한국외대 DSC(Developer Student Club) 멤버들과 함께 머신러닝 스터디를 진행하면서 “머신 러닝 교과서“를 블로그에 정리한 내용입니다.
웹 애플리케이션에 머신 러닝 모델 저장
- 머신 러닝 모델의 현재 훈련 상태 저장하기
- SQLite 데이터베이스를 사용하여 데이터 저장하기
- 유명한 플라스크 웹 프레임워크 사용하여 웹 앱 개발하기
- 공개 웹 서버에 머신 러닝 앱 배포하기
9.1 학습된 사이킷런 추정기 저장
- pickle 모듈 사용
import pickle
import os
dest = os.path.join('movieclassifier', 'pkl_objects')
if not os.path.exists(dest):
os.makedirs(dest)
pickle.dump(stop, open(os.path.join(dest, 'stopwords.pkl'), 'wb'), protocol=4)
pickle.dump(clf, open(os.path.join(dest, 'classifier.pkl'), 'wb'), protocol=4)
from sklearn.feature_extraction.text import HashingVectorizer
import re
import os
import pickle
cur_dir = os.path.dirname(__file__)
stop = pickle.load(open(
os.path.join(cur_dir,
'pkl_objects',
'stopwords.pkl'), 'rb'))
def tokenizer(text):
text = re.sub('<[^>]*>', '', text)
emoticons = re.findall('(?::|;|=)(?:-)?(?:\)|\(|D|P)',
text.lower())
text = re.sub('[\W]+', ' ', text.lower()) \
+ ' '.join(emoticons).replace('-', '')
tokenized = [w for w in text.split() if w not in stop]
return tokenized
vect = HashingVectorizer(decode_error='ignore',
n_features=2**21,
preprocessor=None,
tokenizer=tokenizer)
import pickle
import re
import os
from vectorizer import vect
clf = pickle.load(open(os.path.join('pkl_objects', 'classifier.pkl'), 'rb'))
import numpy as np
label = {0:'양성', 1:'음성'}
example = ['I love this movie']
X = vect.transform(example)
print('예측: %s\n확률: %.2f%%' %\
(label[clf.predict(X)[0]],
np.max(clf.predict_proba(X))*100))
9.2 데이터를 저장하기 위해 SQLite 데이터베이스 설정
리뷰 저장하기
import sqlite3
conn = sqlite3.connect('reviews.sqlite')
c = conn.cursor()
c.execute('DROP TABLE IF EXISTS review_db')
c.execute('CREATE TABLE review_db (review TEXT, sentiment INTEGER, date TEXT)')
example1 = 'I love this movie'
c.execute("INSERT INTO review_db (review, sentiment, date) VALUES (?, ?, DATETIME('now'))", (example1, 1))
example2 = 'I disliked this movie'
c.execute("INSERT INTO review_db (review, sentiment, date) VALUES (?, ?, DATETIME('now'))", (example2, 0))
conn.commit()
conn.close()
conn = sqlite3.connect('reviews.sqlite')
c = conn.cursor()
c.execute("SELECT * FROM review_db WHERE date BETWEEN '2017-01-01 10:10:10' AND DATETIME('now')")
results = c.fetchall()
conn.close()
9.3 플라스크 웹 애플리케이션 개발
9.3.1 첫 번째 플라스크 애플리케이션
pip install flask
from flask import Flask, render_template, request
from wtforms import Form, TextAreaField, validators
app = Flask(__name__)
class HelloForm(Form):
sayhello = TextAreaField('',[validators.DataRequired()])
@app.route('/')
def index():
form = HelloForm(request.form)
return render_template('first_app.html', form=form)
@app.route('/hello', methods=['POST'])
def hello():
form = HelloForm(request.form)
if request.method == 'POST' and form.validate():
name = request.form['sayhello']
return render_template('hello.html', name=name)
return render_template('first_app.html', form=form)
if __name__ == '__main__':
app.run(debug=True)
9.3.2 폼 검증과 화면 출력
pip install wtforms
결과 페이지
<!doctype html>
<html>
<head>
<title>첫 번째 애플리케이션</title>
<link rel="stylesheet" href="">
</head>
<body>
<div> 님 안녕하세요!</div>
</body>
</html>
9.4 영화 리뷰 분류기를 웹 애플리케이션으로 만들기
9.4.1 파일과 폴더: 디렉터리 구조 살펴보기
책에서 살펴보자
9.4.2 메인 애플리케이션 app.py 구현
from flask import Flask, render_template, request
from wtforms import Form, TextAreaField, validators
import pickle
import sqlite3
import os
import numpy as np
# 로컬 디렉토리에서 HashingVectorizer를 임포트합니다
from vectorizer import vect
app = Flask(__name__)
######## 분류기 준비
cur_dir = os.path.dirname(__file__)
clf = pickle.load(open(os.path.join(cur_dir,
'pkl_objects',
'classifier.pkl'), 'rb'))
db = os.path.join(cur_dir, 'reviews.sqlite')
def classify(document):
label = {0: 'negative', 1: 'positive'}
X = vect.transform([document])
y = clf.predict(X)[0]
proba = np.max(clf.predict_proba(X))
return label[y], proba
def train(document, y):
X = vect.transform([document])
clf.partial_fit(X, [y])
def sqlite_entry(path, document, y):
conn = sqlite3.connect(path)
c = conn.cursor()
c.execute("INSERT INTO review_db (review, sentiment, date)"\
" VALUES (?, ?, DATETIME('now'))", (document, y))
conn.commit()
conn.close()
######## 플라스크
class ReviewForm(Form):
moviereview = TextAreaField('',
[validators.DataRequired(),
validators.length(min=15)])
@app.route('/')
def index():
form = ReviewForm(request.form)
return render_template('reviewform.html', form=form)
@app.route('/results', methods=['POST'])
def results():
form = ReviewForm(request.form)
if request.method == 'POST' and form.validate():
review = request.form['moviereview']
y, proba = classify(review)
return render_template('results.html',
content=review,
prediction=y,
probability=round(proba*100, 2))
return render_template('reviewform.html', form=form)
@app.route('/thanks', methods=['POST'])
def feedback():
feedback = request.form['feedback_button']
review = request.form['review']
prediction = request.form['prediction']
inv_label = {'negative': 0, 'positive': 1}
y = inv_label[prediction]
if feedback == 'Incorrect':
y = int(not(y))
train(review, y)
sqlite_entry(db, review, y)
return render_template('thanks.html')
if __name__ == '__main__':
app.run(debug=True)
9.4.3 리뷰 폼 구성
9.4.4 결과 페이지 템플릿 만들기
9.5 공개 서버에 웹 애플리케이션 배포
9.5.1 PythonAnywhere 계정 만들기
https://www.pythonanywhere.com/