コード例 #1
0
ファイル: ImportVariables.java プロジェクト: bioit/crezoo
  public boolean imp() {
    boolean res = false;

    DbVariable dbVariable = null;
    String fullFileName = "";
    String errMessage = null;
    DbImportFile dbInFile = new DbImportFile();
    try {
      dbVariable = new DbVariable();

      // Store the file on server filesystem
      fullFileName = dbInFile.storeImportFileBLOB(conn_viss, ifid);

      FileParser fileParser = new FileParser(fullFileName);
      fileParser.Parse(
          FileTypeDefinitionList.matchingDefinitions(
              FileTypeDefinition.VARIABLE, FileTypeDefinition.LIST));

      dbVariable.CreateVariables(fileParser, connection, sampleUnitId, Integer.parseInt(userId));

      errMessage = dbVariable.getErrorMessage();
      Assertion.assertMsg(errMessage == null || errMessage.trim().equals(""), errMessage);

      dbInFile.setStatus(conn_viss, ifid, "IMPORTED");
      // dbInFile.UpdateImportFile(connection,null,null,"Done",Integer.parseInt(ifid),Integer.parseInt(userId));

      // Add a message to the log
      dbInFile.addErrMsg(
          conn_viss,
          ifid,
          "File imported to sampling unit "
              + DbSamplingUnit.getSUName(conn_viss, Integer.toString(sampleUnitId))
              + "Note: Markers is always imported in Create mode.");
      res = true;
    } catch (Exception e) {
      Errors.logError("ImportVariables.imp(...)" + e.getMessage());

      dbInFile.setStatus(conn_viss, ifid, "ERROR");
      // dbInFile.UpdateImportFile(connection,null,null,e.getMessage(),Integer.parseInt(ifid),Integer.parseInt(userId));

      // Add a message to the log
      dbInFile.addErrMsg(conn_viss, ifid, e.getMessage());

      e.printStackTrace(System.err);
      if (errMessage == null) {
        errMessage = e.getMessage();
      }
    } finally {
      try {
        /*
         * Delete files uploaded
         */
        File tmp = new File(fullFileName);
        tmp.delete();
      } catch (Exception ignore) {
      }
    }

    return res;
  }
コード例 #2
0
  @Test
  public void test() throws IOException {
    String rootPath = "data/";

    FileParser parser = new FileParser();
    String absOutputPath = parser.setOutputPath(rootPath);
    System.out.println("Output path: " + absOutputPath);
    // Assert.assertEquals("", absOutputPath);

    int count = parser.parse(new File(rootPath + "wsj_0600.tok"));
    Assert.assertEquals(2, count);
    count = parser.parse(new File(rootPath + "file2.tok"));
    Assert.assertEquals(24, count);
    Assert.assertEquals(2, parser.docCount);
  }
コード例 #3
0
  @Test
  public void testParse() throws ParsingFailedException, IOException {
    try (InputStream stream =
        ClassLoader.getSystemClassLoader().getResourceAsStream("testfile.xlsx")) {
      FileParser parser = new XlsxFileParser();

      parser.setRowParsedListener(
          new RowParsedListener() {
            @Override
            public void parsed(final Row row) {
              parsedLines++;
            }
          });
      parser.parse(stream);
      Assert.assertEquals(1, parsedLines, 0.1);
    }
  }
コード例 #4
0
  public void writeCoverageInfoIfLineStartsANewFieldDeclaration(FileParser fileParser) {
    if (classAndFieldNames != null && className.equals(fileParser.getCurrentlyPendingClass())) {
      LineElement initialLineElement = fileParser.lineParser.getInitialElement();
      LineElement elementWithFieldName = initialLineElement.findWord(fieldName);

      if (elementWithFieldName != null) {
        buildOpeningTagForFieldWrapper();
        elementWithFieldName.wrapText(openingTag.toString(), "</span>");
        moveToNextField();
      }
    }
  }
コード例 #5
0
  /* Arguments: [0] = name to search for, [1] = the path of the file to search.*/
  public static void main(String args[]) {

    if (args.length != 2) {
      System.err.println(
          "\nYou have entered an invalid number of arguments."
              + "\n\nPlease use the name to search for followed by file to search through.");
      System.exit(1);
    }

    String key = args[0];
    String pathName = args[1];

    System.out.println("\nSearching for '" + key + "' in " + pathName + "...");

    ArrayList<Record> dataStore = FileParser.Parse(pathName);

    String phoneNumber = BinarySearchAlgorithm.pullKeyValue(key, (ArrayList<Record>) dataStore);
    if (phoneNumber == null) {
      System.out.println("\nNo record was found for " + key + ".");
    } else {
      System.out.println("\nRetrieved " + phoneNumber + " for " + key + ".\n");
    }
  }
コード例 #6
0
ファイル: ImportVariables.java プロジェクト: bioit/crezoo
  public boolean check() {
    Errors.logDebug("CheckVariables started");
    boolean res = false;
    DbImportFile dbInFile = new DbImportFile();
    String fullFileName = "";
    String checkFileName = "";
    String errMessage = null;

    try {
      // Create the variable
      DbVariable dbVariable = new DbVariable();

      dbInFile.setStatus(conn_viss, ifid, "0%");

      // Store the file on server filesystem
      fullFileName = dbInFile.storeImportFileBLOB(conn_viss, ifid);
      checkFileName = fullFileName + "_checked";

      FileHeader header = FileParser.scanFileHeader(fullFileName);
      String type = header.formatTypeName().toUpperCase();
      char delimiter = header.delimiter().charValue();

      FileParser fileParser = new FileParser(fullFileName);
      fileParser.Parse(
          FileTypeDefinitionList.matchingDefinitions(
              FileTypeDefinition.VARIABLE, FileTypeDefinition.LIST));

      // Write out the result to a new file
      FileWriter fileOut = new FileWriter(checkFileName);
      fileOut.write(
          header.objectTypeName()
              + "/"
              + header.formatTypeName()
              + "/"
              + header.version()
              + "/"
              + header.delimiter()
              + "\n");

      String titles[] = fileParser.columnTitles();
      for (int j = 0; j < titles.length; j++) {
        fileOut.write(titles[j] + delimiter);
      }
      fileOut.write("\n");

      String errorMsg = "";
      errorMsg = checkList(fileParser, fileOut, delimiter);
      fileOut.close();

      /*
       * Save the file to database
       */
      dbInFile.saveCheckedFile(conn_viss, ifid, checkFileName);

      if (errorMsg.startsWith("ERROR:")) {
        res = false;
        dbInFile.setStatus(conn_viss, ifid, "ERROR");

