Clustermatch is an efficient clustering method for processing highly diverse data. It can handle very different data types (such as numerical and categorical), in the presence of linear or non-linear relationships, also with noise, and without the need of any previous pre-processing.
This web-demo requires a file with the data (an example is provided for download) and the number of clusters desired. The input data file can be:
- CSV: a single data source in the CSV file.
- XLS: data sources can be placed in different worksheets.
- ZIP: including several CSV or XLS files with different data sources.
After choosing the file, click Upload. Enter the number of clusters, click Submit. The output is an XLS file with the data partition, and an zoomable plot showing how the variables are clustered.
See sample results here.
Note: this webdemo has a limit of 500 variables. To use clustermatch with more variables, download the full version.
Contact: Milton Pividori