Skip to content

Commit

Permalink
Add files via upload
Browse files Browse the repository at this point in the history
  • Loading branch information
@justincbagley
justincbagley authored Mar 15, 2019
1 parent 0c4d8d3 commit 7fa0c1f
Show file tree
Hide file tree
Showing 4 changed files with 892 additions and 287 deletions.
309 changes: 262 additions & 47 deletions bin/MLEResultsProc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,10 @@
# | #
# #
# File: MLEResultsProc.sh #
VERSION="v1.3" #
VERSION="v1.4.0" #
# Author: Justin C. Bagley #
# Date: Created by Justin Bagley on Fri, 29 Jul 2016 11:21:37 -0300. #
# Last update: March 6, 2019 #
# Last update: March 15, 2019 #
# Copyright (c) 2016-2019 Justin C. Bagley. All rights reserved. #
# Please report bugs to <[email protected]>. #
# #
Expand All @@ -19,43 +19,164 @@
# #
##########################################################################################

if [[ "$1" == "-V" ]] || [[ "$1" == "--version" ]]; then
echo "$(basename $0) $VERSION";
exit
# Provide a variable with the location of this script.
SCRIPT_PATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"

# Source Scripting Utilities
# -----------------------------------
# These shared utilities provide many functions which are needed to provide
# the functionality in this boilerplate. This script will fail if they can
# not be found.
# -----------------------------------

UTILS_LOCATION="${SCRIPT_PATH}/../lib/utils.sh" # Update this path to find the utilities.

if [[ -f "${UTILS_LOCATION}" ]]; then
source "${UTILS_LOCATION}"
else
echo "Please find the file util.sh and add a reference to it in this script. Exiting..."
exit 1
fi

echo "
##########################################################################################
# MLEResultsProc v1.3, March 2019 #

# Source shared functions and variables
# -----------------------------------

FUNCS_LOCATION="${SCRIPT_PATH}/../lib/sharedFunctions.sh" # Update this path to find the shared functions.
VARS_LOCATION="${SCRIPT_PATH}/../lib/sharedVariables.sh" # Update this path to find the shared variables.

if [[ -f "${FUNCS_LOCATION}" ]] && [[ -f "${VARS_LOCATION}" ]]; then
source "${FUNCS_LOCATION}" ;
source "${VARS_LOCATION}" ;
else
echo "Please find the files sharedFunctions.sh and sharedVariables.sh and add references to them in this script. Exiting... "
exit 1
fi

2LOGEB10_RSCRIPT_LOCATION="${SCRIPT_PATH}/2logeB10.R" # Update this path to find the 2logeB10.R Rscript.

# trapCleanup Function
# -----------------------------------
# Any actions that should be taken if the script is prematurely
# exited. Always call this function at the top of your script.
# -----------------------------------
function trapCleanup() {
echo ""
# Delete temp files, if any
if is_dir "${tmpDir}"; then
rm -r "${tmpDir}"
fi
die "Exit trapped. In function: '${FUNCNAME[*]}'"
}

# safeExit
# -----------------------------------
# Non destructive exit for when script exits naturally.
# Usage: Add this function at the end of every script.
# -----------------------------------
function safeExit() {
# Delete temp files, if any
if is_dir "${tmpDir}"; then
rm -r "${tmpDir}"
fi
trap - INT TERM EXIT
exit
}

# Set Flags
# -----------------------------------
# Flags which can be overridden by user input.
# Default values are below
# -----------------------------------
quiet=false
printLog=false
verbose=false
force=false
strict=false
debug=false
args=()

# Set Temp Directory
# -----------------------------------
# Create temp directory with three random numbers and the process ID
# in the name. This directory is removed automatically at exit.
# -----------------------------------
tmpDir="/tmp/${SCRIPT_NAME}.$RANDOM.$RANDOM.$RANDOM.$$"
(umask 077 && mkdir "${tmpDir}") || {
die "Could not create temporary directory! Exiting."
}

# Logging
# -----------------------------------
# Log is only used when the '-l' flag is set.
#
# To never save a logfile change variable to '/dev/null'
# Save to Desktop use: $HOME/Desktop/${SCRIPT_BASENAME}.log
# Save to standard user log location use: $HOME/Library/Logs/${SCRIPT_BASENAME}.log
# -----------------------------------
logFile="$HOME/Library/Logs/${SCRIPT_BASENAME}.log"

