Selby Kendrick selbyk

## lsblk.txt
xvda    202:0    0   300G  0 disk /
xvdf    202:80   0   350G  0 disk
├─xvdf1 202:81   0     8G  0 part
├─xvdf2 202:82   0   512M  0 part
└─xvdf3 202:83   0 341.5G  0 part

## fstab
# Swap file created on DATE
/var/swapfile       none    swap    sw      0       0

## batch_resize.sh
#/bin/bash
# Usage: ./batch_resize.sh input_dir output_dir “10 30 50”
#        ./batch_resize.sh help

# Setup our globals
PARAM_CHECK_FAIL=0
INPUT_DIR=""
OUTPUT_DIR=""
SIZES=()

## start_with_java_7.sh
export JAVA_HOME=/usr/lib/jvm/java-7-openjdk/jre
program_to_run

## cli-broken.ini
# This is an example of the kind of things you can do in a configuration file.
# All flags used by the client can be configured here. Run Let's Encrypt with
# "--help" to learn more about the available options.

# Use a 4096 bit RSA key instead of 2048
rsa-key-size = 4096

# Always use the staging/testing server
server = https://acme-v01.api.letsencrypt.org/directory

## video_from_jpg.sh
#!/bin/bash

rm *.jpg
rm *.png
rm *.gif
rm *.mp4
find ../ -mindepth 1 -maxdepth 1 -mtime -7  -name "*.jpg" -exec cp -t . {} +

export MAGICK_THREAD_LIMIT=4

## movie.sh
#!/bin/bash

# Set to number of cores your computer has or you want to use
export MAGICK_THREAD_LIMIT=8

# Deleted old files
rm *.jpg
rm *.png
rm *.gif
rm *.mp4

## gist:c102049678eb3515822c
Scraper/Content Extraction Training
Goal: Fetch relevant information sources, extract only appropriate content, save as documents as training data and usable by Watson


Method:
Fetch a few pages from various data sources using Phantom.js, then parse and save the website’s HTML as JSON
Iterate the text elements and extract features such as size, position, text, CSS properties, etc
Run the DBSCAN clustering algorithm over the document’s extracted feature data. Similar elements such as titles, headers, and article content should be grouped into the same clusters
Manually tag a portion of the documents to use as training data
A support vector machine (SVM) with linear kernel using a 4-fold cross validation should be capable of detecting the main content of a scraped page

## find_running_process.sh
#/bin/bash
# Usage: ./find_running_process.sh <process_name>
#        DEBUG=1 ./find_running_process.sh <process_name>

# Function to help with debug messages
debug_message () {
  if [ $DEBUG -eq 1 ]
  then
    echo $1
  fi

## process_pids.sh
#!/bin/bash
# Usage: ./process_pids.sh

for proc in /proc/*
do
  FILENAME=${proc##*/}
  if [[ $FILENAME =~ ^-?[0-9]+ ]]
  then
   echo $FILENAME
  fi
	xvda 202:0 0 300G 0 disk /
	xvdf 202:80 0 350G 0 disk
	├─xvdf1 202:81 0 8G 0 part
	├─xvdf2 202:82 0 512M 0 part
	└─xvdf3 202:83 0 341.5G 0 part
	#/bin/bash
	# Usage: ./batch_resize.sh input_dir output_dir “10 30 50”
	# ./batch_resize.sh help

	# Setup our globals
	PARAM_CHECK_FAIL=0
	INPUT_DIR=""
	OUTPUT_DIR=""
	SIZES=()
	export JAVA_HOME=/usr/lib/jvm/java-7-openjdk/jre
	program_to_run
	# This is an example of the kind of things you can do in a configuration file.
	# All flags used by the client can be configured here. Run Let's Encrypt with
	# "--help" to learn more about the available options.

	# Use a 4096 bit RSA key instead of 2048
	rsa-key-size = 4096

	# Always use the staging/testing server
	server = https://acme-v01.api.letsencrypt.org/directory
	#!/bin/bash

	rm *.jpg
	rm *.png
	rm *.gif
	rm *.mp4
	find ../ -mindepth 1 -maxdepth 1 -mtime -7 -name "*.jpg" -exec cp -t . {} +

	export MAGICK_THREAD_LIMIT=4
	#!/bin/bash

	# Set to number of cores your computer has or you want to use
	export MAGICK_THREAD_LIMIT=8

	# Deleted old files
	rm *.jpg
	rm *.png
	rm *.gif
	rm *.mp4
	Scraper/Content Extraction Training
	Goal: Fetch relevant information sources, extract only appropriate content, save as documents as training data and usable by Watson


	Method:
	Fetch a few pages from various data sources using Phantom.js, then parse and save the website’s HTML as JSON
	Iterate the text elements and extract features such as size, position, text, CSS properties, etc
	Run the DBSCAN clustering algorithm over the document’s extracted feature data. Similar elements such as titles, headers, and article content should be grouped into the same clusters
	Manually tag a portion of the documents to use as training data
	A support vector machine (SVM) with linear kernel using a 4-fold cross validation should be capable of detecting the main content of a scraped page
	#/bin/bash
	# Usage: ./find_running_process.sh <process_name>
	# DEBUG=1 ./find_running_process.sh <process_name>

	# Function to help with debug messages
	debug_message () {
	if [ $DEBUG -eq 1 ]
	then
	echo $1
	fi
	#!/bin/bash
	# Usage: ./process_pids.sh

	for proc in /proc/*
	do
	FILENAME=${proc##*/}
	if [[ $FILENAME =~ ^-?[0-9]+ ]]
	then
	echo $FILENAME
	fi