Basic Text Classification with Scikit-learn [Question/Answer Classifier]

class.py

# ! usr/bin/python

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.externals import joblib
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer

text_clf = Pipeline([('vect', CountVectorizer()), ('tfidf', TfidfTransformer()), ('clf', MultinomialNB()),])
df = pd.read_csv('example.csv', header=None, sep=',', names=['tweets', 'class'])
X = df['tweets']
y = df['class']
text_clf.fit(X,y)
joblib.dump(text_clf, 'qa_modal.pkl') 
clf = joblib.load('qa_modal.pkl') 
docs_new = ['who are you', 'I love drinks', 'Do you know french']

predicted = clf.predict(docs_new)

print predicted

modal.py

# ! usr/bin/python

from sklearn.externals import joblib



clf = joblib.load('qa_modal.pkl') 
docs_new = ['who are you', 'Do you know me', 'Do you know french']


predicted = clf.predict(docs_new)

print predicted

can you please provide example.csv.