        // Add a message to the log
        dbInFile.addErrMsg(
            conn_viss,
            ifid,
            "File checked failed for sampling unit "
                + DbSamplingUnit.getSUName(conn_viss, Integer.toString(sampleUnitId))
                + ". <br>"
                + errorMsg);
        Errors.logDebug("ErrorMsg=" + errorMsg);
      } else if (errorMsg.startsWith("WARNING:")) {
        dbInFile.setStatus(conn_viss, ifid, "WARNING");
        res = true;

        // Add a message to the log
        dbInFile.addErrMsg(conn_viss, ifid, "Warnings exists: " + errorMsg);
      } else {
        dbInFile.setStatus(conn_viss, ifid, "CHECKED");
        res = true;

        // Add a message to the log
        dbInFile.addErrMsg(
            conn_viss,
            ifid,
            "File checked for sampling unit "
                + DbSamplingUnit.getSUName(conn_viss, Integer.toString(sampleUnitId))
                + ".<br>"
                + errorMsg);
      }

      /*
      if (errorMsg.length()>0)
      {
          res = false;
          dbInFile.setStatus(conn_viss,ifid,"ERROR");
          // Add a message to the log
          dbInFile.addErrMsg(conn_viss,ifid,"File failed the check for sampling unit "+DbSamplingUnit.getSUName(conn_viss,Integer.toString(sampleUnitId)) +"<br>"+errorMsg);
      }
      else
      {
          res = true;
          dbInFile.setStatus(conn_viss,ifid,"CHECKED");
          // Add a message to the log
          dbInFile.addErrMsg(conn_viss,ifid,"File checked for sampling unit "+DbSamplingUnit.getSUName(conn_viss,Integer.toString(sampleUnitId)) +"<br>"+errorMsg);
      }*/
    } catch (Exception e) {
      dbInFile.setStatus(conn_viss, ifid, "ERROR");

      // Add a message to the log
      dbInFile.addErrMsg(conn_viss, ifid, e.getMessage());

      e.printStackTrace(System.err);
      if (errMessage == null) {
        errMessage = e.getMessage();
      }
    } finally {
      try {
        /*
         * Delete files uploaded
         */
        File tmp = new File(checkFileName);
        tmp.delete();

        tmp = new File(fullFileName);
        tmp.delete();
      } catch (Exception ignore) {
      }
    }

    Errors.logDebug("CheckVariables completed");
    return res;
  }
コード例 #7
0
ファイル: Main.java プロジェクト: omacha/IVAOPlaneList
  public static void main(String[] args) {

    if (args.length < 2) {
      System.out.println(Helper.message());
      return;
    }

    Scanner sc = new Scanner(System.in);

    String inputFname = args[0];
    String outputFname = args[1];
    String errorFname;

    if (args.length < 3) {
      errorFname = "ERROR.log";
    } else {
      errorFname = args[2];
    }

    File input = new File(inputFname);
    File output = new File(outputFname);
    File error = new File(errorFname);

    if (!getFileType(input).toLowerCase().equals("dat")) {
      System.out.print(" Input file type is not DAT. Do you want to continue (Y/N) ? ");
      String answer = sc.nextLine();
      if (!answer.toLowerCase().equals("y")) {
        System.out.println(" Aborting...");
        sc.close();
        return;
      }
    }

    if (!getFileType(output).toLowerCase().equals("vmr")) {
      System.out.print(" Output file type is not VMR. Do you want to continue (Y/N) ? ");
      String answer = sc.nextLine();
      if (!answer.toLowerCase().equals("y")) {
        System.out.println(" Aborting...");
        sc.close();
        return;
      }
    }

    if (!getFileType(error).toLowerCase().equals("log")) {
      System.out.print(" Output file type is not LOG. Do you want to continue (Y/N) ? ");
      String answer = sc.nextLine();
      if (!answer.toLowerCase().equals("y")) {
        System.out.println(" Aborting...");
        sc.close();
        return;
      }
    }

    FileParser parser = new FileParser(input, output, error);

    try {
      int numErrors = parser.execute();

      if (numErrors == 0) {
        System.out.println("No errors during execution.");
        if (error.exists()) {
          error.delete();
        }
      } else {
        System.out.println(
            "There were " + numErrors + " errors during execution, see " + error.getName() + ".");
      }
    } catch (FileParserException e) {
      System.out.println("  Fatal error during execution:");
      System.out.println("	" + e.getMessage());
    }

    sc.close();
  }
コード例 #8
0
ファイル: ImportPhenotypes.java プロジェクト: bioit/crezoo
  public boolean imp() {
    boolean res = false;
    String errMessage = null;

    DbImportFile dbInFile = new DbImportFile();
    DbPhenotype dbp = new DbPhenotype();
    String fullFileName = null;

    try {
      Errors.logInfo("CheckPhenotype started");
      // connection.setAutoCommit(false);
      dbInFile.setStatus(conn_viss, ifid, "0%");

      fullFileName = dbInFile.storeImportFileBLOB(conn_viss, ifid);

      FileHeader header = FileParser.scanFileHeader(fullFileName);
      FileParser fileParser = new FileParser(fullFileName);

      // Set status
      dbInFile.setStatus(conn_viss, ifid, "10%");

      // Ensure file format is list or matrix
      Assertion.assertMsg(
          header.formatTypeName().equalsIgnoreCase(FileTypeDefinition.LIST)
              || header.formatTypeName().equalsIgnoreCase(FileTypeDefinition.MATRIX),
          "Format type name should be list or matrix "
              + "but found found "
              + header.formatTypeName());

      // If file is a list
      if (header.formatTypeName().equalsIgnoreCase(FileTypeDefinition.LIST)) {
        fileParser.Parse(
            FileTypeDefinitionList.matchingDefinitions(
                FileTypeDefinition.PHENOTYPE, FileTypeDefinition.LIST));
        dbInFile.setStatus(conn_viss, ifid, "20%");

        if (updateMethod.equals("CREATE")) {
          dbp.CreatePhenotypesList(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        } else if (updateMethod.equals("UPDATE")) {
          dbp.UpdatePhenotypesList(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        } else if (updateMethod.equals("CREATE_OR_UPDATE")) {
          dbp.CreateOrUpdatePhenotypesList(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        }
      }

      // If file is a matrix
      else if (header.formatTypeName().equalsIgnoreCase(FileTypeDefinition.MATRIX)) {
        fileParser.Parse(
            FileTypeDefinitionList.matchingDefinitions(
                FileTypeDefinition.PHENOTYPE, FileTypeDefinition.MATRIX));
        dbInFile.setStatus(conn_viss, ifid, "20%");

        if (updateMethod.equals("CREATE")) {
          dbp.CreatePhenotypesMatrix(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        } else if (updateMethod.equals("UPDATE")) {
          dbp.UpdatePhenotypesMatrix(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        } else if (updateMethod.equals("CREATE_OR_UPDATE")) {
          dbp.CreateOrUpdatePhenotypesMatrix(
              fileParser, connection, sampleUnitId, Integer.valueOf(userId).intValue());
        }
      }
      errMessage = dbp.getErrorMessage();

