path= r'C:\Users\vrozenbaum\Documents\Inter_POC\IACC\clust'

#tagging the files
class DocIterator(object):
    def __init__(self, doc_list, labels_list):
        self.labels_list = labels_list
        self.doc_list = doc_list

    def __iter__(self):
        for idx, doc in enumerate(self.doc_list):
            yield TaggedDocument(words=doc.split(), tags=[self.labels_list[idx]])

labels = [f for f in listdir(path) if f.endswith('-out.csv')]
print(labels)
data = []
for doc in labels:
    data.append(open(join(path, doc), 'r',errors='ignore').read())

it = DocIterator(data, labels)