Fix javadoc and cleanup

brutex-extended-tests/src/test/java/net/brutex/spark/BrianTest.java

@@ -139,7 +139,6 @@ public class BrianTest /*extends BaseDL4JTest*/ {
                 //.setExecutorEnv("spark.executor.cores", "2")
                 //.setExecutorEnv("spark.executor.memory", "2g")
                 //.set("spark.submit.deployMode", "client")
-                ;
 
 /*
         SparkSession spark = SparkSession
@@ -240,7 +239,7 @@ public class BrianTest /*extends BaseDL4JTest*/ {
         */
         TransformProcess tp = new TransformProcess.Builder(inputSchema)
                 .removeAllColumnsExceptFor("country_code", "lat", "lon")
-                .stringToCategorical("country_code", Arrays.asList(new String[] {"GR", "FR", "DE", "CH"}))
+                .stringToCategorical("country_code", Arrays.asList("GR", "FR", "DE", "CH"))
                 .filter(new FilterInvalidValues())
                 .categoricalToOneHot("country_code")
                 .build();

brutex-extended-tests/src/test/java/net/brutex/spark/BrianTest2.java

@@ -225,7 +225,7 @@ public class BrianTest2 /*extends BaseDL4JTest*/ {
         */
         TransformProcess tp = new TransformProcess.Builder(inputSchema)
                 .removeAllColumnsExceptFor("country_code", "lat", "lon")
-                .stringToCategorical("country_code", Arrays.asList(new String[] {"GR", "FR", "DE", "CH"}))
+                .stringToCategorical("country_code", Arrays.asList("GR", "FR", "DE", "CH"))
                 .filter(new FilterInvalidValues())
                 .categoricalToOneHot("country_code")
                 .build();

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/IntegrationTestRunner.java

@@ -91,10 +91,10 @@ public class IntegrationTestRunner {
 
     public static final double MAX_REL_ERROR_SCORES = 1e-4;
 
-    private static List<Class<?>> layerClasses = new ArrayList<>();
+    private static final List<Class<?>> layerClasses = new ArrayList<>();
-    private static List<Class<?>> preprocClasses = new ArrayList<>();
+    private static final List<Class<?>> preprocClasses = new ArrayList<>();
-    private static List<Class<?>> graphVertexClasses = new ArrayList<>();
+    private static final List<Class<?>> graphVertexClasses = new ArrayList<>();
-    private static List<Class<?>> evaluationClasses = new ArrayList<>();
+    private static final List<Class<?>> evaluationClasses = new ArrayList<>();
 
     private static Map<Class<?>, Integer> layerConfClassesSeen = new HashMap<>();
     private static Map<Class<?>, Integer> preprocessorConfClassesSeen = new HashMap<>();

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/dl4j/CNN1DTestCases.java

@@ -67,8 +67,8 @@ public class CNN1DTestCases {
                 testOverfitting = false;
             }
 
-            int miniBatchSize = 16;
+            final int miniBatchSize = 16;
-            int exampleLength = 128;
+            final int exampleLength = 128;
 
             @Override
             public ModelType modelType() {

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/dl4j/CNN2DTestCases.java

@@ -271,11 +271,11 @@ public class CNN2DTestCases {
     public static TestCase getYoloHouseNumbers() {
         return new TestCase() {
 
-            private int width = 416;
+            private final int width = 416;
-            private int height = 416;
+            private final int height = 416;
-            private int nChannels = 3;
+            private final int nChannels = 3;
-            private int gridWidth = 13;
+            private final int gridWidth = 13;
-            private int gridHeight = 13;
+            private final int gridHeight = 13;
 
             {
                 testName = "YOLOHouseNumbers";

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/dl4j/CNN3DTestCases.java

@@ -108,7 +108,7 @@ public class CNN3DTestCases {
             public MultiDataSet getGradientsTestData() throws Exception {
                 Nd4j.getRandom().setSeed(12345);
                 //NCDHW format
-                INDArray arr = Nd4j.rand(new int[]{2, 3, 8, 8, 8});
+                INDArray arr = Nd4j.rand(2, 3, 8, 8, 8);
                 INDArray labels = org.deeplearning4j.integration.TestUtils.randomOneHot(2, 10);
                 return new org.nd4j.linalg.dataset.MultiDataSet(arr, labels);
             }
@@ -135,6 +135,6 @@ public class CNN3DTestCases {
             }
 
         };
-    };
+    }
 
 }

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/dl4j/RNNTestCases.java

@@ -93,8 +93,8 @@ public class RNNTestCases {
                 minAbsErrorParamsPostTraining = 2e-3;
             }
 
-            private int miniBatchSize = 32;
+            private final int miniBatchSize = 32;
-            private int exampleLength = 200;
+            private final int exampleLength = 200;
 
 
             @Override

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/dl4j/misc/CharacterIterator.java

@@ -31,23 +31,24 @@ import java.io.File;
 import java.io.IOException;
 import java.net.URL;
 import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.util.*;
 
 public class CharacterIterator implements DataSetIterator {
     //Valid characters
-    private char[] validCharacters;
+    private final char[] validCharacters;
     //Maps each character to an index ind the input/output
-    private Map<Character, Integer> charToIdxMap;
+    private final Map<Character, Integer> charToIdxMap;
     //All characters of the input file (after filtering to only those that are valid
-    private char[] fileCharacters;
+    private final char[] fileCharacters;
     //Length of each example/minibatch (number of characters)
-    private int exampleLength;
+    private final int exampleLength;
     //Size of each minibatch (number of examples)
-    private int miniBatchSize;
+    private final int miniBatchSize;
-    private Random rng;
+    private final Random rng;
     //Offsets for the start of each example
-    private LinkedList<Integer> exampleStartOffsets = new LinkedList<>();
+    private final LinkedList<Integer> exampleStartOffsets = new LinkedList<>();
 
     /**
      * @param textFilePath     Path to text file to use for generating samples
@@ -299,7 +300,7 @@ public class CharacterIterator implements DataSetIterator {
         if (!f.exists()) throw new IOException("File does not exist: " + fileLocation);    //Download problem?
 
         char[] validCharacters = CharacterIterator.getMinimalCharacterSet();    //Which characters are allowed? Others will be removed
-        return new CharacterIterator(fileLocation, Charset.forName("UTF-8"),
+        return new CharacterIterator(fileLocation, StandardCharsets.UTF_8,
                 miniBatchSize, sequenceLength, validCharacters, new Random(12345));
     }
 

brutex-extended-tests/src/test/java/org/deeplearning4j/integration/testcases/samediff/SameDiffCNNCases.java

@@ -305,7 +305,7 @@ public class SameDiffCNNCases {
                 // [minibatch,8,1,1,1]
 
 
-                int channels_height_width_depth = 8 * 1 * 1 * 1;
+                int channels_height_width_depth = 8;
 
                 SDVariable layer1_reshaped = layer1.reshape(-1, channels_height_width_depth);
 
@@ -331,7 +331,7 @@ public class SameDiffCNNCases {
             public Map<String,INDArray> getGradientsTestDataSameDiff() throws Exception {
                 Nd4j.getRandom().setSeed(12345);
                 //NCDHW format
-                INDArray arr = Nd4j.rand(new int[]{2, 3, 8, 8, 8});
+                INDArray arr = Nd4j.rand(2, 3, 8, 8, 8);
                 INDArray labels = org.deeplearning4j.integration.TestUtils.randomOneHot(2, 10);
 
                 Map<String, INDArray> map = new HashMap<>();
@@ -357,7 +357,7 @@ public class SameDiffCNNCases {
                 Nd4j.getRandom().setSeed(12345);
 
                 List<Map<String, INDArray>> list = new ArrayList<>();
-                INDArray arr = Nd4j.rand(new int[]{2, 3, 8, 8, 8});
+                INDArray arr = Nd4j.rand(2, 3, 8, 8, 8);
 
                 list.add(Collections.singletonMap("in", arr));
 
@@ -368,7 +368,7 @@ public class SameDiffCNNCases {
             public MultiDataSet getGradientsTestData() throws Exception {
                 Nd4j.getRandom().setSeed(12345);
                 //NCDHW format
-                INDArray arr = Nd4j.rand(new int[]{2, 3, 8, 8, 8});
+                INDArray arr = Nd4j.rand(2, 3, 8, 8, 8);
                 INDArray labels = org.deeplearning4j.integration.TestUtils.randomOneHot(2, 10);
                 return new org.nd4j.linalg.dataset.MultiDataSet(arr, labels);
             }

build_requirements.md

@@ -129,4 +129,20 @@ echo "nameserver 8.8.8.8" | sudo tee -a /etc/resolv.conf
  # Buildparameter: #
 
  -P\<xxx>\
- CAVIS_AVX_EXTENSION = {avx2 | avx512}, default is avx2
+ CAVIS_AVX_EXTENSION = {avx2 | avx512}, default is avx2
+ 
+# Zeppelin Spark dependencies #
+3
+
+
+To add the dependency to the language models, use the following format in the Dependencies section of the of the Spark Interpreter configuration (Interpreters -> Spark -> Edit -> Dependencies):
+
+groupId:artifactId:packaging:classifier:version
+
+In your case it should work with
+
+edu.stanford.nlp:stanford-corenlp:jar:models:3.8.0
+
+
+Native cpu code under linux needs libc6-dev
+/lib/x86_64-linux-gnu/libm.so.6: version `GLIBC_2.29' not found

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/conf/Configuration.java

@@ -266,7 +266,7 @@ public class Configuration implements Iterable<Map.Entry<String, String>>, Writa
         reloadConfiguration();
     }
 
-    private static Pattern varPat = Pattern.compile("\\$\\{[^\\}\\$\u0020]+\\}");
+    private static final Pattern varPat = Pattern.compile("\\$\\{[^\\}\\$\u0020]+\\}");
 
     private String substituteVars(String expr) {
         if (expr == null) {
@@ -555,7 +555,7 @@ public class Configuration implements Iterable<Map.Entry<String, String>>, Writa
     }
 
     /**
-     * Get the value of the <code>name</code> property as a <ocde>Pattern</code>.
+     * Get the value of the <code>name</code> property as a {@code Pattern}.
      * If no such property is specified, or if the specified value is not a valid
      * <code>Pattern</code>, then <code>DefaultValue</code> is returned.
      *

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/formats/output/OutputFormat.java

@@ -27,7 +27,7 @@ import org.datavec.api.records.writer.RecordWriter;
 
 public interface OutputFormat {
 
-    public static final String OUTPUT_PATH = "org.nd4j.outputpath";
+    String OUTPUT_PATH = "org.nd4j.outputpath";
 