      Assertion.assertMsg(errMessage == null || errMessage.trim().equals(""), errMessage);

      dbInFile.setStatus(conn_viss, ifid, "IMPORTED");

      // Add a message to the log
      dbInFile.addErrMsg(
          conn_viss,
          ifid,
          "File imported for sampling unit "
              + DbSamplingUnit.getSUName(conn_viss, Integer.toString(sampleUnitId)));
      res = true;

      Errors.logInfo("Check Phenotype ended");
    } catch (Exception e) {
      // Flag for error and set the errMessage if it has not been set
      // isOk = false;
      dbInFile.setStatus(conn_viss, ifid, "ERROR");

      // Add a message to the log
      dbInFile.addErrMsg(conn_viss, ifid, e.getMessage());

      e.printStackTrace(System.err);
      if (errMessage == null) {
        errMessage = e.getMessage();
      }
    }

    return res;
  }
コード例 #9
0
ファイル: ImportPhenotypes.java プロジェクト: bioit/crezoo
  public boolean check() {
    Errors.logDebug("CheckPhenotype started");

    boolean res = false;

    String errMessage = null;
    FileWriter fileOut = null;
    DbImportFile dbInFile = new DbImportFile();

    String fullFileName = "";
    String checkFileName = "";
    try {
      dbInFile.setStatus(conn_viss, ifid, "0%");

      fullFileName = dbInFile.storeImportFileBLOB(conn_viss, ifid);
      checkFileName = fullFileName + "_checked";

      // Create the Phenotype
      DbPhenotype dbPhenotype = new DbPhenotype();

      FileHeader header = FileParser.scanFileHeader(fullFileName);
      String type = header.formatTypeName().toUpperCase();
      char delimiter = header.delimiter().charValue();

      // AbstractValueFileParser fp = null;
      FileParser fp = null;

      if (type.equals("LIST")) {
        fp = new FileParser(fullFileName);
        fp.Parse(
            FileTypeDefinitionList.matchingDefinitions(
                FileTypeDefinition.PHENOTYPE, FileTypeDefinition.LIST));
      } else if (type.equals("MATRIX")) {
        fp = new FileParser(fullFileName);
        fp.Parse(
            FileTypeDefinitionList.matchingDefinitions(
                FileTypeDefinition.PHENOTYPE, FileTypeDefinition.MATRIX));
      }

      // Write out the result to a new file
      fileOut = new FileWriter(checkFileName);
      fileOut.write(
          header.objectTypeName()
              + "/"
              + header.formatTypeName()
              + "/"
              + header.version()
              + "/"
              + header.delimiter()
              + "\n");

      String titles[] = fp.columnTitles();
      for (int j = 0; j < titles.length; j++) {
        fileOut.write(titles[j] + delimiter);
      }
      fileOut.write("\n");

      // Garbage collect the unused variables
      header = null;
      // fullFileName = null;
      // checkFileName = null;

      // Fix to upper case
      updateMethod = updateMethod.toUpperCase();

      Vector fatalErrors = new Vector();

      if (type.equals("LIST")) checkListTitles(titles, fatalErrors);
      else checkMatrixTitles(titles, fatalErrors);

      writeTitleErrors(fileOut, fatalErrors);

      String indId;

      if (titles[0].equals("IDENTITY")) indId = "IDENTITY";
      else indId = "Alias";

      String errMsg = "";
      if (type.equals("LIST")) errMsg = checkList((FileParser) fp, fileOut, delimiter, indId);
      // errMsg = checkList((FileParser)fp, fatalErrors,fileOut,delimiter,indId);
      else if (type.equals("MATRIX"))
        errMsg = checkMatrix((FileParser) fp, fatalErrors, fileOut, delimiter, indId);

      // Close the file
      fileOut.close();

      /*
       * Save the file to database
       */
      dbInFile.saveCheckedFile(conn_viss, ifid, checkFileName);

      // Get the error message from the database object. If it is set an
      // error occured during the operation so an error is thrown.
      // errMessage = dbIndividual.getErrorMessage();
      // Assertion.assertMsg(errMessage == null ||
      //                     errMessage.trim().equals(""), errMessage);

      if (errMsg.startsWith("ERROR:")) {
        dbInFile.setStatus(conn_viss, ifid, "ERROR");
        res = false;
      } else if (errMsg.startsWith("WARNING:")) {
        dbInFile.setStatus(conn_viss, ifid, "WARNING");
        res = true;
      } else {
        dbInFile.setStatus(conn_viss, ifid, "CHECKED");
        res = true;
      }

      // Add a message to the log
      dbInFile.addErrMsg(
          conn_viss,
          ifid,
          "File checked for sampling unit "
              + DbSamplingUnit.getSUName(conn_viss, Integer.toString(sampleUnitId))
              + "<br>\n"
              + errMsg);

    } catch (Exception e) {
      // Flag for error and set the errMessage if it has not been set
      // isOk = false;
      dbInFile.setStatus(conn_viss, ifid, "ERROR");
      // dbInFile.UpdateImportFile(connection,null,null,e.getMessage(),Integer.parseInt(ifid),Integer.parseInt(userId));

      // Add a message to the log
      dbInFile.addErrMsg(conn_viss, ifid, e.getMessage());

      e.printStackTrace(System.err);
      if (errMessage == null) {
        errMessage = e.getMessage();
      }
    } finally {
      try {

        /*
         * Delete temporary file
         */
        File tmp = new File(fullFileName);
        tmp.delete();
        tmp = null;

        tmp = new File(checkFileName);
        tmp.delete();
        tmp = null;
      } catch (Exception ignore) {
      }
    }

    Errors.logDebug("CheckPhenotype completed");

    return res;
  }
コード例 #10
0
ファイル: ImportPhenotypes.java プロジェクト: bioit/crezoo
  public String checkMatrix(
      FileParser fp, Vector fatalErrors, FileWriter fileOut, char delimiter, String indId) {

    String errMsg = "";
    // String ind, marker = "", allele1 = "", allele2 = ""; //, raw1, raw2; //, //ref; //, comm;
    String ind = "", variable = "", value = "";
    // String alleles[];

    int nrErrors = 0;
    int nrWarnings = 0;
    int nrDeviations = 0;

    /*
    Vector errorMessages = new Vector();
    Vector warningMessages = new Vector();
    Vector deviationMessages = new Vector();
    Vector databaseValues = new Vector();
    */

