Created
January 16, 2020 22:23
-
-
Save reality/56c3e7e8f4c862ce4d40e7e10ce716e8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@Grab('com.xlson.groovycsv:groovycsv:1.3') | |
@Grab(group='org.apache.commons', module='commons-lang3', version='3.4') | |
@Grab(group='edu.stanford.nlp', module='stanford-corenlp', version='3.7.0') | |
@Grab(group='edu.stanford.nlp', module='stanford-corenlp', version='3.7.0', classifier='models') | |
@Grab(group='edu.stanford.nlp', module='stanford-parser', version='3.7.0') | |
import static com.xlson.groovycsv.CsvParser.parseCsv | |
import edu.stanford.nlp.pipeline.* | |
import edu.stanford.nlp.ling.* | |
import edu.stanford.nlp.semgraph.* | |
import org.apache.commons.lang3.RandomUtils | |
println "Loading file... " | |
def entries = [] | |
def file = new RandomAccessFile('./NOTEEVENTS.csv', 'r') | |
println "File loaded. Beginning selection sequence..." | |
while(entries.size() < 1000) { | |
def rPos = RandomUtils.nextLong(new Long(0), file.length()) | |
file.seek(rPos) | |
def foundNewRecord | |
def newText | |
while(!foundNewRecord) { | |
newText = file.readLine() | |
if(newText.indexOf('",') != -1) { | |
foundNewRecord = true | |
} | |
} | |
foundNewRecord = false | |
def textRecord = '' | |
while(!foundNewRecord) { | |
newText = file.readLine() | |
if(newText.indexOf('",') != -1) { | |
foundNewRecord = true | |
} else { | |
textRecord += newText | |
} | |
} | |
if(textRecord.indexOf(' ') == -1) { | |
entries << textRecord.replaceAll('\n', '').replaceAll('\\s+', ' ').replaceAll('\\.', '. ') | |
} | |
println entries.size() | |
} | |
println "Selecting sentences...." | |
def props = new Properties() | |
props.put("annotators", "tokenize, ssplit") | |
coreNLP = new StanfordCoreNLP(props) | |
pipeline = new AnnotationPipeline() | |
pipeline.addAnnotator(coreNLP) | |
def i = 0 | |
def sentences = entries.collect { entry -> | |
def aDocument = new Annotation(entry.toLowerCase()) | |
pipeline.annotate(aDocument) | |
println "${++i}" | |
def s = aDocument.get(CoreAnnotations.SentencesAnnotation.class).collect { it.toString() } | |
//s = s.findAll { it.indexOf('\t') == -1 && it.indexOf('---') == -1 && it.tokenize(' ').size() < 30 } | |
//def rPos = RandomUtils.nextInt(0, s.size()) | |
//s[rPos]*/ | |
s | |
}.flatten() | |
sentences.removeAll([null]) | |
new File('sentences_healtac.txt').text = sentences.join('\n') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment