similar_posts.py 文件源码

def gridSearch(data, params, true_k):

    tfidf = TfidfVectorizer(strip_accents=None,
                            lowercase=True,
                            sublinear_tf=True,
                            analyzer='word')

    lr_tfidf = Pipeline([('vect', tfidf),
                         ('clf', KMeans(init='k-means++',
                                        n_jobs=-1,
                                        random_state=0,
                                        verbose=0))])
    gsTfIdf = GridSearchCV(
        lr_tfidf, params, n_jobs=1, verbose=1)

    gsTfIdf.fit(data)
    print()
    print("Best score: %0.3f" % gsTfIdf.best_score_)
    print("Best parameters set:")
    best_parameters = gsTfIdf.best_estimator_.get_params()
    for param_name in sorted(params.keys()):
        print("\t%s: %r" % (param_name, best_parameters[param_name]))