22 k-Means

Oracle Machine Learning supports enhanced k-Means clustering algorithm. Learn how to use the algorithm.

• About k-Means
  The k-Means algorithm is a distance-based clustering algorithm that partitions the data into a specified number of clusters.
• k-Means Algorithm Configuration
  The Oracle Machine Learning enhanced k-Means algorithm supports several build-time settings.
• Data Preparation for k-Means
  Learn about preparing data for k-Means algorithm.

22.1 About k-Means

The k-Means algorithm is a distance-based clustering algorithm that partitions the data into a specified number of clusters.

Distance-based algorithms rely on a distance function to measure the similarity between cases. Cases are assigned to the nearest cluster according to the distance function used.

• Oracle Machine Learning for SQL Enhanced k-Means
  Oracle Machine Learning offers an enhanced k-Means algorithm with efficient initialization, scalable parallel model build, and detailed cluster properties.
• Centroid
  A centroid represents the most typical case in a cluster, with mean values for numerical attributes and mode values for categorical attributes.

22.1.1 Oracle Machine Learning for SQL Enhanced k-Means

Oracle Machine Learning offers an enhanced k-Means algorithm with efficient initialization, scalable parallel model build, and detailed cluster properties.

Oracle Machine Learning for SQL implements an enhanced version of the k-Means algorithm with the following features:

• Distance function: The algorithm supports Euclidean and Cosine distance functions. The default is Euclidean.

• Scalable Parallel Model build: The algorithm uses a very efficient method of initialization based on Bahmani, Bahman, et al. "Scalable k-means++." Proceedings of the VLDB Endowment 5.7 (2012): 622-633.

• Cluster properties: For each cluster, the algorithm returns the centroid, a histogram for each attribute, and a rule describing the hyperbox that encloses the majority of the data assigned to the cluster. The centroid reports the mode for categorical attributes and the mean and variance for numerical attributes.

This approach to k-Means avoids the need for building multiple k-Means models and provides clustering results that are consistently superior to the traditional k-Means.

22.1.2 Centroid

A centroid represents the most typical case in a cluster, with mean values for numerical attributes and mode values for categorical attributes.

The centroid represents the most typical case in a cluster. For example, in a data set of customer ages and incomes, the centroid of each cluster would be a customer of average age and average income in that cluster. The centroid is a prototype. It does not necessarily describe any given case assigned to the cluster.

The attribute values for the centroid are the mean of the numerical attributes and the mode of the categorical attributes.

22.2 k-Means Algorithm Configuration

The Oracle Machine Learning enhanced k-Means algorithm supports several build-time settings.

All the settings have default values. There is no reason to override the defaults unless you want to influence the behavior of the algorithm in some specific way.

You can configure k-Means by specifying the following considerations:

• Number of clusters

• Distance Function. The default distance function is Euclidean.

See Also:

DBMS_DATA_MINING —Algorithm Settings: k-Means for a listing and explanation of the available model settings.

Note:

The term hyperparameter is also interchangeably used for model setting.

22.3 Data Preparation for k-Means

Learn about preparing data for k-Means algorithm.

Normalization is typically required by the k-Means algorithm. Automatic Data Preparation performs normalization for k-Means. If you do not use ADP, you must normalize numeric attributes before creating or applying the model.

When there are missing values in columns with simple data types (not nested), k-Means interprets them as missing at random. The algorithm replaces missing categorical values with the mode and missing numerical values with the mean.

When there are missing values in nested columns, k-Means interprets them as sparse. The algorithm replaces sparse numerical data with zeros and sparse categorical data with zero vectors.

Data can be constrained in a window size of 6 standard-deviations around the mean value by using the KMNS_WINSORIZE parameter. The KMNS_WINSORIZE parameter can be used whether ADP is set to ON or OFF. Values outside the range are mapped to the range's ends. This parameter is applicable only when the Euclidean distance is used.