[PYTHON] I checked the image of Science University on Twitter with 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("Science University").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 'Science University,,,1,noun,General,*,*,*,*,Rikadai,Rikadai,Rikadai' >> tus.csv

#compile
/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

#Press Enter to compile

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

done!

#pass through path

vi /usr/local/etc/mecabrc
#Specify where the generated dic is
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

#Create a word-separated file
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'Science University'],topn= 100)
for x in out:
    print(x[0],x[1])

Recommended Posts