    DbImportFile dbInFile = new DbImportFile();
    String statusStr;
    double status;
    double status_last = 0.0;

    int dataRows = fp.dataRows();
    String titles[] = fp.columnTitles();
    String variables[] = new String[titles.length - 1];
    for (int i = 0; i < variables.length; i++) variables[i] = titles[i + 1];

    Vector deviationMessages = null;
    Vector databaseValues = null;
    Vector newAlleles = null;
    Vector values = null;

    warningList = new ArrayList();
    errorList = new ArrayList();

    for (int row = 0; row < fp.dataRows(); row++) {
      deviationMessages = new Vector();
      databaseValues = new Vector();
      values = new Vector();

      ind = fp.getValue(indId, row);

      // newAlleles = new Vector();

      // check the whole row
      for (int mNum = 0; mNum < variables.length; mNum++) {
        // String old_alleles[]=null;
        variable = variables[mNum];
        value = fp.getValue(variable, row);

        // Add the values for error writing
        values.add(value);

        // check that values exist, have correct length etc
        checkValues(ind, variable, value, null, null, null);

        if (updateMethod.equals("CREATE"))
          checkCreate(titles[0], ind, variable, value, null, null, null, sampleUnitId);
        else if (updateMethod.equals("UPDATE"))
          checkUpdate(
              titles[0],
              ind,
              variable,
              value,
              null,
              null,
              null,
              sampleUnitId,
              deviationMessages,
              databaseValues,
              delimiter);
        else if (updateMethod.equals("CREATE_OR_UPDATE"))
          checkCreateOrUpdate(
              titles[0],
              ind,
              variable,
              value,
              null,
              null,
              null,
              sampleUnitId,
              deviationMessages,
              databaseValues,
              delimiter);
      } // for markers

      nrErrors += errorList.size();
      nrDeviations += deviationMessages.size();
      nrWarnings += warningList.size();

      writeMatrixErrors(
          fileOut, deviationMessages, databaseValues, values, ind, delimiter, variable, value);

      /*
      //newAlleles= new Vector();
      databaseValues = new Vector();
      errorMessages=new Vector();
      warningMessages=new Vector();
      deviationMessages=new Vector();
      */
      /*
       * Set the status of the import, visible to the user
       */
      status = (new Double(row * 100 / (1.0 * dataRows))).doubleValue();
      if (status_last + 5 < status) {
        status_last = status;
        statusStr = Integer.toString((new Double(status)).intValue()) + "%";
        dbInFile.setStatus(conn_viss, ifid, statusStr);
      }
      errorList.clear();
      warningList.clear();
    } // for rows

    if (nrErrors > 0) errMsg = "ERROR: Import of the genotypes failed.";
    else if (nrWarnings > 0) errMsg = "WARNING: Some warnings exist in the import file";
    else errMsg = "Genotype file is correct";
    errMsg += "\nDeviations:" + nrDeviations + "\nWarnings:" + nrWarnings + "\nErrors:" + nrErrors;

    return errMsg;
  }
コード例 #11
0
ファイル: ImportPhenotypes.java プロジェクト: bioit/crezoo
  // public String checkList(FileParser fp, Vector errorMessages, FileWriter fileOut, char
  // delimiter, String indId)
  public String checkList(FileParser fp, FileWriter fileOut, char delimiter, String indId) {
    // String ind, marker, allele1, allele2, raw1, raw2, ref, comm;
    String ind, variable, value, date, ref, comm;

    String errMsg = "";

    int nrErrors = 0;
    int nrWarnings = 0;
    int nrDeviations = 0;

    int dataRows = fp.dataRows();
    String titles[] = fp.columnTitles();

    DbImportFile dbInFile = new DbImportFile();
    String statusStr;
    double status;
    double status_last = 0.0;

    warningList = new ArrayList();
    errorList = new ArrayList();

    for (int i = 0; i < dataRows; i++) {
      //  Vector errorMessages = new Vector();
      //      Vector warningMessages = new Vector();
      Vector deviationMessages = new Vector();
      Vector databaseValues = new Vector();

      ind = ((FileParser) fp).getValue(indId, i).trim();
      variable = ((FileParser) fp).getValue("VARIABLE", i).trim();
      value = ((FileParser) fp).getValue("VALUE", i).trim();
      date = ((FileParser) fp).getValue("DATE", i).trim();
      ref = ((FileParser) fp).getValue("REF", i).trim();
      comm = ((FileParser) fp).getValue("COMMENT", i).trim();

      // Check for valid data values.
      // Check for length, remove null and so on.
      // Syntax check.

      checkValues(ind, variable, value, date, ref, comm);
      //  checkValues(ind, variable, value, date, ref, comm, fatalErrors);

      // If create updateMethod
      if (updateMethod == null || updateMethod.equals("CREATE"))
        checkCreate(titles[0], ind, variable, value, date, ref, comm, sampleUnitId);

      // If update updateMethod
      else if (updateMethod.equals("UPDATE"))
        checkUpdate(
            titles[0],
            ind,
            variable,
            value,
            date,
            ref,
            comm,
            sampleUnitId,
            deviationMessages,
            databaseValues,
            delimiter);

      // if both update and add
      else if (updateMethod.equals("CREATE_OR_UPDATE"))
        checkCreateOrUpdate(
            titles[0],
            ind,
            variable,
            value,
            date,
            ref,
            comm,
            sampleUnitId,
            deviationMessages,
            databaseValues,
            delimiter);

      nrErrors += errorList.size();
      nrDeviations += deviationMessages.size();
      nrWarnings += warningList.size();

      // write row + all errors encountered to file

      writeListErrors(
          fileOut,
          deviationMessages,
          databaseValues,
          ind,
          delimiter,
          variable,
          value,
          date,
          ref,
          comm);