     /**
      * Create a record writer

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/BinaryComparable.java

@@ -34,7 +34,7 @@ public abstract class BinaryComparable implements Comparable<BinaryComparable> {
 
     /**
      * Compare bytes from {#getBytes()}.
-     * @see org.apache.hadoop.io.WritableComparator#compareBytes(byte[],int,int,byte[],int,int)
+     * {@code org.apache.hadoop.io.WritableComparator#compareBytes(byte[], int, int, byte[], int, int)}
      */
     public int compareTo(BinaryComparable other) {
         if (this == other)
@@ -63,7 +63,7 @@ public abstract class BinaryComparable implements Comparable<BinaryComparable> {
 
     /**
      * Return a hash of the bytes returned from {#getBytes()}.
-     * @see org.apache.hadoop.io.WritableComparator#hashBytes(byte[],int)
+     * {@code org.apache.hadoop.io.WritableComparator#hashBytes(byte[],int)}
      */
     public int hashCode() {
         return WritableComparator.hashBytes(getBytes(), getLength());

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/DataInputBuffer.java

@@ -50,7 +50,7 @@ public class DataInputBuffer extends DataInputStream {
         }
     }
 
-    private Buffer buffer;
+    private final Buffer buffer;
 
     /** Constructs a new empty buffer. */
     public DataInputBuffer() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/DataOutputBuffer.java

@@ -44,7 +44,7 @@ public class DataOutputBuffer extends DataOutputStream {
         public void write(DataInput in, int len) throws IOException {
             int newcount = count + len;
             if (newcount > buf.length) {
-                byte newbuf[] = new byte[Math.max(buf.length << 1, newcount)];
+                byte[] newbuf = new byte[Math.max(buf.length << 1, newcount)];
                 System.arraycopy(buf, 0, newbuf, 0, count);
                 buf = newbuf;
             }
@@ -53,7 +53,7 @@ public class DataOutputBuffer extends DataOutputStream {
         }
     }
 
-    private Buffer buffer;
+    private final Buffer buffer;
 
     /** Constructs a new empty buffer. */
     public DataOutputBuffer() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/RawComparator.java

@@ -25,6 +25,6 @@ import java.util.Comparator;
 
 public interface RawComparator<T> extends Comparator<T> {
 
-    public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2);
+    int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2);
 
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/WritableComparator.java

@@ -31,7 +31,7 @@ import java.util.HashMap;
 
 public class WritableComparator implements RawComparator {
 
-    private static HashMap<Class, WritableComparator> comparators = new HashMap<>(); // registry
+    private static final HashMap<Class, WritableComparator> comparators = new HashMap<>(); // registry
 
     /** Get a comparator for a {@link WritableComparable} implementation. */
     public static synchronized WritableComparator get(Class<? extends WritableComparable> c) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/WritableUtils.java

@@ -229,7 +229,7 @@ public final class WritableUtils {
 
     /**
      * Serializes an integer to a binary stream with zero-compressed encoding.
-     * For -120 <= i <= 127, only one byte is used with the actual value.
+     * For -120 &lt;= i &lt;= 127, only one byte is used with the actual value.
      * For other values of i, the first byte value indicates whether the
      * integer is positive or negative, and the number of bytes that follow.
      * If the first byte value v is between -121 and -124, the following integer
@@ -248,7 +248,7 @@ public final class WritableUtils {
 
     /**
      * Serializes a long to a binary stream with zero-compressed encoding.
-     * For -112 <= i <= 127, only one byte is used with the actual value.
+     * For -112 &lt;= i lt;= 127, only one byte is used with the actual value.
      * For other values of i, the first byte value indicates whether the
      * long is positive or negative, and the number of bytes that follow.
      * If the first byte value v is between -113 and -120, the following long

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/converters/LabelWriterConverter.java

@@ -27,7 +27,7 @@ import org.datavec.api.writable.Writable;
 import java.util.List;
 
 public class LabelWriterConverter implements WritableConverter {
-    private List<String> labels;
+    private final List<String> labels;
 
     public LabelWriterConverter(List<String> labels) {
         this.labels = labels;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/labels/PathLabelGenerator.java

@@ -35,7 +35,7 @@ public interface PathLabelGenerator extends Serializable {
      * If true: infer the set of possible label classes, and convert these to integer indexes. If when true, the
      * returned Writables should be text writables.<br>
      * <br>
-     * For regression use cases (or PathLabelGenerator classification instances that do their own label -> integer
+     * For regression use cases (or PathLabelGenerator classification instances that do their own label -&gt; integer
      * assignment), this should return false.
      *
      * @return whether label classes should be inferred

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/io/serializers/SerializationFactory.java

@@ -35,7 +35,7 @@ public class SerializationFactory extends Configured {
 
     private static final Logger LOG = LoggerFactory.getLogger(SerializationFactory.class.getName());
 
-    private List<Serialization<?>> serializations = new ArrayList<>();
+    private final List<Serialization<?>> serializations = new ArrayList<>();
 
     /**
      * <p>
@@ -47,7 +47,7 @@ public class SerializationFactory extends Configured {
     public SerializationFactory(Configuration conf) {
         super(conf);
         for (String serializerName : conf.getStrings("io.serializations",
-                        new String[] {"org.apache.hadoop.io.serializer.WritableSerialization"})) {
+                "org.apache.hadoop.io.serializer.WritableSerialization")) {
             add(conf, serializerName);
         }
     }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/Buffer.java

@@ -113,7 +113,7 @@ public class Buffer implements Comparable, Cloneable {
 
     /**
      * Change the capacity of the backing storage.
-     * The data is preserved if newCapacity >= getCount().
+     * The data is preserved if newCapacity >= getCount().
      * @param newCapacity The new capacity in bytes.
      */
     public void setCapacity(int newCapacity) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/IOUtils.java

@@ -209,9 +209,7 @@ public class IOUtils {
      * @return
      */
     static String toCSVBuffer(Buffer buf) {
-        StringBuilder sb = new StringBuilder("#");
+        return "#" + buf.toString();
-        sb.append(buf.toString());
-        return sb.toString();
     }
 
     /**
@@ -441,7 +439,7 @@ public class IOUtils {
 
     /**
      * Serializes a long to a binary stream with zero-compressed encoding.
-     * For -112 <= i <= 127, only one byte is used with the actual value.
+     * For -112 &lt;= i &lt;= 127, only one byte is used with the actual value.
      * For other values of i, the first byte value indicates whether the
      * long is positive or negative, and the number of bytes that follow.
      * If the first byte value v is between -113 and -120, the following long

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/RecordReader.java

@@ -99,8 +99,6 @@ public interface RecordReader extends AutoCloseable, Serializable, Configurable
 
     /**
      * Reset record reader iterator
-     *
-     * @return
      */
     void reset();
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/ComposableRecordReader.java

@@ -39,7 +39,7 @@ import java.util.List;
  */
 public class ComposableRecordReader extends BaseRecordReader {
 
-    private RecordReader[] readers;
+    private final RecordReader[] readers;
 
     public ComposableRecordReader(RecordReader... readers) {
         this.readers = readers;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/ConcatenatingRecordReader.java

@@ -35,7 +35,7 @@ import java.util.List;
 
 public class ConcatenatingRecordReader extends BaseRecordReader {
 
-    private RecordReader[] readers;
+    private final RecordReader[] readers;
 
     public ConcatenatingRecordReader(RecordReader... readers) {
         this.readers = readers;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/FileRecordReader.java

@@ -23,14 +23,14 @@ package org.datavec.api.records.reader.impl;
 import lombok.Getter;
 import lombok.Setter;
 import org.datavec.api.conf.Configuration;
-import org.datavec.api.Record;
+import org.datavec.api.records.Record;
 import org.datavec.api.records.metadata.RecordMetaData;
 import org.datavec.api.records.metadata.RecordMetaDataURI;
 import org.datavec.api.records.reader.BaseRecordReader;
 import org.datavec.api.split.InputSplit;
 import org.datavec.api.writable.IntWritable;
 import org.datavec.api.writable.Text;
-import org.datavec.api.Writable;
+import org.datavec.api.writable.Writable;
 
 import java.io.*;
 import java.net.URI;
@@ -40,206 +40,202 @@ import java.util.*;
 
 /**
  * File reader/writer
+ *
+ * @author Adam Gibson
  */
 public class FileRecordReader extends BaseRecordReader {
 
-  protected Iterator<URI> locationsIterator;
+    protected Iterator<URI> locationsIterator;
-  protected Configuration conf;
+    protected Configuration conf;
-  protected URI currentUri;
+    protected URI currentUri;
-  protected List<String> labels;
+    protected List<String> labels;
-  protected boolean appendLabel = false;
+    protected boolean appendLabel = false;
-  @Getter
+    @Getter @Setter
-  @Setter
+    protected String charset = StandardCharsets.UTF_8.name(); //Using String as StandardCharsets.UTF_8 is not serializable
-  protected String charset = StandardCharsets.UTF_8.name(); //Using String as StandardCharsets.UTF_8 is not serializable
 
-  public FileRecordReader() {
+    public FileRecordReader() {}
-  }
 
-  @Override
+    @Override
-  public void initialize(InputSplit split) throws IOException, InterruptedException {
+    public void initialize(InputSplit split) throws IOException, InterruptedException {
-    super.initialize(split);
+        super.initialize(split);
-    doInitialize(split);
+        doInitialize(split);
-  }
+    }
 
 
-  protected void doInitialize(InputSplit split) {
+    protected void doInitialize(InputSplit split) {
 
