DeepLearningPolarityClassifier

Instance Constructors

new DeepLearningPolarityClassifier()

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
var CEM_DIMENSIONS: Int
val CONTROLLED: String
val CONTROLLER: String
var HIDDEN_SIZE: Int
var IS_DYNET_INITIALIZED: Boolean
var MLP_HIDDEN_SIZE: Int
var NUM_LAYERS: Int
var N_EPOCH: Int
val THEME: String
var VOC_SIZE: Int
var WEM_DIMENSIONS: Int
final def asInstanceOf[T0]: T0

Definition Classes
Any
val builderBwd: LstmBuilder
val builderFwd: LstmBuilder
val c2i: Map[Char, Int]
var c2iPath: String
val c2v_cemb: LookupParameter
val charBwRnnBuilder: LstmBuilder
val charFwRnnBuilder: LstmBuilder
def charToIndex(w2v_voc: Map[String, Int], special_voc: Map[String, Int]): Map[Char, Int]
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val config: Config
val configPath: String
var dynetBlockMem: String
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def fit(trainingPath: String = spreadsheetPath, trainRatio: Float = 0.8.toFloat, saveFlag: Boolean = true): Unit

Trains the classifier.
Trains the classifier. This method is meant to have side effects by fitting the parameters
trainingPath
Training data
trainRatio
Ratio of training samples in the dataset

Definition Classes
DeepLearningPolarityClassifier → PolarityClassifier
def fitSingleEpoch(input_sens: Seq[(Seq[String], Int)], labels: Seq[Int]): Unit
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getExpandBound(event: BioEventMention, controller_start: Int, controlled_start: Int): (Int, Int)
def getIntervalRecursively(theme: Mention, mention: Mention): (Boolean, Int, Int)
def getPrecisionRecallF1(predLabels: Seq[Int], trueLabels: Seq[Int]): (Float, Float, Float)
def hashCode(): Int

Definition Classes
AnyRef → Any
def initializeDyNet(mem: String = ""): Unit
def isFitted: Boolean

Returns whether fit has been called before.
Returns whether fit has been called before. Mostly for control
returns
True if the parameters of the model have been fit previously

Definition Classes
DeepLearningPolarityClassifier → PolarityClassifier
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def loadModelEval(trainingPath: String = spreadsheetPath, trainRatio: Float = 0.8.toFloat): Float
lazy val logger: Logger

Attributes
protected
Definition Classes
LazyLogging
var loss: Float
def maskDirect(lemmas: Array[String], maskOption: String, role: String, intervalStart: Int, intervalEnd: Int): Array[String]
def maskEvent(lemmas_raw: Array[String], event: BioEventMention, maskOption: String): Array[String]
var maskOption: String
def maskRecursively(lemmas: Array[String], mention: Mention, maskOption: String, role: String): Array[String]
val missing_charVec: FloatVector
val missing_vec: FloatVector
def mkCharEmbedding(word: String): Expression
def mkEmbedding(word: String): Expression
def mkVocabs(spreadSheetPath: String): (Map[String, Int], Map[Char, Int])
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val p_W: Parameter
val p_b: Parameter
val pc: ParameterCollection
def predict(event: BioEventMention): Polarity

Convenience overload to predict a single instance
Convenience overload to predict a single instance
event
to get its polarity predicted
returns
polarity of the argument

Definition Classes
DeepLearningPolarityClassifier → PolarityClassifier
def predict(events: Seq[BioEventMention]): Seq[Polarity]

Gets the predicted polarity for the provided argument
Gets the predicted polarity for the provided argument
events
Ordered sequence of events to get their polarity from
returns
Predictions of Polarity subclasses

Definition Classes
DeepLearningPolarityClassifier → PolarityClassifier
def predictManual(event: String, rulePolarity: Int): Unit
def readFromCsv2Map(filename: String): Map[String, Int]
def readFromSpreadsheet(spreadsheetPath: String, train_ratio: Float, mask_option: String = "tag_name"): (Seq[(Seq[String], Int)], Seq[Int], Seq[(Seq[String], Int)], Seq[Int])
def runInstance(words: Seq[String], rulePolarityNum: Int): Expression
def save(modelPath: String = savedModelPath, w2iPath: String = w2iPath, c2iPath: String = c2iPath): Unit

Saves the model parameter's to a file
Saves the model parameter's to a file
modelPath
file path to save the model to.

