CountVectorizer

import pandas as pd
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer


train_data = [
	"I like apple",
    "I hate soccer",
    "I love you"
]
train_emotion = [
	"happy",
    "sad",
    "happy"
]

#####################  Train 과정  ######################

# CountVectorizer 객체 cv를 만들고, 
# fit_transform 으로  train_data 를 학습할 수 있게 벡터화
cv = CountVectorizer()
transformed_text = cv.fit_transform(train_data)

# MultinomialNB 객체 MB를 만들고, 
# fit으로 학습을 진행함 (위에서 만든 데이터로)
MB = MultinomialNB()
clf.fit(transformed_text,train_emotion)
########################################################

#####################  Inference 과정  ###################
# CountVectorizer의 transform으로 test 데이터를 벡터화
# predict
test_data = ['i am happy', 'who are you']
result_vector = cv.transform(test_data)
result = clf.predict(result_vector)
########################################################