Skip to main content

Questions tagged [dbscan]

Density-based spatial clustering of applications with noise (DBSCAN) is a data clustering algorithm. DBSCAN views clusters as areas of high density separated by areas of low density.

Filter by
Sorted by
Tagged with
1 vote
1 answer
17 views

Quantifying (observed) spatial clustering?

I am looking for some advice regarding spatial statistics. I have a large dataset with multiple samples across 5 different conditions. Each sample is composed of different point types in 2D space. For ...
stellaria's user avatar
1 vote
0 answers
38 views

Why is HDBSCAN considered a transductive clustering algorithm despite having approximate_predict?

In the documents for HDBSCAN it says the following: Often it is useful to train a model once on a large amount of data, and then query the model repeatedly with small amounts of new data. This is ...
TunaFishLies's user avatar
0 votes
0 answers
60 views

Assumption in DBSCAN Clustering

Does the non-multicollinearity assumption apply to DBSCAN? I've read that this clustering method makes no assumptions about the density or variance in clusters that may exist in the data set. Can that ...
Anna's user avatar
  • 3
0 votes
1 answer
117 views

Data Standardization in DBSCAN Clustering

"If the data has a much different range of measurement values, data standardization is carried out so that the distance calculation becomes effective. For example, if the income variable is ...
Anna's user avatar
  • 3
4 votes
2 answers
365 views

Question about Silhouette index calculation using scikit

I am currently working with continuous data measured from different sensors (thermometers and voltmeters). I have a matrix whose columns represent the sensors and the rows are normalized measurements (...
slow_learner's user avatar
1 vote
1 answer
122 views

Elbow method for tuning DBSCAN when the minimum number of points per cluster is one

The elbow method calls for setting the number of nearest neighbors (let's call it $k$) to the minimum number of points for a cluster (let's call it $m$), but what do you do when $m\leftarrow1$? Is the ...
Chris Coffee's user avatar
1 vote
1 answer
35 views

Is there a way to automatically split large clusters that are greater than some maximum number of points?

I ran HDBSCAN on these coordinates and got some clusters but some are too large. HDBSCAN has a minimum cluster size parameter, but no maximum size. All I want is to intuitively divide larger clusters ...
Ben Hendel's user avatar
0 votes
0 answers
119 views

When using a gower dissimilarity matrix for use in dbscan clustering, the bools still perfectly separate the clusters

I am working on a clustering analysis where my data is a mix of bool and numeric. From research it looks like one should not do a simple kmeans with mixed data types since the extreme end of scaled ...
Doug Fir's user avatar
  • 1,588
4 votes
1 answer
872 views

HDBSCAN on UMAP output

My question is about using UMAP as a dimensional reduction technique before HDBSCAN clustering. I have a dataset of ~5000 observations each with ~20 descriptors. According to HDBSCAN guidelines, ...
IvyBlue's user avatar
  • 43
1 vote
0 answers
247 views

Unstable HDBSCAN & UMAP clustering results

I've segmented my data using UMAP (dimensionality reduction, with a fixed random seed) and subsequently HDBSCAN to generate a number of clusters. I've also looped through different values to fine-tune ...
sara's user avatar
  • 11
1 vote
0 answers
19 views

unable to figure out why overlapped clustering is occuring

i am appling k means and DBSCAN to the same data set which is in csv format, but i'm unable to get good results. I have attached the DBSCAN results.I,m getting overlapped clusters and can't figure out ...
user387109's user avatar
1 vote
0 answers
32 views

Spatial clustering [duplicate]

I am interested in investigating spatial clustering in a certain dataset. Spatial clustering is a technique used in data analysis to group together objects or data points based on their proximity in ...
DanielTheRocketMan's user avatar
1 vote
1 answer
231 views

Unsupervised learning: How to identify differences between clusters?

I'm learning about unsupervised learning and I tried to use KMeans, AgglomerativeClustering and DBSCAN on the same datase. The result was ok, they seems to work fine according silhouette_score() ...
Antonio Caipora's user avatar
2 votes
1 answer
94 views

In DBSCAN, what happens if points have distance exactly equal to the Epsilon radius of a core point?

In DBSCAN the border points are points in the eps-neighborhood of a core point. But what if a point has distance exactly equal to Epsilon from a core point? Is it considered inside the eps radius, or ...
SuperFluo's user avatar
0 votes
0 answers
2k views

Silhouette Score with Noise (from DBSCAN)

I stumbled across this example on scikit-learn (1.2.0), where the silhouette score alongside some other metrics is computed for DBSCAN cluster assignments. These assignments include some Noise ...
MERose's user avatar
  • 419
0 votes
0 answers
105 views

What are consequences of forming clusters on variables that are not normally distributed?

