A
- DocumentInterface::applyTransformation() — Method in class DocumentInterface
- Apply the transformation to the data of this document.
- RawDocument::applyTransformation() — Method in class RawDocument
- Apply the transformation to the data of this document.
- TokensDocument::applyTransformation() — Method in class TokensDocument
- Apply the transformation to the data of this document.
- TrainingDocument::applyTransformation() — Method in class TrainingDocument
- Pass the transformation to the decorated document
- TrainingSet::addDocument() — Method in class TrainingSet
- Add a document to the set.
- TrainingSet::applyTransformations() — Method in class TrainingSet
- Apply an array of transformations to all documents in this container.
- WordDocument::applyTransformation() — Method in class WordDocument
- Apply the transformation to the data of this document.
- FunctionFeatures::add() — Method in class FunctionFeatures
- Add a function as a feature
- AbstractDistribution — Class in namespace NlpTools\Random\Distributions
C
- ClassifierInterface — Class in namespace NlpTools\Classifiers
- ClassifierInterface::classify() — Method in class ClassifierInterface
- Decide in which class C member of $classes would $d fit best.
- FeatureBasedLinearClassifier::classify() — Method in class FeatureBasedLinearClassifier
- Compute the vote for every class.
- MultinomialNBClassifier::classify() — Method in class MultinomialNBClassifier
- Compute the probability of $d belonging to each class successively and return that class that has the maximum probability.
- CentroidFactoryInterface — Class in namespace NlpTools\Clustering\CentroidFactories
- Clusterer — Class in namespace NlpTools\Clustering
- Clusterer::cluster() — Method in class Clusterer
- Group the documents together
- Hierarchical::cluster() — Method in class Hierarchical
- Group the documents together
- KMeans::cluster() — Method in class KMeans
- Apply the feature factory to the documents and then cluster the resulting array using the provided distance metric and centroid factory.
- CompleteLink — Class in namespace NlpTools\Clustering\MergeStrategies
- In single linkage clustering the new distance of the merged cluster with cluster i is the maximum distance of either cluster x to i or y to i.
- TrainingSet::current() — Method in class TrainingSet
- TrainingSet::count() — Method in class TrainingSet
- Maxent::CLogLik() — Method in class Maxent
- Not implemented yet.
- CosineSimilarity — Class in namespace NlpTools\Similarity
- Given two vectors compute cos(theta) where theta is the angle between the two vectors in a N-dimensional vector space.
- ClassifierBasedTokenizer — Class in namespace NlpTools\Tokenizers
- A tokenizer that uses a classifier (of any type) to determine if there is an "end of word" (EOW).
- ClassifierBasedTransformation — Class in namespace NlpTools\Utils
- Classify whatever is passed in the transform and pass it a different set of transformations based on the class.
D
- Hierarchical::dendrogramToClusters() — Method in class Hierarchical
- Flatten a dendrogram to an almost specific number of clusters (the closest power of 2 larger than $NC)
- DocumentInterface — Class in namespace NlpTools\Documents
- A Document is a representation of a Document to be classified.
- DataAsFeatures — Class in namespace NlpTools\FeatureFactories
- Maxent::dumpWeights() — Method in class Maxent
- Simply print_r weights.
- Dirichlet — Class in namespace NlpTools\Random\Distributions
- Implement a k-dimensional Dirichlet distribution using draws from k gamma distributions and then normalizing.
- CosineSimilarity::dist() — Method in class CosineSimilarity
- DistanceInterface — Class in namespace NlpTools\Similarity
- Distance should return a number proportional to how dissimilar the two instances are(with any metric)
- DistanceInterface::dist() — Method in class DistanceInterface
- Euclidean::dist() — Method in class Euclidean
- HammingDistance::dist() — Method in class HammingDistance
- JaccardIndex::dist() — Method in class JaccardIndex
- Simhash::dist() — Method in class Simhash
E
- Euclidean — Class in namespace NlpTools\Clustering\CentroidFactories
- Computes the euclidean centroid of the provided sparse vectors
- ExternalMaxentOptimizer — Class in namespace NlpTools\Optimizers
- This class enables the use of a program written in a different language to optimize our model and return the weights for use in php.
- Euclidean — Class in namespace NlpTools\Similarity
- This class computes the very simple euclidean distance between two vectors ( sqrt(sum((a_i-b_i)^2)) ).
