Notebook

Stop Words¶

nltk

In [1]:

# # 분석에 필요한 모듈설치
! pip3 install sklearn nltk

import nltk
nltk.download('punkt')
nltk.download('stopwords')
news_texts = "https://raw.githubusercontent.com/YongBeomKim/nltk_basic/master/data/News.txt"

Requirement already satisfied: sklearn in /usr/local/lib/python3.6/dist-packages (0.0)
Requirement already satisfied: nltk in /usr/local/lib/python3.6/dist-packages (3.2.5)
Requirement already satisfied: scikit-learn in /usr/local/lib/python3.6/dist-packages (from sklearn) (0.20.3)
Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from nltk) (1.11.0)
Requirement already satisfied: scipy>=0.13.3 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->sklearn) (1.1.0)
Requirement already satisfied: numpy>=1.8.2 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->sklearn) (1.14.6)
[nltk_data] Downloading package punkt to /root/nltk_data...
[nltk_data]   Package punkt is already up-to-date!
[nltk_data] Downloading package stopwords to /root/nltk_data...
[nltk_data]   Package stopwords is already up-to-date!

In [2]:

# Stopwords 사용가능한 언어목록 
from nltk.corpus import stopwords
stopwords.ensure_loaded
stopwords.__dict__.get('_fileids')

Out[2]:

['arabic',
 'azerbaijani',
 'danish',
 'dutch',
 'english',
 'finnish',
 'french',
 'german',
 'greek',
 'hungarian',
 'indonesian',
 'italian',
 'kazakh',
 'nepali',
 'norwegian',
 'portuguese',
 'romanian',
 'russian',
 'spanish',
 'swedish',
 'turkish']

In [3]:

from nltk.corpus import stopwords
stop_eng = stopwords.words("english")
stop_eng[:8]

Out[3]:

['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves']

In [4]:

# 영문 내용을 소문자로 전처리
texts = 'I like such a Wonderful Snow Ice Cream'
texts = texts.lower()
texts

Out[4]:

'i like such a wonderful snow ice cream'

In [5]:

from nltk import word_tokenize
tokens = word_tokenize(texts)
tokens

Out[5]:

['i', 'like', 'such', 'a', 'wonderful', 'snow', 'ice', 'cream']

In [6]:

tokens = [word   for word in tokens   
                 if word not in stop_eng]
print(tokens)

['like', 'wonderful', 'snow', 'ice', 'cream']

Tf-idf¶

scikit learn

In [7]:

# with open(news_texts, 'r') as f:
#     texts = f.read()
# texts = texts.lower()

import requests
texts = requests.get(news_texts).text.lower()
texts[:300]

Out[7]:

'samsung electronics posted krw 65.98 trillion in consolidated revenue and krw 15.15 trillion in operating profit for the fourth quarter of 2017.\n \noverall, the company reported full-year revenue of krw 239.58 trillion and full-year operating profit of krw 53.65 trillion.\n \nfourth quarter earnings we'

In [8]:

# 영문 Token만 추출한다 (숫자와 문장기호를 제거)
import re
tokenizer = re.compile('[a-z]\w+')
tokens    = tokenizer.findall(texts)
document  = " ".join(tokens)
document[:300]

Out[8]:

'samsung electronics posted krw trillion in consolidated revenue and krw trillion in operating profit for the fourth quarter of overall the company reported full year revenue of krw trillion and full year operating profit of krw trillion fourth quarter earnings were driven by the components business '

In [9]:

import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
tfidf_vec     = TfidfVectorizer(stop_words='english')
transformed = tfidf_vec.fit_transform(raw_documents = [document])
transformed = np.array(transformed.todense())
transformed