-    if (labels == null && appendLabel) {
+        if (labels == null && appendLabel) {
-      URI[] locations = split.locations();
+            URI[] locations = split.locations();
-      if (locations.length > 0) {
+            if (locations.length > 0) {
-        Set<String> labels = new HashSet<>();
+                Set<String> labels = new HashSet<>();
-        for (URI u : locations) {
+                for(URI u : locations){
-          String[] pathSplit = u.toString().split("[/\\\\]");
+                    String[] pathSplit = u.toString().split("[/\\\\]");
-          labels.add(pathSplit[pathSplit.length - 2]);
+                    labels.add(pathSplit[pathSplit.length-2]);
+                }
+                this.labels = new ArrayList<>(labels);
+                Collections.sort(this.labels);
+            }
         }
-        this.labels = new ArrayList<>(labels);
+        locationsIterator = split.locationsIterator();
-        Collections.sort(this.labels);
-      }
-    }
-    locationsIterator = split.locationsIterator();
-  }
-
-  @Override
-  public void initialize(Configuration conf, InputSplit split)
-      throws IOException, InterruptedException {
-    appendLabel = conf.getBoolean(APPEND_LABEL, true);
-    doInitialize(split);
-    this.inputSplit = split;
-    this.conf = conf;
-  }
-
-  @Override
-  public List<Writable> next() {
-    return nextRecord().getRecord();
-  }
-
-  private List<Writable> loadFromStream(URI uri, InputStream next, Charset charset) {
-    List<Writable> ret = new ArrayList<>();
-    try {
-      if (!(next instanceof BufferedInputStream)) {
-        next = new BufferedInputStream(next);
-      }
-      String s = org.apache.commons.io.IOUtils.toString(next, charset);
-      ret.add(new Text(s));
-      if (appendLabel) {
-        int idx = getLabel(uri);
-        ret.add(new IntWritable(idx));
-      }
-    } catch (IOException e) {
-      throw new IllegalStateException("Error reading from input stream: " + uri);
-    }
-    return ret;
-  }
-
-  /**
-   * Return the current label. The index of the current file's parent directory in the label list
-   *
-   * @return The index of the current file's parent directory
-   */
-  public int getCurrentLabel() {
-    return getLabel(currentUri);
-  }
-
-  public int getLabel(URI uri) {
-    String s = uri.toString();
-    int lastIdx = Math.max(s.lastIndexOf('/'),
-        s.lastIndexOf('\\'));    //Note: if neither are found, -1 is fine here
-    String sub = s.substring(0, lastIdx);
-    int secondLastIdx = Math.max(sub.lastIndexOf('/'), sub.lastIndexOf('\\'));
-    String name = s.substring(secondLastIdx + 1, lastIdx);
-    return labels.indexOf(name);
-  }
-
-  public List<String> getLabels() {
-    return labels;
-  }
-
-  public void setLabels(List<String> labels) {
-    this.labels = labels;
-  }
-
-  @Override
-  public boolean hasNext() {
-    return locationsIterator.hasNext();
-  }
-
-  @Override
-  public void close() throws IOException {
-
-  }
-
-  @Override
-  public void setConf(Configuration conf) {
-    this.conf = conf;
-  }
-
-  @Override
-  public Configuration getConf() {
-    return conf;
-  }
-
-  @Override
-  public List<List<Writable>> next(int num) {
-    List<List<Writable>> ret = new ArrayList<>(num);
-    int numBatches = 0;
-    while (hasNext() && numBatches < num) {
-      ret.add(next());
     }
 
-    return ret;
+    @Override
-  }
+    public void initialize(Configuration conf, InputSplit split) throws IOException, InterruptedException {
-
+        appendLabel = conf.getBoolean(APPEND_LABEL, true);
-  @Override
+        doInitialize(split);
-  public void reset() {
+        this.inputSplit = split;
-      if (inputSplit == null) {
+        this.conf = conf;
-          throw new UnsupportedOperationException("Cannot reset without first initializing");
-      }
-    try {
-      doInitialize(inputSplit);
-    } catch (Exception e) {
-      throw new RuntimeException("Error during LineRecordReader reset", e);
-    }
-  }
-
-  @Override
-  public boolean resetSupported() {
-    if (inputSplit != null) {
-      return inputSplit.resetSupported();
-    }
-    return false;   //reset() throws exception on reset() if inputSplit is null
-  }
-
-  @Override
-  public List<Writable> record(URI uri, DataInputStream dataInputStream) throws IOException {
-    invokeListeners(uri);
-    //Here: reading the entire file to a Text writable
-    BufferedReader br = new BufferedReader(new InputStreamReader(dataInputStream));
-    StringBuilder sb = new StringBuilder();
-    String line;
-    while ((line = br.readLine()) != null) {
-      sb.append(line).append("\n");
-    }
-    return Collections.singletonList(new Text(sb.toString()));
-  }
-
-  @Override
-  public Record nextRecord() {
-    URI next = locationsIterator.next();
-    invokeListeners(next);
-
-    List<Writable> ret;
-    try (InputStream s = streamCreatorFn.apply(next)) {
-      ret = loadFromStream(next, s, Charset.forName(charset));
-    } catch (IOException e) {
-      throw new RuntimeException("Error reading from stream for URI: " + next);
     }
 
-    return new org.datavec.api.records.impl.Record(ret,
+    @Override
-        new RecordMetaDataURI(next, FileRecordReader.class));
+    public List<Writable> next() {
-  }
+        return nextRecord().getRecord();
-
-  @Override
-  public Record loadFromMetaData(RecordMetaData recordMetaData) throws IOException {
-    return loadFromMetaData(Collections.singletonList(recordMetaData)).get(0);
-  }
-
-  @Override
-  public List<Record> loadFromMetaData(List<RecordMetaData> recordMetaDatas) throws IOException {
-    List<Record> out = new ArrayList<>();
-
-    for (RecordMetaData meta : recordMetaDatas) {
-      URI uri = meta.getURI();
-
-      List<Writable> list;
-      try (InputStream s = streamCreatorFn.apply(uri)) {
-        list = loadFromStream(uri, s, Charset.forName(charset));
-      } catch (IOException e) {
-        throw new RuntimeException("Error reading from stream for URI: " + uri);
-      }
-
-      out.add(new org.datavec.api.records.impl.Record(list, meta));
     }
 
-    return out;
+    private List<Writable> loadFromStream(URI uri, InputStream next, Charset charset) {
-  }
+        List<Writable> ret = new ArrayList<>();
+        try {
+            if(!(next instanceof BufferedInputStream)){
+                next = new BufferedInputStream(next);
+            }
+            String s = org.apache.commons.io.IOUtils.toString(next, charset);
+            ret.add(new Text(s));
+            if (appendLabel) {
+                int idx = getLabel(uri);
+                ret.add(new IntWritable(idx));
+            }
+        } catch (IOException e) {
+            throw new IllegalStateException("Error reading from input stream: " + uri);
+        }
+        return ret;
+    }
+
+    /**
+     * Return the current label.
+     * The index of the current file's parent directory
+     * in the label list
+     * @return The index of the current file's parent directory
+     */
+    public int getCurrentLabel() {
+        return getLabel(currentUri);
+    }
+
+    public int getLabel(URI uri){
+        String s = uri.toString();
+        int lastIdx = Math.max(s.lastIndexOf('/'), s.lastIndexOf('\\'));    //Note: if neither are found, -1 is fine here
+        String sub = s.substring(0, lastIdx);
+        int secondLastIdx = Math.max(sub.lastIndexOf('/'), sub.lastIndexOf('\\'));
+        String name = s.substring(secondLastIdx+1, lastIdx);
+        return labels.indexOf(name);
+    }
+
+    public List<String> getLabels() {
+        return labels;
+    }
+
+    public void setLabels(List<String> labels) {
+        this.labels = labels;
+    }
+
+    @Override
+    public boolean hasNext() {
+        return locationsIterator.hasNext();
+    }
+
+    @Override
+    public void close() throws IOException {
+
+    }
+
+    @Override
+    public void setConf(Configuration conf) {
+        this.conf = conf;
+    }
+
+    @Override
+    public Configuration getConf() {
+        return conf;
+    }
+
+    @Override
+    public List<List<Writable>> next(int num) {
+        List<List<Writable>> ret = new ArrayList<>(num);
+        int numBatches = 0;
+        while (hasNext() && numBatches < num) {
+            ret.add(next());
+        }
+
+        return ret;
+    }
+    @Override
+    public void reset() {
+        if (inputSplit == null)
+            throw new UnsupportedOperationException("Cannot reset without first initializing");
+        try {
+            doInitialize(inputSplit);
+        } catch (Exception e) {
+            throw new RuntimeException("Error during LineRecordReader reset", e);
+        }
+    }
+
+    @Override
+    public boolean resetSupported() {
+        if(inputSplit != null){
+            return inputSplit.resetSupported();
+        }
+        return false;   //reset() throws exception on reset() if inputSplit is null
+    }
+
+    @Override
+    public List<Writable> record(URI uri, DataInputStream dataInputStream) throws IOException {
+        invokeListeners(uri);
+        //Here: reading the entire file to a Text writable
+        BufferedReader br = new BufferedReader(new InputStreamReader(dataInputStream));
+        StringBuilder sb = new StringBuilder();
+        String line;
+        while ((line = br.readLine()) != null) {
+            sb.append(line).append("\n");
+        }
+        return Collections.singletonList(new Text(sb.toString()));
+    }
+
+    @Override
+    public Record nextRecord() {
+        URI next = locationsIterator.next();
+        invokeListeners(next);
+
+        List<Writable> ret;
+        try(InputStream s = streamCreatorFn.apply(next)) {
+            ret = loadFromStream(next, s, Charset.forName(charset));
+        } catch (IOException e){
+            throw new RuntimeException("Error reading from stream for URI: " + next);
+        }
+
+        return new org.datavec.api.records.impl.Record(ret,new RecordMetaDataURI(next, FileRecordReader.class));
+    }
+
+    @Override
+    public Record loadFromMetaData(RecordMetaData recordMetaData) throws IOException {
+        return loadFromMetaData(Collections.singletonList(recordMetaData)).get(0);
+    }
+
+    @Override
+    public List<Record> loadFromMetaData(List<RecordMetaData> recordMetaDatas) throws IOException {
+        List<Record> out = new ArrayList<>();
+
+        for (RecordMetaData meta : recordMetaDatas) {
+            URI uri = meta.getURI();
+
+            List<Writable> list;
+            try(InputStream s = streamCreatorFn.apply(uri)) {
+                list = loadFromStream(uri, s, Charset.forName(charset));
+            } catch (IOException e){
+                throw new RuntimeException("Error reading from stream for URI: " + uri);
+            }
+
+            out.add(new org.datavec.api.records.impl.Record(list, meta));
+        }
+
+        return out;
+    }
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/LineRecordReader.java

@@ -200,7 +200,7 @@ public class LineRecordReader extends BaseRecordReader {
         //Here: we are reading a single line from the DataInputStream
         BufferedReader br = new BufferedReader(new InputStreamReader(dataInputStream));
         String line = br.readLine();
-        return Collections.singletonList((Writable) new Text(line));
+        return Collections.singletonList(new Text(line));
     }
 
     protected Iterator<String> getIterator(int location) {
@@ -265,7 +265,7 @@ public class LineRecordReader extends BaseRecordReader {
                 throw new IllegalArgumentException(
                                 "Invalid metadata; expected RecordMetaDataLine instance; got: " + rmd);
             }
-            list.add(new Triple<>(count++, (RecordMetaDataLine) rmd, (List<Writable>) null));
+            list.add(new Triple<>(count++, (RecordMetaDataLine) rmd, null));
             if (rmd.getURI() != null)
                 uris.add(rmd.getURI());
         }
@@ -332,7 +332,7 @@ public class LineRecordReader extends BaseRecordReader {
                     throw new IllegalStateException("Could not get line " + nextLineIdx + " from URI " + currentURI
                                     + ": has only " + currentLineIdx + " lines");
                 }
-                t.setThird(Collections.<Writable>singletonList(new Text(line)));
+                t.setThird(Collections.singletonList(new Text(line)));
             }
         } else {
             //Not URI based: String split, etc
@@ -347,7 +347,7 @@ public class LineRecordReader extends BaseRecordReader {
                     line = iterator.next();
                     currentLineIdx++;
                 }
-                t.setThird(Collections.<Writable>singletonList(new Text(line)));
+                t.setThird(Collections.singletonList(new Text(line)));
             }
             closeIfRequired(iterator);
         }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/collection/CollectionSequenceRecordReader.java

