Java Code Examples for com.opencsv.CSVReader#close()

public static List<String[]> readAll(Reader reader) {

        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

        CSVReader csvReader = new CSVReaderBuilder(reader)
                .withSkipLines(0)
                .withCSVParser(parser)
                .build();

        List<String[]> list = new ArrayList<>();
        try {
            list = csvReader.readAll();
            reader.close();
            csvReader.close();
        } catch (Exception ex) {
            Helpers.err(ex);
        }
        return list;
    }
 

private void initColumns() throws EmptyDataFileContentException, WrongDataFileFormatException, IOException {
    columns = new ArrayList<>();
    final CSVReader reader = openInputData();
    final String[] headers = reader.readNext();
    for (final String header : headers) {
        if (!"".equals(header)) {
            columns.add(header);
        }
    }
    reader.close();
    if (columns.size() < 2) {
        throw new EmptyDataFileContentException(Messages.getMessage(EmptyDataFileContentException.EMPTY_DATA_FILE_CONTENT_ERROR_MESSAGE));
    }
    resultColumnName = columns.get(columns.size() - 1);
    if (!isResultColumnNameAuthorized(resultColumnName)) {
        throw new WrongDataFileFormatException(String.format(Messages.getMessage(WrongDataFileFormatException.WRONG_RESULT_COLUMN_NAME_ERROR_MESSAGE), ResultColumnNames.getAuthorizedNames()));
    }
}
 

/**
 * Reads a csv file with structure of yahoo api: No info line with name and timeFormatId, just header line and
 * {@link TimeFormatType timeFormat YAHOO}
 * @param name the name of this symbol
 * @param file the csv file with financial data in yahoo format
 * @return the corresponding TimeSeries object
 * @throws IOException IOException
 */
public TaBarSeries getSeriesFromYahooFile(String name, File file) throws IOException{
    CSVReader reader = new CSVReaderBuilder(new FileReader(file)).withCSVParser(new CSVParser()).build();
    String line[];
    line = reader.readNext();
    Map<Parameter.Columns, Integer> headers = FormatUtils.getHeaderMap(Arrays.asList(line));
    List<Bar> Bars = new ArrayList<>();
    while((line = reader.readNext()) != null) {
        Bars.add(FormatUtils.extractOHLCData(
                headers, DateTimeFormatter.ofPattern(TimeFormatType.YAHOO.pattern),line,false));
    }
    reader.close();
    if(Bars.get(Bars.size()-1).getEndTime().isBefore(Bars.get(0).getEndTime())){
        Collections.reverse(Bars);
    }
    String yahooIntervall = YahooSettingsManager.getProperties().getProperty(Parameter.PROPERTY_YAHOO_INTERVAL);
    GeneralTimePeriod timePeriod = YahooTimePeriod.of(yahooIntervall).generalTimePeriod;
    return new TaBarSeries(name==null?"unnamed":name.toUpperCase(),Bars,Currency.getInstance("USD"),timePeriod);
}
 

private String[] parseCsv(final String string) {
    String[] parts = new String[0];
    try {
        final CSVReader reader = new CSVReader(new StringReader(string),
                separator);
        final List<String[]> lines = reader.readAll();
        if (lines.size() > 0) {
            parts = lines.get(0);
        }
        reader.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
    return parts;
}
 

@DataProvider(name = "searchWords")
public Iterator<Object[]> provider() throws Exception {

    CSVReader reader = new CSVReader(
            new FileReader("./src/test/resources/data/data.csv")
            , ',', '\'', 1);

    List<Object[]> myEntries = new ArrayList<Object[]>();
    String[] nextLine;
    while ((nextLine = reader.readNext()) != null) {
        myEntries.add(nextLine);
    }
    reader.close();
    return myEntries.iterator();
}
 

public CSVFileParser(InputStream stream, String encoding, char delimiter,
        final String mandatory_columns[],
        final String mandatory_column_values[]) throws Exception {

    this.lines = new HashSet<String>();
    this.mandatory_cols = mandatory_column_values;
    this.data = new LinkedHashMap<String, String>();
    reader = new CSVReader(new InputStreamReader(stream, encoding),
            delimiter);
    try {
        mappings = reader.readNext();
        if (mappings == null) {
            throw new IOException("Empty CSV file given.");
        }
        line = 1;
        List<String> checkCols = Arrays.asList(mappings);
        for (String reqCol : mandatory_columns) {
            if (!checkCols.contains(reqCol)) {
                throw new Exception(
                        "Missing mandatory column '" + reqCol + "'.");
            }
        }

