chyikwei

import nltk
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import LatentDirichletAllocation

def print_top_words(model, feature_names, n_top_words):
    for topic_idx, topic in enumerate(model.components_):
        message = "Topic #%d: " % topic_idx
        message += " ".join([feature_names[i] + " (" + str(round(topic[i], 2)) + ")"
                             for i in topic.argsort()[:-n_top_words - 1:-1]])

chyikwei

presto> explain (type distributed, format json) select * from example.example.numbers;
                                                                                                               Query Plan
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 [ {
   "id" : "5",
   "name" : "Output",
   "identifier" : "[text, value]",
   "details" : "",
   "children" : [ {
     "id" : "63",