Taxam Grouper

• pt-br

TaxAM Grouper is a module of tools of the project TaxAM created to group samples by the matrices generated by TaxAM. In this module, we have the following tools:

• Grouper

  Used to group samples by the matrices generated by TaxAM.

• Taxam Grouper GUI

  Used to visualize the groups generated by TaxAM Grouper.

Grouper

It uses some algortihms to group samples. The first one is the K-means algorithm. The second one is the Hierarchical Clustering algorithm.

How to use Grouper

1. Install all the dependencies in the requirements.txt file.

pip install -r requirements.txt

2. Run grouper script.

python grouper <algorithm_name> <flag_1> <value_1> <flag_2> <value_2> ...

• Global flags:

  • -fp or --file_path: Matrix to group.
  • -on or --output_name: Name for the taxam grouper file. Default "TaxAM_grouper".
  • -h or --help: Show help message and exit.

• K-means flags:

  • -n or --number_of_clusters: Set the number of clusters that Kmeans will use to group samples. Default 2.
  • -ni or n_init: Number of times that k-means algorithm will be run with different centroid seeds. The final results will be the best output of n_init consecutive runs in terms of inertia. Default 10
  • -mi or max_iter: Maximum number of iterations of the k-means algorithm for a single run. Default 300.

Use example

python grouper kmeans -fp "matrix.txt" -on "TaxAM_grouper" -n 3

Taxam Grouper GUI

It is a GUI that allows you to visualize the groups generated by TaxAM Grouper.

• Open the index.html file in the folder of the TaxAM Grouper GUI.

• Select the matrix that you want to visualize.

  

• Click on the button "Visualizar".

  

• Then you can see the groups.