Out[9]:

array([[0.01705916, 0.00852958, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.01705916, 0.00852958, 0.03411832,
        0.02558874, 0.01705916, 0.00852958, 0.00852958, 0.00852958,
        0.03411832, 0.02558874, 0.03411832, 0.01705916, 0.00852958,
        0.01705916, 0.0426479 , 0.03411832, 0.00852958, 0.00852958,
        0.00852958, 0.05970706, 0.00852958, 0.0426479 , 0.01705916,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.01705916,
        0.00852958, 0.03411832, 0.02558874, 0.00852958, 0.00852958,
        0.03411832, 0.01705916, 0.00852958, 0.03411832, 0.01705916,
        0.00852958, 0.00852958, 0.00852958, 0.01705916, 0.27294655,
        0.0426479 , 0.01705916, 0.00852958, 0.00852958, 0.01705916,
        0.00852958, 0.00852958, 0.00852958, 0.01705916, 0.00852958,
        0.00852958, 0.01705916, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.01705916, 0.02558874, 0.00852958, 0.00852958,
        0.01705916, 0.15353243, 0.00852958, 0.00852958, 0.03411832,
        0.05970706, 0.00852958, 0.01705916, 0.00852958, 0.00852958,
        0.03411832, 0.00852958, 0.00852958, 0.0426479 , 0.02558874,
        0.01705916, 0.03411832, 0.01705916, 0.00852958, 0.01705916,
        0.00852958, 0.00852958, 0.0426479 , 0.01705916, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.0426479 , 0.01705916,
        0.00852958, 0.02558874, 0.01705916, 0.02558874, 0.02558874,
        0.00852958, 0.01705916, 0.05970706, 0.28147613, 0.00852958,
        0.06823664, 0.03411832, 0.00852958, 0.01705916, 0.01705916,
        0.01705916, 0.00852958, 0.00852958, 0.03411832, 0.00852958,
        0.06823664, 0.01705916, 0.00852958, 0.05970706, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.05117748, 0.00852958,
        0.01705916, 0.02558874, 0.00852958, 0.00852958, 0.01705916,
        0.18765075, 0.00852958, 0.00852958, 0.00852958, 0.01705916,
        0.00852958, 0.02558874, 0.05117748, 0.00852958, 0.10235496,
        0.00852958, 0.01705916, 0.01705916, 0.00852958, 0.01705916,
        0.02558874, 0.00852958, 0.0852958 , 0.07676622, 0.03411832,
        0.00852958, 0.14500285, 0.05117748, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.0852958 , 0.00852958,
        0.03411832, 0.00852958, 0.00852958, 0.09382538, 0.02558874,
        0.00852958, 0.02558874, 0.01705916, 0.00852958, 0.00852958,
        0.00852958, 0.03411832, 0.05970706, 0.01705916, 0.01705916,
        0.0426479 , 0.00852958, 0.00852958, 0.00852958, 0.02558874,
        0.02558874, 0.02558874, 0.0426479 , 0.01705916, 0.10235496,
        0.0426479 , 0.00852958, 0.13647327, 0.01705916, 0.00852958,
        0.00852958, 0.02558874, 0.00852958, 0.00852958, 0.03411832,
        0.00852958, 0.00852958, 0.05117748, 0.01705916, 0.00852958,
        0.00852958, 0.07676622, 0.06823664, 0.07676622, 0.05970706,
        0.00852958, 0.01705916, 0.02558874, 0.00852958, 0.00852958,
        0.00852958, 0.03411832, 0.02558874, 0.00852958, 0.01705916,
        0.01705916, 0.00852958, 0.13647327, 0.05970706, 0.00852958,
        0.01705916, 0.01705916, 0.00852958, 0.03411832, 0.10235496,
        0.00852958, 0.0426479 , 0.03411832, 0.05117748, 0.00852958,
        0.00852958, 0.00852958, 0.0426479 , 0.00852958, 0.00852958,
        0.05117748, 0.05970706, 0.02558874, 0.00852958, 0.02558874,
