This chapter provides a general introduction to the field of Data Mining and explains some basic terms.

• What is Data Mining and what can it do?
• Structure of the book
• Data analysis process
• Interdisciplinarity
• Tools

Files

• [1] Weather data, numercal, [2] and nominal
• [3] Knime-Weather-Workflow Fig. 1.6 / 1.8 (you have to configure the FileReader)
• [4] Iris data, arff-Format
• [5] Knime-Loops Fig. 1.13 (you have to configure the FileReader)

Tools

• Knime: http://www.knime.org/
• WEKA: http://www.cs.waikato.ac.nz/ml/weka/
• JavaNNS
• Rapid Miner http://rapid-i.com

Competitions

• Kaggle: http://www.kaggle.com/competitions

Data collections:

• Kaggle: http://www.kaggle.com/
• Open Data Inception opendatainception.io
• Google Clud https://cloud.google.com/public-datasets/
• GitHub https://github.com/awesomedata/awesome-public-datasets
• Open Data on AWS https://registry.opendata.aws/
• EU Open Data Portal https://data.europa.eu/euodp/en/data/
• World-Bank https://data.worldbank.org/
• WHO https://www.who.int/gho/database/en/
• Data.gov https://catalog.data.gov/dataset

Here are some notes on the tasks in the book. 

This chapter clarifies some fundamental concepts.

• Basic terms
• Data types
• Similarity/distance measures
• Fundamentals of artificial neural networks
• Logic
• Supervised and unsupervised learning

This chapter provides an overview of the application classes in Data Mining.

• Cluster analysis
• Classification
• Numerical prediction
• Association analysis
• Text mining
• Web mining

This chapter provides an overview of the possibilities for representing (Data Mining) knowledge on a computer.

• Decision table
• Decision trees
• Rules
• Association rules
• Instance-based representation
• Representation of clusters
• Neural networks as knowledge repository

This chapter provides an overview of basic classification methods.

• k-Nearest Neighbour
• Decision Trees
• Naive Bayes
• Feed-forward Neural Networks
• SVM

Files

• [1] Income data
• [2] Knime-KNN-Income (you have to reconfigure the FileReader)
• Weather data (nominal, csv). Training set [3] und Test set  [3a].
• [4] Knime-NaiveBayes-Weather (you have to reconfigure the FileReader)
• [5] Employee data (csv)
• [6] Knime-SVM Employee data (you have to reconfigure the FileReader)

This chapter provides an overview of basic clustering methods.

• k-Means
• k-Medoid
• Expectation maximisation
• Density-based clustering
• SOM
• Neural gas
• ART networks

Files

• [1] Iris data, arff-Format
• [2] Knime-KMeans Fig. 6.14 (configure the FileReader)
• [3] File for String Replace-Node

This chapter provides an overview of basic association analysis methods.

• A-Priori
• Frequent Pattern Growth

Files

• [1] Condition data, csv-Format (Tab. 7.1)
• Link auf die Umfrage 2006 (available only in German)

This chapter provides an overview of basic data preparation techniques.

• Data selection and integration
• Data cleansing
• Data reduction
• Data transformation

Files

• [1] Iris-Daten, arff-Format
• [2] Condition data, csv-Format (Ex. 8.7)
• [3] KNIME-Workflow 1, KNN without normalisation
• [4] KNIME-Workflow 2, KNN with normalisation

This chapter provides an overview of basic options for evaluating results and for visualisation.

• Interest measures
• Quality measures and error costs
• Test and validation sets
• Visualisation

Files

• [1] GnuPlot-File Fig. 9.6
• [2] GnuPlot-File Fig. 9.14

This chapter discusses possible approaches to the Data Mining Cup 2002.

Best score in the DM Cup 2002 :

• 12.12.13 Tanja Ciernioch (Wismar University of Applied Sciences): 7,771.80

Dateien

• The DMC Task 2002.
• [2]Knime-Workflow first attempt (Fig. 10.1).
• [3]Knime-Workflow k-nearest neighbor (Fig. 10.5).
• [4]Knime-Workflow Naive Bayes (Fig. 10.6).
• [5]Knime-Workflow Decision Tree 1 (Fig. 10.7).
• [6]Knime-Workflow Decision Tree 2 (Fig. 10.8).
• [7]Knime-Workflow Neural Network (Fig. 10.9).