mfansler

#################################################################################
# INSTALL MAMBA ON GOOGLE COLAB
#################################################################################
! wget -O miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py37_4.10.3-Linux-x86_64.sh
! chmod +x miniconda.sh
! bash ./miniconda.sh -b -f -p /usr/local
! rm miniconda.sh
! conda config --add channels conda-forge
! conda install -y mamba
! mamba update -qy --all

mfansler

#!/usr/bin/env bash -l
#'   Usage: `bash -l new-cran-pkg.sh {r-package}`
#' Purpose: Generates a Conda Forge recipe using `conda_r_skeleton_helper` and
#'          pushes this to a personal fork of `staged-recipes`.
#'  Notes: Should be located in and run from a `staged-recipes` clone prefix.
#'         `git remote -v` should show `origin` set to a personal fork
#'         and `upstream` set to 'git@github.com:conda-forge/staged-recipes.git'.
#'         CRAN package name should be prefixed with 'r-' and given in all lowercase.

set -xe -o pipefail

mfansler

#!/bin/bash

## How to install ascp, in a gist.

## The URI below is not persistent! 
## Check for latest link: https://www.ibm.com/aspera/connect/
wget -qO- https://ak-delivery04-mul.dhe.ibm.com/sar/CMA/OSA/0a07f/0/ibm-aspera-connect_4.1.0.46-linux_x86_64.tar.gz | tar xvz

## run it
chmod +x ibm-aspera-connect_4.1.0.46-linux_x86_64.sh

mfansler

#!/bin/bash                                                                                                                                    

if [ "$#" -ne 1 ]; then
  echo -e "Incorrect number of parameters! Usage:\n    index-gtf.sh <file.gtf(.gz)>" >&2
  exit 1
fi

gtf="$1"

if [[ $gtf =~ \.gz$ ]]; then

mfansler

#!/usr/bin/env awk -f
#' Author: Mervin Fansler
#' GitHub: @mfansler
#' License: MIT
#' 
#' Basic usage
#' $ conda list --export | awk -f list_export_to_yaml.awk
#' 
#' Omitting builds with 'no_builds'
#' $ conda list --export | awk -v no_builds=1 -f list_export_to_yaml.awk

mfansler

## see https://stackoverflow.com/q/76039888/570918

diffmat <- function(drow_margin, dcol_margin, freeze=TRUE) {
    nrow <- length(drow_margin)
    ncol <- length(dcol_margin)
    rmat <- matrix(drow_margin, nrow, ncol)
    cmat <- matrix(dcol_margin, nrow, ncol, byrow=TRUE)
    dmat <- 0.5*(rmat + cmat)
    if (freeze) {
        ## keep satisfactory rows and columns fixed

mfansler

#!/usr/bin/env bash -l

## PARAMS
## file should have one "[name]=[version]=[build]" per line
FILE_PKG_BUILDS="r-tiff.cf_pkgs.txt"

##
DYLIB_LOC="lib/R/library/tiff/libs"

tmp=$(mktemp -d)

mfansler

library(rhdf5)
library(tidyverse)

read_ad_df <- function (file, name) {
    x_attrs <- h5readAttributes(file, name)
    
    ## check requested entry is a dataframe
    ## TODO: do we need to check encoding-version?
    stopifnot(x_attrs[['encoding-type']] == "dataframe")
    

mfansler

#!/bin/bash
## space-separated input
## -n1: run each separately
## -P6: run up to 6 in parallel
## -I '{}': replace {} with argument
## \$ delays evaluation to bash execution
## waits randomly for up to five seconds, then prints
echo {1..12} |\
  xargs -n1 -P6 -I '{}' \
  bash -c "sleep \$[ \$RANDOM % 5 ]; echo {}"

mfansler

#!/bin/bash

# download SRR from NCBI SRA via Aspera Connect
#
# > get-srr SRR304976
get-srr () {
    SRR=${1}
    SRR_6=$(echo $SRR | cut -c1-6)
       
    ascp -i ~/.aspera/connect/etc/asperaweb_id_dsa.openssh \