    } catch (Exception e) {
        reader.close();
        throw e;
    }

}
 

/**
 * @param is The input stream for the CSV data.
 * @return The header line.
 * @throws IOException
 */
public static String[] getHeaderLine(InputStream is) throws IOException {
	CSVReader reader = new CSVReader(new InputStreamReader(is, StandardCharsets.UTF_8));
	String[] headerLine = reader.readNext();
	reader.close();
	return headerLine;
}
 

public void closeReader() {
    try {
        CSVReader.close();
        fileReader.close();
    } catch (IOException e) {
        logger.error("Error while closing reader.");
    }
}
 

/**
 * Converts the csv input data , where rows represent datacase and columns represent variables, to 
 * the form of tuples. For Example in the original dataset if each datacase is a documnet, then we would 
 * have tuples like (doc,word1),(doc(word2)...
 * Here word1 represents the name of the corresponding variable in the .csv file
 * We then write this converted dataset to a file for future use.
 * @param DataSetNameCsv .csv datafile name
 * @param OutputDataSetPath the path where the converted input data format will be saved
 * @throws IOException 
 */

public static void convertCSVtoTuples(String DataSetNameCsv, String OutputDataSetPath) throws IOException{
	
	PrintWriter out = new PrintWriter(OutputDataSetPath+File.separator+"SparseDataInputFormat.txt");
	
	// get the reader, split char = , and quotation char = " 
	// We start from line 0
	CSVReader reader = new CSVReader(new FileReader(DataSetNameCsv), ',', '"', 0);
	
	Iterator<String[]> iter = reader.iterator();
	
	//Line 0 should contain the variable names so read them first
	String[] varName = iter.next();
	
	int row_id = 1;
	while(iter.hasNext()){
		
		String[] datacase = iter.next();
		
		for(int i = 0 ; i < datacase.length ; i++){
			// For each datacase get the variables which are 1
			if(Integer.parseInt(datacase[i]) == 1){
				out.println(Integer.toString(row_id)+","+varName[i]);// write a (doc,varName) tuple
			}
		}
		
		row_id++;
	}
	
	out.close();
	reader.close();
}
 

public String getFileHead(String fileName) throws IOException, CsvValidationException {
    String head = "";
    FileReader fileReader = new FileReader(new File(fileName));
    CSVReader csvReader = new CSVReader(fileReader);
    String[] line = csvReader.readNext();
    if (line != null) {
        head = line[0];
    }
    csvReader.close();
    return head;
}
 

@Test
public void test() throws IOException {
	CSVReader r = new CSVReader(new StringReader("a,b\n1,2\n3,4"));
	try {
		assertArrayEquals(new String[]{"a","b"}, r.readNext());
		assertArrayEquals(new String[]{"1","2"}, r.readNext());
		assertArrayEquals(new String[]{"3","4"}, r.readNext());
		assertNull(r.readNext());
	} finally {
		r.close();
	}
}
 

/**
 * Loads shapes (if available) and puts them in {@link #shapes}. A shape is a sequence of points, i.e. a line.
 * <p/>
 * <br/><br/>
 * shapes.txt <i>[https://developers.google.com/transit/gtfs/reference]</i><br/>
 * Rules for drawing lines on a map to represent a transit organization's routes.
 */
protected void loadShapes() {
	// shapes are optional
	log.info("Looking for shapes.txt");

	int l = 1;
	try {
		CSVReader reader = createCSVReader(root + GtfsDefinitions.Files.SHAPES.fileName);
		String[] header = reader.readNext();
		Map<String, Integer> col = getIndices(header, GtfsDefinitions.Files.SHAPES.columns, GtfsDefinitions.Files.SHAPES.optionalColumns);

