davidandrzej

import pandas as pd
import itertools

# Tag every row in a CSV with repeating 3 tags
df = pd.read_csv('source.csv')
tags = ['foo','baz','buzz']
df['tag'] = [tag for (tag, row) in zip(itertools.cycle(people), df['targetcolumn'])]
df.to_csv('destination.csv')

davidandrzej

//
// CASE 1: Map without default value
// Result: behavior seems reasonable
//
val boo = Map("a" -> 1, "b" -> 2) 
// boo: scala.collection.immutable.Map[String,Int] = Map(a -> 1, b -> 2)
boo("c") // java.util.NoSuchElementException: key not found: c
boo.get("c") //res1: Option[Int] = None

//

davidandrzej

import scalaz._, Scalaz._
val data = Vector(Map(1 -> "a", 2 -> "b"), Map(2 -> "c", 3 -> "d"))
data.foldMap(_.keys.toSet)
// res0: scala.collection.immutable.Set[Int] = Set(1, 2, 3)

davidandrzej

import csv
import random

outf = open('output.csv','w')
writer = csv.writer(outf)

for row in csv.reader(open('input.csv', 'rb')):
    if(random.randint(0,1) == 0): # eg, drop 50%
        writer.writerow(row)
outf.close()

davidandrzej

<!-- INSERT MATHJAX CONFIGURATION FROM MATH.STACKEXCHANGE -->
<script type="text/x-mathjax-config">
  MathJax.Hub.Config({
    jax: ["input/TeX", "output/HTML-CSS"],
    tex2jax: {
      inlineMath: [ ['$', '$'] ],
      displayMath: [ ['$$', '$$']],
      processEscapes: true,
      skipTags: ['script', 'noscript', 'style', 'textarea', 'pre', 'code']
    },

davidandrzej

// 
// If a "lazy val" initialization fails, the val is not initialized 
// to anything and subsequent calls re-evaluate the RHS
// 
object LazyRetry extends App {

  class ServiceFactory() {
    // Only returns a value after two failures
    // (simulate waiting for service availability)
    var tries = 0

davidandrzej

object CombineMaps {
  type Counts = Map[String,Int]	
  def combine(x: Counts, y: Counts): Counts = {
    val x0 = x.withDefaultValue(0)
    val y0 = y.withDefaultValue(0)
    val keys = x.keys.toSet.union(y.keys.toSet)
    keys.map{ k => (k -> (x0(k) + y0(k))) }.toMap
  }
}

davidandrzej

// Map.keys returns an Iterable that happens to be backed by a Set so 
// if you map() over it you get Set-like behavior.  Good times.
//
// $ scalac TrickyMapKeys.scala
// $ scala TrickyMapKeys
// keys mod 2 (VERSION A): Set(0, 1)
// keys mod 2 (VERSION B): List(0, 0, 1, 0)
//
object TrickyMapKeys extends App {
 

davidandrzej

//
// TIL Scala Map.mapValues returns a lazy view
// 
// This has the horrific consequence that supplying a non-pure function
// can yield a result map with unexpected / undesired behavior (see below)
//
// Further discussion here: 
// http://stackoverflow.com/questions/14882642/scala-why-mapvalues-produces-a-view-and-is-there-any-stable-alternatives
// https://issues.scala-lang.org/browse/SI-4776
// 

davidandrzej

scala> val x = Seq(1,2)
x: Seq[Int] = List(1, 2)

scala> val y = Seq(2,3)
y: Seq[Int] = List(2, 3)

scala> x.union(y)
res0: Seq[Int] = List(1, 2, 2, 3)