echoDoc0.1.py 文件源码

def newDBSCANModel(vectorFile, outputFile):
    model = Doc2Vec.load("Models\\" + vectorFile)
    vecs = []
    for doc in range(0, len(model.docvecs)):
        doc_vec = model.docvecs[doc]
        # print doc_vec
        vecs.append(doc_vec.reshape((1, 300)))

    doc_vecs = np.array(vecs, dtype='float')  # TSNE expects float type values

    # print doc_vecs
    docs = []
    for i in doc_vecs:
        docs.append(i[0])
    db = DBSCAN(eps=0.03, algorithm="brute", metric='cosine').fit(docs)
    joblib.dump(db, outputFile)


    core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
    core_samples_mask[db.core_sample_indices_] = True
    labels = db.labels_
    n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
    clusters = db.labels_.tolist()
    cluster_info = {'labels': model.docvecs.offset2doctag,
                    "index, wordcount and repeated words": [model.docvecs.doctags[x] for x in
                                                            model.docvecs.offset2doctag],
                    'clusters': clusters}
    sentenceDF = pd.DataFrame(cluster_info, index=[clusters],
                              columns=['labels', "index, wordcount and repeated words", 'clusters'])
    print(sentenceDF)
    sentenceDF.to_csv("DBSCAN.csv")

    print('Estimated number of clusters: %d' % n_clusters_)