		String[] line = reader.readNext();
		while(line != null) {
			l++;
			usesShapes = true; // shape file might exists but could be empty

			Id<RouteShape> shapeId = Id.create(line[col.get(GtfsDefinitions.SHAPE_ID)], RouteShape.class);

			RouteShape currentShape = shapes.get(shapeId);
			if(currentShape == null) {
				currentShape = new GtfsShape(line[col.get(GtfsDefinitions.SHAPE_ID)]);
				shapes.put(shapeId, currentShape);
			}
			Coord point = new Coord(Double.parseDouble(line[col.get(GtfsDefinitions.SHAPE_PT_LON)]), Double.parseDouble(line[col.get(GtfsDefinitions.SHAPE_PT_LAT)]));
			currentShape.addPoint(point, Integer.parseInt(line[col.get(GtfsDefinitions.SHAPE_PT_SEQUENCE)]));
			line = reader.readNext();
		}
		reader.close();
		log.info("...     shapes.txt loaded");
	} catch (IOException e) {
		log.info("...     no shapes file found.");
	} catch (ArrayIndexOutOfBoundsException i) {
		throw new RuntimeException("Line " + l + " in shapes.txt is empty or malformed.");
	}
}
 

/**
 * Basically just reads all routeIds and their corresponding names and types and puts them in {@link #routes}.
 * <p/>
 * <br/><br/>
 * routes.txt <i>[https://developers.google.com/transit/gtfs/reference]</i><br/>
 * Transit routes. A route is a group of trips that are displayed to riders as a single service.
 *
 * @throws IOException
 */
protected void loadRoutes() throws IOException {
	log.info("Loading routes.txt");

	int l = 1;
	try {
		CSVReader reader = createCSVReader(root + GtfsDefinitions.Files.ROUTES.fileName);
		String[] header = reader.readNext();
		Map<String, Integer> col = getIndices(header, GtfsDefinitions.Files.ROUTES.columns, GtfsDefinitions.Files.ROUTES.optionalColumns);

		String[] line = reader.readNext();
		while(line != null) {
			l++;
			int routeTypeNr = Integer.parseInt(line[col.get(GtfsDefinitions.ROUTE_TYPE)]);

			ExtendedRouteType extendedRouteType = RouteType.getExtendedRouteType(routeTypeNr);

			if(extendedRouteType == null) {
				log.warn("Route " + line[col.get(GtfsDefinitions.ROUTE_ID)] + " of type " + routeTypeNr + " will be ignored");
				ignoredRoutes.add(line[col.get(GtfsDefinitions.ROUTE_ID)]);
			} else {
				String routeId = line[col.get(GtfsDefinitions.ROUTE_ID)];
				String shortName = line[col.get(GtfsDefinitions.ROUTE_SHORT_NAME)];
				String longName = line[col.get(GtfsDefinitions.ROUTE_LONG_NAME)];
				Route newGtfsRoute = new RouteImpl(routeId, shortName, longName, extendedRouteType);
				routes.put(line[col.get(GtfsDefinitions.ROUTE_ID)], newGtfsRoute);
			}

			line = reader.readNext();
		}
		reader.close();
	} catch (ArrayIndexOutOfBoundsException i) {
		throw new RuntimeException("Line " + l + " in routes.txt is empty or malformed.");
	}
	log.info("...     routes.txt loaded");
}
 

/**
 * Parses a command file (csv) and runs the commands specified
 */
@Override
public void parseCommandCsv(String filePath) throws IOException {
	CSVReader reader = new CSVReader(new FileReader(filePath), ';');

	String[] line = reader.readNext();
	while(line != null) {
		log.info(CollectionUtils.arrayToString(line));
		executeCmdLine(line);
		line = reader.readNext();
	}
	reader.close();
}
 

/**
	 * @param args the command line arguments
	 */
	public static void main(String[] args) throws FileNotFoundException, IOException {

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\rankingCandidateGenes");


