lukleh

df = spark.sql('select abs(n1 - n2) as rdiff, count(1) as cnt from tempsampledata group by rdiff order by cnt desc')
df.persist()
df.show(n=100, truncate=False)

lukleh

import pyspark.sql.functions as F

df = spark.range(1, 1000000, numPartitions=2000)
df = df.withColumn('n1', (F.rand() * 100000).cast('integer')).withColumn('n2', (F.rand() * 100000).cast('integer'))
df.createOrReplaceTempView('tempsampledata')

lukleh

#!/usr/bin/env bash

current_branch="$(git rev-parse --abbrev-ref HEAD)"

branch_regex='([0-9]+)_.*'
if [[ ! $current_branch =~ $branch_regex ]]; then
    echo "branch does not start with a number" >&2
    exit 1
fi
branch_num=${BASH_REMATCH[1]}

lukleh

import asyncio, random
import threading
import time

q = asyncio.Queue()

@asyncio.coroutine
def produce():
    while True:
        print("putting")

lukleh

-- scanl definition
scanl :: (a -> b -> a) -> a -> [b] -> [a]
scanl f q ls =
  q : (case ls of
         [] -> []
         x:xs -> scanl f (f q x) xs)


fibs = 1 : scanl (+) 1 fibs

lukleh

__version__ = "0.1.6.8"

if __name__ == "__main__":
    import sys
    import argparse


    def increment_line(args):
        vi = [int(i) for i in __version__.split('.')]
        print('current version: %s' % __version__)

lukleh

echo "Delete DBs"
curl -s -X DELETE 'http://localhost:9200/test_twitter_cs/'
echo
curl -s -X DELETE 'http://localhost:9200/test_twitter_en/'
echo
echo "Create Czech index"
curl -s -X PUT 'http://localhost:9200/test_twitter_cs/'
echo
echo "Create English index"
curl -s -X PUT 'http://localhost:9200/test_twitter_en/'