I am trying to use DBSCAN to obtain clusters of chess player rating changes (Elo rank) over one year of games. I have a bunch of input variables, some of which are not normally distributed even if I ...
TunaFishLies's user avatar
2 votes
2 answers
2k views

Implementing cross-validation to tune the hyperparameters of an unsupervised model

I have extensively researched the application of cross validation for unsupervised learning (as it is a requirement by my project manager) but it seems that there is no clear consensus as to how to ...
Octave's user avatar
  • 35
0 votes
0 answers
27 views

Regarding kmeans clustering, is it ok if I set the number of clusters just to get appropriate number of data of target cluster that I'm interested in?

For example, let me suppose that I have 100 thousands of geospatial data in my dataset, and I want to extract certain group that which is the most crucial. So I decided to do clustering and pick 'one ...
hogu's user avatar
  • 23
5 votes
1 answer
734 views

Why do I get different results after shuffling data using DBSCAN

Sometimes, by simply shuffling my data, not changing the parameters, I get a different cluster result using sklearn.DBSCAN. Why this happens? I mean, by shuffling data, the data distribution is the ...
Brown_Z's user avatar
  • 53
0 votes
0 answers
35 views

Which clustering methodologies are likely to be best for this data?

I'm using the classic "use-case" example of clustering pixels in a photograph. I've tried K-means, agglomerative clustering, and DBSCAN. When I plot the RGB coordinates in 3-D space, all 3 ...
NaiveBae's user avatar
  • 257
1 vote
0 answers
705 views

DBSCAN clustering - epsilon

How do we decide on the optimum epsilon and min_samples to be specified given our data? Take this for example - Demo of DBSCAN clustering algorithm via https://scikit-learn.org/stable/auto_examples/...
Wong's user avatar
  • 33
0 votes
1 answer
307 views

Normalizing Topic Vectors in Top2vec

I am trying to understand how Top2Vec works. I have some questions about the code that I could not find an answer for in the paper. A summary of what the algorithm does is that it: embeds words and ...
Ahmed Elashry's user avatar
3 votes
0 answers
54 views

Cluster Algorithm for multidimensional data

My goal is to cluster data (20000 samples with a range from 0.0 to 1.0, and 14 dimensions/features). Since I don't know the number of clusters, I tried using MeanShift and DBSCAN. My problem with ...
Flitschi's user avatar
1 vote
1 answer
1k views

Is there a way to locate automatically the knee of the k-nearest neighbour graph in a DBSCAN analysis? [duplicate]

I am trying to write a function in R that automatically chooses the optimal parameters epsilon and MinPts in a DBSCAN analysis. I found that the k-nearest neighbour plot was very useful in order to ...
Swann's user avatar
  • 11
4 votes
3 answers
2k views

HDBSCAN: most data clustered as noise (-1)

I am trying to perform topic modeling on text data, ie. cluster the text messages by topic. I am approaching this by using a BERT model to get sentence embeddings, then use T-sne to reduce the ...
Fiori's user avatar
  • 211
1 vote
0 answers
142 views

External loss functions for Spectral/Density-based clustering

In this article, Abou-Mustafa and Schuurmans proposed a method that makes it easy to decide what unsupervised learning algorithm generalizes 'better' to the entire dataset. In particular, this needs ...
drommedaris's user avatar
4 votes
2 answers
3k views

Suitable approach to cluster histogram-like dataset using HDBSCAN implementation in python

My dataset below shows product sales per price (link to download dataset csv): ...
Eduardo Gomes's user avatar
0 votes
1 answer
225 views

Minimum distance between pair of points in DBSCAN

I have just used DBSCAN to detect the outliers. If $\epsilon$ is the radius as the given parameter, then a point is outlier means it's distance with all points greater than $\epsilon$, But I have just ...
Subhajit Saha's user avatar
0 votes
0 answers
565 views

HDBSCAN Soft clustering - Why everything becomes 1 class?

GOAL Using HDBSCAN Putting all data points in to a class and leaving behind 0 point as noise (in other words partitioning the data without leaving behind any unallocated data points) DONE I have a ...
sogu's user avatar
  • 101
0 votes
0 answers
254 views

How to group every data point with HDBSCAN to some group to have no noise?

TASK I am clustering products with about 70 dimensions ex.: price, rating 5/5, product tag(cleaning, toy, food, fruits) I use HDBSCAN to do it GOAL The goal is when users come on our site and I can ...
sogu's user avatar
  • 101
1 vote
0 answers
25 views

Does the N-dimensional hypervolume refer to the N attributes we have in the training sets?

If we have $N$ features in the feature set that is being used to train a machine learning model, does the $N$ here cause the data points to be in hyperspace provided that $N > 3$? I'm assuming that ...
learnerX's user avatar
  • 223
1 vote
0 answers
720 views

ROC and AUC for clustering algorithms [closed]

I am working on some clustering algorithms like DBSCAN and local outlier factor. Now i want to know how can I make ROC and AUC curves from clustering results. Do anyone know how can i make RO and AUC ...
Saqlain Gardezi's user avatar
1 vote
1 answer
1k views

Clustering DBSCAN's parameter Epsilon: How is eps related to scale of data being clustered?

