltk_data] | Downloading package nonbreaking_prefixes to\n",
241+
"[nltk_data] | C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
242+
"[nltk_data] | Package nonbreaking_prefixes is already up-to-date!\n",
243+
"[nltk_data] | \n",
244+
"[nltk_data] Done downloading collection all-corpora\n",
245+
"[nltk_data] Downloading package punkt to\n",
246+
"[nltk_data] C:\\Users\\sk8er\\AppData\\Roaming\\nltk_data...\n",
247+
"[nltk_data] Package punkt is already up-to-date!\n"
248+
]
249+
},
250+
{
251+
"data": {
252+
"text/plain": [
253+
"True"
254+
]
255+
},
256+
"execution_count": 1,
257+
"metadata": {},
258+
"output_type": "execute_result"
259+
}
260+
],
261+
"source": [
262+
"import nltk\n",
263+
"\n",
264+
"nltk.download('all-corpora')\n",
265+
"nltk.download('punkt')"
266+
]
267+
},
268+
{
269+
"cell_type": "code",
270+
"execution_count": 2,
271+
"metadata": {},
272+
"outputs": [
273+
{
274+
"name": "stdout",
275+
"output_type": "stream",
276+
"text": [
277+
"['Natural', 'language', 'processing', '(', 'NLP', ')', 'is', 'a', 'subfield', 'of', 'computer', 'science', ',', 'information', 'engineering', ',', 'and', 'artificial', 'intelligence', 'concerned', 'with', 'the', 'interactions', 'between', 'computers', 'and', 'human', '(', 'natural', ')', 'languages', ',', 'in', 'particular', 'how', 'to', 'program', 'computers', 'to', 'process', 'and', 'analyze', 'large', 'amounts', 'of', 'natural', 'language', 'data', '.']\n"
278+
]
279+
}
280+
],
281+
"source": [
282+
"from nltk.tokenize import word_tokenize\n",
283+
"\n",
284+
"sentence = \"Natural language processing (NLP) is a subfield of computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data.\"\n",
285+
"\n",
286+
"print(word_tokenize(sentence))"
287+
]
288+
},
289+
{
290+
"cell_type": "code",
291+
"execution_count": 3,
292+
"metadata": {},
293+
"outputs": [
294+
{
295+
"name": "stdout",
296+
"output_type": "stream",
297+
"text": [
298+
"['Natural language processing (NLP) is a subfield of computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data.', 'Challenges in natural language processing frequently involve speech recognition, natural language understanding, and natural language generation.']\n"
299+
]
300+
}
301+
],
302+
"source": [
303+
"from nltk.tokenize import sent_tokenize\n",
304+
"\n",
305+
"paragraph = \"Natural language processing (NLP) is a subfield of computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data. Challenges in natural language processing frequently involve speech recognition, natural language understanding, and natural language generation.\"\n",
306+
"\n",
307+
"print(sent_tokenize(paragraph))"
308+
]
309+
},
310+
{
311+
"cell_type": "code",
312+
"execution_count": null,
313+
"metadata": {},
314+
"outputs": [],
315+
"source": []
316+
}
317+
],
318+
"metadata": {
319+
"kernelspec": {
320+
"display_name": "Python 3",
321+
"language": "python",
322+
"name": "python3"
323+
},
324+
"language_info": {
325+
"codemirror_mode": {
326+
"name": "ipython",
327+
"version": 3
328+
},
329+
"file_extension": ".py",
330+
"mimetype": "text/x-python",
331+
"name": "python",
332+
"nbconvert_exporter": "python",
333+
"pygments_lexer": "ipython3",
334+
"version": "3.6.12"
335+
}
336+
},
337+
"nbformat": 4,
338+
"nbformat_minor": 4
339+
}

0 commit comments

Comments
 (0)