com.opencsv.CSVReaderBuilder Java Examples

public static void main(String[] args) throws FileNotFoundException, IOException {
    // TODO code application logic here 
    File phase3File = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\phase3_corrected.psam");
    File traitFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\TraitFile.txt");
    File probeAnnotationFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\ProbeAnnotationFile.txt");
    File couplingFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\CouplingFile.txt");
    //FileReader(String phase3_corrected)
    final CSVParser gmtParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
    final CSVReader gmtReader = new CSVReaderBuilder(new BufferedReader(new FileReader(phase3File))).withSkipLines(1).withCSVParser(gmtParser).build();


    List<String> iids = new ArrayList<>();

    String[] inputLine;
    while ((inputLine = gmtReader.readNext()) != null) {

        String iid = inputLine[0];

        iids.add(iid);
    }

    trait(iids, traitFile);
    probeAnnotation(probeAnnotationFile);
    coupling(iids, couplingFile);
}
 

/**
 * Loads a {@link MetricFrame} from a CSV input stream.
 *
 * @param metricDef The underlying metric.
 * @param in        CSV input stream.
 * @param hasHeader Indicates whether the data has a header row.
 * @return A data frame containing the CSV data.
 * @throws IOException if there's a problem reading the CSV input stream.
 */
public static MetricFrame loadCsv(MetricDefinition metricDef, InputStream in, boolean hasHeader)
        throws IOException {

    List<String[]> rows;
    try (val br = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8))) {
        val skipLines = hasHeader ? 1 : 0;
        val reader = new CSVReaderBuilder(br).withSkipLines(skipLines).build();
        rows = reader.readAll();
    }

    val numRows = rows.size();
    val metricData = new MetricData[numRows];

    for (int i = 0; i < numRows; i++) {
        metricData[i] = toMetricData(metricDef, rows.get(i));
    }

    return new MetricFrame(metricData);
}
 

public static List<String[]> oneByOne(Reader reader) {
    List<String[]> list = new ArrayList<>();
    try {
        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

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

        String[] line;
        while ((line = csvReader.readNext()) != null) {
            list.add(line);
        }
        reader.close();
        csvReader.close();
    } catch (Exception ex) {
        Helpers.err(ex);
    }
    return list;
}
 

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;
    }
 

@SuppressWarnings("Duplicates")
private static TimeSeries getCo2Data() throws IOException {

	final String path =  "../StlDemoRestServer/co2.csv";

	CSVReaderBuilder builder = new CSVReaderBuilder(new FileReader(path));

	TimeSeries ts = new TimeSeries();

	try (CSVReader reader = builder.withSkipLines(1).build()) {

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {
			double dateAsYear = Double.parseDouble(nextLine[1]);
			long time = (long) ((dateAsYear - 1970.0) * 365.25 * 24 * 60 * 60 * 1000);
			ts.times.add(time);

			double value = Double.parseDouble(nextLine[2]);
			ts.values.add(value);
		}
	}
	return ts;
}
 

private static TimeSeries getHourlyData() throws IOException {
	final String path = "./fortran_benchmark/hourly_stl_test.csv";

	CSVReaderBuilder builder = new CSVReaderBuilder(new FileReader(path));

	TimeSeries ts = new TimeSeries();

	try (CSVReader reader = builder.build()) {

		String[] nextLine;
		long time = 1492457959000L;
		while ((nextLine = reader.readNext()) != null) {
			ts.times.add(time);
			time += 3600 * 1000;
			double value = Double.parseDouble(nextLine[0]);
			ts.values.add(value);
		}
	}
	return ts;
}
 

@SuppressWarnings("Duplicates")
public static TimeSeries getTimeSeries(String fileName) throws IOException {
	CSVReaderBuilder builder = new CSVReaderBuilder(new FileReader(fileName));

	TimeSeries ts = new TimeSeries();

	try (CSVReader reader = builder.withSkipLines(1).build()) {

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {
			double dateAsYear = Double.parseDouble(nextLine[1]);
			long time = (long) ((dateAsYear - 1970.0) * 365.25 * 24 * 60 * 60 * 1000);
			ts.times.add(time);

			double value = Double.parseDouble(nextLine[2]);
			ts.values.add(value);
		}
	}
	return ts;
}
 

