Laboratoire ICAR » Plateforme TXM

package org.txm.macro.stats

// Copyright © 2010-2016 ENS de Lyon.

// Copyright © 2007-2010 ENS de Lyon, CNRS, INRP, University of

// Lyon 2, University of Franche-Comté, University of Nice

// Sophia Antipolis, University of Paris 3.

// @author mdecorde

// @author sheiden

//

// The TXM platform is free software: you can redistribute it

// and/or modify it under the terms of the GNU General Public

// License as published by the Free Software Foundation,

// either version 2 of the License, or (at your option) any

// later version.

//

// The TXM platform is distributed in the hope that it will be

// useful, but WITHOUT ANY WARRANTY; without even the implied

// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR

// PURPOSE. See the GNU General Public License for more

// details.

//

// You should have received a copy of the GNU General

// Public License along with the TXM platform. If not, see

// http://www.gnu.org/licenses.

// This macro computes the basic vocabulary of a partition

// given a specificities table. The result is saved in a

// TSV file.

import org.txm.Toolbox

import org.txm.searchengine.cqp.clientExceptions.*

import org.txm.searchengine.cqp.corpus.*

import org.txm.searchengine.cqp.corpus.query.*

import org.txm.statsengine.r.core.RWorkspace

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.txm.specificities.core.functions.Specificities

if (!(corpusViewSelection instanceof Specificities)) {

	println "** You need to select a Specificities result icon in the Corpus view before calling this macro. Aborting."

	return

}

// PARAMETERS

@Field @Option(name="outputFile", usage="TSV result file", widget="String", required=true, def="top.tsv")

def outputFile

@Field @Option(name="nTop", usage="Number of words per column", widget="Integer", required=false, def="10")

def nTop

// END OF PARAMETERS

if (!ParametersDialog.open(this)) return

Specificities specif = corpusViewSelection

def indices = specif.getSpecificitesIndices()

def freqs = specif.getFrequencies()

def rownames = specif.getRowNames()

def colnames = specif.getColumnsNames()

def output = new File(outputFile)

def writer = output.newWriter("UTF-8")

for (int j = 0; j < colnames.size() ; j++) {

	writer.println "## "+colnames[j]

	writer.println "unit\tF\tindice"

	def sorted = []

	for (int i = 0; i < rownames.length ; i++) {

		sorted << [rownames[i], freqs[i][j], indices[i][j]]

	}

	sorted.sort() { -it[2]}

	for (int i = 0 ; i < nTop ; i++) {

		writer.println sorted[i].join("\t")

	}

	for (int i = nTop ; i >= 1 ; i--) {

		writer.println sorted[sorted.size() - i].join("\t")

	}

	writer.println "\n\n"

}

writer.close()

println "Result: "+output.getAbsolutePath()