def extractFeaturesFromFile(data_file="sentiment.txt", stoplist=None):
res = []
if stoplist is None:
stoplist = makeStoplist()
with open(data_file, "r", encoding=ENCODING) as f:
for line in f:
res.append(extractFeaturesFromString(line, stoplist))
return res
def learn():
stoplist = makeStoplist()
features = extractFeaturesFromFile(stoplist=stoplist)
vectorizer = TfidfVectorizer(encoding=ENCODING)
X_train = vectorizer.fit_transform([" ".join(feature[1:]) for feature in features])
y_train = np.zeros(len(features))
for i in range(len(features)):
if features[i][0] == "+1":
y_train[i] = 1
clf = LogisticRegression()
clf.fit(X_train, y_train)
io.savemat("X_train", {"X_train": X_train})
np.save("y_train", y_train)
joblib.dump(vectorizer, "tfidf.vec")
joblib.dump(clf, "logreg.clf")
#coding:utf-8
import sys
from sklearn.externals import joblib
from question71 import makeStoplist
from question72 import extractFeaturesFromString
if __name__ == "__main__":
vectorizer = joblib.load("tfidf.vec")
clf = joblib.load("logreg.clf")
stoplist = makeStoplist()
while True:
test = input()
test = extractFeaturesFromString(test, stoplist)
print(["-1", "+1"
][int(clf.predict(vectorizer.transform([" ".join(test)]))[0])])
sys.stdout.flush()