- Trending Categories
- Data Structure
- Networking
- RDBMS
- Operating System
- Java
- iOS
- HTML
- CSS
- Android
- Python
- C Programming
- C++
- C#
- MongoDB
- MySQL
- Javascript
- PHP

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

# What is scipy.cluster.hierarchy.fcluster()method?

**scipy.cluster.hierarchy.fcluster(Z,t,criterion=’inconsistent’depth=2,R=None, monocrat=None)**− The fcluster() method forms flat clusters from the hierarchical clustering. This hierarchical clustering is defined by the given linkage matrix, identifying a link between clustered classes.

Below is given the detailed explanation of its parameters −

## Parameters

**Z**− ndarrayIt represents the hierarchical clustering which is encoded with the linkage matrix.

**t**− scalarThe value of t depends on the type of criteria. For ‘inconsistent’, ‘distance’, and ‘monocrit’ criteria, the value of t represents the threshold to apply when forming flat clusters. On the other hand, for ‘maxclust’, and ‘maxclust_monocrit’ criteria, the value of t represents the maximum number of clusters requested.

**criterion**− str, optional

This parameter represents the criterion to use in forming flat clusters. The values of criterion can be any one among the followings −

**inconsistent**− Inconsistent criterion means that the cluster node and all its descendants have an inconsistent value less than or equal to the value of t. In such case, the leaf descendants of cluster node will belong to the same flat cluster. Whereas, if this is not the case then every node will be assigned to its own cluster.**distance**− The criterion distance will form flat clusters having condition that the original observations in each flat cluster have cophenetic distance equal to or less than t.**maxclust**− The criterion maxclust will find a minimum threshold value r. It assures that the cophenetic distance between any two original observations in the same flat clusters will always be less than or equal to r and t.**monocrit**− The criterion monocrit will form a flat cluster from a cluster node with index i when monocrit[i] <=t.**maxclust_monocrit**− The criterion maxclust_monocrit will form a flat cluster from a non-singleton cluster node with index i when monocrit[i] <=r.**depth**− int, optionalThis parameter represents the maximum depth to perform the inconsistency calculation. The default value of depth parameter is 2 and it has no meaning for any other criteria.

**R**− ndarray, optionalThis parameter represents the inconsistency matrix to be used for the inconsistent criterion. The default value is NONE and if it is not provided then the matrix will be computed.

**monocrit**− ndarray, optionalThis parameter is an array length of n-1.

## Returns

**flcuster**− ndarrayIt returns an array of length n.

- Related Questions & Answers
- What is scipy cluster hierarchy? How to cut hierarchical clustering into flat clustering?
- What is Cluster Computing?
- What Is Cluster Analysis?
- What is memory hierarchy?
- What is Semi-Supervised Cluster Analysis?
- What is a process hierarchy?
- What is Chomsky Hierarchy in compiler design?
- What is IPV4 address notation and hierarchy of addressing?
- What is the difference between SciPy and NumPy?
- What are the elements of the cluster?
- What is SciPy and why should we use it?
- Storage Device Hierarchy
- What are the types of Constraint-Based Cluster Analysis?
- What is the use of scipy.interpolate.interp1d class of SciPy python library?
- SciPy is built upon which core packages?
- What is the techniques of Discretization and Concept Hierarchy Generation for Categorical Data?