      /*
       * Set the status of the import, visible to the user
       */
      status = (new Double(i * 100 / (1.0 * dataRows))).doubleValue();
      if (status_last + 5 < status) {
        status_last = status;
        statusStr = Integer.toString((new Double(status)).intValue()) + "%";
        dbInFile.setStatus(conn_viss, ifid, statusStr);
      }

      errorList.clear();
      warningList.clear();
    }

    if (nrErrors > 0) errMsg = "ERROR: Import of the Phenotypes failed.";
    else if (nrWarnings > 0) errMsg = "WARNING: Some warnings exist in the import file";
    else errMsg = "Phenotype file is correct";
    errMsg += "\nDeviations:" + nrDeviations + "\nWarnings:" + nrWarnings + "\nErrors:" + nrErrors;

    return errMsg;
  }
コード例 #12
0
ファイル: Main.java プロジェクト: YpGu/gcoev
  public static void test1(String seed) {
    /* read, init data & parameters */
    for (int t = t0; t < T; t++) {
      //      String fileDir = "../../data/graph/" + Integer.toString(t) + ".csv";  // original
      // co-voting dataset
      //      String fileDir = "./data/" + Integer.toString(t) + ".csv";  // artificial toy dataset
      String fileDir =
          "../../data_sm/nips_17/out/"
              + seed
              + "/"
              + Integer.toString(t)
              + ".train.csv"; // nips dataset (smaller)
      Map<Integer, Double> freq = FileParser.readCSVDict(fileDir);

      double[][] G = new double[n][n];
      double[][] A = new double[n][n];
      double[][] mu = new double[n][K];
      double[][] mu_hat = new double[n][K];
      double[][] mu_prime = new double[n][K];
      double[][] mu_hat_prime = new double[n][K];
      double[][] h = new double[n][K];
      double[][] h_hat = new double[n][K];
      FileParser.readCSVGraph(fileDir, freq, G, A);
      for (int i = 0; i < n; i++)
        for (int k = 0; k < K; k++) {
          mu[i][k] = scale_0 * (rand.nextDouble() - 0.5);
          mu_hat[i][k] = scale_0 * (rand.nextDouble() - 0.5);
          mu_prime[i][k] = mu[i][k];
          mu_hat_prime[i][k] = mu_hat[i][k];
          h[i][k] = scale * (rand.nextDouble() - 0.5);
          h_hat[i][k] = scale * (rand.nextDouble() - 0.5);
        }

      GS.add(G);
      AS.add(A);
      mu_s.add(mu);
      mu_hat_s.add(mu_hat);
      mu_prime_s.add(mu_prime);
      mu_hat_prime_s.add(mu_hat_prime);
      h_s.add(h);
      h_prime_s.add(h);
      h_hat_s.add(h_hat);
      h_hat_prime_s.add(h);

      /* for test */
      delta_s.add(delta);
      delta_prime_s.add(delta); // TODO previous: 0.1

      v_s.add(0.1);
      v_hat_s.add(0.1);
      v_prime_s.add(0.1);
      v_hat_prime_s.add(0.1);

      System.out.println("done! t = " + t);
    }

    for (int t = t0; t < T; t++) {
      for (int s = t0; s < T; s++) {
        grad_mu_s.add(new double[n][K]);
        grad_mu_hat_s.add(new double[n][K]);
        grad_mu_prime_s.add(new double[n][K]);
        grad_mu_hat_prime_s.add(new double[n][K]);
      }
      grad_h_hat_s.add(new double[n][K]);
      grad_h_hat_prime_s.add(new double[n][K]);
    }
    /* end initialization */

    /* outer for-loop */
    double old_obj_1 = -1, old_obj_2 = -1;
    for (int iter = 0; iter < MAX_ITER; iter++) {
      //      Scanner sc = new Scanner(System.in); int gu; gu = sc.nextInt();
      System.out.println("====== iter = " + iter + " ======");
      /** intrinsic feature * */
      forward1(true, iter);
      backward1(true);
      compute_gradient1(iter);
      double new_obj_1 = 0;
      /* gradient descent: inner for-loop here */
      int inner_iter_1 = 0;
      while (inner_iter_1 < INNER_ITER) {
        /* update variational parameters \hat{h} using gradient descent */
        for (int t = 0; t < T - t0; t++) {
          double[][] h_hat_t = h_hat_s.get(t);
          double[][] grad_h_hat_t = grad_h_hat_s.get(t);
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              h_hat_t[i][k] += lr_1 * grad_h_hat_t[i][k];
            }
          h_hat_s.set(t, h_hat_t);
        }
        /* update \hat{\mu} and \hat{V}, since both are function of \hat{h} */
        forward1(false, iter);
        backward1(false);
        double obj1 = compute_objective1();
        if (inner_iter_1 % 10 == 0)
          System.out.println("(1) iter = " + inner_iter_1 + ", obj 1 = " + obj1);
        if (inner_iter_1 != 0 && obj1 < new_obj_1) {
          lr_1 *= 0.8;
          break;
        }
        new_obj_1 = obj1;
        inner_iter_1 += 1;
      }
      if (inner_iter_1 == INNER_ITER) lr_1 *= 2;
      /* sample */
      for (int t = 0; t < T - t0; t++) {
        double[][] samples =
            Operations.sample_multivariate_normal(mu_hat_s.get(t), v_hat_s.get(t), N_SAMPLES);
        double[][] h_t = new double[n][K];
        for (int i = 0; i < n; i++)
          for (int k = 0; k < K; k++) {
            h_t[i][k] = samples[i][k];
          }
        h_s.set(t, h_t);
      }

      /** impression feature * */
      forward2(true);
      backward2(true);
      compute_gradient2(iter);
      double new_obj_2 = 0;
      /* gradient descent: inner for-loop here */
      int inner_iter_2 = 0;
      while (inner_iter_2 < INNER_ITER) {
        /* update \hat{h}' using gradient descent */
        for (int t = 0; t < T - t0; t++) {
          double[][] h_hat_prime_t = h_hat_prime_s.get(t);
          double[][] grad_h_hat_prime_t = grad_h_hat_prime_s.get(t);
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              h_hat_prime_t[i][k] += lr_2 * grad_h_hat_prime_t[i][k];
            }
          h_hat_prime_s.set(t, h_hat_prime_t);
        }
        /* update \hat{\mu}' and \hat{V}', since both are function of \hat{h}' */
        forward2(false);
        backward2(false);
        double obj2 = compute_objective2();
        if (inner_iter_2 % 10 == 0)
          System.out.println("(2) iter = " + inner_iter_2 + ", obj 2 = " + obj2);
        if (inner_iter_2 != 0 && obj2 < new_obj_2) {
          lr_2 *= 0.8;
          break;
        }
        new_obj_2 = obj2;
        inner_iter_2 += 1;
      }
      if (inner_iter_2 == INNER_ITER) lr_2 *= 2;
      /* sample */
      for (int t = 0; t < T - t0; t++) {
        double[][] samples =
            Operations.sample_multivariate_normal(
                mu_hat_prime_s.get(t), v_hat_prime_s.get(t), N_SAMPLES);
        double[][] h_prime_t = new double[n][K];
        for (int i = 0; i < n; i++)
          for (int k = 0; k < K; k++) {
            h_prime_t[i][k] = samples[i][k];
          }
        h_prime_s.set(t, h_prime_t);
      }

      /** output * */
      for (int t = 0; t < T - t0; t++) {
        double[][] h_t = h_s.get(t);
        double[][] h_prime_t = h_prime_s.get(t);
        /* output filename:
         *    ./res/<seed>_<sigma>/h_<time>_<iter>.txt
         */
        FileParser.output(
            h_t, "./res/" + seed + "_" + delta_str + "/h_" + (t + t0) + "_" + iter + ".txt");
        FileParser.output(
            h_prime_t,
            "./res/" + seed + "_" + delta_str + "/h_p_" + (t + t0) + "_" + iter + ".txt");
      }