@@ -43,7 +43,7 @@ public class CollectionSequenceRecordReader extends BaseRecordReader implements
 
     /**
      *
-     * @param records    Collection of sequences. For example, List<List<List<Writable>>> where the inner  two lists
+     * @param records    Collection of sequences. For example, {@code List<List<List<Writable>>>} where the inner  two lists
      *                   are a sequence, and the outer list/collection is a list of sequences
      */
     public CollectionSequenceRecordReader(Collection<? extends Collection<? extends Collection<Writable>>> records) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/csv/CSVMultiSequenceRecordReader.java

@@ -45,9 +45,9 @@ public class CSVMultiSequenceRecordReader extends CSVRecordReader implements Seq
         PAD
     }
 
-    private String sequenceSeparatorRegex;
+    private final String sequenceSeparatorRegex;
-    private Mode mode;
+    private final Mode mode;
-    private Writable padValue;
+    private final Writable padValue;
 
     /**
      * Create a sequence reader using the default value for skip lines (0), the default delimiter (',') and the default

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/csv/CSVNLinesSequenceRecordReader.java

@@ -41,7 +41,7 @@ public class CSVNLinesSequenceRecordReader extends CSVRecordReader implements Se
     public static final String LINES_PER_SEQUENCE = NAME_SPACE + ".nlinespersequence";
 
     private int nLinesPerSequence;
-    private String delimiter;
+    private final String delimiter;
 
     /**
      * No-arg constructor with the default number of lines per sequence (10)
@@ -124,7 +124,7 @@ public class CSVNLinesSequenceRecordReader extends CSVRecordReader implements Se
                                 "Invalid metadata; expected RecordMetaDataLineInterval instance; got: " + rmd);
             }
             list.add(new Triple<>(count++, (RecordMetaDataLineInterval) rmd,
-                            (List<List<Writable>>) new ArrayList<List<Writable>>()));
+                    new ArrayList<List<Writable>>()));
         }
 
         //Sort by starting line number:

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/csv/CSVVariableSlidingWindowRecordReader.java

@@ -39,8 +39,8 @@ public class CSVVariableSlidingWindowRecordReader extends CSVRecordReader implem
     public static final String LINES_PER_SEQUENCE = NAME_SPACE + ".nlinespersequence";
 
     private int maxLinesPerSequence;
-    private String delimiter;
+    private final String delimiter;
-    private int stride;
+    private final int stride;
     private LinkedList<List<Writable>> queue;
     private boolean exhausted;
 
@@ -60,7 +60,7 @@ public class CSVVariableSlidingWindowRecordReader extends CSVRecordReader implem
 
     /**
      * @param maxLinesPerSequence Number of lines in each sequence, use default delemiter(,) between entries in the same line
-     * @param stride Number of lines between records (increment window > 1 line)
+     * @param stride Number of lines between records (increment window &gt; 1 line)
      */
     public CSVVariableSlidingWindowRecordReader(int maxLinesPerSequence, int stride) {
         this(maxLinesPerSequence, 0, stride, String.valueOf(CSVRecordReader.DEFAULT_DELIMITER));
@@ -68,7 +68,7 @@ public class CSVVariableSlidingWindowRecordReader extends CSVRecordReader implem
 
     /**
      * @param maxLinesPerSequence Number of lines in each sequence, use default delemiter(,) between entries in the same line
-     * @param stride Number of lines between records (increment window > 1 line)
+     * @param stride Number of lines between records (increment window &gt; 1 line)
      */
     public CSVVariableSlidingWindowRecordReader(int maxLinesPerSequence, int stride, String delimiter) {
         this(maxLinesPerSequence, 0, stride, String.valueOf(CSVRecordReader.DEFAULT_DELIMITER));
@@ -78,7 +78,7 @@ public class CSVVariableSlidingWindowRecordReader extends CSVRecordReader implem
      *
      * @param maxLinesPerSequence Number of lines in each sequences
      * @param skipNumLines Number of lines to skip at the start of the file (only skipped once, not per sequence)
-     * @param stride Number of lines between records (increment window > 1 line)
+     * @param stride Number of lines between records (increment window &gt; 1 line)
      * @param delimiter Delimiter between entries in the same line, for example ","
      */
     public CSVVariableSlidingWindowRecordReader(int maxLinesPerSequence, int skipNumLines, int stride, String delimiter) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/csv/SerializableCSVParser.java

@@ -302,7 +302,7 @@ public class SerializableCSVParser implements Serializable {
     }
 
     /**
-     * precondition: sb.length() > 0
+     * precondition: sb.length() > 0
      *
      * @param sb A sequence of characters to examine
      * @return true if every character in the sequence is whitespace

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/inmemory/InMemoryRecordReader.java

@@ -114,8 +114,6 @@ public class InMemoryRecordReader implements RecordReader {
 
     /**
      * Reset record reader iterator
-     *
-     * @return
      */
     @Override
     public void reset() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/inmemory/InMemorySequenceRecordReader.java

@@ -195,8 +195,6 @@ public class InMemorySequenceRecordReader implements SequenceRecordReader {
 
     /**
      * Reset record reader iterator
-     *
-     * @return
      */
     @Override
     public void reset() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/jackson/FieldSelection.java

@@ -31,8 +31,8 @@ public class FieldSelection implements Serializable {
 
     public static final Writable DEFAULT_MISSING_VALUE = new Text("");
 
-    private List<String[]> fieldPaths;
+    private final List<String[]> fieldPaths;
-    private List<Writable> valueIfMissing;
+    private final List<Writable> valueIfMissing;
 
     private FieldSelection(Builder builder) {
         this.fieldPaths = builder.fieldPaths;
@@ -53,8 +53,8 @@ public class FieldSelection implements Serializable {
 
     public static class Builder {
 
-        private List<String[]> fieldPaths = new ArrayList<>();
+        private final List<String[]> fieldPaths = new ArrayList<>();
-        private List<Writable> valueIfMissing = new ArrayList<>();
+        private final List<Writable> valueIfMissing = new ArrayList<>();
 
 
         /**

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/jackson/JacksonLineRecordReader.java

@@ -29,8 +29,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 
 public class JacksonLineRecordReader extends LineRecordReader {
 
-    private FieldSelection selection;
+    private final FieldSelection selection;
-    private ObjectMapper mapper;
+    private final ObjectMapper mapper;
 
 	public JacksonLineRecordReader(FieldSelection selection, ObjectMapper mapper) {
 		this.selection = selection;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/jackson/JacksonLineSequenceRecordReader.java

@@ -39,8 +39,8 @@ import java.util.NoSuchElementException;
 
 public class JacksonLineSequenceRecordReader extends FileRecordReader implements SequenceRecordReader {
 
-    private FieldSelection selection;
+    private final FieldSelection selection;
-    private ObjectMapper mapper;
+    private final ObjectMapper mapper;
 
     /**
      *

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/jackson/JacksonRecordReader.java

@@ -45,12 +45,12 @@ public class JacksonRecordReader extends BaseRecordReader {
 
     private static final TypeReference<Map<String, Object>> typeRef = new TypeReference<Map<String, Object>>() {};
 
-    private FieldSelection selection;
+    private final FieldSelection selection;
-    private ObjectMapper mapper;
+    private final ObjectMapper mapper;
-    private boolean shuffle;
+    private final boolean shuffle;
-    private long rngSeed;
+    private final long rngSeed;
-    private PathLabelGenerator labelGenerator;
+    private final PathLabelGenerator labelGenerator;
-    private int labelPosition;
+    private final int labelPosition;
     private InputSplit is;
     private Random r;
     @Getter @Setter

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/misc/MatlabRecordReader.java

@@ -35,7 +35,7 @@ import java.util.List;
 
 public class MatlabRecordReader extends FileRecordReader {
 
-    private List<List<Writable>> records = new ArrayList<>();
+    private final List<List<Writable>> records = new ArrayList<>();
     private Iterator<List<Writable>> currIter;
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/misc/SVMLightRecordReader.java

@@ -96,8 +96,6 @@ public class SVMLightRecordReader extends LineRecordReader {
      * Set configuration.
      *
      * @param conf          DataVec configuration
-     * @throws IOException
-     * @throws InterruptedException
      */
     @Override
     public void setConf(Configuration conf) {
@@ -181,7 +179,7 @@ public class SVMLightRecordReader extends LineRecordReader {
                     if (index < 0)
                         throw new NumberFormatException("");
                 } catch (NumberFormatException e) {
-                    String msg = String.format("Feature index must be positive integer (found %s)", featureTokens[i].toString());
+                    String msg = String.format("Feature index must be positive integer (found %s)", featureTokens[i]);
                     throw new NumberFormatException(msg);
                 }
 
@@ -218,7 +216,7 @@ public class SVMLightRecordReader extends LineRecordReader {
                             if (index < 0)
                                 throw new NumberFormatException("");
                         } catch (NumberFormatException e) {
-                            String msg = String.format("Multilabel index must be positive integer (found %s)", labelTokens[i].toString());
+                            String msg = String.format("Multilabel index must be positive integer (found %s)", labelTokens[i]);
                             throw new NumberFormatException(msg);
                         }
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/regex/RegexLineRecordReader.java

@@ -41,11 +41,11 @@ import java.util.regex.Pattern;
 public class RegexLineRecordReader extends LineRecordReader {
     public final static String SKIP_NUM_LINES = NAME_SPACE + ".skipnumlines";
 
-    private String regex;
+    private final String regex;
     private int skipNumLines;
-    private Pattern pattern;
+    private final Pattern pattern;
     private int numLinesSkipped;
-    private int currLine = 0;
+    private final int currLine = 0;
 
     public RegexLineRecordReader(String regex, int skipNumLines) {
         this.regex = regex;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/regex/RegexSequenceRecordReader.java

@@ -61,11 +61,11 @@ public class RegexSequenceRecordReader extends FileRecordReader implements Seque
 
     public static final Logger LOG = LoggerFactory.getLogger(RegexSequenceRecordReader.class);
 
