J'ai vérifié l'image de l'Université des sciences sur Twitter avec Word2Vec.

# gem install twitter
require "twitter"

client = Twitter::REST::Client.new do |config|
  config.consumer_key        = ""
  config.consumer_secret     = ""
  config.access_token        = ""
  config.access_token_secret = ""
end

@result = client.search("Université des sciences").take(10000)

File.open("tus.csv", 'w') do |file|
  @result.each do |tweet|
    file.write(tweet.text.gsub(/(\s)/,""))
    file.write("\n")
  end
end

cd /usr/local/lib/mecab/dic
mkdir userdic
cd userdic
touch tus.csv
echo 'Université des sciences,,,1,nom,Général,*,*,*,*,Rikadai,Rikadai,Rikadai' >> tus.csv

#compiler
/usr/local/Cellar/mecab/0.996/libexec/mecab/mecab-dict-index \
-d /usr/local/lib/mecab/dic/ipadic \
-u tus.dic \
-f utf-8 \
-t utf-8 tus.csv

#Appuyez sur Entrée pour compiler

reading tus.csv ... 1
emitting double-array: 100% |###########################################| 

done!

#traverser le chemin

vi /usr/local/etc/mecabrc
#Spécifiez où se trouve le dic généré
userdic = /usr/local/lib/mecab/dic/userdic/tus.dic

# coding: UTF-8
import pandas as pd
import numpy as np
import MeCab

tweets = pd.read_csv('/Users/Hiroto/git/scripts/tus.csv').tweet

#Créer un fichier séparé
wakati = ""
for tweet in tweets:
    mt = MeCab.Tagger("-Owakati")
    wakati = wakati + mt.parse(tweet)

f = open('tus_wakati.txt', 'w')
f.write(wakati)
f.close()

# word2vec
from gensim.models import word2vec
data = word2vec.Text8Corpus('tus_wakati.txt')
model = word2vec.Word2Vec(data, size=100)

out=model.most_similar(positive=[u'Université des sciences'],topn= 100)
for x in out:
    print(x[0],x[1])

Recommended Posts