import utils
from sklearn.svm import SVC
from sklearn.model_selection import cross_val_score
from hyperopt import fmin, tpe, hp, STATUS_OK, Trials
data = utils.read_data()
X = utils.combined_embeddings(data.text.tolist())
y = data.sentiment
def hyperopt_train_SVC(params):
clf = SVC(decision_function_shape='ovo', probability=True, **params)
return cross_val_score(clf, X, y).mean()
space = {
'C': hp.uniform('C', 0, 10),
'kernel': hp.choice('kernel', ['linear', 'sigmoid', 'rbf']),
'gamma': hp.uniform('gamma', 0, 10)
}
def f(params):
acc = hyperopt_train_SVC(params)
return {
'loss': -acc,
'status': STATUS_OK
}
trials = Trials()
best = fmin(
f,
import utils
import pickle
from os.path import isfile
from sklearn.ensemble import ExtraTreesClassifier as ETC
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
filename = '/usr/src/app/sentiment/models/pickles/BernoulliNB.pickle'
if isfile(filename) == False:
train, test = train_test_split(utils.read_data(), test_size=0.2)
train_embeddings = utils.combined_embeddings(train['text'].tolist())
test_embeddings = utils.combined_embeddings(test['text'].tolist())
clf = ETC(n_estimators=100)
clf.fit(train_embeddings, train['sentiment'])
prediction = clf.predict(test_embeddings)
report = classification_report(test['sentiment'], prediction)
print(report)
with open(filename, 'wb') as f:
pickle.dump(clf, f)
else:
print('Already Trained!')