gistfile1.txt

import fileinput
from string import join
import json
import csv
import json
### read the output from MAHOUT and collect into hash ###
with open('x','rb') as csv_file:
    csv_reader = csv.reader(csv_file,delimiter='\t')
    old_id = ""
    indicators = []
    update = {"_id":""}
    doc = {"indicators":[], "numFields":0}
    for row in csv_reader:
        id = row[0]
        if (id != old_id and old_id != ""):
            update["_id"] = old_id
            doc["indicators"] = indicators
            doc["numFields"] = len(indicators)
            print(json.dumps(update))
            print(json.dumps(doc))
            indicators = [row[1]]
        else:
            indicators.extend(row[1])
        old_id = id