Index

A

• affinity matrix
  • URL / Mahout implementation of spectral clustering
• algorithms
  • sequential algorithms / Algorithm support in Mahout
  • parallel algorithms / Algorithm support in Mahout
• applications, Clustering
  • for marketing / Application of clustering
  • for recommendations / Application of clustering
  • image segmentation / Application of clustering
  • in bioinformatics / Application of clustering
  • web search / Application of clustering
  • about / Application of clustering

B

• BallKMeans step
  • about / The BallKMeans step
  • seeding stage / The BallKMeans step
  • numRuns parameter / The BallKMeans step
  • testProbabilty parameter / The BallKMeans step
  • correctWeigths parameter / The BallKMeans step
  • numClusters parameter / The BallKMeans step
  • trimFraction parameter / The BallKMeans step
  • maxNumIterations parameter / The BallKMeans step
  • kMeansPlusPlusInit parameter / The BallKMeans step
• Bayesian information criterion (BIC) / Learning model-based clustering

C

• canopy clustering
  • running, on Mahout / Running Canopy clustering on Mahout
  • URL / Running Canopy clustering on Mahout
  • generation phase / The Canopy generation phase
  • clustering phase / The Canopy clustering phase
  • running / Running Canopy clustering
  • output, using for K-means / Using the Canopy output for K-means
• Class UnitVectorizerJob
  • URL / Mahout implementation of spectral clustering
• Clustering
  • about / The clustering concept
  • pattern finding algorithm / The clustering concept
  • distance measuring technique / The clustering concept
  • Grouping and Stopping / The clustering concept
  • Analysis of Output / The clustering concept
  • applications / Application of clustering
  • techniques / Understanding different clustering techniques
• Clustering algorithms
  • K-means Clustering / Clustering algorithms in Mahout
  • Fuzzy K-means / Clustering algorithms in Mahout
  • Streaming K-means / Clustering algorithms in Mahout
  • Spectral Clustering / Clustering algorithms in Mahout
  • Canopy Clustering / Clustering algorithms in Mahout
  • Latent Dirichlet Allocation for topic modeling / Clustering algorithms in Mahout
• clustering phase, Canopy clustering / The Canopy clustering phase
• cluster quality
  • improving / Using DistanceMeasure interface
• clusters
  • visualizing / Visualizing clusters, Visualizing clusters, Visualizing clusters
  • evaluating / Evaluating clusters
  • quality, improving / Using DistanceMeasure interface
• clusters evaluation
  • methods / Evaluating clusters
  • extrinsic methods / Extrinsic methods
  • intrinsic methods / Intrinsic methods
• CSV files
  • working with / Working with CSV files

D

• data
  • preparation, for using in clustering techniques / Preparing data for use with clustering techniques
• dataset
  • URL / Dataset selection
  • preparing / Preparing the dataset
• Davies-Bouldin index
  • about / Intrinsic methods
  • URL / Intrinsic methods
• density-based method, Clustering / The density-based method
• Dirichlet clustering / Understanding Dirichlet clustering
• distance measures
  • about / Understanding distance measures
  • for numeric variables / Understanding distance measures
  • SquaredEuclideanDistanceMeasure / Understanding distance measures
  • WeightedEuclideanDistanceMeasure / Understanding distance measures
  • ManhattanDistanceMeasure / Understanding distance measures
  • WeightedManhattanDistanceMeasure class / Understanding distance measures
  • ChebyshevDistanceMeasure / Understanding distance measures
  • CosineDistanceMeasure / Understanding distance measures
  • TanimotoDistanceMeasure / Understanding distance measures
• Dunn Index
  • URL / Running Streaming K-means
  • about / Intrinsic methods

E

• Eclipse
  • URL / Building Mahout code using Maven
  • used, for setting up development environment / Setting up the development environment using Eclipse
• Elbow method / Learning K-means
• expectation-maximization (EM) algorithm / Learning model-based clustering
• Expectation Maximization (EM) algorithm / Learning K-means
  • Expectation Step / Learning K-means
  • Maximization Step / Learning K-means
• extrinsic methods, cluster
  • about / Extrinsic methods
  • cluster homogeneity / Extrinsic methods
  • cluster completeness / Extrinsic methods
  • rag bag / Extrinsic methods
  • cluster size versus quantity / Extrinsic methods
  • Jaccard index / Extrinsic methods
  • rand statistics / Extrinsic methods
  • F-measure / Extrinsic methods
  • Fowlkes-Mallows index (FM) / Extrinsic methods
  • entropy-based cluster evaluation / Extrinsic methods

F

• Fuzzy K-means clustering
  • about / Learning Fuzzy K-means clustering
  • running, on Mahout / Running Fuzzy K-means on Mahout
  • running, with liver disorders dataset / Dataset
  • vector, creating for dataset / Creating a vector for the dataset
  • vector reader / Vector reader

G

• generation phase, Canopy clustering / The Canopy generation phase
• graph Laplacian
  • obtaining, from affinity matrix / Getting graph Laplacian from the affinity matrix
  • eigenvector / Eigenvectors and eigenvalues
  • eigenvalues / Eigenvectors and eigenvalues

H

• Hadoop
  • URL / Installing Mahout
• hierarchical methods, Clustering
  • about / Hierarchical methods
  • top-down approach / Hierarchical methods
  • bottom-up approach / Hierarchical methods
• Hortonworks Sandbox, for VirtualBox
  • URL / Setting up Mahout for Windows users

