org.deeplearning4j.text.movingwindow

Class Windows

java.lang.Object

org.deeplearning4j.text.movingwindow.Windows

public class Windows
extends Object

Static utility class for textual based windowing cooccurrences

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
static Window	windowForWordInPosition(int windowSize, int wordPos, List<String> sentence) Creates a sliding window from text
static List<Window>	windows(InputStream words, int windowSize) Constructs a list of window of size windowSize.
static List<Window>	windows(InputStream words, TokenizerFactory tokenizerFactory, int windowSize) Constructs a list of window of size windowSize.
static List<Window>	windows(List<String> words, int windowSize) Constructs a list of window of size windowSize
static List<Window>	windows(String words) Constructs a list of window of size windowSize.
static List<Window>	windows(String words, int windowSize) Constructs a list of window of size windowSize.
static List<Window>	windows(String words, TokenizerFactory tokenizerFactory) Constructs a list of window of size windowSize.
static List<Window>	windows(String words, TokenizerFactory tokenizerFactory, int windowSize, WordVectors vectors) Constructs a list of window of size windowSize.

Methods inherited from class java.lang.Object

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

Method Detail

windows

public static List<Window> windows(InputStream words,
                                   int windowSize)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

windowSize - the window size to generate

Returns:

the list of windows for the tokenized string

windows

public static List<Window> windows(InputStream words,
                                   TokenizerFactory tokenizerFactory,
                                   int windowSize)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

tokenizerFactory - tokenizer factory to use

windowSize - the window size to generate

Returns:

the list of windows for the tokenized string

windows

public static List<Window> windows(String words,
                                   int windowSize)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

windowSize - the window size to generate

Returns:

the list of windows for the tokenized string

windows

public static List<Window> windows(String words,
                                   @NonNull
                                   TokenizerFactory tokenizerFactory,
                                   int windowSize,
                                   WordVectors vectors)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

tokenizerFactory - tokenizer factory to use

windowSize - the window size to generate

Returns:

the list of windows for the tokenized string

windows

public static List<Window> windows(String words)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

Returns:

the list of windows for the tokenized string

windows

public static List<Window> windows(String words,
                                   TokenizerFactory tokenizerFactory)

Constructs a list of window of size windowSize. Note that padding for each window is created as well.

Parameters:

words - the words to tokenize and construct windows from

tokenizerFactory - tokenizer factory to use

Returns:

the list of windows for the tokenized string

windowForWordInPosition

public static Window windowForWordInPosition(int windowSize,
                                             int wordPos,
                                             List<String> sentence)

Creates a sliding window from text

Parameters:

windowSize - the window size to use

wordPos - the position of the word to center

sentence - the sentence to createComplex a window for

Returns:

a window based on the given sentence

windows

public static List<Window> windows(List<String> words,
                                   int windowSize)

Constructs a list of window of size windowSize

Parameters:

words - the words to construct windows from

Returns:

the list of windows for the tokenized string