@Override
public void doProcessStream(InputStream stream, String source, JCas jCas) throws IOException {
  super.doProcessStream(stream, source, jCas);
  CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).build();
  try (CSVReader reader =
      new CSVReaderBuilder(new InputStreamReader(stream, StandardCharsets.UTF_8))
          .withCSVParser(parser)
          .build()) {
    String[] cols = reader.readNext();
    if (cols == null || cols.length < contentColumn) {
      throw new IOException("Not enough columns");
    }

    for (int i = 0; i < cols.length; i++) {
      if (i == (contentColumn - 1)) {
        jCas.setDocumentText(cols[i]);
      } else {
        addMetadata(jCas, i, cols[i]);
      }
    }
  }
}
 

/**
 * 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 static HashMap<String, HashMap<String, HashSet<String>>> loadTfData(File tfFile) throws FileNotFoundException, IOException {

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

		HashMap<String, HashMap<String, HashSet<String>>> tfdatabasesPathwayToGenes = new HashMap<>();

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

			if (nextLine[0].charAt(0) == '!') {
				continue;
			}

			String database = nextLine[0];
			String pathway = nextLine[1];
			String ensgId = nextLine[3];

			HashMap<String, HashSet<String>> pathwayToGenes = tfdatabasesPathwayToGenes.get(database);
			if (pathwayToGenes == null) {
				pathwayToGenes = new HashMap<>();
				tfdatabasesPathwayToGenes.put(database, pathwayToGenes);
			}

			HashSet<String> pathwayGenes = pathwayToGenes.get(pathway);
			if (pathwayGenes == null) {
				pathwayGenes = new HashSet<>();
				pathwayToGenes.put(pathway, pathwayGenes);
			}

			pathwayGenes.add(ensgId);

		}

		return tfdatabasesPathwayToGenes;

	}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

/**
 * Initiate countries map.
 */
private void initCountries() {
    Objects.requireNonNull(countriesFile);
    countries = new HashMap<>();
    String[] line;
    try (CSVReader reader = new CSVReaderBuilder(new InputStreamReader(countriesFile, StandardCharsets.UTF_8)).withCSVParser(new CSVParser()).withSkipLines(0).build()) {
        while ((line = reader.readNext()) != null) {
            Country country = new Country();
            country.setName(line[0]);
            countries.put(country.getName(), country);
        }
    } catch (IOException | CsvValidationException exception) {
        throw new IllegalStateException(exception.getMessage());
    }
}
 

public static BarSeries getHourlyBarSeries(URL file, String name){

        List<Bar> ticks = new ArrayList<>();
        CSVReader reader;
        String nameInCSV="";
        try {
            reader = new CSVReaderBuilder(new FileReader(file.getFile())).withSkipLines(1).build();
            String[] line;
            nameInCSV = reader.readNext()[0];
            if(nameInCSV==null || nameInCSV.equals("")){
                nameInCSV = name;
            }
            while ((line = reader.readNext()) != null) {
                ZonedDateTime date = ZonedDateTime.parse(line[0]+" "+line[1]+" PST", DATE_FORMAT_HOURLY_MINUTE);
                double open = Double.parseDouble(line[2]);
                double high = Double.parseDouble(line[3]);
                double low = Double.parseDouble(line[4]);
                double close = Double.parseDouble(line[5]);
                double volume = Double.parseDouble(line[6]);

                ticks.add(new BaseBar(Duration.ZERO, date, open, high, low, close, volume, 0, 0, Parameter.numFunction));
            }
        } catch (IOException e) {
            e.printStackTrace();
        }

        if (ticks.get(0).getEndTime().isAfter(ticks.get(ticks.size()-1).getEndTime()))
            Collections.reverse(ticks);

        return new BaseBarSeries(nameInCSV, ticks);
    }
 

/**
 * Connects to the countries list and build a map of {@link Country} with the name as key.
 *
 * @throws CsvValidationException when the parsing of the file fails
 * @throws IOException            when network error
 * @throws URISyntaxException     when the URI is invalid
 */
public void buildCountries() throws URISyntaxException, IOException, CsvValidationException {
    countries = new HashMap<>();
    URI countriesUri = new URI(COUNTRIES_URI);
    try (InputStream countriesStream = countriesUri.toURL().openStream();
            CSVReader reader = new CSVReaderBuilder(new InputStreamReader(countriesStream, StandardCharsets.UTF_8)).withCSVParser(new CSVParser()).withSkipLines(1).build()) {
        String[] line;
        while ((line = reader.readNext()) != null) {
            Country c = new Country();
            c.setName(line[2]);
            countries.put(line[1], c);
        }
    }
}
 

private static HashMap<String, HashSet<String>> readClusterFile(File hpoFile) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(0).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		HashSet<String> allMyoclonusGenes = new HashSet<>();
		hpoToGenes.put("AllMyoclonus", allMyoclonusGenes);

