Visual data mining : the VisMiner approach / Russell K. Anderson.

Format:

Book

Author/Creator:

Anderson, Russell K.

Series:

New York Academy of Sciences Ser.

Language:

English

Subjects (All):

Data mining.

Information visualization.

VisMiner (Electronic resource).

Physical Description:

1 online resource (210 p.)

Edition:

2nd ed.

Place of Publication:

Chichester, West Sussex, U.K. ; Hoboken, N.J. : Wiley, 2012.

Language Note:

English

System Details:

text file

Summary:

A visual approach to data mining. Data mining has been defined as the search for useful and previously unknown patterns in large datasets, yet when faced with the task of mining a large dataset, it is not always obvious where to start and how to proceed. This book introduces a visual methodology for data mining demonstrating the application of methodology along with a sequence of exercises using VisMiner. VisMiner has been developed by the author and provides a powerful visual data mining tool enabling the reader to see the data that they ar

Contents:

Visual Data Mining: THE VISMINER APPROACH; Contents; Preface; Acknowledgments; 1. Introduction; Data Mining Objectives; Introduction to VisMiner; The Data Mining Process; Initial Data Exploration; Dataset Preparation; Algorithm Selection and Application; Model Evaluation; Summary; 2. Initial Data Exploration and Dataset Preparation Using VisMiner; The Rationale for Visualizations; Tutorial - Using VisMiner; Initializing VisMiner; Initializing the Slave Computers; Opening a Dataset; Viewing Summary Statistics; Exercise 2.1; The Correlation Matrix; Exercise 2.2; The Histogram; The Scatter Plot

Exercise 2.3The Parallel Coordinate Plot; Exercise 2.4; Extracting Sub-populations Using the Parallel Coordinate Plot; Exercise 2.5; The Table Viewer; The Boundary Data Viewer; Exercise 2.6; The Boundary Data Viewer with Temporal Data; Exercise 2.7; Summary; 3. Advanced Topics in Initial Exploration and Dataset Preparation Using VisMiner; Missing Values; Missing Values - An Example; Exploration Using the Location Plot; Exercise 3.1; Dataset Preparation - Creating Computed Columns; Exercise 3.2; Aggregating Data for Observation Reduction; Exercise 3.3; Combining Datasets; Exercise 3.4

Outliers and Data ValidationRange Checks; Fixed Range Outliers; Distribution Based Outliers; Computed Checks; Exercise 3.5; Feasibility and Consistency Checks; Data Correction Outside of VisMiner; Distribution Consistency; Pattern Checks; A Pattern Check of Experimental Data; Exercise 3.6; Summary; 4. Prediction Algorithms for Data Mining; Decision Trees; Stopping the Splitting Process; A Decision Tree Example; Using Decision Trees; Decision Tree Advantages; Limitations; Artificial Neural Networks; Overfitting the Model; Moving Beyond Local Optima; ANN Advantages and Limitations

Support Vector MachinesData Transformations; Moving Beyond Two-dimensional Predictors; SVM Advantages and Limitations; Summary; 5. Classification Models in VisMiner; Dataset Preparation; Tutorial - Building and Evaluating Classification Models; Model Evaluation; Exercise 5.1; Prediction Likelihoods; Classification Model Performance; Interpreting the ROC Curve; Classification Ensembles; Model Application; Summary; Exercise 5.2; Exercise 5.3; 6. Regression Analysis; The Regression Model; Correlation and Causation; Algorithms for Regression Analysis; Assessing Regression Model Performance

Model ValidityLooking Beyond R2; Polynomial Regression; Artificial Neural Networks for Regression Analysis; Dataset Preparation; Tutorial; A Regression Model for Home Appraisal; Modeling with the Right Set of Observations; Exercise 6.1; ANN Modeling; The Advantage of ANN Regression; Top-Down Attribute Selection; Issues in Model Interpretation; Model Validation; Model Application; Summary; 7. Cluster Analysis; Introduction; Algorithms for Cluster Analysis; Issues with K-Means Clustering Process; Hierarchical Clustering; Measures of Cluster and Clustering Quality; Silhouette Coefficient

Correlation Coefficient

Notes:

Includes bibliographical references and index.

Includes index.

ISBN:

9781118444818

1118444817

9781283645690

1283645696

9781118439234

1118439236

OCLC:

793340277