Stelios Sfakianakis sgsfak

## august5.sh
for j in `seq 2014 2050`; do
 i=8
 ncal $i $j | tail -3 | (echo -n "$j," ; awk  'BEGIN{ORS=","} {print NF-1}';echo)
done | egrep "5,5,5,$" |cut -f1 -d,

## parse_scpecg.js
var fs = require('fs')

var DEBUG = true;

var log = console.log;
if (!DEBUG)
	log = function() {};

function parse_scp_time(fval) {
	var hour = fval.readInt8(0);

## heatmap3.R
# EXAMPLE USAGE

# example of colsidecolors rowsidecolors (single column, single row)
mat <- matrix(1:100, byrow=T, nrow=10)
column_annotation <- sample(c("red", "blue", "green"), 10, replace=T)
column_annotation <- as.matrix(column_annotation)
colnames(column_annotation) <- c("Variable X")

row_annotation <- sample(c("red", "blue", "green"), 10, replace=T)
row_annotation <- as.matrix(t(row_annotation))

## 1000genomes_reprod_align.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                sgsfak
                / 1000genomes_reprod_align.md
            
            
              Last active
              August 29, 2015 14:03
            
          
    Reproducing (some of) the sequence alignment processes of 1000genomes project

Download the 100genomes samples

First I download the sequence.index file from the 1000genomes EBI FRP site:


## jq producing CSV
<out.json jq -r '.Root.ResultSet.Entity[] | [.color, .width, .average, .reference, .Time]|@csv' > out.csv

## exiv2date
exiv2  -Pv -g Exif.Image.DateTime *.JPG | awk '{gsub(/:/,"/", $2); print $1,$2}'

## single tree classifiers
Q: what are "single tree-based" (as opposed to forest-based) supervised learning methods?

A: some of my favorites:

- ADT
    + wiki: http://en.wikipedia.org/wiki/Alternating_decision_tree
    + ref: http://perun.pmf.uns.ac.rs/radovanovic/dmsem/cd/install/Weka/doc/classifiers-papers/trees/ADTree/atrees.pdf

- rpart in R
    + http://cran.r-project.org/web/packages/rpart/vignettes/longintro.pdf

## mutual_info.py
'''
Non-parametric computation of entropy and mutual-information

Adapted by G Varoquaux for code created by R Brette, itself
from several papers (see in the code).

These computations rely on nearest-neighbor statistics
'''
import numpy as np

## curl_multi_test.c
/* curl_multi_test.c

   Clemens Gruber, 2013
   <clemens.gruber@pqgruber.com>

   Code description:
    Requests 4 Web pages via the CURL multi interface
    and checks if the HTTP status code is 200.

   Update: Fixed! The check for !numfds was the problem.

## annotate_gpl17000.sh
## gb_gpl17000.csv contains the Genbank ids of the cDNA EST transcripts, downloaded from
## http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL17000
## (the GB_ACC column)
## So for each of these accession numbers we download the corresponding page from NCBI (EST database)
## and search (grep) for the Entrez Gene id
cat gb_gpl17000.csv |
  parallel -j4 --tagstring '{}' "curl -s http://www.ncbi.nlm.nih.gov/nucest/{} | fgrep '/sites/entrez?db=gene&amp;cmd=retrieve&amp;list_uids='" |
  gawk '{print $1, gensub(/^.*list_uids=([0-9]+).*$/, "\\1", "g", $3)}' |
  tee gb_gpl17000_eg_map.txt
	for j in `seq 2014 2050`; do
	i=8
	ncal $i $j \| tail -3 \| (echo -n "$j," ; awk 'BEGIN{ORS=","} {print NF-1}';echo)
	done \| egrep "5,5,5,$" \|cut -f1 -d,
	var fs = require('fs')

	var DEBUG = true;

	var log = console.log;
	if (!DEBUG)
	log = function() {};

	function parse_scp_time(fval) {
	var hour = fval.readInt8(0);
	# EXAMPLE USAGE

	# example of colsidecolors rowsidecolors (single column, single row)
	mat <- matrix(1:100, byrow=T, nrow=10)
	column_annotation <- sample(c("red", "blue", "green"), 10, replace=T)
	column_annotation <- as.matrix(column_annotation)
	colnames(column_annotation) <- c("Variable X")

	row_annotation <- sample(c("red", "blue", "green"), 10, replace=T)
	row_annotation <- as.matrix(t(row_annotation))
	Q: what are "single tree-based" (as opposed to forest-based) supervised learning methods?

	A: some of my favorites:

	- ADT
	+ wiki: http://en.wikipedia.org/wiki/Alternating_decision_tree
	+ ref: http://perun.pmf.uns.ac.rs/radovanovic/dmsem/cd/install/Weka/doc/classifiers-papers/trees/ADTree/atrees.pdf

	- rpart in R
	+ http://cran.r-project.org/web/packages/rpart/vignettes/longintro.pdf
	'''
	Non-parametric computation of entropy and mutual-information

	Adapted by G Varoquaux for code created by R Brette, itself
	from several papers (see in the code).

	These computations rely on nearest-neighbor statistics
	'''
	import numpy as np
	/* curl_multi_test.c

	Clemens Gruber, 2013
	<clemens.gruber@pqgruber.com>

	Code description:
	Requests 4 Web pages via the CURL multi interface
	and checks if the HTTP status code is 200.

	Update: Fixed! The check for !numfds was the problem.
	## gb_gpl17000.csv contains the Genbank ids of the cDNA EST transcripts, downloaded from
	## http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL17000
	## (the GB_ACC column)
	## So for each of these accession numbers we download the corresponding page from NCBI (EST database)
	## and search (grep) for the Entrez Gene id
	cat gb_gpl17000.csv \|
	parallel -j4 --tagstring '{}' "curl -s http://www.ncbi.nlm.nih.gov/nucest/{} \| fgrep '/sites/entrez?db=gene&cmd=retrieve&list_uids='" \|
	gawk '{print $1, gensub(/^.list_uids=([0-9]+).$/, "\\1", "g", $3)}' \|
	tee gb_gpl17000_eg_map.txt