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String gene = nextLine[0];
			String cluster = nextLine[1];

			HashSet<String> hpoGenes = hpoToGenes.get(cluster);
			if (hpoGenes == null) {
				hpoGenes = new HashSet<>();
				hpoToGenes.put(cluster, hpoGenes);
			}

			allMyoclonusGenes.add(gene);
			hpoGenes.add(gene);

		}

		return hpoToGenes;

	}
 

public CSVReader createCSVReader() throws IOException {
	Path path = Paths.get(this.datasetPath + this.datasetName + this.datasetEnding);
	
	CSVParser parser = new CSVParserBuilder()
			.withSeparator(this.valueSeparator)
			.withQuoteChar(this.valueQuote)
			.withEscapeChar(this.valueEscape)
			.withStrictQuotes(this.valueStrictQuotes)
			.withIgnoreLeadingWhiteSpace(this.valueIgnoreLeadingWhitespace)
			.withFieldAsNull(CSVReaderNullFieldIndicator.EMPTY_SEPARATORS)
			.build();
	
	BufferedReader buffer = Files.newBufferedReader(path, this.charset);
	CSVReader reader = new CSVReaderBuilder(buffer).withCSVParser(parser).build();
	
	if (this.fileHasHeader)
		reader.readNext();
	
	return reader;
}
 

public static BarSeries getDailyBarSeries(String fileName){
    // load a BarSeries
    InputStream inputStream = Loader.class.getClassLoader().getResourceAsStream(fileName);
    BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));

    List<Bar> ticks = new ArrayList<>();
    CSVReader reader;
    String nameInCSV="";
    try {
        reader = new CSVReaderBuilder(bufferedReader).withSkipLines(1).build();
        String[] line;
        nameInCSV = reader.readNext()[0];
        if(nameInCSV==null||nameInCSV.equals("")){
            nameInCSV=fileName;
        }
        while ((line = reader.readNext()) != null) {
            ZonedDateTime date = LocalDate.parse(line[0], DATE_FORMAT_Daily).atStartOfDay(ZoneId.systemDefault());
            double close = Double.parseDouble(line[1]);
            double volume = Double.parseDouble(line[2]);
            double open = Double.parseDouble(line[3]);
            double high = Double.parseDouble(line[4]);
            double low = Double.parseDouble(line[5]);

            ticks.add(new BaseBar(Duration.ZERO, date, open, high, low, close, volume, 0, 0, Parameter.numFunction));
        }
        bufferedReader.close();
    } catch (IOException e) {
        e.printStackTrace();
    }

    if (ticks.get(0).getEndTime().isAfter(ticks.get(ticks.size()-1).getEndTime()))
        Collections.reverse(ticks);
    return new BaseBarSeries(nameInCSV, ticks);
}
 

@Override
  public boolean connect(File resource){
      String separator = properties.getProperty(Parameter.PROPERTY_CSV_SEPARATOR, ",");
      String quote = properties.getProperty(Parameter.PROPERTY_CSV_QUOTE, "\\\\");
      CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).withQuoteChar(quote.charAt(0)).build();
      try(CSVReader reader = new CSVReaderBuilder(new FileReader(resource)).withCSVParser(parser).build();)
      {
      	lines = reader.readAll();
      	String[] infoLine = lines.get(0);
	name = infoLine[0];
       id = FormatUtils.extractInteger(infoLine[1]);
       isDateTwoColumn = id == TimeFormatType.yyyy_MM_ddHmsz.id;
       dateTimeFormatter = FormatUtils.getDateTimeFormatter(id);
       String currencyString = null;
       if(infoLine.length>2) {
           currencyString = infoLine[2].replaceAll("\\s", "");
       }
       if(currencyString == null || currencyString.length() != 3)
           currencyString = Parameter.DEFAULT_CURRENCY;
       currency = Currency.getInstance(currencyString);
       lines.remove(0); // remove InfoLine
} catch (FileNotFoundException e) {
	log.error(e.getMessage());
	e.printStackTrace();
	return false;
} catch (IOException ioe) {
	log.error(ioe.getMessage());
	ioe.printStackTrace();
	return false;
}
      return true;
  }
 

