who.py

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from NLTKPreprocessor import NLTKPreprocessor
import os
import json

PATH = "new.model"

model = Pipeline([
    ('vectorizer', TfidfVectorizer(min_df=1,ngram_range=(1,3))),
    ('clf',MultinomialNB(alpha=.5))
])

with open("questions.json","r") as file:
    content = file.read()
    questions = json.loads(content)
    x = []
    y =  []
    for question in questions:
        x.append(question["text"])
        y.append(question["intentName"])

    model.fit(x, y)

while True:
    print ("Enter the question:")
    print model.predict([raw_input()])


#Train classifier