        0.02558874, 0.02558874, 0.00852958, 0.01705916, 0.0426479 ,
        0.01705916, 0.00852958, 0.00852958, 0.06823664, 0.00852958,
        0.00852958, 0.01705916, 0.00852958, 0.14500285, 0.0426479 ,
        0.02558874, 0.02558874, 0.00852958, 0.00852958, 0.00852958,
        0.01705916, 0.05970706, 0.00852958, 0.03411832, 0.00852958,
        0.02558874, 0.00852958, 0.01705916, 0.16206201, 0.00852958,
        0.0426479 , 0.00852958, 0.00852958, 0.00852958, 0.05970706,
        0.01705916, 0.00852958, 0.01705916, 0.02558874, 0.01705916,
        0.15353243, 0.01705916, 0.0426479 , 0.0426479 , 0.01705916,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.09382538,
        0.00852958, 0.00852958, 0.01705916, 0.06823664, 0.00852958,
        0.00852958, 0.00852958, 0.01705916, 0.01705916, 0.01705916,
        0.00852958, 0.00852958, 0.02558874, 0.00852958, 0.00852958,
        0.00852958, 0.07676622, 0.06823664, 0.00852958, 0.00852958,
        0.01705916, 0.01705916, 0.01705916, 0.00852958, 0.00852958,
        0.00852958, 0.01705916, 0.01705916, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.06823664, 0.00852958,
        0.00852958, 0.00852958, 0.14500285, 0.01705916, 0.00852958,
        0.03411832, 0.01705916, 0.00852958, 0.02558874, 0.0852958 ,
        0.05117748, 0.02558874, 0.22176907, 0.06823664, 0.05117748,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.01705916,
        0.00852958, 0.00852958, 0.00852958, 0.01705916, 0.01705916,
        0.07676622, 0.00852958, 0.00852958, 0.19618033, 0.00852958,
        0.00852958, 0.02558874, 0.01705916, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.03411832,
        0.01705916, 0.02558874, 0.02558874, 0.01705916, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.01705916, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.07676622, 0.02558874,
        0.00852958, 0.01705916, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.17912117, 0.24735781, 0.02558874, 0.00852958,
        0.01705916, 0.01705916, 0.02558874, 0.00852958, 0.13647327,
        0.00852958, 0.01705916, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.03411832, 0.00852958, 0.03411832,
        0.00852958, 0.0426479 , 0.05117748, 0.02558874, 0.01705916,
        0.01705916, 0.05970706, 0.00852958, 0.02558874, 0.01705916,
        0.00852958, 0.01705916, 0.00852958, 0.06823664, 0.09382538,
        0.00852958, 0.00852958, 0.05117748, 0.00852958, 0.03411832,
        0.00852958, 0.00852958, 0.02558874, 0.02558874, 0.02558874,
        0.01705916, 0.00852958, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.01705916, 0.00852958, 0.0426479 , 0.00852958,
        0.05970706, 0.00852958, 0.12794369, 0.00852958, 0.03411832,
        0.00852958, 0.00852958, 0.00852958, 0.01705916, 0.05970706,
        0.00852958, 0.05970706, 0.05117748, 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.12794369, 0.00852958, 0.05970706,
        0.05970706, 0.00852958, 0.0426479 , 0.00852958, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.00852958,
        0.00852958, 0.03411832, 0.00852958, 0.00852958, 0.01705916,
        0.00852958, 0.00852958, 0.02558874, 0.12794369, 0.00852958,
        0.00852958, 0.00852958, 0.00852958, 0.00852958, 0.06823664,
        0.00852958, 0.06823664]])