@Override
protected void configure(InputStream inputStream, final Long lastOffset) throws IOException {
  log.trace("configure() - creating csvParser");
  this.csvParser = this.config.createCSVParserBuilder();
  this.streamReader = new InputStreamReader(inputStream, this.config.charset);
  CSVReaderBuilder csvReaderBuilder = this.config.createCSVReaderBuilder(this.streamReader, csvParser);
  this.csvReader = csvReaderBuilder.build();

  String[] fieldNames;

  if (this.config.firstRowAsHeader) {
    log.trace("configure() - Reading the header row.");
    fieldNames = this.csvReader.readNext();
    log.info("configure() - field names from header row. fields = {}", Joiner.on(", ").join(fieldNames));
  } else {
    log.trace("configure() - Using fields from schema {}", this.config.valueSchema.name());
    fieldNames = new String[this.config.valueSchema.fields().size()];
    int index = 0;
    for (Field field : this.config.valueSchema.fields()) {
      fieldNames[index++] = field.name();
    }
    log.info("configure() - field names from schema order. fields = {}", Joiner.on(", ").join(fieldNames));
  }

  if (null != lastOffset) {
    log.info("Found previous offset. Skipping {} line(s).", lastOffset.intValue());
    String[] row = null;
    while (null != (row = this.csvReader.readNext()) && this.csvReader.getLinesRead() < lastOffset) {
      log.trace("skipped row");
    }
  }

  this.fieldNames = fieldNames;
}
 

public CSVReaderBuilder createCSVReaderBuilder(Reader reader, ICSVParser parser) {
  return new CSVReaderBuilder(reader)
      .withCSVParser(parser)
      .withKeepCarriageReturn(this.keepCarriageReturn)
      .withSkipLines(this.skipLines)
      .withVerifyReader(this.verifyReader)
      .withFieldAsNull(nullFieldIndicator);
}
 

/**
 * Given a Reader and a separator character, return the contents of the table as a list of rows.
 *
 * @param reader a reader to read data from
 * @param separator separator character
 * @return a list of lists of strings
 * @throws IOException on file reading problems
 */
private static List<List<String>> readXSV(Reader reader, char separator) throws IOException {
  CSVReader csv =
      new CSVReaderBuilder(reader)
          .withCSVParser(new CSVParserBuilder().withSeparator(separator).build())
          .build();
  List<List<String>> rows = new ArrayList<>();
  for (String[] nextLine : csv) {
    rows.add(new ArrayList<>(Arrays.asList(nextLine)));
  }
  csv.close();
  return rows;
}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

private static Map<String, String> loadUpdatedIds(File updatedIdFile) throws IOException {

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

		HashMap<String, String> updates = new HashMap<>();

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

			updates.put(nextLine[0], nextLine[1]);

		}

		return Collections.unmodifiableMap(updates);

	}
 

public static LinkedHashSet<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();

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

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

			hpos.add(nextLine[0]);

		}

		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;

	}
 

private static HashSet<String> getMutatedGenes(File genoFile, int colWithGene, int skipHeaderLines) throws IOException {

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

		HashSet<String> genes = new HashSet<>();

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

			genes.add(nextLine[colWithGene]);

		}

		reader.close();

		return genes;

	}
 

/**
	 * @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();

		}

	}
 

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;

	}
 

private static HashMap<String, LinkedHashSet<String>> loadCaseHpo(File caseHpoFile) throws FileNotFoundException, IOException {

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

		HashMap<String, LinkedHashSet<String>> caseHpo = new HashMap<>();

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

			if (nextLine[5].isEmpty()) {

				LinkedHashSet<String> hpo = caseHpo.get(nextLine[0]);
				if (hpo == null) {
					hpo = new LinkedHashSet<>();
					caseHpo.put(nextLine[0], hpo);
				}
				hpo.add(nextLine[1]);

			}

		}

		return caseHpo;

	}
 

private static Map<String, String> loadHgncToEnsg(File mappingFile) throws IOException {

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

		HashMap<String, String> mapping = new HashMap<>();

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

			mapping.put(nextLine[1], nextLine[0]);

		}

		return Collections.unmodifiableMap(mapping);

	}