-    private String regex;
+    private final String regex;
     private int skipNumLines;
-    private Pattern pattern;
+    private final Pattern pattern;
     private transient Charset charset;
-    private LineErrorHandling errorHandling;
+    private final LineErrorHandling errorHandling;
 
     public RegexSequenceRecordReader(String regex, int skipNumLines) {
         this(regex, skipNumLines, DEFAULT_CHARSET, DEFAULT_ERROR_HANDLING);
@@ -92,7 +92,7 @@ public class RegexSequenceRecordReader extends FileRecordReader implements Seque
 
     @Override
     public List<List<Writable>> sequenceRecord(URI uri, DataInputStream dataInputStream) throws IOException {
-        String fileContents = IOUtils.toString(new BufferedInputStream(dataInputStream), charset.name());
+        String fileContents = IOUtils.toString(new BufferedInputStream(dataInputStream), charset);
         return loadSequence(fileContents, uri);
     }
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/transform/TransformProcessRecordReader.java

@@ -145,8 +145,6 @@ public class TransformProcessRecordReader implements RecordReader {
 
     /**
      * Reset record reader iterator
-     *
-     * @return
      */
     @Override
     public void reset() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/reader/impl/transform/TransformProcessSequenceRecordReader.java

@@ -195,8 +195,6 @@ public class TransformProcessSequenceRecordReader implements SequenceRecordReade
 
     /**
      * Reset record reader iterator
-     *
-     * @return
      */
     @Override
     public void reset() {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/records/writer/impl/misc/SVMLightRecordWriter.java

@@ -94,7 +94,7 @@ public class SVMLightRecordWriter extends FileRecordWriter {
     @Override
     public PartitionMetaData write(List<Writable> record) throws IOException {
         if (!record.isEmpty()) {
-            List<Writable> recordList = record instanceof List ? (List<Writable>) record : new ArrayList<>(record);
+            List<Writable> recordList = record instanceof List ? record : new ArrayList<>(record);
 
             /* Infer label columns, if necessary. The default is
              * to assume that last column is a label and that the
@@ -198,7 +198,7 @@ public class SVMLightRecordWriter extends FileRecordWriter {
             }
 
             // Remove extra label delimiter at beginning
-            String line = result.substring(1).toString();
+            String line = result.substring(1);
             out.write(line.getBytes());
             out.write(NEW_LINE.getBytes());
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/BaseInputSplit.java

@@ -124,9 +124,7 @@ public abstract class BaseInputSplit implements InputSplit {
 
             for (int i = 0; i < weights.length; i++) {
                 List<URI> uris = new ArrayList<>();
-                for (int j = partitions[i]; j < partitions[i + 1]; j++) {
+                uris.addAll(Arrays.asList(paths).subList(partitions[i], partitions[i + 1]));
-                    uris.add(paths[j]);
-                }
                 splits[i] = new CollectionInputSplit(uris);
             }
             return splits;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/FileSplit.java

@@ -138,7 +138,7 @@ public class FileSplit extends BaseInputSplit {
             return addNewLocation(new File(rootDir, UUID.randomUUID().toString()).toURI().toString());
         else {
             //add a file in the same directory as the file with the same extension as the original file
-            return addNewLocation(new File(rootDir.getParent(), UUID.randomUUID().toString() + "." + FilenameUtils.getExtension(rootDir.getAbsolutePath())).toURI().toString());
+            return addNewLocation(new File(rootDir.getParent(), UUID.randomUUID() + "." + FilenameUtils.getExtension(rootDir.getAbsolutePath())).toURI().toString());
 
         }
     }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/InputStreamInputSplit.java

@@ -31,7 +31,7 @@ import java.util.Iterator;
 
 public class InputStreamInputSplit implements InputSplit {
     private InputStream is;
-    private URI[] location;
+    private final URI[] location;
 
     /**
      * Instantiate with the given
@@ -130,7 +130,7 @@ public class InputStreamInputSplit implements InputSplit {
     public Iterator<String> locationsPathIterator() {
         if(location.length >= 1)
             return Collections.singletonList(location[0].getPath()).iterator();
-        return Arrays.asList("").iterator();
+        return Collections.singletonList("").iterator();
     }
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/ListStringSplit.java

@@ -33,7 +33,7 @@ import java.util.List;
  * has delimited data of some kind.
  */
 public class ListStringSplit implements InputSplit {
-    private List<List<String>> data;
+    private final List<List<String>> data;
 
 
     public ListStringSplit(List<List<String>> data) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/NumberedFileInputSplit.java

@@ -43,12 +43,12 @@ public class NumberedFileInputSplit implements InputSplit {
      *                   the index of the file, possibly zero-padded to x digits if the pattern is in the form %0xd.
      * @param minIdxInclusive Minimum index/number (starting number in sequence of files, inclusive)
      * @param maxIdxInclusive Maximum index/number (last number in sequence of files, inclusive)
-     *                        @see {NumberedFileInputSplitTest}
+     *
      */
     public NumberedFileInputSplit(String baseString, int minIdxInclusive, int maxIdxInclusive) {
         Matcher m = p.matcher(baseString);
         if (baseString == null || !m.find()) {
-            throw new IllegalArgumentException("Base String must match this regular expression: " + p.toString());
+            throw new IllegalArgumentException("Base String must match this regular expression: " + p);
         }
         this.baseString = baseString;
         this.minIdx = minIdxInclusive;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/split/StringSplit.java

@@ -31,7 +31,7 @@ import java.util.Iterator;
  * @author Adam Gibson
  */
 public class StringSplit implements InputSplit {
-    private String data;
+    private final String data;
 
     public StringSplit(String data) {
         this.data = data;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/TransformProcess.java

@@ -449,7 +449,7 @@ public class TransformProcess implements Serializable {
     /**
      * Infer the categories for the given record reader for a particular column
      *  Note that each "column index" is a column in the context of:
-     * List<Writable> record = ...;
+     * {@code List<Writable> record = ...;}
      * record.get(columnIndex);
      *
      *  Note that anything passed in as a column will be automatically converted to a
@@ -483,7 +483,7 @@ public class TransformProcess implements Serializable {
      * if you have more than one column you plan on inferring categories for)
      *
      * Note that each "column index" is a column in the context of:
-     * List<Writable> record = ...;
+     * {@code List<Writable> record = ...;}
      * record.get(columnIndex);
      *
      *
@@ -607,8 +607,8 @@ public class TransformProcess implements Serializable {
      */
     public static class Builder {
 
-        private List<DataAction> actionList = new ArrayList<>();
+        private final List<DataAction> actionList = new ArrayList<>();
-        private Schema initialSchema;
+        private final Schema initialSchema;
 
         public Builder(Schema initialSchema) {
             this.initialSchema = initialSchema;
@@ -1274,7 +1274,7 @@ public class TransformProcess implements Serializable {
          * not be modified.
          *
          * @param columnName Name of the column in which to do replacement
-         * @param mapping    Map of oldValues -> newValues
+         * @param mapping    Map of oldValues -&gt; newValues
          */
         public Builder stringMapTransform(String columnName, Map<String, String> mapping) {
             return transform(new StringMapTransform(columnName, mapping));
@@ -1358,7 +1358,8 @@ public class TransformProcess implements Serializable {
          * Keys in the map are the regular expressions; the Values in the map are their String replacements.
          * For example:
          * <blockquote>
-         * <table cellpadding="2">
+         * <table>
+         *     <caption></caption>
          * <tr>
          *      <th>Original</th>
          *      <th>Regex</th>
@@ -1378,7 +1379,7 @@ public class TransformProcess implements Serializable {
          *      <td>BoneConeTone</td>
          * </tr>
          * <tr>
-         *      <td>'&nbsp&nbsp4.25&nbsp'</td>
+         *      <td>'&nbsp;&nbsp;4.25&nbsp;'</td>
          *      <td>^\\s+|\\s+$</td>
          *      <td></td>
          *      <td>'4.25'</td>

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/columns/NDArrayAnalysis.java

@@ -55,7 +55,7 @@ public class NDArrayAnalysis implements ColumnAnalysis {
     public String toString() {
         Map<Integer, Long> sortedCountsByRank = new LinkedHashMap<>();
         List<Integer> keys =
-                        new ArrayList<>(countsByRank == null ? Collections.<Integer>emptySet() : countsByRank.keySet());
+                        new ArrayList<>(countsByRank == null ? Collections.emptySet() : countsByRank.keySet());
         Collections.sort(keys);
         for (Integer i : keys) {
             sortedCountsByRank.put(i, countsByRank.get(i));

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/counter/IntegerAnalysisCounter.java

@@ -101,8 +101,8 @@ public class IntegerAnalysisCounter implements AnalysisCounter<IntegerAnalysisCo
             countNegative++;
         }
 
-        digest.add((double) value);
+        digest.add(value);
-        counter.add((double) value);
+        counter.add(value);
 
         return this;
     }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/counter/NDArrayAnalysisCounter.java

@@ -38,7 +38,7 @@ public class NDArrayAnalysisCounter implements AnalysisCounter<NDArrayAnalysisCo
     private long minLength = Long.MAX_VALUE;
     private long maxLength = -1;
     private long totalNDArrayValues;
-    private Map<Integer, Long> countsByRank = new HashMap<>();
+    private final Map<Integer, Long> countsByRank = new HashMap<>();
     private double minValue = Double.MAX_VALUE;
     private double maxValue = -Double.MAX_VALUE;
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/counter/StringAnalysisCounter.java

@@ -83,7 +83,7 @@ public class StringAnalysisCounter implements AnalysisCounter<StringAnalysisCoun
             countMaxLength = 1;
         }
 
-        counter.add((double) length);
+        counter.add(length);
 
         return this;
     }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/histogram/CategoricalHistogramCounter.java

@@ -27,9 +27,9 @@ import java.util.List;
 import java.util.Map;
 
 public class CategoricalHistogramCounter implements HistogramCounter {
-    private HashMap<String, Integer> counts = new HashMap<>();
+    private final HashMap<String, Integer> counts = new HashMap<>();
 
-    private List<String> stateNames;
+    private final List<String> stateNames;
 
     public CategoricalHistogramCounter(List<String> stateNames) {
         this.stateNames = stateNames;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/json/TDigestDeserializer.java

@@ -34,8 +34,8 @@ import java.io.ObjectInputStream;
 
 public class TDigestDeserializer extends JsonDeserializer<TDigest> {
     @Override
-    public TDigest deserialize(JsonParser jp, DeserializationContext d) throws IOException, JsonProcessingException {
+    public TDigest deserialize(JsonParser jp, DeserializationContext d) throws IOException {
-        JsonNode node = (JsonNode)jp.getCodec().readTree(jp);
+        JsonNode node = jp.getCodec().readTree(jp);
         String field = node.get("digest").asText();
         Base64 b = new Base64();
         byte[] bytes = b.decode(field);

