de.lmu.ifi.dbs.elki.datasource.parser

Class SparseNumberVectorLabelParser<V extends SparseNumberVector>

java.lang.Object

de.lmu.ifi.dbs.elki.datasource.parser.AbstractStreamingParser

de.lmu.ifi.dbs.elki.datasource.parser.NumberVectorLabelParser<V>

de.lmu.ifi.dbs.elki.datasource.parser.SparseNumberVectorLabelParser<V>

Type Parameters:

V - vector type

All Implemented Interfaces:

BundleStreamSource, Parser, StreamingParser

Direct Known Subclasses:

LibSVMFormatParser

@Title(value="Sparse Vector Label Parser")
 @Description(value="Parser for the following line format:\nA single line provides a single point. Entries are separated by whitespace. The values will be parsed as floats (resulting in a set of SparseFloatVectors).\nA line is expected in the following format:\nThe first entry of each line is the number of attributes with coordinate value not zero. Subsequent entries are of the form (index, value), where index is the number of the corresponding dimension, and value is the value of the corresponding attribute. Any pair of two subsequent substrings not containing whitespace is tried to be read as int and float. If this fails for the first of the pair (interpreted ans index), it will be appended to a label. (Thus, any label must not be parseable as Integer.) If the float component is not parseable, an exception will be thrown. Empty lines and lines beginning with \"#\" will be ignored.")
public class SparseNumberVectorLabelParser<V extends SparseNumberVector>
extends NumberVectorLabelParser<V>

Parser for parsing one point per line, attributes separated by whitespace.

Several labels may be given per point. A label must not be parseable as double. Lines starting with "#" will be ignored.

A line is expected in the following format: The first entry of each line is the number of attributes with coordinate value not zero. Subsequent entries are of the form index value each, where index is the number of the corresponding dimension, and value is the value of the corresponding attribute. A complete line then could look like this:

 3 7 12.34 8 56.78 11 1.234 objectlabel
 

where 3 indicates there are three attributes set, 7,8,11 are the attributes indexes and there is a non-numerical object label.

An index can be specified to identify an entry to be treated as class label. This index counts all entries (numeric and labels as well) starting with 0.

Since:

0.2

Author:

Arthur Zimek

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SparseNumberVectorLabelParser.Parameterizer<V extends SparseNumberVector> Parameterization class.

Nested classes/interfaces inherited from interface de.lmu.ifi.dbs.elki.datasource.bundle.BundleStreamSource

BundleStreamSource.Event

Field Summary

Fields

Modifier and Type	Field and Description
(package private) java.util.ArrayList<java.lang.String>	labels (Reused) label buffer.
private static Logging	LOG Class logger.
protected SparseNumberVector.Factory<V>	sparsefactory Same as NumberVectorLabelParser.factory, but subtype.
(package private) it.unimi.dsi.fastutil.ints.Int2DoubleOpenHashMap	values (Reused) set of values for the number vector.

Fields inherited from class de.lmu.ifi.dbs.elki.datasource.parser.NumberVectorLabelParser

attributes, columnnames, curlbl, curvec, factory, haslabels, maxdim, meta, mindim, nextevent, unique, warnedPrecision

Fields inherited from class de.lmu.ifi.dbs.elki.datasource.parser.AbstractStreamingParser

reader, tokenizer

Constructor Summary

Constructors

Constructor and Description
SparseNumberVectorLabelParser(CSVReaderFormat format, long[] labelIndices, SparseNumberVector.Factory<V> factory) Constructor.
SparseNumberVectorLabelParser(java.util.regex.Pattern colSep, java.lang.String quoteChars, java.util.regex.Pattern comment, long[] labelIndices, SparseNumberVector.Factory<V> factory) Constructor.

Method Summary

Modifier and Type	Method and Description
protected Logging	getLogger() Get the logger for this class.
protected SimpleTypeInformation<V>	getTypeInformation(int mindim, int maxdim) Get a prototype object for the given dimensionality.
protected boolean	parseLineInternal() Internal method for parsing a single line.

Methods inherited from class de.lmu.ifi.dbs.elki.datasource.parser.NumberVectorLabelParser

buildMeta, cleanup, createVector, data, getMeta, initStream, isLabelColumn, nextEvent

Methods inherited from class de.lmu.ifi.dbs.elki.datasource.parser.AbstractStreamingParser

asMultipleObjectsBundle, assignDBID, hasDBIDs, parse

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LOG

private static final Logging LOG

Class logger.

sparsefactory

protected SparseNumberVector.Factory<V extends SparseNumberVector> sparsefactory

Same as NumberVectorLabelParser.factory, but subtype.

values

it.unimi.dsi.fastutil.ints.Int2DoubleOpenHashMap values

(Reused) set of values for the number vector.

labels

java.util.ArrayList<java.lang.String> labels

(Reused) label buffer.

Constructor Detail

SparseNumberVectorLabelParser

public SparseNumberVectorLabelParser(CSVReaderFormat format,
                                     long[] labelIndices,
                                     SparseNumberVector.Factory<V> factory)

Constructor.

Parameters:

format - Input format

labelIndices - Indices to use as labels

factory - Vector factory

SparseNumberVectorLabelParser

public SparseNumberVectorLabelParser(java.util.regex.Pattern colSep,
                                     java.lang.String quoteChars,
                                     java.util.regex.Pattern comment,
                                     long[] labelIndices,
                                     SparseNumberVector.Factory<V> factory)

Constructor.

Parameters:

colSep - Column separator

quoteChars - Quotation character

comment - Comment pattern

labelIndices - Indices to use as labels

factory - Vector factory

Method Detail

parseLineInternal

protected boolean parseLineInternal()

Description copied from class: NumberVectorLabelParser

Internal method for parsing a single line. Used by both line based parsing as well as block parsing. This saves the building of meta data for each line.

Overrides:

parseLineInternal in class NumberVectorLabelParser<V extends SparseNumberVector>

Returns:

true when a valid line was read, false on a label row.

getTypeInformation

protected SimpleTypeInformation<V> getTypeInformation(int mindim,
                                                      int maxdim)

Description copied from class: NumberVectorLabelParser

Get a prototype object for the given dimensionality.

Overrides:

getTypeInformation in class NumberVectorLabelParser<V extends SparseNumberVector>

Parameters:

mindim - Minimum dimensionality

maxdim - Maximum dimensionality

Returns:

Prototype object

getLogger

protected Logging getLogger()

Description copied from class: AbstractStreamingParser

Get the logger for this class.

Overrides:

getLogger in class NumberVectorLabelParser<V extends SparseNumberVector>

Returns:

Logger.