clarkfitzg

@article{floratou2014sql,
  title={SQL-on-Hadoop: full circle back to shared-nothing database architectures},
  author={Floratou, Avrilia and Minhas, Umar Farooq and {\"O}zcan, Fatma},
  journal={Proceedings of the VLDB Endowment},
  volume={7},
  number={12},
  pages={1295--1306},
  year={2014},
  publisher={VLDB Endowment}
}

clarkfitzg

clarkfitzg

clark@campus-108-089 ~/dev/Rtesseract (master)
$ ./configure
checking for pkg-config... /usr/local/bin/pkg-config
Package tesseract was not found in the pkg-config search path.
Perhaps you should add the directory containing `tesseract.pc'
to the PKG_CONFIG_PATH environment variable
No package 'tesseract' found
Package tesseract was not found in the pkg-config search path.
Perhaps you should add the directory containing `tesseract.pc'
to the PKG_CONFIG_PATH environment variable

clarkfitzg

#!/usr/bin/env Rscript

# 2018-06-04 11:26:12
# Automatically generated from R by autoparallel version 0.0.1

library(parallel)

nworkers = 2
timeout = 600

clarkfitzg

# Given observations of linear functions f and g at points a and b this
# calculates the integral of f * g from a to b.
#
# Looks like it will already work as a vectorized function. Sweet!
inner_one_piece = function(a, b, fa, fb, ga, gb)
{
    # Roughly following my notes
    fslope = (fb - fa) / (b - a)
    gslope = (gb - ga) / (b - a)

clarkfitzg

# Following:
# https://cran.r-project.org/web/packages/rslurm/vignettes/rslurm.html

library(rslurm)


test_func <- function(par_mu, par_sd) {
    samp <- rnorm(10^6, par_mu, par_sd)
    c(s_mu = mean(samp), s_sd = sd(samp))
}

clarkfitzg

#' Split And Append Results To CSV File
#'
#' x will be split by f and each group will be appended to a directory of
#' csv files named according to f
#'
#' @param x data frame to split
#' @param f factor defining splits
#' @param ... further arguments to split
#' @param dirname character directory, will be created if doesn't exist
#' @return NULL

clarkfitzg

# Mon Aug 28 16:33:46 PDT 2017
#
# sweep() used to implement scale() is inefficient. Profiling shows that
# only 2% of the time is spent in colMeans. The only other thing to do is
# subtract the mean, which should be fast, but isn't because memory
# layout requires a transpose to use recycling (broadcasting).
#
# But I don't know how to do any better short of writing in C

library(microbenchmark)

clarkfitzg

cov_chunked = function(x, nchunks = 2L)
{

    p = ncol(x)
    indices = parallel::splitIndices(p, nchunks)

    diagonal_blocks = lapply(indices, function(idx) cov(x[, idx, drop = FALSE]))

    upper_right_indices = combn(indices, 2, simplify = FALSE)

clarkfitzg

# From wlandau
# https://github.com/duncantl/CodeDepends/issues/19

library(CodeDepends)


#' Recursively Find Global Variables
#'
#' TODO: Modify this to work without requiring that the code be evaluated
#' Probably means we can't use codetools::findGlobals