Laboratoire ICAR » Plateforme TXM

println buffer.toString().substring(1)

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

import org.txm.libs.office.WriteODS

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

@Field @Option(name="showPositiveIndices", usage="Show positive indices", widget="Boolean", required=false, def="true")

		def showPositiveIndices

@Field @Option(name="showNegativeIndices", usage="Show negative indices", widget="Boolean", required=false, def="false")

		def showNegativeIndices

// END OF PARAMETERS

if (!ParametersDialog.open(this)) { return }

if (!showPositiveIndices && !showNegativeIndices) {

	println "Select positive or/and negative indices. Aborting."

	return;

}

Specificities specif = corpusViewSelection

def indices = specif.getSpecificitesIndices()

def freqs = specif.getFrequencies()

def rownames = specif.getRowNames()

def colnames = specif.getColumnsNames()

def allTopKeys = new LinkedHashSet()

def output = new File(outputFile)

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

def allResults = new LinkedHashMap()

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

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

	writer.println "unit\tF\tindice"

	def sorted = []

	def tops = []

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

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

	}

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

	if (showPositiveIndices) {

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

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

			allTopKeys << rownames[i]

			tops << sorted[i]

		}

	}

	if (showNegativeIndices) {

		if (showPositiveIndices) {

			writer.println "\n"

			tops << ["","",""]

		}

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

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

			allTopKeys << rownames[i]

			tops << sorted[sorted.size() - i]

		}

	}

	allResults[colnames[j]] = tops

}

writer.close()

WriteODS odsWriter = new WriteODS(new File(output.getAbsolutePath()+".ods"))

def firstLine = []

for (def c : colnames) {

	firstLine << c

	firstLine << ""

	firstLine << ""

}

odsWriter.writeLine(firstLine)

int icol = 0;

for (def c : colnames) {

	def cellRange = odsWriter.table.getCellRangeByPosition(icol, 1, icol+2, 1);

	cellRange.merge();

	icol += 3;

}

firstLine = []

for (def c : colnames) {

	firstLine << "Unit"

	firstLine << "F"

	firstLine << "Indice"

}

odsWriter.writeLine(firstLine)

println "write lines..."

def lines = []

for (def col : allResults.keySet()) {

	iline = 0;

	for (def s : allResults[col]) {

		if (lines.size() == iline) lines << []

		for (def ss : s) lines[iline] << ss

		iline++

	}

}

for (def line : lines) {

	odsWriter.writeLine(line)

}

odsWriter.save()

println "Result: "+output.getAbsolutePath()