DenStream | Python implementation of the data stream clustering | Machine Learning library
kandi X-RAY | DenStream Summary
kandi X-RAY | DenStream Summary
This a Python implementation of the data stream clustering algorithm "DenStream". The implementation is compatible with scikit-learn and follows the scikit-learn API for clustering algorithms. Details about how the algorithm works can be found in the original paper "Density-Based Clustering over an Evolving Data Stream with Noise", which is available here.
Support
Quality
Security
License
Reuse
Top functions reviewed by kandi - BETA
- Fit the predictive clustering
- Insert a new sample
- Attempt to merge the given sample into a new one
- Performs partial fitting
- Validate the sample weight
- Find the nearest micro clusters in the given sample
- Try to merge the given sample with the given weight
- Calculate the decay function
- Return sum of weights
- Perform partial clustering
- Calculate the radius
- The radius of the distribution
- Center of the mean
- Center of the linear sum
DenStream Key Features
DenStream Examples and Code Snippets
Community Discussions
Trending Discussions on DenStream
QUESTION
I am new into using moa and I am having a hard time trying to decode how the clustering algorithms have to be used. The documentation lacks of sample code for common usages, and the implementation is not well explained with comments ... have not found any tutorial either.
So, here is my code:
...ANSWER
Answered 2019-Nov-19 at 07:04I have updated the code. It is working as I mentioned in the github, you have to assign header to your instance. See the github discussion
here is the updated code:
QUESTION
I have always used Python for clustering, but recently I came across a situation in which I need the implementations of both CluStream and DenStream (stream clustering algorithms), available in R and Java (there are some implementations in Python from the community but I already tried them and they do no work).
The thing is that I have to compare many clustering algorithms written in Python, and as a prev stage I was using the well known scikit learn data sets (to show how algorithms handle non-globular clusters - of course then I will use time series data).
Now, I wanna know if the proper way to try those R/Java algorithms and compute a metric coded in Python (DBCV) with the R/Java clustering results ....
--> So, summing up, I need to compare many algorithms (coded in Python and R/Java) using the same data sets (which I figured could be persisted into csv files) and computing the same validity metric (Python).
Any help would be appreciated. Thanks in advance!
EDIT: the solution I came across is the following:
- Generate the toy data sets with sklearn and persist them into csv files
- Use the different clustering algorithms with those data sets and persist also the clustering results into csv files (it does not matter which programming language it's used)
- Develop another app which:
- takes the clustering solutions stored in the cvs files
- computes the metric and shows the results
PLEASE let me know if you find a better solution!
Notes:
- This R package is the one i wanna try: streamMOA
- I do not know anything about R and I have worked with Java before (what implementation I choose depends on the better approach regarding the integration with Python)
ANSWER
Answered 2019-Nov-13 at 16:31MOA is a Java software. There is no good reason to use it via R unless you are already in the R ecosystem (which you aren't).
You can write the data to CSV and load it in whatever tool you like
These data sets are not streams. They lack all the difficulties and challenges of streams - a simple subsample will be enough to identify the clustering structure. Conclusions drawn from this data are useless. Use real data streams, not synthetic data with no sequential order to it.
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install DenStream
You can use DenStream like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.
Support
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page