Examples of org.encog.app.analyst.csv.balance.BalanceCSV

Package org.encog.app.analyst.csv.balance

Examples of org.encog.app.analyst.csv.balance.BalanceCSV

org.encog.app.analyst.csv.balance.BalanceCSV
Balance a CSV file. This utility is useful when you have several an unbalanced training set. You may have a large number of one particular class, and many fewer elements of other classes. This can hinder many Machine Learning methods. This class can be used to balance the data. Obviously this class cannot generate data. You must request how many items you want per class. Some classes will have lower than this number if they were already below the specified amount. Any class above this amount will be trimmed to that amount.

    out.close();
  }


  public void testBalanceCSVHeaders() throws IOException {
    generateTestFile(true);
    BalanceCSV norm = new BalanceCSV();
    norm.analyze(INPUT_NAME, true, CSVFormat.ENGLISH);
    norm.process(OUTPUT_NAME, 1, 2);


    BufferedReader tr = new BufferedReader(new FileReader(OUTPUT_NAME));


    Assert.assertEquals("\"a\",\"b\"", tr.readLine());
    Assert.assertEquals("one,1", tr.readLine());
    Assert.assertEquals("two,1", tr.readLine());
    Assert.assertEquals("four,2", tr.readLine());
    Assert.assertEquals("five,2", tr.readLine());
    Assert.assertEquals("six,3", tr.readLine());
    Assert.assertEquals(2, norm.getCounts().get("1").intValue());
    Assert.assertEquals(2, norm.getCounts().get("2").intValue());
    Assert.assertEquals(1, norm.getCounts().get("3").intValue());
    tr.close();


    INPUT_NAME.delete();
    OUTPUT_NAME.delete();

View Full Code Here


  }


  public void TestBalanceCSVNoHeaders() throws IOException {
    generateTestFile(false);
    BalanceCSV norm = new BalanceCSV();
    norm.analyze(INPUT_NAME, false, CSVFormat.ENGLISH);
    norm.process(OUTPUT_NAME, 1, 2);


    BufferedReader tr = new BufferedReader(new FileReader(OUTPUT_NAME));


    Assert.assertEquals("one,1", tr.readLine());
    Assert.assertEquals("two,1", tr.readLine());
    Assert.assertEquals("four,2", tr.readLine());
    Assert.assertEquals("five,2", tr.readLine());
    Assert.assertEquals("six,3", tr.readLine());
    Assert.assertEquals(2, norm.getCounts().get("1").intValue());
    Assert.assertEquals(2, norm.getCounts().get("2").intValue());
    Assert.assertEquals(1, norm.getCounts().get("3").intValue());
    tr.close();


    INPUT_NAME.delete();
    OUTPUT_NAME.delete();
  }

View Full Code Here

    final CSVFormat inputFormat = getScript()
        .determineInputFormat(sourceID);
    final CSVFormat outputFormat = getScript().determineOutputFormat();


    // prepare to normalize
    final BalanceCSV balance = new BalanceCSV();
    balance.setScript(getScript());
    getAnalyst().setCurrentQuantTask(balance);
    balance.setReport(new AnalystReportBridge(getAnalyst()));


    final boolean headers = getScript().expectInputHeaders(sourceID);
    balance.analyze(sourceFile, headers, inputFormat);
    balance.setOutputFormat(outputFormat);
    balance.setProduceOutputHeaders(true);
    balance.process(targetFile, targetFieldIndex, countPer);
    getAnalyst().setCurrentQuantTask(null);
    return balance.shouldStop();
  }

View Full Code Here


    // get formats
    final CSVFormat format = getScript().determineFormat();


    // prepare to normalize
    final BalanceCSV balance = new BalanceCSV();
    balance.setScript(getScript());
    getAnalyst().setCurrentQuantTask(balance);
    balance.setReport(new AnalystReportBridge(getAnalyst()));


    final boolean headers = getScript().expectInputHeaders(sourceID);
    balance.analyze(sourceFile, headers, format);
    balance.setProduceOutputHeaders(true);
    balance.process(targetFile, targetFieldIndex, countPer);
    getAnalyst().setCurrentQuantTask(null);
    return balance.shouldStop();
  }

View Full Code Here

    out.close();
  }


  public void testBalanceCSVHeaders() throws IOException {
    generateTestFile(true);
    BalanceCSV norm = new BalanceCSV();
    norm.analyze(INPUT_NAME, true, CSVFormat.ENGLISH);
    norm.process(OUTPUT_NAME, 1, 2);


    BufferedReader tr = new BufferedReader(new FileReader(OUTPUT_NAME));


    Assert.assertEquals("\"a\",\"b\"", tr.readLine());
    Assert.assertEquals("one,1", tr.readLine());
    Assert.assertEquals("two,1", tr.readLine());
    Assert.assertEquals("four,2", tr.readLine());
    Assert.assertEquals("five,2", tr.readLine());
    Assert.assertEquals("six,3", tr.readLine());
    Assert.assertEquals(2, norm.getCounts().get("1").intValue());
    Assert.assertEquals(2, norm.getCounts().get("2").intValue());
    Assert.assertEquals(1, norm.getCounts().get("3").intValue());
    tr.close();


    INPUT_NAME.delete();
    OUTPUT_NAME.delete();

View Full Code Here


  }


  public void TestBalanceCSVNoHeaders() throws IOException {
    generateTestFile(false);
    BalanceCSV norm = new BalanceCSV();
    norm.analyze(INPUT_NAME, false, CSVFormat.ENGLISH);
    norm.process(OUTPUT_NAME, 1, 2);


    BufferedReader tr = new BufferedReader(new FileReader(OUTPUT_NAME));


    Assert.assertEquals("one,1", tr.readLine());
    Assert.assertEquals("two,1", tr.readLine());
    Assert.assertEquals("four,2", tr.readLine());
    Assert.assertEquals("five,2", tr.readLine());
    Assert.assertEquals("six,3", tr.readLine());
    Assert.assertEquals(2, norm.getCounts().get("1").intValue());
    Assert.assertEquals(2, norm.getCounts().get("2").intValue());
    Assert.assertEquals(1, norm.getCounts().get("3").intValue());
    tr.close();


    INPUT_NAME.delete();
    OUTPUT_NAME.delete();
  }

View Full Code Here

TOP

Related Classes of org.encog.app.analyst.csv.balance.BalanceCSV

org.encog.app.analyst.commands.CmdBalance

org.encog.app.analyst.csv.basic.LoadedRow

org.encog.app.quant.TestBalanceCSV

org.encog.util.csv.ReadCSV

java.io.PrintWriter

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.