- EnglishVowels — Class in namespace NlpTools\Utils
- Helper Vowel class, determines if the character at a given index is a vowel
- English — Class in namespace NlpTools\Utils\Normalizers
- For English we simply transform to lower case using mb_strtolower.
F
- FreqDist — Class in namespace NlpTools\Analysis
- Extract the Frequency distribution of keywords
- FeatureBasedLinearClassifier — Class in namespace NlpTools\Classifiers
- Classify using a linear model.
- FeatureFactoryInterface — Class in namespace NlpTools\FeatureFactories
- FunctionFeatures — Class in namespace NlpTools\FeatureFactories
- An implementation of FeatureFactoryInterface that takes any number of callables (function names, closures, array($object,'func_name'), etc.) and calls them consecutively using the return value as a feature's unique string.
- FeatureBasedNB — Class in namespace NlpTools\Models
- Implement a MultinomialNBModel by training on a TrainingSet with a FeatureFactoryInterface and additive smoothing.
- FeatureBasedLinearOptimizerInterface — Class in namespace NlpTools\Optimizers
- FromFile — Class in namespace NlpTools\Random\Generators
- Return floats from a file.
- Normalizer::factory() — Method in class Normalizer
- Just instantiate the normalizer using a factory method.
- VowelsAbstractFactory::factory() — Method in class VowelsAbstractFactory
- Return the correct language vowel checker
G
- FreqDist::getTotalTokens() — Method in class FreqDist
- Get the total number of tokens in this tokensDocument
- FreqDist::getWeightPerToken() — Method in class FreqDist
- Return the weight of a single token
- FreqDist::getTotalUniqueTokens() — Method in class FreqDist
- Return get the total number of unique tokens
- FreqDist::getKeys() — Method in class FreqDist
- Return the sorted keys by frequency desc
- FreqDist::getValues() — Method in class FreqDist
- Return the sorted values by frequency desc
- FreqDist::getKeyValues() — Method in class FreqDist
- Return the full key value store
- FreqDist::getHapaxes() — Method in class FreqDist
- Returns an array of tokens that occurred once
- FeatureBasedLinearClassifier::getVote() — Method in class FeatureBasedLinearClassifier
- Compute the features that fire for the Document $d.
- MultinomialNBClassifier::getScore() — Method in class MultinomialNBClassifier
- Compute the log of the probability of the Document $d belonging to class $class.
- CentroidFactoryInterface::getCentroid() — Method in class CentroidFactoryInterface
- Parse the provided docs and create a doc that given a metric of distance is the centroid of the provided docs.
- Euclidean::getCentroid() — Method in class Euclidean
- Parse the provided docs and create a doc that given a metric of distance is the centroid of the provided docs.
- Hamming::getCentroid() — Method in class Hamming
- Parse the provided docs and create a doc that given a metric of distance is the centroid of the provided docs.
- MeanAngle::getCentroid() — Method in class MeanAngle
- Parse the provided docs and create a doc that given a metric of distance is the centroid of the provided docs.
- GroupAverage — Class in namespace NlpTools\Clustering\MergeStrategies
- In single linkage clustering the new distance of the merged cluster with cluster i is the average distance of all points in cluster x to i and y to i.
- GroupAverage::getNextMerge() — Method in class GroupAverage
- Return the pair of clusters x,y to be merged.
- HeapLinkage::getNextMerge() — Method in class HeapLinkage
- Return the pair of clusters x,y to be merged.
- MergeStrategyInterface::getNextMerge() — Method in class MergeStrategyInterface
- Return the next two clusters for merging and assume they are merged (ex.
- DocumentInterface::getDocumentData() — Method in class DocumentInterface
- Return the data of what is being represented.
- RawDocument::getDocumentData() — Method in class RawDocument
- Return the data of what is being represented.
- TokensDocument::getDocumentData() — Method in class TokensDocument
- Return the data of what is being represented.
- TrainingDocument::getDocumentData() — Method in class TrainingDocument
- Return the data of what is being represented.
- TrainingDocument::getClass() — Method in class TrainingDocument
- TrainingSet::getClassSet() — Method in class TrainingSet
- WordDocument::getDocumentData() — Method in class WordDocument
- Return the data of what is being represented.
