renaud

package ch.epfl.bbp.uima.projects.references;

import static cc.mallet.pipe.iterator.FileIterator.LAST_DIRECTORY;
import static com.google.common.collect.Lists.newArrayList;
import static java.util.regex.Pattern.compile;
import static org.apache.commons.lang.StringUtils.join;
import static org.slf4j.LoggerFactory.getLogger;

import java.io.File;
import java.io.FileFilter;

renaud

#!/bin/sh

############################################
# MAKE SURE TO BACKUP YOUR FILES FIRST
############################################

# see http://uima.apache.org/d/uimafit-2.0.0/tools.uimafit.book.html#d5e617

#Change of package names:
find . -name '*.java' -print | xargs perl -p -i -e 's/org.uimafit/org.apache.uima.fit/g'

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

from Bio import Entrez
Entrez.email = "A.N.Other@example.com"

handle = Entrez.esearch(db="pubmed", term="pyramidal cell")
record = Entrez.read(handle)
len(record) # this matches http://www.ncbi.nlm.nih.gov/pubmed/?term=pyramidal%20cell

first = record["IdList"][0]

# from http://stackoverflow.com/a/20149984/125617

renaud

cc.mallet.types.InstanceList.CrossValidationIterator crossValidationIt = trainingInstanceList.crossValidationIterator(folds, new Random().nextInt());
while (crossValidationIt.hasNext()) {

    InstanceList[] il = crossValidationIt.nextSplit();
    CRF crf = new CRF(trainingInstanceList.getPipe(), null);
    CRFTrainerByThreadedLabelLikelihood trainer = new CRFTrainerByThreadedLabelLikelihood(crf, threads);
    // CRFTrainerByLabelLikelihood trainer = new CRFTrainerByLabelLikelihood(crf);

    MultiSegmentationEvaluator eval = new MyMultiSegmentationEvaluator(//
       new InstanceList[] { testingSet }, new String[] { "TTesting" }, tags, continueTags);