//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\Prioritisations\\samples.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\CandidateGenes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\rankingCandidateGenes");

		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\hpo5gpm.txt");
		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\Genes\\");
		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\Prioritisations\\");
		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\RankingCandidateGenes\\");

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader sampleFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(sampleFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		while ((nextLine = sampleFileReader.readNext()) != null) {

			String sample = nextLine[0];

			String genoSampleName = sample + ".txt";

			File genoFile = new File(genoFolder, genoSampleName);
			File prioFile = new File(prioFolder, sample + ".txt");
			File rankingFile = new File(resultFolder, sample + ".txt");

			System.out.println("------------------------------------------------------------------");
			System.out.println("Sample: " + sample);
			System.out.println("Geno: " + genoFile.getAbsolutePath());
			System.out.println("Prio: " + prioFile.getAbsolutePath());
			System.out.println("Ranking: " + rankingFile.getAbsolutePath());

			HashSet<String> genesWithMutation = getMutatedGenes(genoFile, 0, 0);

			final CSVReader prioFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(prioFile))).withSkipLines(0).withCSVParser(parser).build();

			CSVWriter writer = new CSVWriter(new FileWriter(rankingFile), '\t', '\0', '\0', "\n");

			String[] outputLine = prioFileReader.readNext();
			writer.writeNext(outputLine);

			while ((outputLine = prioFileReader.readNext()) != null) {

				if (genesWithMutation.contains(outputLine[1])) {
					writer.writeNext(outputLine);
				}

			}

			writer.close();
			prioFileReader.close();

		}

	}
 

/**
	 * @param args the command line arguments
	 */
	public static void main(String[] args) throws FileNotFoundException, IOException {
//
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\rankingCandidateGenes");

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\rankingCandidateGenes");
		
		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\samplesWithGeno.txt");
		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\gavinRes\\");
		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\Prioritisations");
		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\rankingCandidateGenes");

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\rankingCandidateGenes");
//
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsSpiked");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsSpiked\\rankingCandidateGenes");
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\Gavin\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\");
//		
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\Prioritisations\\samples.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\CandidateGenes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\");
//
//		
		resultFolder.mkdirs();

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader sampleFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(sampleFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		while ((nextLine = sampleFileReader.readNext()) != null) {

			String sample = nextLine[0];

			String genoSampleName = new File(nextLine[1]).getName();
			if (!genoSampleName.endsWith(".txt")) {
				genoSampleName += ".txt";
			}

			File genoFile = new File(genoFolder, genoSampleName);
			File prioFile = new File(prioFolder, sample + ".txt");
			File rankingFile = new File(resultFolder, sample + ".txt");

			System.out.println("------------------------------------------------------------------");
			System.out.println("Sample: " + sample);
			System.out.println("Geno: " + genoFile.getAbsolutePath());
			System.out.println("Prio: " + prioFile.getAbsolutePath());
			System.out.println("Ranking: " + rankingFile.getAbsolutePath());

			HashSet<String> genesWithMutation = getMutatedGenes(genoFile);

			final CSVReader prioFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(prioFile))).withSkipLines(0).withCSVParser(parser).build();

			CSVWriter writer = new CSVWriter(new FileWriter(rankingFile), '\t', '\0', '\0', "\n");

			String[] outputLine = prioFileReader.readNext();
			writer.writeNext(outputLine);

			while ((outputLine = prioFileReader.readNext()) != null) {

				if (genesWithMutation.contains(outputLine[1])) {
					writer.writeNext(outputLine);
				}

			}

			writer.close();
			prioFileReader.close();

		}

	}
 

public static TObjectDoubleMap<String> readPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		TObjectDoubleMap<String> hpos = new TObjectDoubleHashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			hpos.put(nextLine[0], Double.parseDouble(nextLine[3]));

		}

		reader.close();

		return hpos;

	}
 

public static TObjectDoubleMap<String> readSignificantPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		TObjectDoubleMap<String> hpos = new TObjectDoubleHashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if(Double.parseDouble(nextLine[4]) <= 0.05){
				hpos.put(nextLine[0], Double.parseDouble(nextLine[3]));
			}
			

