import subprocess as sub
import d2vec_kmeans as d2v
import numpy as np

# pull in text table
raw = sub.Popen(['cat', '/Users/Nick/Desktop/dtas/ContagiousIndex/DOC2VEC/DATA/rawtextfinal.txt'], stdout=sub.PIPE)
raw = raw.communicate()[0].split('\n')
raw = [tuple(ele.split('\t')) for ele in raw if ele != '' and len(ele.split('\t')) == 5]

# store text
raw_text = list(zip(*raw))[4]
raw_text
ids = list(zip(*raw))[0]