In [10]:

index_value   = {i[1]:i[0] for i in tfidf_vec.vocabulary_.items()}
fully_indexed = {index_value[column]:value  for row in transformed  
                                            for (column,value) in enumerate(row)}
fully_indexed

Out[10]:

{'a8': 0.017059159255788922,
 'accelerating': 0.008529579627894461,
 'accountable': 0.008529579627894461,
 'achieve': 0.008529579627894461,
 'achieved': 0.008529579627894461,
 'achieving': 0.008529579627894461,
 'actively': 0.008529579627894461,
 'activities': 0.017059159255788922,
 'add': 0.008529579627894461,
 'added': 0.034118318511577844,
 'addition': 0.025588738883683383,
 'address': 0.017059159255788922,
 'adopting': 0.008529579627894461,
 'adoption': 0.008529579627894461,
 'advanced': 0.008529579627894461,
 'affected': 0.034118318511577844,
 'ahead': 0.025588738883683383,
 'ai': 0.034118318511577844,
 'aim': 0.017059159255788922,
 'aiming': 0.008529579627894461,
 'aims': 0.017059159255788922,
 'america': 0.042647898139472305,
 'amid': 0.034118318511577844,
 'amounting': 0.008529579627894461,
 'announcement': 0.008529579627894461,
 'anticipated': 0.008529579627894461,
 'appliances': 0.05970705739526123,
 'application': 0.008529579627894461,
 'applications': 0.042647898139472305,
 'applying': 0.017059159255788922,
 'appreciation': 0.008529579627894461,
 'approximately': 0.008529579627894461,
 'aps': 0.008529579627894461,
 'areas': 0.008529579627894461,
 'asp': 0.017059159255788922,
 'asps': 0.008529579627894461,
 'automotive': 0.034118318511577844,
 'b2b': 0.025588738883683383,
 'backed': 0.008529579627894461,
 'base': 0.008529579627894461,
 'based': 0.034118318511577844,
 'basis': 0.017059159255788922,
 'billion': 0.008529579627894461,
 'bixby': 0.034118318511577844,
 'bolster': 0.017059159255788922,
 'boost': 0.008529579627894461,
 'bringing': 0.008529579627894461,
 'building': 0.008529579627894461,
 'builds': 0.017059159255788922,
 'business': 0.27294654809262275,
 'businesses': 0.042647898139472305,
 'camera': 0.017059159255788922,
 'cameras': 0.008529579627894461,
 'capabilities': 0.008529579627894461,
 'capex': 0.017059159255788922,
 'capital': 0.008529579627894461,
 'capitalizing': 0.008529579627894461,
 'case': 0.008529579627894461,
 'ce': 0.017059159255788922,
 'challenges': 0.008529579627894461,
 'channels': 0.008529579627894461,
 'china': 0.017059159255788922,
 'chips': 0.008529579627894461,
 'chipsets': 0.008529579627894461,
 'circumstances': 0.008529579627894461,
 'cis': 0.008529579627894461,
 'class': 0.017059159255788922,
 'cloud': 0.025588738883683383,
 'coming': 0.008529579627894461,
 'commercialization': 0.008529579627894461,
 'communications': 0.017059159255788922,
 'company': 0.1535324333021003,
 'compared': 0.008529579627894461,
 'competencies': 0.008529579627894461,
 'competition': 0.034118318511577844,
 'competitiveness': 0.05970705739526123,
 'completion': 0.008529579627894461,
 'components': 0.017059159255788922,
 'comprising': 0.008529579627894461,
 'concentrated': 0.008529579627894461,
 'conditions': 0.034118318511577844,
 'connected': 0.008529579627894461,
 'connectivity': 0.008529579627894461,
 'consolidated': 0.042647898139472305,
 'consumer': 0.025588738883683383,
 'content': 0.017059159255788922,
 'continue': 0.034118318511577844,
 'continued': 0.017059159255788922,
 'continues': 0.008529579627894461,
 'continuing': 0.017059159255788922,
 'contribution': 0.008529579627894461,