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/json/TDigestSerializer.java

@@ -33,7 +33,7 @@ import java.io.ObjectOutputStream;
 
 public class TDigestSerializer extends JsonSerializer<TDigest> {
     @Override
-    public void serialize(TDigest td, JsonGenerator j, SerializerProvider sp) throws IOException, JsonProcessingException {
+    public void serialize(TDigest td, JsonGenerator j, SerializerProvider sp) throws IOException {
         try(ByteArrayOutputStream baos = new ByteArrayOutputStream(); ObjectOutputStream oos = new ObjectOutputStream(baos)){
             oos.writeObject(td);
             oos.close();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/bytes/BytesQualityAnalysisState.java

@@ -29,7 +29,7 @@ import org.datavec.api.writable.Writable;
 public class BytesQualityAnalysisState implements QualityAnalysisState<BytesQualityAnalysisState> {
 
     @Getter
-    private BytesQuality bytesQuality;
+    private final BytesQuality bytesQuality;
 
     public BytesQualityAnalysisState() {
         this.bytesQuality = new BytesQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/categorical/CategoricalQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class CategoricalQualityAnalysisState implements QualityAnalysisState<Cat
 
     @Getter
     private CategoricalQuality categoricalQuality;
-    private CategoricalQualityAddFunction addFunction;
+    private final CategoricalQualityAddFunction addFunction;
-    private CategoricalQualityMergeFunction mergeFunction;
+    private final CategoricalQualityMergeFunction mergeFunction;
 
     public CategoricalQualityAnalysisState(CategoricalMetaData integerMetaData) {
         this.categoricalQuality = new CategoricalQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/integer/IntegerQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class IntegerQualityAnalysisState implements QualityAnalysisState<Integer
 
     @Getter
     private IntegerQuality integerQuality;
-    private IntegerQualityAddFunction addFunction;
+    private final IntegerQualityAddFunction addFunction;
-    private IntegerQualityMergeFunction mergeFunction;
+    private final IntegerQualityMergeFunction mergeFunction;
 
     public IntegerQualityAnalysisState(IntegerMetaData integerMetaData) {
         this.integerQuality = new IntegerQuality(0, 0, 0, 0, 0);

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/longq/LongQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class LongQualityAnalysisState implements QualityAnalysisState<LongQualit
 
     @Getter
     private LongQuality longQuality;
-    private LongQualityAddFunction addFunction;
+    private final LongQualityAddFunction addFunction;
-    private LongQualityMergeFunction mergeFunction;
+    private final LongQualityMergeFunction mergeFunction;
 
     public LongQualityAnalysisState(LongMetaData longMetaData) {
         this.longQuality = new LongQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/real/RealQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class RealQualityAnalysisState implements QualityAnalysisState<RealQualit
 
     @Getter
     private DoubleQuality realQuality;
-    private RealQualityAddFunction addFunction;
+    private final RealQualityAddFunction addFunction;
-    private RealQualityMergeFunction mergeFunction;
+    private final RealQualityMergeFunction mergeFunction;
 
     public RealQualityAnalysisState(DoubleMetaData realMetaData) {
         this.realQuality = new DoubleQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/string/StringQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class StringQualityAnalysisState implements QualityAnalysisState<StringQu
 
     @Getter
     private StringQuality stringQuality;
-    private StringQualityAddFunction addFunction;
+    private final StringQualityAddFunction addFunction;
-    private StringQualityMergeFunction mergeFunction;
+    private final StringQualityMergeFunction mergeFunction;
 
     public StringQualityAnalysisState(StringMetaData stringMetaData) {
         this.stringQuality = new StringQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/quality/time/TimeQualityAnalysisState.java

@@ -31,8 +31,8 @@ public class TimeQualityAnalysisState implements QualityAnalysisState<TimeQualit
 
     @Getter
     private TimeQuality timeQuality;
-    private TimeQualityAddFunction addFunction;
+    private final TimeQualityAddFunction addFunction;
-    private TimeQualityMergeFunction mergeFunction;
+    private final TimeQualityMergeFunction mergeFunction;
 
     public TimeQualityAnalysisState(TimeMetaData timeMetaData) {
         this.timeQuality = new TimeQuality();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/analysis/sequence/SequenceLengthAnalysis.java

@@ -46,12 +46,11 @@ public class SequenceLengthAnalysis implements Serializable {
 
     @Override
     public String toString() {
-        StringBuilder sb = new StringBuilder();
+        String sb = "SequenceLengthAnalysis(" + "totalNumSequences=" + totalNumSequences +
-        sb.append("SequenceLengthAnalysis(").append("totalNumSequences=").append(totalNumSequences)
+                ",minSeqLength=" + minSeqLength + ",maxSeqLength=" + maxSeqLength +
-                        .append(",minSeqLength=").append(minSeqLength).append(",maxSeqLength=").append(maxSeqLength)
+                ",countZeroLength=" + countZeroLength + ",countOneLength=" +
-                        .append(",countZeroLength=").append(countZeroLength).append(",countOneLength=")
+                countOneLength + ",meanLength=" + meanLength + ")";
-                        .append(countOneLength).append(",meanLength=").append(meanLength).append(")");
+        return sb;
-        return sb.toString();
     }
 
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/BaseColumnCondition.java

@@ -92,7 +92,7 @@ public abstract class BaseColumnCondition implements ColumnCondition {
                 return false;
             case NoSequenceMode:
                 throw new IllegalStateException(
-                                "Column condition " + toString() + " does not support sequence execution");
+                                "Column condition " + this + " does not support sequence execution");
             default:
                 throw new RuntimeException("Unknown/not implemented sequence mode: " + sequenceMode);
         }
@@ -116,7 +116,7 @@ public abstract class BaseColumnCondition implements ColumnCondition {
                 return false;
             case NoSequenceMode:
                 throw new IllegalStateException(
-                                "Column condition " + toString() + " does not support sequence execution");
+                                "Column condition " + this + " does not support sequence execution");
             default:
                 throw new RuntimeException("Unknown/not implemented sequence mode: " + sequenceMode);
         }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/DoubleColumnCondition.java

@@ -42,7 +42,7 @@ public class DoubleColumnCondition extends BaseColumnCondition {
      * Uses default sequence condition mode, {@link BaseColumnCondition#DEFAULT_SEQUENCE_CONDITION_MODE}
      *
      * @param columnName Column to check for the condition
-     * @param op         Operation (<, >=, !=, etc)
+     * @param op         Operation {@code (<, >=, !=, etc)}
      * @param value      Value to use in the condition
      */
     public DoubleColumnCondition(String columnName, ConditionOp op, double value) {
@@ -54,7 +54,7 @@ public class DoubleColumnCondition extends BaseColumnCondition {
      *
      * @param column                Column to check for the condition
      * @param sequenceConditionMode Mode for handling sequence data
-     * @param op                    Operation (<, >=, !=, etc)
+     * @param op                    Operation {@code (<, >=, !=, etc)}
      * @param value                 Value to use in the condition
      */
     public DoubleColumnCondition(String column, SequenceConditionMode sequenceConditionMode, ConditionOp op,

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/FloatColumnCondition.java

@@ -42,7 +42,7 @@ public class FloatColumnCondition extends BaseColumnCondition {
      * Uses default sequence condition mode, {@link BaseColumnCondition#DEFAULT_SEQUENCE_CONDITION_MODE}
      *
      * @param columnName Column to check for the condition
-     * @param op         Operation (<, >=, !=, etc)
+     * @param op         Operation {@code (<, >=, !=, etc)}
      * @param value      Value to use in the condition
      */
     public FloatColumnCondition(String columnName, ConditionOp op, float value) {
@@ -54,7 +54,7 @@ public class FloatColumnCondition extends BaseColumnCondition {
      *
      * @param column                Column to check for the condition
      * @param sequenceConditionMode Mode for handling sequence data
-     * @param op                    Operation (<, >=, !=, etc)
+     * @param op                    Operation {@code (<, >=, !=, etc)}
      * @param value                 Value to use in the condition
      */
     public FloatColumnCondition(String column, SequenceConditionMode sequenceConditionMode, ConditionOp op,

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/IntegerColumnCondition.java

@@ -42,7 +42,7 @@ public class IntegerColumnCondition extends BaseColumnCondition {
      * Uses default sequence condition mode, {@link BaseColumnCondition#DEFAULT_SEQUENCE_CONDITION_MODE}
      *
      * @param columnName Column to check for the condition
-     * @param op         Operation (<, >=, !=, etc)
+     * @param op         Operation {@code (<, >=, !=, etc)}
      * @param value      Value to use in the condition
      */
     public IntegerColumnCondition(String columnName, ConditionOp op, int value) {
@@ -54,7 +54,7 @@ public class IntegerColumnCondition extends BaseColumnCondition {
      *
      * @param column                Column to check for the condition
      * @param sequenceConditionMode Mode for handling sequence data
-     * @param op                    Operation (<, >=, !=, etc)
+     * @param op                    Operation {@code (<, >=, !=, etc)}
      * @param value                 Value to use in the condition
      */
     public IntegerColumnCondition(String column, SequenceConditionMode sequenceConditionMode, ConditionOp op,

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/LongColumnCondition.java

@@ -42,7 +42,7 @@ public class LongColumnCondition extends BaseColumnCondition {
      * Uses default sequence condition mode, {@link BaseColumnCondition#DEFAULT_SEQUENCE_CONDITION_MODE}
      *
      * @param columnName Column to check for the condition
-     * @param op         Operation (<, >=, !=, etc)
+     * @param op         Operation {@code (<, >=, !=, etc)}
      * @param value      Value to use in the condition
      */
     public LongColumnCondition(String columnName, ConditionOp op, long value) {
@@ -54,7 +54,7 @@ public class LongColumnCondition extends BaseColumnCondition {
      *
      * @param column                Column to check for the condition
      * @param sequenceConditionMode Mode for handling sequence data
-     * @param op                    Operation (<, >=, !=, etc)
+     * @param op                    Operation {@code (<, >=, !=, etc)}
      * @param value                 Value to use in the condition
      */
     public LongColumnCondition(String column, SequenceConditionMode sequenceConditionMode, ConditionOp op, long value) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/condition/column/TimeColumnCondition.java

