echoDoc0.1.py 文件源码

def newKMeansModel(vectorFile, outputFile, numClusters):
    # https://stackoverflow.com/questions/43476869/doc2vec-sentence-clustering

    model = Doc2Vec.load("Models\\" + vectorFile)
    docVecs = model.docvecs.doctag_syn0
    km = KMeans(n_clusters=numClusters)
    print("Starting")
    km.fit(docVecs)
    print("Fitting Data")
    joblib.dump(km, outputFile)