MichaelChirico

library(data.table)
library(sp)
library(rgdal)
library(rgeos)

# Via CA GIS Data site
ca = readOGR("~/Downloads/CA_Counties", "CA_Counties_TIGER2016")

travel_zone = gBuffer(
  ca[ca$NAME == "Santa Clara", ],

MichaelChirico

library(data.table)

DT = fread("~/Downloads/spotifyclass.csv")

# add new columns. they're great predictors!
DT[ , paste0("V", 1:nrow(DT)) := replicate(.N, rnorm(.N), simplify = FALSE)]

summary(lm(DT$target ~ ., data = DT[ , .SD, .SDcols = patterns("^V")]))$r.squared

MichaelChirico

# caveat -- doesn't have 100% overlap w the dictionary
CENTER=u
LETTERS=${CENTER}cfinot
grep $CENTER /usr/share/dict/words | grep -E "^[$LETTERS]{4,}$"

MichaelChirico

#/bin/sh
# built on ImageMagick tools via convert; constituent SO answers:
#   https://askubuntu.com/a/101527/362864
#   https://askubuntu.com/a/1052902/362864
#   https://stackoverflow.com/a/20075227/3576984
#   https://unix.stackexchange.com/a/24019/112834

# INPUT: foo.gif
# step 0: isolate foo to its own folder
TMPDIR=/tmp/__flop_mirror__

MichaelChirico

test_xml = '
<div>
  <div>
    <div>
      <div>
        <p>1</p>
        <p>2</p>
        <p>3</p>
      </div>
    </div>

MichaelChirico

# NB: not fully reproducible since I've had to censor some stuff / obscure credentialling
library(data.table)
mtcars = cbind(car = rownames(mtcars), mtcars)
mtcars = lapply(mtcars, function(x) if (is.character(x)) sQuote(x, "'") else x)
colnames = toString(names(mtcars))
mtcars$sep = ', '
# \n\t are bells&whistles to make cat(query) look nicer
mtcars$collapse = '),\n\t('
query = sprintf("select * from (values\n\t(%s)\n)\nt(%s)", do.call(paste, mtcars), colnames)
presto_rest_endpoint = file.path('/path/to/rest', 'statement')

MichaelChirico

# sources:
#   https://prestodb.io/docs/current/functions/datetime.html
#   https://docs.oracle.com/javase/7/docs/api/java/text/SimpleDateFormat.html
# NB: when multiple matches are possible (e.g. %h=%I), the higher one is "preferred"
# NB: %r/%T are basically blocked out from being returned Java->Presto by putting
#     them at the bottom, as a way of preferring the more verbose "full" form
# NB: the following supported formats don't have an exact equivalent: %w, %x, %v
time_fmt_mapping = fread('posix,java
%Y,yyyy
%y,yy

MichaelChirico

P0 = c(...)        # initial principal
R = c(...)         # annualized interest
r = (1+R)^(1/12)-1 # monthly interest

np = length(P0)

X = ...  # monthly willingness-to-pay

BB = 1e7 # repetitions
# slightly more principled... find how many months it takes if

MichaelChirico

library(data.table)
library(microbenchmark)

get_reduce = function(FUN, ELEMENT) {
  function(..., na.rm=FALSE) {
    l = list(...)
    if (length(l) == 1L && is.list(l[[1L]])) l = l[[1L]]
    if (length(l) == 1L && (identical(FUN, `|`) || identical(FUN, `&`))) l[[1L]] = as.logical(l[[1L]])
    if (na.rm) {
      # TODO: nafill to support complex input, then use nafill here

MichaelChirico

library(data.table)
library(rtweet)
library(ggplot2)
library(ggrepel)

nyt_words = get_timeline(
  'NYT_first_said', 
  n = 900, 
  exclude_replies = TRUE, 
  include_rts = FALSE