firemonk9

[
   {
      "classification":"spark",
      "properties":{
         "maximizeResourceAllocation":"true",
         "spark.yarn.executor.memoryOverhead":"1024M"
      },
      "configurations":[
         
      ]

firemonk9

CREATE TABLE dataq_demo.tbl_ItemTransactions1 
 (
     TranID SERIAL
     ,TransactionDate TIMESTAMPTZ
     ,TransactionName TEXT
     
 );

drop table dataq_demo.tbl_ItemTransactions1

firemonk9

CREATE TABLE dataq_demo.large_test (num1 bigint, num2 double precision, num3 double precision);

INSERT INTO dataq_demo.large_test (num1, num2, num3)
  SELECT round(random()*10), random(), random()*142
  FROM generate_series(1, 20000000) s(i);

firemonk9

for file in *; do mv "$file" "${file//[ ()@$]/_}" ; done

firemonk9

import subprocess	
vval='"c:\Program Files (x86)\Google\Chrome\Application\chrome.exe" <URL>'


def run_win_cmd(cmd):
    result = []
    process = subprocess.Popen(cmd,
                               shell=True,
                               stdout=subprocess.PIPE,
                               stderr=subprocess.PIPE)

firemonk9

import xlrd
import csv
import glob
import os
from os import sys

def csv_from_excel(excel_file):
    workbook = xlrd.open_workbook(excel_file)
    all_worksheets = workbook.sheet_names()
    for worksheet_name in all_worksheets:

firemonk9

There are two modes to compare the datasets.
a. Compare two way : Compares source and destination records.