      /* check convergence */
      double diff_1 = -(new_obj_1 - old_obj_1) / old_obj_1;
      double diff_2 = -(new_obj_2 - old_obj_2) / old_obj_2;
      if (iter != 0 && diff_1 < 1e-6 && diff_2 < 1e-6) {
        System.out.println("diff_1 = " + diff_1);
        System.out.println("diff_2 = " + diff_2);
        break;
      }
      old_obj_1 = new_obj_1;
      old_obj_2 = new_obj_2;
    }
  }
コード例 #13
0
ファイル: Main.java プロジェクト: YpGu/gcoev
  public static void compute_gradient2(int iteration) {
    double[][][] tmp_grad_h_hat_prime_s = new double[T - t0][n][K];

    /*
     * compute
     *	  nti[t][i] = \sum_{j} { n_{ij} }
     * and
     *	  nti_h[t][j][k] = \sum_{i} { n_{ij}^{t} h_{ik}^{t} }
     */
    double[][] nti = new double[T - t0][n];
    double[][][] nti_h = new double[T - t0][n][K];
    for (int t = 0; t < T - t0; t++) {
      double[][] G_t = GS.get(t);
      double[][] h_t = h_s.get(t); // h^{t}
      for (int i = 0; i < n; i++)
        for (int j = 0; j < n; j++) {
          nti[t][i] += G_t[i][j];
          for (int k = 0; k < K; k++) {
            nti_h[t][j][k] += G_t[i][j] * h_t[i][k];
          }
        }
    }

    for (int t = 0; t < T - t0; t++) {
      double delta_t = delta_prime_s.get(t);
      double[][] h_t = h_s.get(t); // h^{t}
      double[][] h_hat_prime_t = h_hat_prime_s.get(t); // \hat{h}^{t}
      double[][] mu_hat_t = mu_hat_s.get(t); // \hat{\mu}^{t}
      double[][] mu_hat_prime_t = mu_hat_prime_s.get(t); // \hat{\mu}'^{t}
      double[][] h_prime_t = h_prime_s.get(t);

      if (t != 0) {
        Matrix a = new Matrix(AS.get(t - 1));
        Matrix hprime_pre_t = new Matrix(h_prime_s.get(t - 1));
        Matrix ave_neighbors = a.times(hprime_pre_t);

        double[][] G_pre_t = GS.get(t - 1); // G^{t-1}
        double[][] A_pre_t = AS.get(t - 1); // A^{t-1}
        double[][] h_pre_t = h_s.get(t - 1); // h^{t-1}
        double[][] mu_hat_prime_pre_t = mu_hat_prime_s.get(t - 1); // \hat{\mu}'^{t-1}  [t]

        for (int s = 0; s < T - t0; s++) {
          double[][] grad_mu_hat_prime_t = grad_mu_hat_prime_s.get(t * (T - t0) + s);
          double[][] grad_mu_hat_prime_pre_t = grad_mu_hat_prime_s.get((t - 1) * (T - t0) + s);
          double[] h2delta2 = new double[n];
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              h2delta2[i] += 0.5 * h_t[i][k] * h_t[i][k] * delta_t * delta_t;
            }

          /* compute weighted_exp for later use */
          double[][][] weighted_exp_num = new double[K][n][n];
          double[][] weighted_exp_den = new double[K][n];
          double[][][] weighted_exp = new double[K][n][n];
          for (int i = 0; i < n; i++)
            for (int j = 0; j < n; j++) {
              double h_muhp = Operations.inner_product(h_t[j], mu_hat_prime_t[i], K);
              for (int k = 0; k < K; k++) {
                weighted_exp_num[k][i][j] = h_t[j][k] * Math.exp(h_muhp + h2delta2[j]);
                weighted_exp_den[k][j] += Math.exp(h_muhp + h2delta2[j]);
              }
            }
          for (int i = 0; i < n; i++)
            for (int j = 0; j < n; j++)
              for (int k = 0; k < K; k++) {
                weighted_exp[k][i][j] = weighted_exp_num[k][i][j] / weighted_exp_den[k][j];
              }
          /* compute sum_mu_hat_prime for later use */
          double[] sum_mu_hat_prime = new double[K];
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              sum_mu_hat_prime[k] += mu_hat_prime_pre_t[i][k];
            }

          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              /* first term */
              double g1 = nti_h[t][i][k] * grad_mu_hat_prime_t[i][k];
              tmp_grad_h_hat_prime_s[s][i][k] += g1;

              /* second term */
              double g2 = 0;
              for (int j = 0; j < n; j++) {
                g2 -= nti[t][j] * weighted_exp[k][i][j] * grad_mu_hat_prime_t[i][k];
              }
              tmp_grad_h_hat_prime_s[s][i][k] += g2;

              /* third term */
              for (int j = 0; j < n; j++)
                if (G_pre_t[j][i] != 0) {
                  //	      double g3 = ( h_t[j][k] - (1-lambda) * h_pre_t[j][k] - lambda *
                  // A_pre_t[j][i] * sum_mu_hat_prime[k] )
                  double g3 =
                      (h_t[j][k]
                              - (1 - lambda) * h_pre_t[j][k]
                              - lambda * A_pre_t[j][i] * mu_hat_prime_pre_t[i][k])
                          * lambda
                          * A_pre_t[j][i]
                          * grad_mu_hat_prime_pre_t[i][k]
                          / (sigma * sigma);
                  tmp_grad_h_hat_prime_s[s][j][k] += g3; // j instead of i!
                }
            }

          /* fourth term */
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              double g4 =
                  -(mu_hat_prime_t[i][k] - mu_hat_prime_pre_t[i][k])
                      * (grad_mu_hat_prime_t[i][k] - grad_mu_hat_prime_pre_t[i][k])
                      / (sigma * sigma);
              tmp_grad_h_hat_prime_s[s][i][k] += g4;
            }
        }
      } else {
        /*
        for (int s = 0; s < T-t0; s++) {
          double[] grad_mu_hat_prime_t = grad_mu_hat_prime_s.get(t * (T-t0) + s);
          for (int i = 0; i < n; i++) {
            // first term
            double g1 = nti_hp[t][i] * grad_mu_hat_prime_t[i];
            tmp_grad_h_hat_prime_s[s][i] += g1;