How is scale of eps related to data to be clustered in DBSCAN? e.g. in image of 1024x1024, we have points as: ...
sandeepsign's user avatar
2 votes
0 answers
197 views

Can DBSCAN overcome the drawbacks of K-means?

We have a great post to discuss the drawbacks of K-means. Can DBSCAN overcome these drawbacks? and what are the drawbacks of DBSCAN?
Haitao Du's user avatar
  • 37.2k
1 vote
0 answers
1k views

What are the assumptions of DBSCAN?

Does DBSCAN (Density-based spatial clustering of applications with noise) assume that the data follows a Gaussian distribution? and does the data need to be standardized (mean $0$ and standard ...
Aastha Jha's user avatar
3 votes
1 answer
339 views

Do $k$-means, dbscan, and hierarchical clustering all rely on (pseudo)metrics?

I seems to me that the clustering methods $k$-means, dbscan, and hierarchical clustering all work on distance measures $d$ that are (pseudo)metrics, i.e., fulfill the following requirements: $$ d(x,x)=...
Thomas's user avatar
  • 33
1 vote
1 answer
291 views

Definition of boundary points in DBSCAN

If I understand correctly, DBSCAN is the following method of decomposing a set, which has parameters $\epsilon$ and $k$. Given a set $E$ of points in $\mathbb R^n$, consider the graph $G$ whose ...
Justthisguy's user avatar
1 vote
0 answers
294 views

How to achieve good clustering results in subsequence time series clustering with DBSCAN?

I want to find patterns in a time series and use clustering for that. Before I cluster, I create subsequences from the time series using a sliding window approach. (STS-clustering) So far I have tried ...
Philipp's user avatar
  • 121
2 votes
2 answers
202 views

Separate clusters from a single column of data

Is there any statistical method to separate the visual groups of data from the graph shown below? As you can see from the figure, there are 4 clusters of data which I wan to separate them out. I ...
ACE's user avatar
  • 213
0 votes
0 answers
193 views

Clustering Highly Skewed and Segmented Data

So I am trying to cluster a dataset that looks like the following: I have tried K-Means and GMM, which give me horrible results. I have tried DBSCAN, which was okay, but it is difficult to choose the ...
The Dude's user avatar
  • 111
0 votes
1 answer
922 views

Generated more than 10+ clusters DBScan

So I am trying to generate a clustered graph using DBScan. I am able to do so but somehow gotten the clustered graph with more than 10+ clusters. It can be seen below. What I was expecting was ...
digdigdoot's user avatar
0 votes
0 answers
226 views

Which is the best clustering algorithm for clustering multidimensional data with low density difference?

I am working on a project currently and I wish to cluster multi-dimensional data. I tried K-Means clustering and DBSCAN clustering, both being completely different algorithms. The K-Means model ...
Ashish Rao's user avatar
4 votes
1 answer
909 views

Unsupervised soft clustering methods

I have a D-dimensional dataset composed of exactly two clusters (this is known) for which I have no labels; the clusters can potentially be wildly imbalanced. I'm after a soft (or fuzzy) clustering ...
Gabriel's user avatar
  • 4,352
0 votes
1 answer
139 views

Searching for a DBSCAN toy example

I have been searching in many sources (data science books, google scholar, google and medium) but I havn't found a good example. I'm searching for something like that just in DBSCAN. Thanks
Amit S's user avatar
  • 57
1 vote
0 answers
198 views

How to plot categories after clustering

I am trying to plot the categories I have obtained via DBSCAN on a 30-dimensional dataset 12 categories, and I want to visualize them in a 2d plot. My procedure was to reduce that 30-dimensional ...
astro_xyz's user avatar
4 votes
1 answer
6k views

which metrics are suitable for density-based clustering validation?

I'm working on a project where I use several clustering methods, mainly density based ones such as hdbscan, optics... I'm looking for a metric to evaluate clustering results that takes into account ...
curiosus's user avatar
  • 323
4 votes
2 answers
8k views

How to use Gower's Distance with DBSCAN algorithm in Python [closed]

I have been researching about using DBSCAN with sklearn in python but it doesn't have Gower's distance metric built in. All the other implementations are in R in this community. I'm using a dataset ...
Gonzalo Garcia's user avatar
1 vote
1 answer
107 views

Correct clustering approach for segmenting stores

Domain : Retail I have a set of stores which I want to cluster into similar stores based on 10 variables: revenue, avg income, market share etc. I took 2 approach: Approach 1: Given there are 10 ...
bakas's user avatar
  • 143
0 votes
1 answer
1k views

Suggestions to cluster more than 300k observations

I am trying to perform an hierarchical clustering on data frame that contains 300k records 7 features (3 binaries and 4 continuous) in order to get insights on what looks like my dataset. I've chosen ...
nariver1's user avatar
  • 121
1 vote
1 answer
1k views

How does non-uniqueness of data (aka duplicate data points) affect clustering?

I am trying to self-learn more about different clustering methods. I think I understand the main idea of the algorithms, but perhaps their use-cases can shed light on something that puzzles me - ...
user avatar