Definition Classes
DeepLearningPolarityClassifier → PolarityClassifier
var savedModelPath: String
val sgd: AdamTrainer
var spreadsheetPath: String
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def testSingleEpoch(input_sens: Seq[(Seq[String], Int)], labels: Seq[Int]): Float
def toString(): String

Definition Classes
AnyRef → Any
def transduce(embeddings: Iterable[Expression], builder: RnnBuilder): Iterable[Expression]
val w2i: Map[String, Int]
var w2iPath: String
val w2v_wemb_lp: LookupParameter
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
def writeMap2Csv(inputMap: Map[String, Int], filename: String): Unit

Related Docs: object DeepLearningPolarityClassifier | package ml

class DeepLearningPolarityClassifier extends PolarityClassifier

Instance Constructors

new DeepLearningPolarityClassifier()

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

var CEM_DIMENSIONS: Int

val CONTROLLED: String

val CONTROLLER: String

var HIDDEN_SIZE: Int

var IS_DYNET_INITIALIZED: Boolean

var MLP_HIDDEN_SIZE: Int

var NUM_LAYERS: Int

var N_EPOCH: Int

val THEME: String

var VOC_SIZE: Int

var WEM_DIMENSIONS: Int

final def asInstanceOf[T0]: T0

val builderBwd: LstmBuilder

val builderFwd: LstmBuilder

val c2i: Map[Char, Int]

var c2iPath: String

val c2v_cemb: LookupParameter

val charBwRnnBuilder: LstmBuilder

val charFwRnnBuilder: LstmBuilder

def charToIndex(w2v_voc: Map[String, Int], special_voc: Map[String, Int]): Map[Char, Int]

def clone(): AnyRef

val config: Config

val configPath: String

var dynetBlockMem: String

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

def fit(trainingPath: String = spreadsheetPath, trainRatio: Float = 0.8.toFloat, saveFlag: Boolean = true): Unit

def fitSingleEpoch(input_sens: Seq[(Seq[String], Int)], labels: Seq[Int]): Unit

final def getClass(): Class[_]

def getExpandBound(event: BioEventMention, controller_start: Int, controlled_start: Int): (Int, Int)

def getIntervalRecursively(theme: Mention, mention: Mention): (Boolean, Int, Int)

def getPrecisionRecallF1(predLabels: Seq[Int], trueLabels: Seq[Int]): (Float, Float, Float)

def hashCode(): Int

def initializeDyNet(mem: String = ""): Unit

def isFitted: Boolean

final def isInstanceOf[T0]: Boolean

def loadModelEval(trainingPath: String = spreadsheetPath, trainRatio: Float = 0.8.toFloat): Float

lazy val logger: Logger

var loss: Float

def maskDirect(lemmas: Array[String], maskOption: String, role: String, intervalStart: Int, intervalEnd: Int): Array[String]

def maskEvent(lemmas_raw: Array[String], event: BioEventMention, maskOption: String): Array[String]

var maskOption: String

def maskRecursively(lemmas: Array[String], mention: Mention, maskOption: String, role: String): Array[String]

val missing_charVec: FloatVector

val missing_vec: FloatVector

def mkCharEmbedding(word: String): Expression

def mkEmbedding(word: String): Expression

def mkVocabs(spreadSheetPath: String): (Map[String, Int], Map[Char, Int])

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val p_W: Parameter

val p_b: Parameter

val pc: ParameterCollection

def predict(event: BioEventMention): Polarity

def predict(events: Seq[BioEventMention]): Seq[Polarity]

def predictManual(event: String, rulePolarity: Int): Unit

def readFromCsv2Map(filename: String): Map[String, Int]

def readFromSpreadsheet(spreadsheetPath: String, train_ratio: Float, mask_option: String = "tag_name"): (Seq[(Seq[String], Int)], Seq[Int], Seq[(Seq[String], Int)], Seq[Int])

def runInstance(words: Seq[String], rulePolarityNum: Int): Expression

def save(modelPath: String = savedModelPath, w2iPath: String = w2iPath, c2iPath: String = c2iPath): Unit

var savedModelPath: String

val sgd: AdamTrainer

var spreadsheetPath: String

final def synchronized[T0](arg0: ⇒ T0): T0

def testSingleEpoch(input_sens: Seq[(Seq[String], Int)], labels: Seq[Int]): Float

def toString(): String

def transduce(embeddings: Iterable[Expression], builder: RnnBuilder): Iterable[Expression]

val w2i: Map[String, Int]

var w2iPath: String