- DataAsFeatures::getFeatureArray() — Method in class DataAsFeatures
- For use with TokensDocument mostly.
- FeatureFactoryInterface::getFeatureArray() — Method in class FeatureFactoryInterface
- Return an array with unique strings that are the features that "fire" for the specified Document $d and class $class
- FunctionFeatures::getFeatureArray() — Method in class FunctionFeatures
- Compute the features that "fire" for a given class,document pair.
- FeatureBasedNB::getPrior() — Method in class FeatureBasedNB
- Return the prior probability of class $class P(c) as computed by the training data
- FeatureBasedNB::getCondProb() — Method in class FeatureBasedNB
- Return the conditional probability of a term for a given class.
- Lda::generateDocs() — Method in class Lda
- Generate an array suitable for use with Lda::initialize and Lda::gibbsSample from a training set.
- Lda::gibbsSample() — Method in class Lda
- Generate one gibbs sample.
- Lda::getWordsPerTopicsProbabilities() — Method in class Lda
- Get the probability of a word given a topic (phi according to Griffiths and Steyvers)
- Lda::getPhi() — Method in class Lda
- Shortcut to getWordsPerTopicsProbabilities
- Lda::getDocumentsPerTopicsProbabilities() — Method in class Lda
- Get the probability of a document given a topic (theta according to Griffiths and Steyvers)
- Lda::getTheta() — Method in class Lda
- Shortcut to getDocumentsPerTopicsProbabilities
- Lda::getLogLikelihood() — Method in class Lda
- Log likelihood of the model having generated the data as implemented by M.
- LinearModel::getWeight() — Method in class LinearModel
- Get the weight for a given feature
- LinearModel::getWeights() — Method in class LinearModel
- Get all the weights as an array.
- MultinomialNBModelInterface::getPrior() — Method in class MultinomialNBModelInterface
- MultinomialNBModelInterface::getCondProb() — Method in class MultinomialNBModelInterface
- GradientDescentOptimizer — Class in namespace NlpTools\Optimizers
- Implements gradient descent with fixed step.
- Gamma — Class in namespace NlpTools\Random\Distributions
- Implement the gamma distribution.
- FromFile::generate() — Method in class FromFile
- Generates a pseudo-random number with uniform distribution in the interval [0,1)
- GeneratorInterface — Class in namespace NlpTools\Random\Generators
- An interface for pseudo-random number generators.
- GeneratorInterface::generate() — Method in class GeneratorInterface
- Generates a pseudo-random number with uniform distribution in the interval [0,1)
- MersenneTwister::generate() — Method in class MersenneTwister
- Generates a pseudo-random number with uniform distribution in the interval [0,1)
- MersenneTwister::get() — Method in class MersenneTwister
- GreekStemmer — Class in namespace NlpTools\Stemmers
- This stemmer is an implementation of the stemmer described by G.
- LancasterStemmer::getDefaultRuleSet() — Method in class LancasterStemmer
- Contains an array with the default lancaster rules
- Greek — Class in namespace NlpTools\Utils\Normalizers
- To normalize greek text we use mb_strtolower to transform to lower case and then replace every accented character with its non-accented counter part and the final ς with σ
H
- Hamming — Class in namespace NlpTools\Clustering\CentroidFactories
- This class computes the centroid of the hamming distance between two stringsthat are the binary representations of two integers (the strings are supposedto only contain the characters 1 and 0).
- Hierarchical — Class in namespace NlpTools\Clustering
- This class implements hierarchical agglomerative clustering.
- HeapLinkage — Class in namespace NlpTools\Clustering\MergeStrategies
- HeapLinkage is an abstract merge strategy.
- HammingDistance — Class in namespace NlpTools\Similarity
- This class implements the hamming distance of two strings or sets.
I
- Idf — Class in namespace NlpTools\Analysis
- Idf implements the inverse document frequency measure.
- GroupAverage::initializeStrategy() — Method in class GroupAverage
- Initialize the distance matrix and any other data structure needed to calculate the merges later.
- HeapLinkage::initializeStrategy() — Method in class HeapLinkage
- Initialize the distance matrix and any other data structure needed to calculate the merges later.