 'core': 0.008529579627894461,
 'cost': 0.042647898139472305,
 'costs': 0.017059159255788922,
 'cryptocurrency': 0.008529579627894461,
 'cup': 0.008529579627894461,
 'currencies': 0.008529579627894461,
 'customer': 0.008529579627894461,
 'customers': 0.042647898139472305,
 'cutting': 0.017059159255788922,
 'dampened': 0.008529579627894461,
 'datacenter': 0.025588738883683383,
 'datacenters': 0.017059159255788922,
 'decline': 0.025588738883683383,
 'declined': 0.025588738883683383,
 'declining': 0.008529579627894461,
 'decrease': 0.017059159255788922,
 'decreased': 0.05970705739526123,
 'demand': 0.2814761277205172,
 'demands': 0.008529579627894461,
 'density': 0.06823663702315569,
 'despite': 0.034118318511577844,
 'device': 0.008529579627894461,
 'devices': 0.017059159255788922,
 'differentiate': 0.017059159255788922,
 'differentiated': 0.017059159255788922,
 'differentiating': 0.008529579627894461,
 'differentiation': 0.008529579627894461,
 'digital': 0.034118318511577844,
 'digits': 0.008529579627894461,
 'display': 0.06823663702315569,
 'displays': 0.017059159255788922,
 'distribution': 0.008529579627894461,
 'division': 0.05970705739526123,
 'dollar': 0.008529579627894461,
 'door': 0.008529579627894461,
 'dot': 0.008529579627894461,
 'double': 0.008529579627894461,
 'dram': 0.051177477767366766,
 'drive': 0.008529579627894461,
 'driven': 0.017059159255788922,
 'dual': 0.025588738883683383,
 'duo': 0.008529579627894461,
 'earlier': 0.008529579627894461,
 'early': 0.017059159255788922,
 'earnings': 0.18765075181367816,
 'east': 0.008529579627894461,
 'economic': 0.008529579627894461,
 'ecosystem': 0.008529579627894461,
 'edge': 0.017059159255788922,
 'effect': 0.008529579627894461,
 'efforts': 0.025588738883683383,
 'electronics': 0.051177477767366766,
 'employees': 0.008529579627894461,
 'end': 0.10235495553473353,
 'engines': 0.008529579627894461,
 'enhance': 0.017059159255788922,
 'enhancing': 0.017059159255788922,
 'enjoy': 0.008529579627894461,
 'europe': 0.017059159255788922,
 'events': 0.025588738883683383,
 'executed': 0.008529579627894461,
 'expand': 0.08529579627894461,
 'expanding': 0.07676621665105016,
 'expansion': 0.034118318511577844,
 'expect': 0.008529579627894461,
 'expected': 0.14500285367420584,
 'expects': 0.051177477767366766,
 'expenditure': 0.008529579627894461,
 'experiences': 0.008529579627894461,
 'experiential': 0.008529579627894461,
 'face': 0.008529579627894461,
 'family': 0.008529579627894461,
 'fast': 0.008529579627894461,
 'favorable': 0.008529579627894461,
 'features': 0.008529579627894461,
 'fifa': 0.008529579627894461,
 'finalized': 0.008529579627894461,
 'flagship': 0.08529579627894461,
 'flex': 0.008529579627894461,
 'flexible': 0.034118318511577844,
 'flexibly': 0.008529579627894461,
 'flexwash': 0.008529579627894461,
 'focus': 0.09382537590683908,
 'foldable': 0.025588738883683383,
 'following': 0.008529579627894461,
 'forecast': 0.025588738883683383,
 'forecasts': 0.017059159255788922,
 'foresees': 0.008529579627894461,
 'forward': 0.008529579627894461,
 'foundation': 0.008529579627894461,
 'foundry': 0.034118318511577844,
 'fourth': 0.05970705739526123,
 'frs': 0.017059159255788922,
 'gains': 0.017059159255788922,
 'galaxy': 0.042647898139472305,
 'games': 0.008529579627894461,
 'gb': 0.008529579627894461,
 'gears': 0.008529579627894461,
 'generation': 0.025588738883683383,
 'global': 0.025588738883683383,
 'grew': 0.025588738883683383,
