org.deeplearning4j.util

Class StringGrid

java.lang.Object

java.util.AbstractCollection<E>

java.util.AbstractList<E>

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

org.deeplearning4j.util.StringGrid

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, java.lang.Iterable<java.util.List<java.lang.String>>, java.util.Collection<java.util.List<java.lang.String>>, java.util.List<java.util.List<java.lang.String>>, java.util.RandomAccess

public class StringGrid
extends java.util.ArrayList<java.util.List<java.lang.String>>

String matrix

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	NONE

Fields inherited from class java.util.AbstractList

modCount

Constructor Summary

Constructors

Constructor and Description
StringGrid(java.lang.String sep, java.util.Collection<java.lang.String> data)
StringGrid(StringGrid grid)
StringGrid(java.lang.String sep, int numColumns)

Method Summary

Modifier and Type	Method and Description
void	addColumn(java.util.List<java.lang.String> column)
void	addRow(java.util.List<java.lang.String> row)
void	appendToEach(java.lang.String append, int toColumn)
StringCluster	clusterColumn(int column)
void	combineColumns(int templateColumn, int[] paramColumns) Combine the column based on a template and a number of template variable columns.
void	combineColumns(int templateColumn, java.lang.Integer[] paramColumns) Combine the column based on a template and a number of template variable columns.
void	dedupeByCluster(int column) Deduplicate based on the column clustering signature
void	dedupeByClusterAll()
void	fillDown(java.lang.String value, int column)
void	filterBySimilarity(double threshold, int firstColumn, int secondColumn)
java.util.List<java.lang.Integer>	filterRowsByColumn(int column, java.util.Collection<java.lang.String> values)
static StringGrid	fromFile(java.lang.String file, java.lang.String sep)
static StringGrid	fromInput(java.io.InputStream from, java.lang.String sep)
StringGrid	getAllWithSimilarity(double threshold, int firstColumn, int secondColumn)
java.util.List<java.lang.String>	getColumn(int column)
int	getNumColumns()
java.util.List<java.lang.String>	getRow(int row)
java.util.List<java.util.List<java.lang.String>>	getRowsWithColumnValues(java.util.Collection<java.lang.String> values, int column)
StringGrid	getRowsWithDuplicateValuesInColumn(int column)
StringGrid	getRowWithOnlyOneOccurrence(int column)
StringGrid	getUniqueRows()
void	head(int num)
java.util.Map<java.lang.String,java.util.List<java.util.List<java.lang.String>>>	mapByPrimaryKey(int columnKey)
void	merge(int column1, int column2)
void	prependToEach(java.lang.String prepend, int toColumn)
void	removeColumns(java.lang.Integer... columns) Removes the specified columns from the grid
void	removeRowsWithEmptyColumn(int column) Removes all rows with a column of NONE
void	removeRowsWithEmptyColumn(int column, java.lang.String missingValue) Removes all rows with a column of missingValue
StringGrid	select(int column, java.lang.String value)
void	sortBy(int column)
void	sortColumnsByWordLikelihoodIncluded(int column)
void	split(int column, java.lang.String sepBy)
void	stripDuplicateRows()
void	swap(int column1, int column2)
java.util.List<java.lang.String>	toLines()
void	writeLinesTo(java.lang.String path)

Methods inherited from class java.util.ArrayList

add, add, addAll, addAll, clear, clone, contains, ensureCapacity, forEach, get, indexOf, isEmpty, iterator, lastIndexOf, listIterator, listIterator, remove, remove, removeAll, removeIf, removeRange, replaceAll, retainAll, set, size, sort, spliterator, subList, toArray, toArray, trimToSize

Methods inherited from class java.util.AbstractList

equals, hashCode

Methods inherited from class java.util.AbstractCollection

containsAll, toString

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface java.util.List

containsAll, equals, hashCode

Methods inherited from interface java.util.Collection

parallelStream, stream

Field Detail

NONE

public static final java.lang.String NONE

See Also:

Constant Field Values

Constructor Detail

StringGrid

public StringGrid(StringGrid grid)

StringGrid

public StringGrid(java.lang.String sep,
                  int numColumns)

