sunahsuh

#!/usr/bin/python3

from google.cloud import bigquery
import re
import requests
import os
import json
from redash_client.client import RedashClient
import csv

sunahsuh

#!/usr/bin/python3

from google.cloud import bigquery
import re


DATASET = 'telemetry'


TABLE_IDS = [

sunahsuh

import argparse
import logging

import apache_beam as beam
import apache_beam.transforms.window as window
from apache_beam.transforms.core import Filter
from apache_beam.examples.wordcount import WordExtractingDoFn
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import SetupOptions
from apache_beam.options.pipeline_options import StandardOptions

sunahsuh

import boto3
import click
import re
import threading
from time import sleep
from queue import Queue
from itertools import ifilter


class DateMatchWorker(threading.Thread):

sunahsuh

import argparse
import csv
import json


BASE_SCHEMA = {
  "eventGroupName": "dt",
  "filters": {
    "docType": [
      "main"

sunahsuh

#!/usr/bin/python

from datetime import datetime, timedelta
import argparse
import threading
import Queue
import subprocess

fmt = "%Y%m%d"
FROM_PATH = "telemetry-parquet"

sunahsuh

# Usage: download_spark_log.sh j-XXXXXXX <optional download path>
# Required: aws cli and jq

cluster=$1
# Optional second argument defaults to .
dlLoc=${2:-\.}

instance=$(aws emr list-instances --cluster-id "$cluster" --instance-group-types MASTER | jq -r '.Instances[0].Ec2InstanceId')
logLocs3n=$(aws emr describe-cluster --cluster-id $cluster | jq -r '.Cluster.LogUri')
logLoc=${logLocs3n//s3n:/s3:}

sunahsuh

sunahsuh

javascript:(function() {
  var bookmarklet = {
    init: function() {
      this.parse();
    },
    parse: function() {
      page = "";
      $(".Track:visible")
        .children(".info")
        .each(function() {

sunahsuh

index
4
p iteration
0, p iteration
1, index
5
p iteration
0, p iteration
0, p iteration
1, 0, p iteration