 'grow': 0.042647898139472305,
 'growing': 0.017059159255788922,
 'growth': 0.10235495553473353,
 'half': 0.042647898139472305,
 'hardware': 0.008529579627894461,
 'high': 0.13647327404631138,
 'higher': 0.017059159255788922,
 'hike': 0.008529579627894461,
 'holiday': 0.008529579627894461,
 'home': 0.025588738883683383,
 'hub': 0.008529579627894461,
 'im': 0.008529579627894461,
 'image': 0.034118318511577844,
 'impact': 0.008529579627894461,
 'impacted': 0.008529579627894461,
 'improve': 0.051177477767366766,
 'improved': 0.017059159255788922,
 'improvement': 0.008529579627894461,
 'incentive': 0.008529579627894461,
 'including': 0.07676621665105016,
 'increase': 0.06823663702315569,
 'increased': 0.07676621665105016,
 'increasing': 0.05970705739526123,
 'indicated': 0.008529579627894461,
 'industry': 0.017059159255788922,
 'intensified': 0.025588738883683383,
 'intensifying': 0.008529579627894461,
 'international': 0.008529579627894461,
 'investment': 0.008529579627894461,
 'investments': 0.034118318511577844,
 'iot': 0.025588738883683383,
 'january': 0.008529579627894461,
 'japan': 0.017059159255788922,
 'korea': 0.017059159255788922,
 'korean': 0.008529579627894461,
 'krw': 0.13647327404631138,
 'large': 0.05970705739526123,
 'largest': 0.008529579627894461,
 'launch': 0.017059159255788922,
 'launched': 0.017059159255788922,
 'launches': 0.008529579627894461,
 'layer': 0.034118318511577844,
 'lcd': 0.10235495553473353,
 'lead': 0.008529579627894461,
 'leadership': 0.042647898139472305,
 'led': 0.034118318511577844,
 'likely': 0.051177477767366766,
 'limited': 0.008529579627894461,
 'line': 0.008529579627894461,
 'lines': 0.008529579627894461,
 'lineup': 0.042647898139472305,
 'long': 0.008529579627894461,
 'look': 0.008529579627894461,
 'looking': 0.051177477767366766,
 'low': 0.05970705739526123,
 'lower': 0.025588738883683383,
 'lpddr4x': 0.008529579627894461,
 'lsi': 0.025588738883683383,
 'lte': 0.025588738883683383,
 'ltps': 0.025588738883683383,
 'machine': 0.008529579627894461,
 'machines': 0.017059159255788922,
 'mainly': 0.042647898139472305,
 'mainstream': 0.017059159255788922,
 'maintaining': 0.008529579627894461,
 'maintains': 0.008529579627894461,
 'major': 0.06823663702315569,
 'make': 0.008529579627894461,
 'managing': 0.008529579627894461,
 'manufactures': 0.017059159255788922,
 'manufacturing': 0.008529579627894461,
 'market': 0.14500285367420584,
 'marketing': 0.042647898139472305,
 'markets': 0.025588738883683383,
 'mass': 0.025588738883683383,
 'material': 0.008529579627894461,
 'measures': 0.008529579627894461,
 'meet': 0.008529579627894461,
 'meeting': 0.017059159255788922,
 'memory': 0.05970705739526123,
 'micro': 0.008529579627894461,
 'mid': 0.034118318511577844,
 'middle': 0.008529579627894461,
 'migration': 0.025588738883683383,
 'mining': 0.008529579627894461,
 'mix': 0.017059159255788922,
 'mobile': 0.16206201292999475,
 'model': 0.008529579627894461,
 'models': 0.042647898139472305,
 'moderate': 0.008529579627894461,
 'month': 0.008529579627894461,
 'months': 0.008529579627894461,
 'nand': 0.05970705739526123,
 'nano': 0.017059159255788922,
 'nd': 0.008529579627894461,
 'needs': 0.017059159255788922,
 'network': 0.025588738883683383,
 'networks': 0.017059159255788922,
 'new': 0.1535324333021003,
 'newly': 0.017059159255788922,
 'nm': 0.042647898139472305,
 'north': 0.042647898139472305,
 'note': 0.017059159255788922,
