renaud

'''
Transforms topic-model input file, 
from DCA format (space separated) 
to LDA-C format (column-separated)

@author renaud@apache.org
'''
import sys

dca_file = sys.argv[1]

renaud

package topic

import spark.broadcast._
import spark.SparkContext
import spark.SparkContext._
import spark.RDD
import spark.storage.StorageLevel
import scala.util.Random
import scala.math.{ sqrt, log, pow, abs, exp, min, max }
import scala.collection.mutable.HashMap

renaud

import urllib, sys
from xml.etree import cElementTree as ElementTree

def get_go_name(go_id):
    sys.stdout.write("GO"+go_id+"\t"),
    #get the GO entry as XML
    xml = urllib.urlopen("http://www.ebi.ac.uk/QuickGO/GTerm?id=GO:"+go_id+"&format=oboxml")
    #open in cElementTree, for fast XML parsing
    for event, element in ElementTree.iterparse(xml):
        #need to make sure we are getting the name contained within the 'term' entry

renaud

alias gita="git status | egrep 'modified: ' | sed $'s/#\tmodified:/git add/g'"
alias gitd="git status | egrep 'deleted: '  | sed $'s/#\tdeleted:/git rm/g'"

renaud

@Test
    public void testSubscripts() throws Exception {

        final Pattern SUBSCRIPTS = Pattern.compile("^[ \\d]{10,1000}$");

        File ROOT = new File(
                        "/Volumes/scratch/richarde/pdfs/201307/");
        for (File pdf : ROOT.listFiles()) {
            if (pdf.getName().endsWith(".pdf")) {
                try {

renaud

DkPro Binary Cas evaluation

Quick evaluation on 126 pdfs, with some preprocessing.

Findings:

• reading is very fast
• writing with BinaryCasWriter and no compression is much slower than BinaryCasWriter with compression, where is the catch?!?
• Maybe this is the catch "Be advised that binary serialization may have drawbacks compared to XMI serialization."
• BinaryCasWriter with compression yields very decent file size

renaud

'''
REST endpoint
'''
import os, json
from datetime import date
from tornado import ioloop, web, autoreload



''' serves index.html'''

renaud

function y = psi(x)
%DIGAMMA   Digamma function.
% DIGAMMA(X) returns digamma(x) = d log(gamma(x)) / dx
% If X is a matrix, returns the digamma function evaluated at each element.

% Reference:
%
%    J Bernardo,
%    Psi ( Digamma ) Function,
%    Algorithm AS 103,

renaud

#!/usr/bin/env python
'''Link abbreviations to their full names

Based on

A Simple Algorithm for Identifying Abbreviations Definitions in Biomedical Text
A. Schwartz and M. Hearst
Biocomputing, 2003, pp 451-462.

renaud

license: apache-2.0
height: 650
scrolling: no
border: no