gregburek

import time

def RateLimited(maxPerSecond):
    minInterval = 1.0 / float(maxPerSecond)
    def decorate(func):
        lastTimeCalled = [0.0]
        def rateLimitedFunction(*args,**kargs):
            elapsed = time.clock() - lastTimeCalled[0]
            leftToWait = minInterval - elapsed
            if leftToWait>0:

nicklasos

-module(plists).
-export([pmap/2,pforeach/2,npforeach/2, parmap/2]).

%%% Map

pmap(F, L) ->
  S = self(),
  Pids = lists:map(fun(I) -> spawn(fun() -> pmap_f(S, F, I) end) end, L),
  pmap_gather(Pids).

samuelsmal

from pyspark.sql.functions import udf
from pyspark.sql.types import BooleanType

def regex_filter(x):
    regexs = ['.*ALLYOURBASEBELONGTOUS.*']
    
    if x and x.strip():
        for r in regexs:
            if re.match(r, x, re.IGNORECASE):
                return True

doyle

curl -X PUT -T test_s3.txt -L "https://your-bucket.s3.amazonaws.com/url-stuff"