 'numbers': 0.008529579627894461,
 'offering': 0.008529579627894461,
 'offerings': 0.008529579627894461,
 'offset': 0.008529579627894461,
 'oled': 0.09382537590683908,
 'olympics': 0.008529579627894461,
 'ones': 0.008529579627894461,
 'online': 0.017059159255788922,
 'operating': 0.06823663702315569,
 'opportunities': 0.008529579627894461,
 'optimization': 0.008529579627894461,
 'optimizing': 0.008529579627894461,
 'order': 0.017059159255788922,
 'orders': 0.017059159255788922,
 'outlook': 0.017059159255788922,
 'oven': 0.008529579627894461,
 'ovens': 0.008529579627894461,
 'overall': 0.025588738883683383,
 'overseas': 0.008529579627894461,
 'packaging': 0.008529579627894461,
 'paid': 0.008529579627894461,
 'panel': 0.07676621665105016,
 'panels': 0.06823663702315569,
 'particularly': 0.008529579627894461,
 'partners': 0.008529579627894461,
 'partnerships': 0.017059159255788922,
 'peak': 0.017059159255788922,
 'performance': 0.017059159255788922,
 'phones': 0.008529579627894461,
 'pick': 0.008529579627894461,
 'plan': 0.008529579627894461,
 'plans': 0.017059159255788922,
 'plant': 0.017059159255788922,
 'platforms': 0.008529579627894461,
 'portfolio': 0.008529579627894461,
 'portion': 0.008529579627894461,
 'position': 0.008529579627894461,
 'post': 0.008529579627894461,
 'posted': 0.06823663702315569,
 'posts': 0.008529579627894461,
 'power': 0.008529579627894461,
 'preliminary': 0.008529579627894461,
 'premium': 0.14500285367420584,
 'previous': 0.017059159255788922,
 'prices': 0.008529579627894461,
 'process': 0.034118318511577844,
 'processes': 0.017059159255788922,
 'processor': 0.008529579627894461,
 'processors': 0.025588738883683383,
 'product': 0.08529579627894461,
 'production': 0.051177477767366766,
 'productivity': 0.025588738883683383,
 'products': 0.221769070325256,
 'profit': 0.06823663702315569,
 'profitability': 0.051177477767366766,
 'profitable': 0.008529579627894461,
 'profits': 0.008529579627894461,
 'programs': 0.008529579627894461,
 'promptly': 0.008529579627894461,
 'provide': 0.017059159255788922,
 'providers': 0.008529579627894461,
 'pursue': 0.008529579627894461,
 'pushing': 0.008529579627894461,
 'pyeongtaek': 0.017059159255788922,
 'qled': 0.017059159255788922,
 'qoq': 0.07676621665105016,
 'qualitative': 0.008529579627894461,
 'quantum': 0.008529579627894461,
 'quarter': 0.1961803314415726,
 'quarterly': 0.008529579627894461,
 'quickdrive': 0.008529579627894461,
 'ramp': 0.025588738883683383,
 'range': 0.017059159255788922,
 'reached': 0.008529579627894461,
 'readout': 0.008529579627894461,
 'ready': 0.008529579627894461,
 'recoveries': 0.008529579627894461,
 'reduction': 0.008529579627894461,
 'refrigerator': 0.008529579627894461,
 'reinforce': 0.034118318511577844,
 'related': 0.017059159255788922,
 'release': 0.025588738883683383,
 'remain': 0.025588738883683383,
 'remained': 0.017059159255788922,
 'replacement': 0.008529579627894461,
 'reported': 0.008529579627894461,
 'required': 0.008529579627894461,
 'requirements': 0.008529579627894461,
 'resolution': 0.017059159255788922,
 'responding': 0.008529579627894461,
 'response': 0.008529579627894461,
 'responsible': 0.008529579627894461,
 'resulting': 0.008529579627894461,
 'revenue': 0.07676621665105016,
 'rise': 0.025588738883683383,
 'rising': 0.008529579627894461,
 'risk': 0.017059159255788922,
 's3': 0.008529579627894461,
 's4': 0.008529579627894461,
 's9': 0.008529579627894461,