# Check for Dependencies
# -----------------------------------
# Arrays containing package dependencies needed to execute this script.
# The script will fail if dependencies are not installed. For Mac users,
# most dependencies can be installed automatically using the package
# manager 'Homebrew'. Mac applications will be installed using
# Homebrew Casks. Ruby and gems via RVM.
# -----------------------------------
homebrewDependencies=()
caskDependencies=()
gemDependencies=()




function MLEResultsProc () {

######################################## START ###########################################
##########################################################################################
"

echo "INFO | $(date) |----------------------------------------------------------------"
echo "INFO | $(date) | MLEResultsProc, v1.4.0 March 2019 (part of PIrANHA v1.0.0) "
echo "INFO | $(date) | Copyright (c) 2016-2019 Justin C. Bagley. All rights reserved. "
echo "INFO | $(date) |----------------------------------------------------------------"

######################################## START ###########################################
echo "INFO | $(date) | STEP #1: SETUP. "
MY_BEAST_OUTPUT_FILES=*.out
echo "INFO | $(date) | Starting MLEResultsProc pipeline... "
echo "INFO | $(date) | Step #1: Set up workspace, check machine type, and read beast .out files into environmental variable. "
############ SET WORKING DIRECTORY AND CHECK MACHINE TYPE
USER_SPEC_PATH="$(printf '%q\n' "$(pwd)")";
echoCDWorkingDir
#echo "INFO | $(date) | Checking machine type... "
checkMachineType
#echo "INFO | $(date) | Found machine type ${machine}. "


echo "INFO | $(date) | STEP #2: CHECK BEAST VERSION (DETECT AND ACCOMODATE RESULTS FILES FROM BEAST1 OR BEAST2). "
MY_BEAST_OUTPUT_FILES=*.out ;

echo "INFO | $(date) | Step #2: Check BEAST version, in order to detect and accommodate results files from BEAST v1 versus BEAST2. "
## CHECK BEAST VERSION.
##--Conditional on the following check, we will run one of two different versions of
##--MLEResultsProc on the current working dir--one specific to the format of output (.out)
##--files from BEAST v1, and one specific to the format of .out files from BEAST v2.
## Conditional on the following check, we will run one of two different versions of
## MLEResultsProc on the current working dir--one specific to the format of output (.out)
## files from BEAST v1, and one specific to the format of .out files from BEAST v2.
(
for i in $MY_BEAST_OUTPUT_FILES; do
echo "$i" > file.tmp;
break;
done
)
y="$(cat file.tmp)"
y="$(cat file.tmp)";

MY_BEAST1_VER_CHECK="$(grep -h 'BEAST\ v1' $y | wc -l)";
MY_BEAST1_VER_CHECK2="$(grep -h 'log\ marginal\ likelihood' $y | wc -l)";

MY_BEAST1_VER_CHECK="$(grep -h 'BEAST\ v1' $y | wc -l)"
MY_BEAST1_VER_CHECK2="$(grep -h 'log\ marginal\ likelihood' $y | wc -l)"
MY_BEAST2_VER_CHECK="$(grep -h 'BEAST\ v2' $y | wc -l)";
MY_BEAST2_VER_CHECK2="$(grep -h 'marginal\ L\ estimate' $y | wc -l)";

MY_BEAST2_VER_CHECK="$(grep -h 'BEAST\ v2' $y | wc -l)"
MY_BEAST2_VER_CHECK2="$(grep -h 'marginal\ L\ estimate' $y | wc -l)"
rm ./file.tmp ;

rm ./file.tmp

echo "INFO | $(date) | STEP #3: EXTRACT MLE RESULTS FROM OUTPUT FILES. "
echo "INFO | $(date) | Step #3: Extract MLE results from BEAST output files in current directory. "

################################## extractB1Results.sh ###################################