@@ -42,7 +42,7 @@ public class TimeColumnCondition extends BaseColumnCondition {
      * Uses default sequence condition mode, {@link BaseColumnCondition#DEFAULT_SEQUENCE_CONDITION_MODE}
      *
      * @param columnName Column to check for the condition
-     * @param op         Operation (<, >=, !=, etc)
+     * @param op         Operation {@code (<, >=, !=, etc)}
      * @param value      Time value (in epoch millisecond format) to use in the condition
      */
     public TimeColumnCondition(String columnName, ConditionOp op, long value) {
@@ -54,7 +54,7 @@ public class TimeColumnCondition extends BaseColumnCondition {
      *
      * @param column                Column to check for the condition
      * @param sequenceConditionMode Mode for handling sequence data
-     * @param op                    Operation (<, >=, !=, etc)
+     * @param op                    Operation {@code (<, >=, !=, etc)}
      * @param value                 Time value (in epoch millisecond format) to use in the condition
      */
     public TimeColumnCondition(String column, SequenceConditionMode sequenceConditionMode, ConditionOp op, long value) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/filter/FilterInvalidValues.java

@@ -111,24 +111,18 @@ public class FilterInvalidValues implements Filter {
     private boolean filterColumn(List<?> row, int i) {
         ColumnMetaData meta = schema.getMetaData(i);
         if (row.get(i) instanceof Float) {
-            if (!meta.isValid(new FloatWritable((Float) row.get(i))))
+            return !meta.isValid(new FloatWritable((Float) row.get(i)));
-                return true;
         } else if (row.get(i) instanceof Double) {
-            if (!meta.isValid(new DoubleWritable((Double) row.get(i))))
+            return !meta.isValid(new DoubleWritable((Double) row.get(i)));
-                return true;
         } else if (row.get(i) instanceof String) {
-            if (!meta.isValid(new Text(((String) row.get(i)).toString())))
+            return !meta.isValid(new Text(((String) row.get(i))));
-                return true;
         } else if (row.get(i) instanceof Integer) {
-            if (!meta.isValid(new IntWritable((Integer) row.get(i))))
+            return !meta.isValid(new IntWritable((Integer) row.get(i)));
-                return true;
 
         } else if (row.get(i) instanceof Long) {
-            if (!meta.isValid(new LongWritable((Long) row.get(i))))
+            return !meta.isValid(new LongWritable((Long) row.get(i)));
-                return true;
         } else if (row.get(i) instanceof Boolean) {
-            if (!meta.isValid(new BooleanWritable((Boolean) row.get(i))))
+            return !meta.isValid(new BooleanWritable((Boolean) row.get(i)));
-                return true;
         }
         return false;
     }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/join/Join.java

@@ -96,7 +96,7 @@ public class Join implements Serializable {
 
     public static class Builder {
 
-        private JoinType joinType;
+        private final JoinType joinType;
         private Schema leftSchema;
         private Schema rightSchema;
         private String[] joinColumnsLeft;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/BinaryMetaData.java

@@ -84,9 +84,8 @@ public class BinaryMetaData extends BaseColumnMetaData {
 
     @Override
     public String toString() {
-        StringBuilder sb = new StringBuilder();
+        String sb = "BinaryMetaData(name=\"" + name + "\"," +
-        sb.append("BinaryMetaData(name=\"").append(name).append("\",");
+                ")";
-        sb.append(")");
+        return sb;
-        return sb.toString();
     }
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/BooleanMetaData.java

@@ -84,9 +84,8 @@ public class BooleanMetaData extends BaseColumnMetaData {
 
     @Override
     public String toString() {
-        StringBuilder sb = new StringBuilder();
+        String sb = "BooleanMetaData(name=\"" + name + "\"," +
-        sb.append("BooleanMetaData(name=\"").append(name).append("\",");
+                ")";
-        sb.append(")");
+        return sb;
-        return sb.toString();
     }
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/DoubleMetaData.java

@@ -84,10 +84,7 @@ public class DoubleMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && d < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && d > maxAllowedValue)
+        return maxAllowedValue == null || !(d > maxAllowedValue);
-            return false;
-
-        return true;
     }
 
     /**
@@ -115,10 +112,7 @@ public class DoubleMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && d < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && d > maxAllowedValue)
+        return maxAllowedValue == null || !(d > maxAllowedValue);
-            return false;
-
-        return true;
     }
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/FloatMetaData.java

@@ -84,10 +84,7 @@ public class FloatMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && d < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && d > maxAllowedValue)
+        return maxAllowedValue == null || d <= maxAllowedValue;
-            return false;
-
-        return true;
     }
 
     /**
@@ -115,10 +112,7 @@ public class FloatMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && d < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && d > maxAllowedValue)
+        return maxAllowedValue == null || d <= maxAllowedValue;
-            return false;
-
-        return true;
     }
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/IntegerMetaData.java

@@ -65,9 +65,7 @@ public class IntegerMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && value < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && value > maxAllowedValue)
+        return maxAllowedValue == null || value <= maxAllowedValue;
-            return false;
-        return true;
     }
 
     /**
@@ -90,9 +88,7 @@ public class IntegerMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && value < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && value > maxAllowedValue)
+        return maxAllowedValue == null || value <= maxAllowedValue;
-            return false;
-        return true;
     }
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/metadata/LongMetaData.java

@@ -66,10 +66,7 @@ public class LongMetaData extends BaseColumnMetaData {
         }
         if (minAllowedValue != null && value < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && value > maxAllowedValue)
+        return maxAllowedValue == null || value <= maxAllowedValue;
-            return false;
-
-        return true;
     }
 
     /**
@@ -92,10 +89,7 @@ public class LongMetaData extends BaseColumnMetaData {
 
         if (minAllowedValue != null && value < minAllowedValue)
             return false;
-        if (maxAllowedValue != null && value > maxAllowedValue)
+        return maxAllowedValue == null || value <= maxAllowedValue;
-            return false;
-
-        return true;
     }
 
     @Override

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/ops/AggregatorImpls.java

@@ -97,9 +97,9 @@ public class AggregatorImpls {
             } else if (a instanceof Float || b instanceof Float) {
                 return new Float(a.floatValue() + b.floatValue());
             } else if (a instanceof Long || b instanceof Long) {
-                return new Long(a.longValue() + b.longValue());
+                return Long.valueOf(a.longValue() + b.longValue());
             } else {
-                return new Integer(a.intValue() + b.intValue());
+                return Integer.valueOf(a.intValue() + b.intValue());
             }
         }
 
@@ -146,9 +146,9 @@ public class AggregatorImpls {
             } else if (a instanceof Float || b instanceof Float) {
                 return new Float(a.floatValue() * b.floatValue());
             } else if (a instanceof Long || b instanceof Long) {
-                return new Long(a.longValue() * b.longValue());
+                return Long.valueOf(a.longValue() * b.longValue());
             } else {
-                return new Integer(a.intValue() * b.intValue());
+                return Integer.valueOf(a.intValue() * b.intValue());
             }
         }
 
@@ -347,7 +347,7 @@ public class AggregatorImpls {
      * of the square root of the arithmetic mean of squared differences to the mean, corrected with Bessel's correction.
      *
      * See <a href="https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation">https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation</a>
-     * This is computed with Welford's method for increased numerical stability & aggregability.
+     * This is computed with Welford's method for increased numerical stability &amp; aggregability.
      */
     public static class AggregableStdDev<T extends Number> implements IAggregableReduceOp<T, Writable> {
 
@@ -402,7 +402,7 @@ public class AggregatorImpls {
      * of the square root of the arithmetic mean of squared differences to the mean.
      *
      * See <a href="https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation">https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation</a>
-     * This is computed with Welford's method for increased numerical stability & aggregability.
+     * This is computed with Welford's method for increased numerical stability &amp; aggregability.
      */
     public static class AggregableUncorrectedStdDev<T extends Number> extends AggregableStdDev<T> {
 
@@ -418,7 +418,7 @@ public class AggregatorImpls {
      * of the arithmetic mean of squared differences to the mean, corrected with Bessel's correction.
      *
      * See <a href="https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation">https://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation</a>
-     * This is computed with Welford's method for increased numerical stability & aggregability.
+     * This is computed with Welford's method for increased numerical stability &amp; aggregability.
      */
     public static class AggregableVariance<T extends Number> implements IAggregableReduceOp<T, Writable> {
 
@@ -474,7 +474,7 @@ public class AggregatorImpls {
      * of the arithmetic mean of squared differences to the mean.
      *
      * See <a href="https://en.wikipedia.org/wiki/Variance#Population_variance_and_sample_variance">https://en.wikipedia.org/wiki/Variance#Population_variance_and_sample_variance</a>
-     * This is computed with Welford's method for increased numerical stability & aggregability.
+     * This is computed with Welford's method for increased numerical stability &amp; aggregability.
      */
     public static class AggregablePopulationVariance<T extends Number> extends AggregableVariance<T> {
 
@@ -491,7 +491,7 @@ public class AggregatorImpls {
      * <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
      *
      * The relative accuracy is approximately `1.054 / sqrt(2^p)`. Setting
-     * a nonzero `sp > p` in HyperLogLogPlus(p, sp) would trigger sparse
+     * a nonzero `sp &gt; p` in HyperLogLogPlus(p, sp) would trigger sparse
      * representation of registers, which may reduce the memory consumption
      * and increase accuracy when the cardinality is small.
      * @param <T>
@@ -501,7 +501,7 @@ public class AggregatorImpls {
 
         private float p = 0.05f;
         @Getter
-        private HyperLogLogPlus hll = new HyperLogLogPlus((int) Math.ceil(2.0 * Math.log(1.054 / p) / Math.log(2)), 0);
+        private final HyperLogLogPlus hll = new HyperLogLogPlus((int) Math.ceil(2.0 * Math.log(1.054 / p) / Math.log(2)), 0);
 
         public AggregableCountUnique(float precision) {
             this.p = precision;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/ops/DispatchWithConditionOp.java

@@ -36,7 +36,7 @@ public class DispatchWithConditionOp<U> extends DispatchOp<Writable, U>
 
     @Getter
     @NonNull
-    private List<Condition> conditions;
+    private final List<Condition> conditions;
 
 
     public DispatchWithConditionOp(List<IAggregableReduceOp<Writable, List<U>>> ops, List<Condition> conds) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/reduce/AggregableColumnReduction.java

@@ -37,14 +37,13 @@ public interface AggregableColumnReduction extends Serializable, ColumnOp {
      * and NOT the single row
      * (as is usually the case for {@code List<Writable>} instances
      *
-     * @param columnData The Writable objects for a column
      * @return Writable containing the reduced data
      */
     IAggregableReduceOp<Writable, List<Writable>> reduceOp();
 