- MergeStrategyInterface::initializeStrategy() — Method in class MergeStrategyInterface
- Study the docs and preprocess anything required for computing the merges
- InvalidExpression — Class in namespace NlpTools\Exceptions
- Used by the tokenization, primarily
- InvalidExpression::invalidRegex() — Method in class InvalidExpression
- Lda::initialize() — Method in class Lda
- Count initially the co-occurences of documents,topics and topics,words and cache them to run Gibbs sampling faster
- EnglishVowels::isVowel() — Method in class EnglishVowels
- Returns true if the letter at the given index is a vowel, works with y
- VowelsAbstractFactory::isVowel() — Method in class VowelsAbstractFactory
- Check if the the letter at the given index is a vowel
J
- JaccardIndex — Class in namespace NlpTools\Similarity
- http://en.wikipedia.org/wiki/Jaccard_index
K
- KMeans — Class in namespace NlpTools\Clustering
- This clusterer uses the KMeans algorithm for clustering documents.
- TrainingSet::key() — Method in class TrainingSet
L
- Lda — Class in namespace NlpTools\Models
- Topic discovery with latent dirchlet allocation using gibbs sampling.
- LinearModel — Class in namespace NlpTools\Models
- This class represents a linear model of the following form f(x_vec) = l1*x1 + l2*x2 + l3*x3 ...
- LancasterStemmer — Class in namespace NlpTools\Stemmers
- A word stemmer based on the Lancaster stemming algorithm.
M
- MultinomialNBClassifier — Class in namespace NlpTools\Classifiers
- Use a multinomia NB model to classify a document
- MeanAngle — Class in namespace NlpTools\Clustering\CentroidFactories
- MeanAngle computes the unit vector with angle the average of all the given vectors.
- MergeStrategyInterface — Class in namespace NlpTools\Clustering\MergeStrategies
- In hierarchical agglomerative clustering each document starts in its own cluster and then it is subsequently merged with the "closest" cluster.
- FunctionFeatures::modelFrequency() — Method in class FunctionFeatures
- Set the feature factory to model frequency instead of presence
- FunctionFeatures::modelPresence() — Method in class FunctionFeatures
- Set the feature factory to model presence instead of frequency
- Maxent — Class in namespace NlpTools\Models
- Maxent is a model that assigns a weight for each feature such that all the weights maximize the Conditional Log Likelihood of the training data.
- MultinomialNBModelInterface — Class in namespace NlpTools\Models
- Interface that describes a NB model.
- MaxentGradientDescent — Class in namespace NlpTools\Optimizers
- Implement a gradient descent algorithm that maximizes the conditional log likelihood of the training data.
- MaxentOptimizerInterface — Class in namespace NlpTools\Optimizers
- Marker interface to use with the Maxent model for type checking
- MersenneTwister — Class in namespace NlpTools\Random\Generators
- A simple wrapper over the built in mt_rand() method
N
- TrainingSet::next() — Method in class TrainingSet
- Normal — Class in namespace NlpTools\Random\Distributions
- English::normalize() — Method in class English
- Transform the word according to the class description
- Greek::normalize() — Method in class Greek
- Transform the word according to the class description
- Normalizer — Class in namespace NlpTools\Utils\Normalizers
- The Normalizer's purpose is to transform any word from any one of the possible writings to a single writing consistently.
- Normalizer::normalize() — Method in class Normalizer
- Transform the word according to the class description
- Normalizer::normalizeAll() — Method in class Normalizer
- Apply the normalize function to all the items in the array
O
- Idf::offsetGet() — Method in class Idf
- Implements the array access interface.
- Idf::offsetExists() — Method in class Idf
- Implements the array access interface.
- Idf::offsetSet() — Method in class Idf
- Will not be implemented.
- Idf::offsetUnset() — Method in class Idf
- Will not be implemented.
- TrainingSet::offsetSet() — Method in class TrainingSet
- TrainingSet::offsetUnset() — Method in class TrainingSet
- TrainingSet::offsetGet() — Method in class TrainingSet
- TrainingSet::offsetExists() — Method in class TrainingSet
- ExternalMaxentOptimizer::optimize() — Method in class ExternalMaxentOptimizer
- This function receives an array that contains an array for each document which contains an array of feature identifiers for each class and at the special key '__label__' the actual class of the training document.
- FeatureBasedLinearOptimizerInterface::optimize() — Method in class FeatureBasedLinearOptimizerInterface
- This function receives an array that contains an array for each document which contains an array of feature identifiers for each class and at the special key '__label__' the actual class of the training document.