Expand All @@ -68,24 +189,24 @@ echo "INFO | $(date) | STEP #3: EXTRACT MLE RESULTS FROM OUTPUT FILES. "
(
for i in $MY_BEAST_OUTPUT_FILES; do
echo "$i"
echo "$(basename $i)" > "${i}"_filename.tmp
echo "$(basename $i)" > "${i}"_filename.tmp ;
#
grep -n "log marginal likelihood (using path sampling) from pathLikelihood.delta =" ${i} | \
awk -F"= " '{print $NF}' > "${i}"_PSMLEs.tmp
awk -F"= " '{print $NF}' > "${i}"_PSMLEs.tmp ;

grep -n "log marginal likelihood (using stepping stone sampling) from pathLikelihood.delta =" ${i} | \
awk -F"= " '{print $NF}' > "${i}"_SSMLEs.tmp
awk -F"= " '{print $NF}' > "${i}"_SSMLEs.tmp ;
#
MY_PS_RESULT="$(head -n1 ${i}_PSMLEs.tmp)"
MY_SS_RESULT="$(head -n1 ${i}_SSMLEs.tmp)"
MY_PS_RESULT="$(head -n1 ${i}_PSMLEs.tmp)";
MY_SS_RESULT="$(head -n1 ${i}_SSMLEs.tmp)";
#
echo "${i}"_filename.tmp "$MY_PS_RESULT" "$MY_SS_RESULT" >> data.tmp
echo "${i}"_filename.tmp "$MY_PS_RESULT" "$MY_SS_RESULT" >> data.tmp ;
done
)

rm ./*_filename.tmp
rm ./*_PSMLEs.tmp
rm ./*_SSMLEs.tmp
rm ./*_filename.tmp ;
rm ./*_PSMLEs.tmp ;
rm ./*_SSMLEs.tmp ;

}

Expand All @@ -100,7 +221,7 @@ echo "INFO | $(date) | STEP #3: EXTRACT MLE RESULTS FROM OUTPUT FILES. "
(
for i in $MY_BEAST_OUTPUT_FILES; do
echo "$i"
echo "$(basename $i)" > "${i}"_filename.tmp
echo "$(basename $i)" > "${i}"_filename.tmp ;
#
grep -n "marginal L estimate =" ${i} | \
awk -F"= " '{print $NF}' > "${i}"_PSMLEs.tmp ;
Expand Down Expand Up @@ -129,9 +250,9 @@ echo "INFO | $(date) | STEP #3: EXTRACT MLE RESULTS FROM OUTPUT FILES. "



##--Don't forget to run the (single) appropriate function! If output files from BEAST1 *and*
##--BEAST2 runs are present in current working directory (=NOT ALLOWED!), then the BEAST1
##--results will simply be overwritten.
## Don't forget to run the (single) appropriate function! If output files from BEAST1 *and*
## BEAST2 runs are present in current working directory (=NOT ALLOWED!), then the BEAST1
## results will simply be overwritten.
if [[ "$MY_BEAST1_VER_CHECK" -gt "0" ]] || [[ "$MY_BEAST1_VER_CHECK2" -gt "0" ]]; then
echo "INFO | $(date) | BEAST v1+ output files detected; conducting post-processing accordingly... "
echo "INFO | $(date) | Extracting MLE results from the following output files: "
Expand All @@ -145,7 +266,7 @@ fi



echo "INFO | $(date) | STEP #4: ARRANGE MLE RESULTS IN TAB-DELIMITED FILE WITH HEADER. "
echo "INFO | $(date) | Step #4: Arrange MLE results in tab-delimited file with header. "
echo "INFO | $(date) | Placing results into 'MLE.output.txt' in current working directory. "
echo "File PS_MLE SS_MLE" > header.txt ; ## Make header row. Change these codes as needed.
cat header.txt data.tmp | sed 's/\_filename.tmp//g; s/\ / /g' > MLE.output.txt ;
Expand All @@ -155,23 +276,117 @@ echo "INFO | $(date) | STEP #4: ARRANGE MLE RESULTS IN TAB-DELIMITED FILE W
rm data.tmp ;


echo "INFO | $(date) | STEP #5: LOAD MLE RESULTS INTO R AND COMPUTE BAYES FACTOR TABLES. "
##--We do this in an R script that I wrote named "2logeB10.R" that we simply call here.
##--Note this script needs to be either in the working directory or the user's path.
echo "INFO | $(date) | Step #5: Load MLE results into R and compute Bayes factor tables. "
## We do this in an R script that I wrote named "2logeB10.R" that we simply call here.
## This script is distributed with PIrANHA and, like all other functions including MLEResultsProc,
## it is in the bin/ folder of the distro. Here we account for different distro locations on
## different (users') machines by calling from ${2LOGEB10_RSCRIPT_LOCATION} defined at the
## top of this script (line 56).