 'said': 0.008529579627894461,
 'sales': 0.1791211721857837,
 'samsung': 0.24735780920893938,
 'saw': 0.025588738883683383,
 'scaling': 0.008529579627894461,
 'screen': 0.017059159255788922,
 'screens': 0.017059159255788922,
 'season': 0.025588738883683383,
 'seasonal': 0.008529579627894461,
 'seasonality': 0.13647327404631138,
 'seasonally': 0.008529579627894461,
 'second': 0.017059159255788922,
 'secure': 0.008529579627894461,
 'secured': 0.008529579627894461,
 'seek': 0.008529579627894461,
 'seeking': 0.008529579627894461,
 'sees': 0.008529579627894461,
 'segment': 0.034118318511577844,
 'sell': 0.008529579627894461,
 'semiconductor': 0.034118318511577844,
 'semiconductors': 0.008529579627894461,
 'sensors': 0.042647898139472305,
 'server': 0.051177477767366766,
 'servers': 0.025588738883683383,
 'services': 0.017059159255788922,
 'set': 0.017059159255788922,
 'shipments': 0.05970705739526123,
 'significantly': 0.008529579627894461,
 'size': 0.025588738883683383,
 'sized': 0.017059159255788922,
 'slightly': 0.008529579627894461,
 'slow': 0.017059159255788922,
 'slowed': 0.008529579627894461,
 'smartphone': 0.06823663702315569,
 'smartphones': 0.09382537590683908,
 'smartthings': 0.008529579627894461,
 'software': 0.008529579627894461,
 'solid': 0.051177477767366766,
 'solidify': 0.008529579627894461,
 'solutions': 0.034118318511577844,
 'specifically': 0.008529579627894461,
 'spite': 0.008529579627894461,
 'sporting': 0.025588738883683383,
 'ssd': 0.025588738883683383,
 'stable': 0.025588738883683383,
 'stack': 0.017059159255788922,
 'start': 0.008529579627894461,
 'stations': 0.008529579627894461,
 'steady': 0.008529579627894461,
 'storage': 0.008529579627894461,
 'stores': 0.008529579627894461,
 'strategic': 0.017059159255788922,
 'strategy': 0.008529579627894461,
 'strengthen': 0.042647898139472305,
 'strengthened': 0.008529579627894461,
 'strengthening': 0.05970705739526123,
 'strive': 0.008529579627894461,
 'strong': 0.1279436944184169,
 'stronger': 0.008529579627894461,
 'supply': 0.034118318511577844,
 'supplying': 0.008529579627894461,
 'tablets': 0.008529579627894461,
 'technological': 0.008529579627894461,
 'technologies': 0.017059159255788922,
 'technology': 0.05970705739526123,
 'term': 0.008529579627894461,
 'thanks': 0.05970705739526123,
 'total': 0.051177477767366766,
 'traditionally': 0.008529579627894461,
 'transition': 0.008529579627894461,
 'trend': 0.008529579627894461,
 'trends': 0.008529579627894461,
 'trillion': 0.1279436944184169,
 'try': 0.008529579627894461,
 'tv': 0.05970705739526123,
 'tvs': 0.05970705739526123,
 'uhd': 0.008529579627894461,
 'ultra': 0.042647898139472305,
 'uncertainties': 0.008529579627894461,
 'upcoming': 0.008529579627894461,
 'upgrades': 0.008529579627894461,
 'ups': 0.008529579627894461,
 'usability': 0.008529579627894461,
 'usage': 0.008529579627894461,
 'used': 0.008529579627894461,
 'utilization': 0.008529579627894461,
 'value': 0.034118318511577844,
 'valued': 0.008529579627894461,
 'various': 0.008529579627894461,
 'vendors': 0.017059159255788922,
 'visual': 0.008529579627894461,
 'vr': 0.008529579627894461,
 'washing': 0.025588738883683383,
 'weak': 0.1279436944184169,
 'weighed': 0.008529579627894461,
 'winter': 0.008529579627894461,
 'won': 0.008529579627894461,
 'world': 0.008529579627894461,
 'xnm': 0.008529579627894461,
 'year': 0.06823663702315569,
 'yield': 0.008529579627894461,
 'yoy': 0.06823663702315569}

In [0]: