arbelt

## ----, include=FALSE-----------------------------------------------------
library(knitr)


## ------------------------------------------------------------------------
source("pre_azw.R")


## ------------------------------------------------------------------------

arbelt

;; Usage Example:
;;  
;; <!-- BEGIN RECEIVE ORGTBL ${1:YOUR_TABLE_NAME} -->
;; <!-- END RECEIVE ORGTBL $1 -->
;;  
;; <!-- 
;; #+ORGTBL: SEND $1 orgtbl-to-gfm
;; | $0 | 
;; -->

arbelt

# CAVEATS:
# 
# 1. This requires nonstandard fonts.  Showtext is the best way to handle this portably, BUT
# it doesn't work within the RStudio viewer pane.  Exported files (and knitr) are fine, also
# interactive sessions without RStudio (e.g., using XQuartz).
#
# When working in RStudio, I generally don't change the font and preview an "ugly" version
# of the chart.  Just make sure all the elements are set when exporting.
#
# To set up showtext:

arbelt

#!/usr/bin/env Rscript

if (!require(pacman, quiet = TRUE)) install.packages("pacman")

pacman::p_load(docopt, dplyr, stringr, purrr)

"
Usage:
  package.r [options] <pkgname>
  package.r <pkgname> [-i <import>...]

arbelt

[[ -x /usr/local/bin/zsh ]] && \
    grep '^/usr/local/bin/zsh' /etc/shells && \
    sudo sh -c 'echo /usr/local/l/bin/zsh >> /etc/shells'

arbelt

ctrl_table = {
    sends_escape = true,
    last_mods = {}
}

control_key_timer = hs.timer.delayed.new(0.15, function()
    ctrl_table["send_escape"] = false
    -- log.i("timer fired")
    -- control_key_timer:stop()
end

arbelt

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

arbelt

library(stringr)
library(purrr)

match_multiple <- function(strings, patterns){
  match_fns <- map(
    as.list(patterns), 
    ~ partial(str_detect, pattern = .,  .lazy = FALSE, .first = FALSE))
  reduce(invoke_map(match_fns, list(list(strings))), `|`)
}

arbelt

library(tidyverse, purrr)

df <- tribble(~a, ~b, ~c, ~d,
              1, 2, NA, 1,
              1, 2, 3, NA,
              2, 2, 1, 1,
              2, 2, 1, 2)

keys_to_merge <- df %>% group_by(a,b) %>% 
  summarise_each(funs(sum(unique(.) %>% is.na %>% `!`))) %>% 

arbelt

abbr R 'R --no-save'
abbr gst 'git status'
abbr gd 'git diff'
abbr ga 'git add'
abbr gc 'git commit'
abbr gdc 'git diff --cached'
abbr gcm 'git commit -m'
abbr gdt 'git difftool --extcmd icdiff'
abbr gl 'git pull'
abbr gco 'git checkout'