            // second term
            double g2 = 0;
            for (int _j = 0; _j < NEG; _j++) {
              double weighted_exp_num = 0, weighted_exp_den = 0;
              int j = neg_samples.get(t)[i][_j];
              double htj = h_t[j][0]; double muhti = mu_hat_t[i];
              weighted_exp_num += htj * Math.exp(htj * muhti + 0.5 * htj * htj * delta_t * delta_t);
              for (int _k = 0; _k < NEG; _k++) {
        	int k = neg_samples.get(t)[i][_k];
        	double muhtk = mu_hat_t[k];
        	weighted_exp_den += Math.exp(htj * muhtk + 0.5 * htj * htj * delta_t * delta_t);
              }
              g2 -= nti[t][j] * weighted_exp_num / weighted_exp_den * grad_mu_hat_prime_t[i];
            }
            tmp_grad_h_hat_prime_s[s][i] += g2;
          }

          // fourth term (if any)
          if (s == t) for (int i = 0; i < n; i++) {
            double g4 = -h_hat_prime_t[i][0] / (sigma*sigma);
            tmp_grad_h_hat_prime_s[s][i] += g4;
          }
        }
        */
      }
    }

    /* update global gradient */
    for (int t = 0; t < T - t0; t++) {
      double[][] grad = new double[n][K];
      for (int i = 0; i < n; i++)
        for (int k = 0; k < K; k++) {
          grad[i][k] = tmp_grad_h_hat_prime_s[t][i][k];
        }
      grad_h_hat_prime_s.set(t, grad);
    }
    FileParser.output_2d(grad_h_hat_prime_s, "./grad/grad_prime_" + iteration + ".txt");

    return;
  }
コード例 #14
0
ファイル: Main.java プロジェクト: YpGu/gcoev
  public static void compute_gradient1(int iteration) {
    double[][][] tmp_grad_h_hat_s = new double[T - t0][n][K];

    for (int t = 0; t < T - t0; t++) {
      //      System.out.println("compute gradient 1, t = " + t);
      double delta_t = delta_s.get(t);
      double[][] G_t = GS.get(t);
      double[][] h_prime_t = h_prime_s.get(t);
      double[][] mu_hat_t = mu_hat_s.get(t);

      if (t != 0) {
        double[][] mu_hat_pre_t = mu_hat_s.get(t - 1);

        Matrix a = new Matrix(AS.get(t - 1));
        Matrix hprime_pre_t = new Matrix(h_prime_s.get(t - 1));
        Matrix ave_neighbors = a.times(hprime_pre_t);

        /* TODO: check whether we can save computation by comparing s and t */
        for (int s = 0; s < T - t0; s++) {
          double[][] grad_hat_t = grad_mu_hat_s.get(t * (T - t0) + s);
          double[][] grad_hat_pre_t = grad_mu_hat_s.get((t - 1) * (T - t0) + s);
          double[] hp2delta2 = new double[n];
          for (int i = 0; i < n; i++)
            for (int k = 0; k < K; k++) {
              hp2delta2[i] += 0.5 * h_prime_t[i][k] * h_prime_t[i][k] * delta_t * delta_t;
            }

          for (int i = 0; i < n; i++) {
            /* first term */
            double[] weighted_exp_num = new double[K];
            double weighted_exp_den = 0;
            for (int l = 0; l < n; l++) {
              double hp_muh = Operations.inner_product(h_prime_t[l], mu_hat_t[i], K);
              double e = Math.exp(hp_muh + hp2delta2[l]);
              if (Double.isNaN(e)) {
                /* check if e explodes */
                System.out.println("ERROR2");
                Scanner sc = new Scanner(System.in);
                int gu;
                gu = sc.nextInt();
              }
              for (int k = 0; k < K; k++) {
                weighted_exp_num[k] += h_prime_t[l][k] * e;
                weighted_exp_den += e;
              }
            }
            for (int j = 0; j < n; j++)
              for (int k = 0; k < K; k++) {
                double weighted_exp = weighted_exp_num[k] / weighted_exp_den;
                double gi1 = G_t[i][j] * grad_hat_t[i][k] * (h_prime_t[j][k] - weighted_exp);
                tmp_grad_h_hat_s[s][i][k] += gi1;
              }

            /* second term */
            for (int k = 0; k < K; k++) {
              double gi2 =
                  -(mu_hat_t[i][k]
                          - (1 - lambda) * mu_hat_pre_t[i][k]
                          - lambda * ave_neighbors.get(i, k))
                      * (grad_hat_t[i][k] - (1 - lambda) * grad_hat_pre_t[i][k])
                      / (sigma * sigma);
              tmp_grad_h_hat_s[s][i][k] += gi2;
            }
          }
        }
      } else {
        /* no such term (t=0) in ELBO */
        /*
        for (int s = 0; s < T-t0; s++) {
          double[] grad_hat_t = grad_mu_hat_s.get(t * (T-t0) + s);

          for (int i = 0; i < n; i++) {
            double n_it = 0;
            for (int j = 0; j < n; j++) n_it += G_t[i][j];

            // first term
            double gi1 = -mu_hat_t[i] * grad_hat_t[i] / (sigma * sigma);
            tmp_grad_h_hat_s[s][i] += gi1;

            // second term
            double gi2 = 0;
            double weighted_exp_num = 0, weighted_exp_den = 0;
            for (int j = 0; j < NEG; j++) {
              int l = neg_samples.get(t)[i][j];
              double hpl = h_prime_t[l][0];
              double muit = mu_hat_t[i];
              double e = Math.exp(hpl * muit + 0.5 * hpl * hpl * delta_t * delta_t);
              // TODO: check if e explodes
              if (Double.isNaN(e)) {
        	System.out.println("ERROR3");
        	Scanner sc = new Scanner(System.in);
        	int gu; gu = sc.nextInt();
              }
              weighted_exp_num += hpl * e;
              weighted_exp_den += e;
            }
            double weighted_exp = weighted_exp_num / weighted_exp_den;
            for (int j = 0; j < n; j++) {
              gi2 += G_t[i][j] * grad_hat_t[i] * (h_prime_t[j][0] - weighted_exp);
            }
            tmp_grad_h_hat_s[s][i] += gi2;
          }
        }
        */
      }
      /* end if-else */
    }

