Return-Path: X-Original-To: apmail-ctakes-commits-archive@www.apache.org Delivered-To: apmail-ctakes-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id C55621072F for ; Wed, 4 Sep 2013 18:05:35 +0000 (UTC) Received: (qmail 72390 invoked by uid 500); 4 Sep 2013 18:05:35 -0000 Delivered-To: apmail-ctakes-commits-archive@ctakes.apache.org Received: (qmail 72359 invoked by uid 500); 4 Sep 2013 18:05:34 -0000 Mailing-List: contact commits-help@ctakes.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@ctakes.apache.org Delivered-To: mailing list commits@ctakes.apache.org Received: (qmail 72349 invoked by uid 99); 4 Sep 2013 18:05:34 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 04 Sep 2013 18:05:34 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 04 Sep 2013 18:05:33 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id F3663238889B; Wed, 4 Sep 2013 18:05:12 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1520087 - /ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java Date: Wed, 04 Sep 2013 18:05:12 -0000 To: commits@ctakes.apache.org From: dligach@apache.org X-Mailer: svnmailer-1.0.9 Message-Id: <20130904180512.F3663238889B@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Author: dligach Date: Wed Sep 4 18:05:12 2013 New Revision: 1520087 URL: http://svn.apache.org/r1520087 Log: printing durations as vectors (for matlab) Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java?rev=1520087&r1=1520086&r2=1520087&view=diff ============================================================================== --- ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java (original) +++ ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/data/analysis/SignSymptomDurations.java Wed Sep 4 18:05:12 2013 @@ -6,6 +6,7 @@ import java.util.Arrays; import java.util.Collection; import java.util.Collections; import java.util.HashMap; +import java.util.LinkedList; import java.util.List; import java.util.Map; import java.util.regex.Matcher; @@ -30,6 +31,7 @@ import org.uimafit.util.JCasUtil; import com.google.common.base.Function; import com.google.common.base.Functions; +import com.google.common.base.Joiner; import com.google.common.collect.HashMultiset; import com.google.common.collect.Multiset; import com.google.common.collect.Ordering; @@ -38,6 +40,7 @@ import com.google.common.collect.Orderin * Extract durations of signs/symptoms. * * TODO: check drinking.txt; fewer day durations are captured than exist in data. + * TODO: need to take care of abbreviations (e.g. wk, yr, etc.) * * @author dmitriy dligach */ @@ -112,9 +115,23 @@ public class SignSymptomDurations { } if(durationDistribution.size() > 0) { - System.out.println(signSymptomText + ": " + durationDistribution); + String durationDistributionAsString = convertToString(durationDistribution); + System.out.println(signSymptomText + "," + durationDistributionAsString); } } + + private static String convertToString(Multiset durationDistribution) { + + List durationBins = Arrays.asList("second", "minute", "hour", "day", "week", "month", "year"); + List durationValues = new LinkedList(); + + for(String durationBin : durationBins) { + durationValues.add(durationDistribution.count(durationBin)); + } + + Joiner joiner = Joiner.on(','); + return joiner.join(durationValues); + } } private static CollectionReader getCollectionReader(List items) throws Exception {