from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np
import sklearn.metrics
from sklearn.cluster import KMeans

with open("dev-0/in.tsv") as f:
    content = f.readlines()
    vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)
    vectorizer = TfidfVectorizer()
    document_vectors = vectorizer.fit_transform(content)
    kmeans = KMeans(n_clusters=77, random_state=0).fit(document_vectors)
    pred_y = kmeans.fit_predict(document_vectors)
    t=kmeans.labels_
    t=np.array2string(t, precision=2, separator='\n',suppress_small=True)
    f = open("dev-0/out.tsv", "a")
    f.write(t)