tagsListDF.py

import pymongo as pm
import unicodedata

client = pm.MongoClient()
db = client.instagram
tagsDB = db.tags

tagsList = []
for tag in tagsDB.find():
    tagsList.append((str(tag['_id']), [unicodedata.normalize('NFKD', t).encode('ascii','ignore') 
                                    for t in tag['tags']
                                       if unicodedata.normalize('NFKD', t).encode('ascii','ignore') != '']))

#filter tags list - remove duplicated tags
filteredList = []
for tag in tagsList:
    filteredList.append((tag[0], list(set(tag[1]))))

#create Spark Data Frame
tagsListDF = sc.parallelize(filteredList).toDF(["id", "tokens"])