echo "INFO | $(date) | Calculating Bayes factors in R using '2logeB10.R' script... "
R CMD BATCH 2logeB10.R
R CMD BATCH "${2LOGEB10_RSCRIPT_LOCATION}"

if [[ -s ./2logeB10.Rout ]] && [[ "$(wc -c 2logeB10.Rout | perl -pe 's/\ +([0-9]{4}).*$/$1/g')" -gt "3960" ]]; then
echo "INFO | $(date) | R calculations complete. "
fi

echo "INFO | $(date) | Done summarizing marginal-likelihood estimation results in BEAST using MLEResultsProc. "
echo "INFO | $(date) | Bye.
"
#
#
#
#echo "INFO | $(date) | Done summarizing marginal-likelihood estimation results in BEAST using MLEResultsProc. "
#echo "INFO | $(date) | Bye.
#"

echo "----------------------------------------------------------------------------------------------------------"
echo ""

##########################################################################################
######################################### END ############################################

exit 0
}



############ SCRIPT OPTIONS
## OPTION DEFAULTS ##
# None at this time.

############ CREATE USAGE & HELP TEXTS
USAGE="Usage: $(basename $0) [OPTION]...
${bold}Options:${reset}
-h help text (also: -help) echo this help text and exit
-V version (also: --version) echo version of this script and exit
${bold}OVERVIEW${reset}
THIS SCRIPT automates post-processing of marginal likelihood estimation results from
running path sampling (ps) or stepping-stone (ss) sampling analyses on different models in
BEAST. The program runs in current working directory containing BEAST output files, i.e.
within a single run folder containing results from a single MLE BEAST run. After attempting
to identify the BEAST version used for the analysis from user's files, the program extracts
MLE results from BEAST output files in current directory. The MLE results are processed and
output to a file named 'MLE.output.txt', and then they are read into R, where a custom
Rscript computes Bayes factors for the models.
This program runs on UNIX-like and Linux systems using commonly distributed utility
software, with usage obtained by running the script with the -h flag. It has been tested
on macOS High Sierra (v10.13+) and Mojave but should work on many earlier versions or
Linux (tested on CentOS 6/7). The main dependencies are R (v3.3+) and Perl (v5+), the later
of which is usually already installed on most mac and Linux distributions.
${bold}Usage examples:${reset}
Call the program using PIrANHA, as follows:
piranha -f MLEResultsProc Run with program defaults in current directory
piranha -f MLEResultsProc --args='-h' Print this help text
${bold}CITATION${reset}
Bagley, J.C. 2019. PIrANHA v1.0.0. GitHub repository, Available at:
<https://github.com/justincbagley/PIrANHA>.
Created by Justin Bagley on Fri, 29 Jul 2016 11:21:37 -0300.
Copyright (c) 2016-2019 Justin C. Bagley. All rights reserved.
"

if [[ "$1" == "-h" ]] || [[ "$1" == "-help" ]]; then
echo "$USAGE"
exit
fi

if [[ "$1" == "-V" ]] || [[ "$1" == "--version" ]]; then
echo "$(basename $0) $VERSION";
exit
fi


# ############# ############# #############
# ## TIME TO RUN THE SCRIPT ##
# ## ##
# ## You shouldn't need to edit anything ##
# ## beneath this line ##
# ## ##
# ############# ############# #############

# Trap bad exits with your cleanup function
trap trapCleanup EXIT INT TERM

# Set IFS to preferred implementation
IFS=$'\n\t'

# Exit on error. Append '||true' when you run the script if you expect an error.
set -o errexit

# Run in debug mode, if set
if ${debug}; then set -x ; fi

# Exit on empty variable
if ${strict}; then set -o nounset ; fi

# Bash will remember & return the highest exitcode in a chain of pipes.
# This way you can catch the error in case mysqldump fails in `mysqldump |gzip`, for example.
set -o pipefail

# Invoke the checkDependenices function to test for Bash packages. Uncomment if needed.
# checkDependencies

# Run the script
MLEResultsProc

# Exit cleanly
safeExit
Loading

0 comments on commit 7fa0c1f

Please sign in to comment.