     /**
      * Post-reduce: what is the name of the column?
-     * For example, "myColumn" -> "mean(myColumn)"
+     * For example, "myColumn" -&gt; "mean(myColumn)"
      *
      * @param columnInputName Name of the column before reduction
      * @return Name of the column after the reduction

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/reduce/ColumnReduction.java

@@ -43,7 +43,7 @@ public interface ColumnReduction extends Serializable, ColumnOp {
 
     /**
      * Post-reduce: what is the name of the column?
-     * For example, "myColumn" -> "mean(myColumn)"
+     * For example, "myColumn" -> "mean(myColumn)"
      *
      * @param columnInputName Name of the column before reduction
      * @return Name of the column after the reduction

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/reduce/Reducer.java

@@ -291,11 +291,11 @@ public class Reducer implements IAssociativeReducer {
 
     public static class Builder {
 
-        private ReduceOp defaultOp;
+        private final ReduceOp defaultOp;
-        private Map<String, List<ReduceOp>> opMap = new HashMap<>();
+        private final Map<String, List<ReduceOp>> opMap = new HashMap<>();
-        private Map<String, AggregableColumnReduction> customReductions = new HashMap<>();
+        private final Map<String, AggregableColumnReduction> customReductions = new HashMap<>();
-        private Map<String, ConditionalReduction> conditionalReductions = new HashMap<>();
+        private final Map<String, ConditionalReduction> conditionalReductions = new HashMap<>();
-        private Set<String> ignoreInvalidInColumns = new HashSet<>();
+        private final Set<String> ignoreInvalidInColumns = new HashSet<>();
         private String[] keyColumns;
 
 
@@ -480,7 +480,6 @@ public class Reducer implements IAssociativeReducer {
          * ignored/excluded.
          *
          * @param column     Name of the column to execute the conditional reduction on
-         * @param outputName Name of the column, after the reduction has been executed
          * @param reductions  Reductions to execute
          * @param condition  Condition to use in the reductions
          */
@@ -500,7 +499,6 @@ public class Reducer implements IAssociativeReducer {
          *
          * @param column     Name of the column to execute the conditional reduction on
          * @param outputName Name of the column, after the reduction has been executed
-         * @param reductions  Reductions to execute
          * @param condition  Condition to use in the reductions
          */
         public Builder conditionalReduction(String column, String outputName, ReduceOp reduction, Condition condition) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/reduce/impl/GeographicMidpointReduction.java

@@ -69,7 +69,7 @@ public class GeographicMidpointReduction implements AggregableColumnReduction {
 
     @Override
     public List<ColumnMetaData> getColumnOutputMetaData(List<String> newColumnName, ColumnMetaData columnInputMeta) {
-        return Collections.<ColumnMetaData>singletonList(new StringMetaData(newColumnName.get(0)));
+        return Collections.singletonList(new StringMetaData(newColumnName.get(0)));
     }
 
     @Override
@@ -111,7 +111,7 @@ public class GeographicMidpointReduction implements AggregableColumnReduction {
     public static class AverageCoordinateReduceOp implements IAggregableReduceOp<Writable, List<Writable>> {
         private static final double PI_180 = Math.PI / 180.0;
 
-        private String delim;
+        private final String delim;
 
         private double sumx;
         private double sumy;
@@ -186,7 +186,7 @@ public class GeographicMidpointReduction implements AggregableColumnReduction {
             Preconditions.checkState(!Double.isNaN(longDeg), "Final longitude is NaN");
 
             String str = latDeg + delim + longDeg;
-            return Collections.<Writable>singletonList(new Text(str));
+            return Collections.singletonList(new Text(str));
         }
     }
 }

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/schema/conversion/TypeConversion.java

@@ -24,7 +24,7 @@ import org.datavec.api.writable.Writable;
 
 public class TypeConversion {
 
-    private static TypeConversion SINGLETON = new TypeConversion();
+    private static final TypeConversion SINGLETON = new TypeConversion();
 
     private TypeConversion() {}
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/sequence/split/SplitMaxLengthSequence.java

@@ -44,7 +44,7 @@ public class SplitMaxLengthSequence implements SequenceSplit {
     /**
      * @param maxSequenceLength max length of sequences
      * @param equalSplits       if true: split larger sequences into equal sized subsequences. If false: split into
-     *                          n maxSequenceLength sequences, and (if necessary) 1 with 1 <= length < maxSequenceLength
+     *                          n maxSequenceLength sequences, and (if necessary) 1 with 1 &lt;= length &lt; maxSequenceLength
      */
     public SplitMaxLengthSequence(@JsonProperty("maxSequenceLength") int maxSequenceLength,
                     @JsonProperty("equalSplits") boolean equalSplits) {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/serde/BaseSerializer.java

@@ -295,7 +295,7 @@ public abstract class BaseSerializer {
 
     /**
      * Deserialize an IStringReducer List serialized using {@link #serializeReducerList(List)}, or
-     * an array serialized using {@link #serialize(IReducer[])}
+     * an array serialized using {@code #serialize(IReducer[])}
      *
      * @param str String representation (YAML/JSON) of the IStringReducer list
      * @return {@code List<IStringReducer>}

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/serde/JsonMappers.java

@@ -34,8 +34,8 @@ import com.fasterxml.jackson.datatype.joda.JodaModule;
 @Slf4j
 public class JsonMappers {
 
-    private static ObjectMapper jsonMapper;
+    private static final ObjectMapper jsonMapper;
-    private static ObjectMapper yamlMapper;
+    private static final ObjectMapper yamlMapper;
     private static ObjectMapper legacyMapper;       //For 1.0.0-alpha and earlier TransformProcess etc
 
     static {

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/serde/JsonSerializer.java

@@ -24,7 +24,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 
 public class JsonSerializer extends BaseSerializer {
 
-    private ObjectMapper om;
+    private final ObjectMapper om;
 
     public JsonSerializer() {
         this.om = JsonMappers.getMapper();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/serde/ListWrappers.java

@@ -37,7 +37,7 @@ public class ListWrappers {
 
     @Getter
     public static class TransformList {
-        private List<Transform> list;
+        private final List<Transform> list;
 
         public TransformList(@JsonProperty("list") List<Transform> list) {
             this.list = list;
@@ -46,7 +46,7 @@ public class ListWrappers {
 
     @Getter
     public static class FilterList {
-        private List<Filter> list;
+        private final List<Filter> list;
 
         public FilterList(@JsonProperty("list") List<Filter> list) {
             this.list = list;
@@ -55,7 +55,7 @@ public class ListWrappers {
 
     @Getter
     public static class ConditionList {
-        private List<Condition> list;
+        private final List<Condition> list;
 
         public ConditionList(@JsonProperty("list") List<Condition> list) {
             this.list = list;
@@ -64,7 +64,7 @@ public class ListWrappers {
 
     @Getter
     public static class ReducerList {
-        private List<IAssociativeReducer> list;
+        private final List<IAssociativeReducer> list;
 
         public ReducerList(@JsonProperty("list") List<IAssociativeReducer> list) {
             this.list = list;
@@ -73,7 +73,7 @@ public class ListWrappers {
 
     @Getter
     public static class SequenceComparatorList {
-        private List<SequenceComparator> list;
+        private final List<SequenceComparator> list;
 
         public SequenceComparatorList(@JsonProperty("list") List<SequenceComparator> list) {
             this.list = list;
@@ -82,7 +82,7 @@ public class ListWrappers {
 
     @Getter
     public static class DataActionList {
-        private List<DataAction> list;
+        private final List<DataAction> list;
 
         public DataActionList(@JsonProperty("list") List<DataAction> list) {
             this.list = list;

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/serde/YamlSerializer.java

@@ -24,7 +24,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 
 public class YamlSerializer extends BaseSerializer {
 
-    private ObjectMapper om;
+    private final ObjectMapper om;
 
     public YamlSerializer() {
         this.om = JsonMappers.getMapperYaml();

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/stringreduce/StringReducer.java

@@ -177,10 +177,10 @@ public class StringReducer implements IStringReducer {
 
     public static class Builder {
 
-        private StringReduceOp defaultOp;
+        private final StringReduceOp defaultOp;
-        private Map<String, StringReduceOp> opMap = new HashMap<>();
+        private final Map<String, StringReduceOp> opMap = new HashMap<>();
-        private Map<String, ColumnReduction> customReductions = new HashMap<>();
+        private final Map<String, ColumnReduction> customReductions = new HashMap<>();
-        private Set<String> ignoreInvalidInColumns = new HashSet<>();
+        private final Set<String> ignoreInvalidInColumns = new HashSet<>();
         private String outputColumnName;
         private List<String> inputColumns;
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/transform/BaseColumnTransform.java

@@ -80,7 +80,7 @@ public abstract class BaseColumnTransform extends BaseTransform implements Colum
         if (writables.size() != inputSchema.numColumns()) {
             throw new IllegalStateException("Cannot execute transform: input writables list length (" + writables.size()
                             + ") does not " + "match expected number of elements (schema: " + inputSchema.numColumns()
-                            + "). Transform = " + toString());
+                            + "). Transform = " + this);
         }
         int n = writables.size();
         List<Writable> out = new ArrayList<>(n);

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/transform/categorical/CategoricalToIntegerTransform.java

@@ -96,7 +96,7 @@ public class CategoricalToIntegerTransform extends BaseTransform {
         if (writables.size() != inputSchema.numColumns()) {
             throw new IllegalStateException("Cannot execute transform: input writables list length (" + writables.size()
                             + ") does not " + "match expected number of elements (schema: " + inputSchema.numColumns()
-                            + "). Transform = " + toString());
+                            + "). Transform = " + this);
         }
         int idx = getColumnIdx();
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/transform/categorical/CategoricalToOneHotTransform.java

@@ -123,7 +123,7 @@ public class CategoricalToOneHotTransform extends BaseTransform {
         if (writables.size() != inputSchema.numColumns()) {
             throw new IllegalStateException("Cannot execute transform: input writables list length (" + writables.size()
                             + ") does not " + "match expected number of elements (schema: " + inputSchema.numColumns()
-                            + "). Transform = " + toString());
+                            + "). Transform = " + this);
         }
         int idx = getColumnIdx();
 

cavis-datavec/cavis-datavec-api/src/main/java/org/datavec/api/transform/transform/categorical/IntegerToCategoricalTransform.java

@@ -89,7 +89,7 @@ public class IntegerToCategoricalTransform extends BaseColumnTransform {
 
         IntegerToCategoricalTransform o2 = (IntegerToCategoricalTransform) o;
 
-        return map != null ? map.equals(o2.map) : o2.map == null;
+        return Objects.equals(map, o2.map);
 
     }