- GradientDescentOptimizer::optimize() — Method in class GradientDescentOptimizer
- This function receives an array that contains an array for each document which contains an array of feature identifiers for each class and at the special key '__label__' the actual class of the training document.
P
- Maxent::P() — Method in class Maxent
- Calculate the probability that document $d belongs to the class $class given a set of possible classes, a feature factory and the model's weights l[i]
- PorterStemmer — Class in namespace NlpTools\Stemmers
- Copyright 2013 Katharopoulos Angelos <katharas@gmail.com>
- PennTreeBankTokenizer — Class in namespace NlpTools\Tokenizers
- PennTreeBank Tokenizer Based on http://www.cis.upenn.edu/~treebank/tokenizer.sed
R
- RawDocument — Class in namespace NlpTools\Documents
- RawDocument simply encapsulates a php variable
- TrainingSet::rewind() — Method in class TrainingSet
- GradientDescentOptimizer::reportProgress() — Method in class GradientDescentOptimizer
- RegexStemmer — Class in namespace NlpTools\Stemmers
- This stemmer removes affixes according to a regular expression.
- RegexTokenizer — Class in namespace NlpTools\Tokenizers
- Regex tokenizer tokenizes text based on a set of regexes
- ClassifierBasedTransformation::register() — Method in class ClassifierBasedTransformation
- Register a set of transformations for a given class.
S
- SingleLink — Class in namespace NlpTools\Clustering\MergeStrategies
- In single linkage clustering the new distance of the merged cluster with cluster i is the smallest distance of either cluster x to i or y to i.
- TrainingSet::setAsKey() — Method in class TrainingSet
- Decide what should be returned as key when iterated upon
- AbstractDistribution::sample() — Method in class AbstractDistribution
- Dirichlet::sample() — Method in class Dirichlet
- Gamma::sample() — Method in class Gamma
- Normal::sample() — Method in class Normal
- CosineSimilarity::similarity() — Method in class CosineSimilarity
- JaccardIndex::similarity() — Method in class JaccardIndex
- Simhash — Class in namespace NlpTools\Similarity
- Simhash is an implementation of the locality sensitive hash function families proposed by Moses Charikar using the Earth Mover's Distance http://www.cs.princeton.edu/courses/archive/spring04/cos598B/bib/CharikarEstim.pdf
- Simhash::simhash() — Method in class Simhash
- Compute the locality sensitive hash for this set.
- Simhash::similarity() — Method in class Simhash
- SimilarityInterface — Class in namespace NlpTools\Similarity
- Similarity should return a number that is proportional to how similar those two instances are (with any metric).
- SimilarityInterface::similarity() — Method in class SimilarityInterface
- GreekStemmer::stem() — Method in class GreekStemmer
- Remove the suffix from $word
- LancasterStemmer::stem() — Method in class LancasterStemmer
- Performs a Lancaster stem on the giving word
- PorterStemmer::stem() — Method in class PorterStemmer
- Remove the suffix from $word
- RegexStemmer::stem() — Method in class RegexStemmer
- Remove the suffix from $word
- Stemmer — Class in namespace NlpTools\Stemmers
- http://en.wikipedia.org/wiki/Stemming
- Stemmer::stem() — Method in class Stemmer
- Remove the suffix from $word
- Stemmer::stemAll() — Method in class Stemmer
- Apply the stemmer to every single token.
- StopWords — Class in namespace NlpTools\Utils
- Stop Words are words which are filtered out because they carry little to no information.
T
- TokensDocument — Class in namespace NlpTools\Documents
- Represents a bag of words (tokens) document.
- TrainingDocument — Class in namespace NlpTools\Documents
- A TrainingDocument is a document that "decorates" any other document to add the real class of the document.
- TrainingSet — Class in namespace NlpTools\Documents
- A collection of TrainingDocument objects.
- FeatureBasedNB::train_with_context() — Method in class FeatureBasedNB
- Train on the given set and fill the model's variables.
- FeatureBasedNB::train() — Method in class FeatureBasedNB
- Train on the given set and fill the models variables
- Lda::train() — Method in class Lda
- Run the gibbs sampler $it times.
- Maxent::train() — Method in class Maxent
- Calculate all the features for every possible class.
- Stemmer::transform() — Method in class Stemmer
- Return the value transformed.