StringGrid

public StringGrid(java.lang.String sep,
                  java.util.Collection<java.lang.String> data)

Method Detail

getNumColumns

public int getNumColumns()

fromFile

public static StringGrid fromFile(java.lang.String file,
                                  java.lang.String sep)
                           throws java.io.IOException

Throws:

java.io.IOException

fromInput

public static StringGrid fromInput(java.io.InputStream from,
                                   java.lang.String sep)
                            throws java.io.IOException

Throws:

java.io.IOException

removeRowsWithEmptyColumn

public void removeRowsWithEmptyColumn(int column)

Removes all rows with a column of NONE

Parameters:

column - the column to remove by

head

public void head(int num)

removeColumns

public void removeColumns(java.lang.Integer... columns)

Removes the specified columns from the grid

Parameters:

columns - the columns to remove

removeRowsWithEmptyColumn

public void removeRowsWithEmptyColumn(int column,
                                      java.lang.String missingValue)

Removes all rows with a column of missingValue

Parameters:

column - he column to remove by

missingValue - the missingValue sentinel value

getRowsWithColumnValues

public java.util.List<java.util.List<java.lang.String>> getRowsWithColumnValues(java.util.Collection<java.lang.String> values,
                                                                                int column)

sortColumnsByWordLikelihoodIncluded

public void sortColumnsByWordLikelihoodIncluded(int column)

clusterColumn

public StringCluster clusterColumn(int column)

dedupeByClusterAll

public void dedupeByClusterAll()

dedupeByCluster

public void dedupeByCluster(int column)

Deduplicate based on the column clustering signature

Parameters:

column -

filterRowsByColumn

public java.util.List<java.lang.Integer> filterRowsByColumn(int column,
                                                            java.util.Collection<java.lang.String> values)

sortBy

public void sortBy(int column)

toLines

public java.util.List<java.lang.String> toLines()

swap

public void swap(int column1,
                 int column2)

merge

public void merge(int column1,
                  int column2)

getAllWithSimilarity

public StringGrid getAllWithSimilarity(double threshold,
                                       int firstColumn,
                                       int secondColumn)

writeLinesTo

public void writeLinesTo(java.lang.String path)
                  throws java.io.IOException

Throws:

java.io.IOException

fillDown

public void fillDown(java.lang.String value,
                     int column)

select

public StringGrid select(int column,
                         java.lang.String value)

split

public void split(int column,
                  java.lang.String sepBy)

filterBySimilarity

public void filterBySimilarity(double threshold,
                               int firstColumn,
                               int secondColumn)

prependToEach

public void prependToEach(java.lang.String prepend,
                          int toColumn)

appendToEach

public void appendToEach(java.lang.String append,
                         int toColumn)

addColumn

public void addColumn(java.util.List<java.lang.String> column)

combineColumns

public void combineColumns(int templateColumn,
                           java.lang.Integer[] paramColumns)

Combine the column based on a template and a number of template variable columns. Note that this will also collapse the columns specified (removing them)

Parameters:

templateColumn - the column with the template ( uses printf style templating)

paramColumns - the columns with template variables

combineColumns

public void combineColumns(int templateColumn,
                           int[] paramColumns)

Combine the column based on a template and a number of template variable columns. Note that this will also collapse the columns specified (removing them)

Parameters:

templateColumn - the column with the template ( uses printf style templating)

paramColumns - the columns with template variables

addRow

public void addRow(java.util.List<java.lang.String> row)

mapByPrimaryKey

public java.util.Map<java.lang.String,java.util.List<java.util.List<java.lang.String>>> mapByPrimaryKey(int columnKey)

getRow

public java.util.List<java.lang.String> getRow(int row)

getColumn

public java.util.List<java.lang.String> getColumn(int column)

getRowsWithDuplicateValuesInColumn

public StringGrid getRowsWithDuplicateValuesInColumn(int column)

getRowWithOnlyOneOccurrence

public StringGrid getRowWithOnlyOneOccurrence(int column)

getUniqueRows

public StringGrid getUniqueRows()

stripDuplicateRows

public void stripDuplicateRows()