NLP基础实验⑤：朴素贝叶斯和SVM

一、朴素贝叶斯

from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn import metrics
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.datasets import fetch_20newsgroups

newsgroups_train = fetch_20newsgroups(subset='train')
newsgroups_test = fetch_20newsgroups(subset='test')
X_train = newsgroups_train.data
X_test = newsgroups_test.data
y_train = newsgroups_train.target
y_test = newsgroups_test.target

text_clf = Pipeline([('vect', CountVectorizer()),
                     ('tfidf', TfidfTransformer()),
                     ('clf', MultinomialNB()),
                     ])

text_clf.fit(X_train, y_train)


predicted = text_clf.predict(X_test)

print(metrics.classification_report(y_test, predicted))

理论参考：https://blog.csdn.net/u013710265/article/details/72780520

二、支持向量机

from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline
from sklearn import metrics
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.datasets import fetch_20newsgroups

newsgroups_train = fetch_20newsgroups(subset='train')
newsgroups_test = fetch_20newsgroups(subset='test')
X_train = newsgroups_train.data
X_test = newsgroups_test.data
y_train = newsgroups_train.target
y_test = newsgroups_test.target

text_clf = Pipeline([('vect', CountVectorizer()),
                     ('tfidf', TfidfTransformer()),
                     ('clf', LinearSVC()),
                     ])

text_clf.fit(X_train, y_train)


predicted = text_clf.predict(X_test)

print(metrics.classification_report(y_test, predicted))

理论参考：https://blog.csdn.net/IOT_victor/article/details/83270404