- ClassifierBasedTokenizer::tokenize() — Method in class ClassifierBasedTokenizer
- Break a character sequence to a token sequence
- PennTreeBankTokenizer::tokenize() — Method in class PennTreeBankTokenizer
- Calls internal functions to handle data processing
- RegexTokenizer::tokenize() — Method in class RegexTokenizer
- Break a character sequence to a token sequence
- TokenizerInterface — Class in namespace NlpTools\Tokenizers
- TokenizerInterface::tokenize() — Method in class TokenizerInterface
- Break a character sequence to a token sequence
- WhitespaceAndPunctuationTokenizer::tokenize() — Method in class WhitespaceAndPunctuationTokenizer
- Break a character sequence to a token sequence
- WhitespaceTokenizer::tokenize() — Method in class WhitespaceTokenizer
- Break a character sequence to a token sequence
- ClassifierBasedTransformation::transform() — Method in class ClassifierBasedTransformation
- Classify the passed in variable w and then apply each transformation to the output of the previous one.
- Normalizer::transform() — Method in class Normalizer
- Return the value transformed.
- StopWords::transform() — Method in class StopWords
- Return the value transformed.
- TransformationInterface — Class in namespace NlpTools\Utils
- TransformationInterface represents any type of transformation to be applied upon documents.
- TransformationInterface::transform() — Method in class TransformationInterface
- Return the value transformed.
V
- TrainingSet::valid() — Method in class TrainingSet
- VowelsAbstractFactory — Class in namespace NlpTools\Utils
- Factory wrapper for Vowels
W
- WordDocument — Class in namespace NlpTools\Documents
- A Document that represents a single word but with a context of a larger document.
- WhitespaceAndPunctuationTokenizer — Class in namespace NlpTools\Tokenizers
- Simple white space tokenizer.
- WhitespaceTokenizer — Class in namespace NlpTools\Tokenizers
- Simple white space tokenizer.
_
- FreqDist::__construct() — Method in class FreqDist
- This sorts the token meta data collection right away so use frequency distribution data can be extracted.
- Idf::__construct() — Method in class Idf
- FeatureBasedLinearClassifier::__construct() — Method in class FeatureBasedLinearClassifier
- MultinomialNBClassifier::__construct() — Method in class MultinomialNBClassifier
- Hierarchical::__construct() — Method in class Hierarchical
- KMeans::__construct() — Method in class KMeans
- Initialize the K Means clusterer
- RawDocument::__construct() — Method in class RawDocument
- TokensDocument::__construct() — Method in class TokensDocument
- TrainingDocument::__construct() — Method in class TrainingDocument
- TrainingSet::__construct() — Method in class TrainingSet
- WordDocument::__construct() — Method in class WordDocument
- FunctionFeatures::__construct() — Method in class FunctionFeatures
- FeatureBasedNB::__construct() — Method in class FeatureBasedNB
- FeatureBasedNB::__sleep() — Method in class FeatureBasedNB
- Just save the probabilities for reuse
- Lda::__construct() — Method in class Lda
- LinearModel::__construct() — Method in class LinearModel
- ExternalMaxentOptimizer::__construct() — Method in class ExternalMaxentOptimizer
- GradientDescentOptimizer::__construct() — Method in class GradientDescentOptimizer
- AbstractDistribution::__construct() — Method in class AbstractDistribution
- Dirichlet::__construct() — Method in class Dirichlet
- Gamma::__construct() — Method in class Gamma
- Normal::__construct() — Method in class Normal
- FromFile::__construct() — Method in class FromFile
- Construct a FromFile generator
- Simhash::__construct() — Method in class Simhash
- LancasterStemmer::__construct() — Method in class LancasterStemmer
- Constructor loads the ruleset into memory
- RegexStemmer::__construct() — Method in class RegexStemmer
- ClassifierBasedTokenizer::__construct() — Method in class ClassifierBasedTokenizer
- PennTreeBankTokenizer::__construct() — Method in class PennTreeBankTokenizer
- RegexTokenizer::__construct() — Method in class RegexTokenizer
- Initialize the Tokenizer
- ClassifierBasedTransformation::__construct() — Method in class ClassifierBasedTransformation
- In order to classify anything with NlpTools we need something that implements the ClassifierInterface.
- StopWords::__construct() — Method in class StopWords