python 问题天真的贝叶斯#machine_learning

Posted 2021-05-09

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

count_vect = CountVectorizer()
values = []
results = []
tsv = pd.read_table("data.tsv").values.tolist()
for row in tsv:
    values.append(row[-1])
    results.append(1 if row[1] == 'p' else 0)
X = count_vect.fit_transform(values)
y = np.array(results)
b_clf = BernoulliNB()
b_clf.fit(X, y)
print(b_clf.score(X, y))
#=> 0.7609423570921667
m_clf = MultinomialNB()
m_clf.fit(X, y)
print(m_clf.score(X, y))
#=> 0.7551450818115486