    /* update global gradient */
    for (int t = 0; t < T - t0; t++) {
      double[][] grad = new double[n][K];
      for (int i = 0; i < n; i++)
        for (int k = 0; k < K; k++) {
          grad[i][k] = tmp_grad_h_hat_s[t][i][k];
        }
      grad_h_hat_s.set(t, grad);
    }
    FileParser.output_2d(grad_h_hat_s, "./grad/grad_" + iteration + ".txt");

    return;
  }
コード例 #15
0
ファイル: NSeqCommand.java プロジェクト: songlab/NSeq
  public NSeqCommand(
      String lengthFilename,
      String seqFilename,
      String fileType,
      int numberOfThreads,
      double fdrCutoff,
      int numberOfSims,
      int windowWidth,
      int centerWidth,
      double tsCutoff,
      String genome,
      boolean verboseQ) {
    // Set options from command line and run
    if (lengthFilename != null) {
      lengthFile = new File(lengthFilename);
    }
    seqFile = new File(seqFilename);
    this.numberOfSims = numberOfSims;
    this.numberOfThreads = numberOfThreads;
    this.windowWidth = windowWidth;
    this.centerWidth = centerWidth;
    this.fdrCutoff = fdrCutoff;
    this.fileType = fileType;
    this.verboseQ = verboseQ;
    this.tsCutoff = tsCutoff;

    setMUE();
    if (genome.toLowerCase().equals("hg19")) {
      chrLengths = StandardGenomes.hg19();
      FileParser.setOrderedChromosomes(chrLengths);
      consoleOut("HG19 genome chosen.");
      consoleOut("Total genome length = " + computeGenomeLength());
      lengthFile = null;
    } else if (genome.toLowerCase().equals("hg18")) {
      chrLengths = StandardGenomes.hg18();
      FileParser.setOrderedChromosomes(chrLengths);
      consoleOut("HG18 genome chosen.");
      consoleOut("Total genome length = " + computeGenomeLength());
      lengthFile = null;
    } else if (genome.toLowerCase().equals("mm10")) {
      chrLengths = StandardGenomes.mm10();
      FileParser.setOrderedChromosomes(chrLengths);
      consoleOut("MM10 genome chosen.");
      consoleOut("Total genome length = " + computeGenomeLength());
      lengthFile = null;
    } else if (genome.toLowerCase().equals("mm9")) {
      chrLengths = StandardGenomes.mm9();
      FileParser.setOrderedChromosomes(chrLengths);
      consoleOut("MM9 genome chosen.");
      consoleOut("Total genome length = " + computeGenomeLength() + "\n");
      lengthFile = null;
    } else if (genome.toLowerCase().equals("ce10")) {
      chrLengths = StandardGenomes.ce10();
      FileParser.setOrderedChromosomes(chrLengths);
      consoleOut("CE10 genome chosen.");
      consoleOut("Total genome length = " + computeGenomeLength() + "\n");
      lengthFile = null;
    } else {
      consoleOut("Chromosome Length File: " + lengthFile);

      chrLengths = FileParser.getChromosomeLength(lengthFile.getPath());
      consoleOut("Total genome length = " + computeGenomeLength());

      consoleOut("Using " + numberOfThreads + " threads.");
      consoleOut(
          "Reading data and constructing probability distributions for nucleosome centers...");
    }

    Runnable read =
        new Runnable() {
          public void run() {
            DataProcess();
          }
        };
    Thread readThread = new Thread(read);
    readThread.start();
  }
コード例 #16
0
ファイル: NSeqCommand.java プロジェクト: songlab/NSeq
  private void DataProcess() {
    long start = System.currentTimeMillis();
    NucleosomeDetector nd = null;

    if (fileType.equals("bed")) {
      consoleOut("Reading " + seqFile.getPath());
      br =
          new BedFileReader(
              chrLengths,
              seqFile.getPath(),
              68,
              NucleosomeCenter.getBetaBins(1.92038028, 1.89366713, 11));

    } else if (fileType.equals("sam")) {
      br =
          new BamFileReader(
              chrLengths,
              seqFile.getPath(),
              68,
              NucleosomeCenter.getBetaBins(1.92038028, 1.89366713, 11));
    } else if (fileType.equals("bam")) {
      br =
          new BamFileReader(
              chrLengths,
              seqFile.getPath(),
              68,
              NucleosomeCenter.getBetaBins(1.92038028, 1.89366713, 11));
    } else {
      br =
          new BedFileReader(
              chrLengths,
              seqFile.getPath(),
              68,
              NucleosomeCenter.getBetaBins(1.92038028, 1.89366713, 11));
    }
    HashMap<String, Chromosome> chrList = br.getChrList();

    consoleOut("*** Finished reading. ***");

    for (String chr : chrLengths.keySet()) {
      if (br.getChrList().get(chr).getPosRawList().length == 0
          && br.getChrList().get(chr).getPosRawList().length == 0) {
        br.removeChr(chr);
        FileParser.removeOrderedChromosome(chr);
      }
    }
    consoleOut("Detecting nucleosomes....");
    // consoleOut(windowWidth + " " + centerWidth + " " + numberOfThreads + " " + numberOfSims);
    nd =
        new NucleosomeDetector(
            windowWidth, centerWidth, numberOfThreads, numberOfSims, chrList, MUE, verboseQ);

    // int intervalSize = Collections.max(chrLengths.values())/nThreadsChrInteger;
    int intervalSize = Math.max(Collections.min(chrLengths.values()) / numberOfThreads, 100000);
    // intervalSize = 50000;

    nucleosomes = nd.computeIntervalWise(tsCutoff, intervalSize);

    consoleOut("Computing FDR using " + numberOfSims + " simulations...");
    nd.computeFDR(tsCutoff, nucleosomes, intervalSize);

    SimpleDateFormat df = new SimpleDateFormat("MM.dd.yyyy_HH.mm.ss");

    String formattedDate = df.format(new Date(System.currentTimeMillis()));
    String tmp = seqFile.getPath();
    if (tmp.lastIndexOf(".txt") == tmp.length() - 4) {
      tmp = tmp.substring(0, tmp.lastIndexOf(".txt"));
    }
    String outFile = tmp + "_NSeq_" + formattedDate + ".txt";
    String outWig = tmp + "_NSeq_" + formattedDate + ".wig";
    String info = "# Sequence file: " + seqFile.getPath() + "\n";
    if (lengthFile != null) {
      info += "# Chromosome length file:" + lengthFile.getPath() + "\n";
    }
    int numPassedNuc = 0;
    try {
      numPassedNuc =
          FileOutput.writeNucleosomes(
              nucleosomes, outFile, ((Double) fdrCutoff).toString(), numberOfSims, info);
      consoleOut(
          numPassedNuc + " nucleosomes found at " + ((Double) fdrCutoff).toString() + " FDR.");
      FileOutput.writeWig(nucleosomes, outWig, ((Double) fdrCutoff).toString());
    } catch (IOException ex) {
      ex.printStackTrace();
    }

    long elapsedTimeMillis = System.currentTimeMillis() - start;
    double elapsedTimeSec = elapsedTimeMillis / 1000.0;
    consoleOut("Output written to " + outFile + "");
    consoleOut("Time taken: " + Double.toString(elapsedTimeSec));
    consoleOut("********** Finished processing. **********");
  }