NeuroSuites

1. Upload dataset/probabilistic clustering model

Select the dataset and features:

Coming soon...

Loading values

Features:

All features selected

Class features (optional):

Discretize continuous values

Max number of bins:

This algorithm requires a
discrete class feature

Upload full model (clusters + graph):

Formats supported: .zip file
Containing files in the following form:
mean_vector_cluster__i.parquet.gzip, covariance_matrix_cluster__i.parquet.gzip, precision_matrix_cluster__i.csv

To create Apache Parquet gzip files please follow this tutorial:
Apache Parquet files creation.

Clustering model

LFt0a7gxqU3CGGUFff5nfKFqiclosRVXwQ7exOu2D4S8ZhyhcrFQc0FIeFw1f3f2

Download example Allen model

Download example mtcars model

Loading

Upload pre-model files (clusters):

Formats supported: .zip file
Containing files in the following form:
mean_vector_cluster__i.parquet.gzip, covariance_matrix_cluster__i.parquet.gzip

To create Apache Parquet gzip files please follow this tutorial:
Apache Parquet files creation.

Clustering model

LFt0a7gxqU3CGGUFff5nfKFqiclosRVXwQ7exOu2D4S8ZhyhcrFQc0FIeFw1f3f2

Additional parameters json file (optional):

(Template file)

Use this to upload external info about groups of nodes:

LFt0a7gxqU3CGGUFff5nfKFqiclosRVXwQ7exOu2D4S8ZhyhcrFQc0FIeFw1f3f2

Probabilistic clustering model name:

Loading dataset...

Estimated time to finish:

Data uploaded

Additional parameters uploaded

2. Learn the structure of the Probabilistic clustering model

Select the structure learning algorithm:

Learning algorithm:

PC algorithm parameters

Max number of parents per node:

Max adjacency size:

Significance level (%):

Backend:

Grow-Shrink algorithm parameters

Significance level (%):

Backend:

Incremental Association algorithm parameters

Significance level (%):

Backend:

Fast Incremental Association algorithm parameters

Significance level (%):

Backend:

Interleaved Incremental Association algorithm parameters

Significance level (%):

Backend:

Hill climbing algorithm parameters

Max number of parents per node:

Max adjacency size:

Sample size:

Backend:

Hill climbing with tabu search algorithm parameters

Max number of parents per node:

Max adjacency size:

Sample size:

Backend:

Chow-Liu tree algorithm parameters

Max number of parents per node:

Backend:

Hiton Parents and Children algorithm parameters

Backend:

sparseBn algorithm parameters

Backend:

FGES algorithm parameters

Penalty:

Mode:

Backend:

Max-Min Hill-Climbing algorithm parameters

Backend:

Max-Min Parents and Children algorithm parameters

Backend:

GOBNILP solver algorithm parameters

Coming soon.

Naive Bayes algorithm parameters

Backend:

Tree Augmented Naive Bayes algorithm parameters

Backend:

Multi-dimensional Probabilistic clustering model classifier algorithm parameters

Backend:

Learning structure...

Estimated time to finish:

Structure learned
Check the graph below.

3. Learn the parameters of the Probabilistic clustering model

Select the parameters learning algorithm:

Learning algorithm:

Gaussian maximum likelihood estimation algorithm parameters

Backend:

Discrete maximum likelihood estimation algorithm parameters

Backend:

Discrete Bayesian estimation algorithm parameters

Prior:

BDeu equivalent sample size:

Backend:

Learning parameters...

Estimated time to finish:

Parameters learned
Click on the nodes to check them.

Data

No data available. If you want to upload your dataset please go here and then come back here.

Visualize Probabilistic clustering model graph

Blue nodes are predictor features, red nodes have fixed evidence.

Double click to reset the camera and the colors.

Find one node:

Select multiple nodes:

List of groups:

Category:

Select cluster:

Filter common edges:

or

Sort list by:

Nodes by evidences effect:

KL divergence:

Mean:

Standard deviation:

Groups by evidences effect (KL divergence):

Category:

Inference mode:

Graphical lasso parameters:

Alpha

Tol

Max iter

Loading

Selected:

Evidence:

Loading parameters

nodes ( selected) edges ( selected)

Structures metrics

Export the Probabilistic clustering model

Export Probabilistic clustering model as:

Loading

Probabilistic clustering

Beta version

1. Upload dataset/probabilistic clustering model

Select the dataset and features:

Upload full model (clusters + graph):

Upload pre-model files (clusters):

Data uploaded

Additional parameters uploaded

2. Learn the structure of the Probabilistic clustering model

Select the structure learning algorithm:

Structure learned Check the graph below.

3. Learn the parameters of the Probabilistic clustering model

Select the parameters learning algorithm:

Parameters learned Click on the nodes to check them.

Data

Visualize Probabilistic clustering model graph

Structures metrics

Export the Probabilistic clustering model

Structure learned
Check the graph below.

Parameters learned
Click on the nodes to check them.