		}

		reader.close();

		return hpos;

	}
 

/**
 * Expects filenames in the map
 */
public static Map<En, List<String[]>> start2(Map<String, Reader> map, AqlOptions op,
		Schema<Ty, En, Sym, Fk, Att> sch, boolean omitCheck) throws Exception {
	Character sepChar = (Character) op.getOrDefault(AqlOption.csv_field_delim_char);
	Character quoteChar = (Character) op.getOrDefault(AqlOption.csv_quote_char);
	Character escapeChar = (Character) op.getOrDefault(AqlOption.csv_escape_char);

	final CSVParser parser = new CSVParserBuilder().withSeparator(sepChar).withQuoteChar(quoteChar)
			.withEscapeChar(escapeChar).withFieldAsNull(CSVReaderNullFieldIndicator.EMPTY_SEPARATORS).build();

	Map<En, List<String[]>> ret = new THashMap<>();
	for (String k : map.keySet()) {
		if (!omitCheck) {
			if (!sch.ens.contains(En.En(k))) {
				throw new RuntimeException("Not an entity: " + k);
			}
		}
		Reader r = map.get(k);

		// File file = new File(map.get(k));
		// BufferedReader fileReader = new BufferedReader(r);
		// String s;
		/// while ((s = fileReader.readLine()) != null) {
		// System.out.println(s);
		// }

		final CSVReader reader = new CSVReaderBuilder(r).withCSVParser(parser)
				.withFieldAsNull(CSVReaderNullFieldIndicator.EMPTY_SEPARATORS).build();

		List<String[]> rows = reader.readAll();
		
		ret.put(En.En(k), rows);
		reader.close();
		r.close();
	}

	if (!omitCheck) {
		for (En en : sch.ens) {
			if (!ret.containsKey(en)) {
				ret.put(en,
						new LinkedList<>(Collections.singletonList(Util
								.union(sch.attsFrom(en).stream().map(Object::toString).collect(Collectors.toList()),
										sch.fksFrom(en).stream().map(Object::toString).collect(Collectors.toList()))
								.toArray(new String[0]))));
			}
		}
	}
	return ret;
}
 

/**
 * @param args the command line arguments
 * @throws java.io.FileNotFoundException
 */
public static void main(String[] args) throws FileNotFoundException, IOException {

	final File logFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_predictions.log");
	final int pcCount = 1588;
	final File outputMatrixFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_compPathwayZscoreMatrix.txt.gz");

	final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
	CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(logFile))).withSkipLines(0).withCSVParser(parser).build();

	LinkedHashSet<String> pathways = new LinkedHashSet<>();

	String[] nextLine;
	while ((nextLine = reader.readNext()) != null) {

		if (nextLine[0].equals("Processing geneset:")) {

			if (!pathways.add(nextLine[1])) {

				System.err.println("Duplicate pathway: " + nextLine[1]);
			}

		}

	}

	System.out.println("Number of pathways: " + pathways.size());

	LinkedHashSet<String> pcs = new LinkedHashSet<>();
	for (int pc = 1; pc <= pcCount; pc++) {
		pcs.add("PC" + pc);
	}

	DoubleMatrixDataset zscoreMatrix = new DoubleMatrixDataset(pathways, pcs);

	reader.close();

	reader = new CSVReaderBuilder(new BufferedReader(new FileReader(logFile))).withSkipLines(0).withCSVParser(parser).build();

	while ((nextLine = reader.readNext()) != null) {

		if (nextLine[0].equals("Processing geneset:")) {

			String pathway = nextLine[1];

			reader.readNext();//skip header

			for (int pc = 1; pc <= pcCount; pc++) {

				nextLine = reader.readNext();
				
				if(!nextLine[0].equals("PC" + pc)){
					System.err.println("Error parsing z-scores for: " + pathway);
				}
				
				zscoreMatrix.setElement(pathway, nextLine[0], Double.valueOf(nextLine[4]));
				
			}

		}

	}

	reader.close();
	zscoreMatrix.save(outputMatrixFile);

}