Run a naive Bayes classificatory

naivebayes.py

import pandas as pd
# vectorize words 
from sklearn.feature_extraction.text import CountVectorizer  
# naive bayes 
from sklearn.naive_bayes import MultinomialNB 
from sklearn.metrics import auc, roc_curve
# train test split 
from sklearn.model_selection import train_test_split

# MAIN 
# preprocess steps
# ... 
#create train, val and test
X_train, X_valid, y_train, y_valid = train_test_split(
        tweets_df['clean_text3'], target_df['sentiment'], train_size=0.75
    )
# count vectorizer
vectorizer = CountVectorizer()
# transform 
X_train = vectorizer.fit(X_train)
X_valid = vectorizer.transform(X_valid)
# model
classifier = MultinomialNB() 
classifier.fit(X_train, y_train)
# run predictions
y_pred = classifier.predict(X_valid)
# compute metrics
fpr, tpr, thresholds = roc_curve(y_valid, y_pred)
roc_auc = auc(fpr, tpr)