I

• Inter-cluster
  • about / Intrinsic methods
• Intra-cluster distance
  • about / Intrinsic methods
• intrinsic methods, cluster
  • entropy-based cluster evaluation / Intrinsic methods
  • Dunn index / Intrinsic methods
  • Inter-cluster / Intrinsic methods
  • Intra-cluster distance / Intrinsic methods
  • Davies-Bouldin index / Intrinsic methods
  • Silhouette coefficient / Intrinsic methods
• Inverse document frequency / Preparing data for use with clustering techniques

K

• K, finding
  • Elbow method / Learning K-means
  • Silhouette coefficient / Learning K-means
  • URL / Learning K-means
• K-means
  • about / Learning K-means
  • algorithms / Learning K-means
  • running, on Mahout / Running K-means on Mahout
  • running, in Map Phase / Running K-means on Mahout
  • running, in Reducer Phase / Running K-means on Mahout
  • URL / Running K-means on Mahout
  • executing / Executing K-means
  • Clusterdump result / The clusterdump result
  • Canopy output, using / Using the Canopy output for K-means

L

• Latent Dirichlet allocation (LDA)
  • about / Topic modeling
  • mapper phase / Topic modeling
  • reducer phase / Topic modeling
  • running, with Mahout / Running LDA using Mahout
• Latent Dirichlet allocation (LDA), running
  • dataset selection / Dataset selection
  • CVB (LDA), executing / Steps to execute CVB (LDA)
• liver disorders dataset
  • about / Dataset
  • URL / Dataset
  • download, URL / Dataset

M

• Mahout
  • algorithms / Algorithm support in Mahout
  • Clustering algorithms / Clustering algorithms in Mahout
  • installing / Installing Mahout
  • distribution file , URL / Building Mahout code using Maven
  • K-means, running / Running K-means on Mahout
  • dataset selection / Dataset selection
  • canopy clustering, running / Running Canopy clustering on Mahout
  • Latent Dirichlet allocation (LDA), running / Running LDA using Mahout
  • used, for Streaming K-Means / Using Mahout for streaming K-means
  • implementation, of spectral clustering / Mahout implementation of spectral clustering
• Mahout installation
  • steps / Installing Mahout
  • code, building with Maven / Building Mahout code using Maven
  • development environment, setting up with Eclipse / Setting up the development environment using Eclipse
  • setting up, for Window users / Setting up Mahout for Windows users
• mahout job
  • launching, on cluster / Launching the Mahout job on the cluster
  • performance tuning / Performance tuning for the job
• map reduce implementation
  • URL / Running Fuzzy K-means on Mahout
  • mapper part / Running Fuzzy K-means on Mahout
  • combiner part / Running Fuzzy K-means on Mahout
  • reducers part / Running Fuzzy K-means on Mahout
• Maven
  • used, for building Mahout / Building Mahout code using Maven
  • URL / Building Mahout code using Maven
• model-based clustering
  • about / Learning model-based clustering
  • Dirichlet clustering / Understanding Dirichlet clustering
  • topic modeling / Topic modeling

N

• 20news-bydate.tar.gz
  • URL / Dataset selection
• ?-neighborhood graph / Affinity (similarity) graph
• n-grams / Preparing data for use with clustering techniques
• normalized graph Laplacian matrix(random-walk) / Eigenvectors and eigenvalues
• normalized graph Laplacian matrix(symmetric) / Eigenvectors and eigenvalues

P

• parallel algorithms / Algorithm support in Mahout
• partitioning method, Clustering / The partitioning method
• performance tuning
  • for mahout job / Performance tuning for the job
• probabilistic Clustering / Probabilistic clustering

S

• sequential algorithms / Algorithm support in Mahout
• Silhouette coefficient / Learning K-means
  • about / Intrinsic methods
  • URL / Intrinsic methods
• spectral clustering
  • about / Understanding spectral clustering
  • affinity (similarity) graph / Affinity (similarity) graph
  • graph Laplacian, obtaining from affinity matrix / Getting graph Laplacian from the affinity matrix
  • Mahout implementation / Mahout implementation of spectral clustering
• spectral clustering algorithm
  • about / The spectral clustering algorithm
  • unnormalized spectral clustering / The spectral clustering algorithm
  • normalized spectral clustering / Normalized spectral clustering
• Stochastic Singular Value Decomposition (SSVD)
  • about / Mahout implementation of spectral clustering
  • URL / Mahout implementation of spectral clustering
• Streaming K-Means
  • about / Learning Streaming K-means
  • URL / Learning Streaming K-means
  • implementing / Learning Streaming K-means
  • Streaming step / The Streaming step
  • BallKMeans step / The BallKMeans step
  • Mahout, using / Using Mahout for streaming K-means
  • dataset selection / Dataset selection
  • CSV file, converting to vector file / Converting CSV to a vector file
  • running / Running Streaming K-means
• Streaming step
  • about / The Streaming step
  • distanceCutOff parameter / The Streaming step
  • Beta parameter / The Streaming step
  • clusterOvershoot parameter / The Streaming step
  • clusterLogFactor parameter / The Streaming step
  • numClusters parameter / The Streaming step
  • URL / The Streaming step

T

• techniques, Clustering
  • about / Understanding different clustering techniques
  • hierarchical methods / Hierarchical methods
  • partitioning method / The partitioning method
  • density-based method / The density-based method
  • probabilistic Clustering / Probabilistic clustering
• TF-IDF / Preparing data for use with clustering techniques
• topic modeling / Topic modeling
• Twitter Apps
  • URL / Preparing the dataset
• Twitter streams
  • collecting, URL / Preparing the dataset

W

• Windows users
  • setting up / Setting up Mahout for Windows users