mlpack_dbscan(1)

💖 mlpack_dbscan — the manual page, but make it bestie ✨

okay so real quick, this is the manpage for mlpack_dbscan(1) from the User Commands crew, and honestly? it's giving "clustering but make it fast". let's get into it 🫶

---

✨ NAME ✨

mlpack_dbscan — dbscan clustering 💅

---

🌸 SYNOPSIS 🌸

mlpack_dbscan -i unknown [-e double] [-m int] [-N bool] [-s string] [-S bool] [-t string] [-V bool] [-a unknown] [-C unknown] [-h -v]

no cap, that's the whole shape of it. now let's break it down 🦋

---

💜 DESCRIPTION 💜

so this program implements the DBSCAN algorithm for clustering, and it does it with accelerated tree-based range search. the type of tree it uses can be parameterized, or you can just go full brute-force mode for the range search instead. your call bestie 😌

the input dataset you wanna cluster gets specified with --input_file (-i). the radius of each range search? that's --epsilon (-e). and the minimum number of points in a cluster? that's --min_size (-m). slay.

for saving your results, you've got --assignments_file (-a) and --centroids_file (-C). --assignments_file (-a) holds the cluster assignments of each point, and --centroids_file (-C) holds the centroids of each cluster. icon behavior ✨

the range search itself is controlled with --tree_type (-t), --single_mode (-S), and --naive (-N). here's the tea:

• --tree_type (-t) controls what kind of tree is used for range search, and it can take a whole variety of values: kd, r, r-star, x, hilbert-r, r-plus, r-plus-plus, cover, ball.
• --single_mode (-S) forces single-tree search (so, not the default dual-tree search).
• --naive (-N) forces brute-force range search. no thoughts, head empty, just raw range searching 💀

an example usage to run DBSCAN on the dataset in input.csv with a radius of 0.5 and a minimum cluster size of 5 is below:

$ mlpack_dbscan --input_file input.csv --epsilon 0.5 --min_size 5

periodt. that's the whole vibe 🔥

---

🎀 REQUIRED INPUT OPTIONS 🎀

• --input_file (-i) [unknown] — the input dataset to cluster. you literally cannot skip this one bestie, it's required.

---

🌈 OPTIONAL INPUT OPTIONS 🌈

• --epsilon (-e) [double] — the radius of each range search. default value is 1.
• --help (-h) [bool] — default help info.
• --info [string] — print help on a specific option. default value is ''.
• --min_size (-m) [int] — the minimum number of points for a cluster. default value is 5.
• --naive (-N) [bool] — if set, brute-force range search (not tree-based) will be used.
• --selection_type (-s) [string] — if using a point selection policy, this is the type of selection to use ('ordered', 'random'). default value is 'ordered'.
• --single_mode (-S) [bool] — if set, single-tree range search (not dual-tree) will be used.
• --tree_type (-t) [string] — if using single-tree or dual-tree search, this is the type of tree to use ('kd', 'r', 'r-star', 'x', 'hilbert-r', 'r-plus', 'r-plus-plus', 'cover', 'ball'). default value is 'kd'.
• --verbose (-v) [bool] — display informational messages and the full list of parameters and timers at the end of execution.
• --version (-V) [bool] — display the version of mlpack.

---

💅 OPTIONAL OUTPUT OPTIONS 💅

• --assignments_file (-a) [unknown] — output matrix for assignments of each point.
• --centroids_file (-C) [unknown] — matrix to save output centroids to.

---

👑 ADDITIONAL INFORMATION 👑

for further information — including relevant papers, citations, and theory — consult the documentation found at http://www.mlpack.org or included with your distribution of mlpack. iykyk 📚

fr fr, if you want the theory deep dive, that's where it lives.

---

and that's a wrap on mlpack_dbscan(1) bestie 🧚 this page is from mlpack-4.8.0, dated 22 June 2026, and it was so real of you to read the whole thing. go cluster something iconic 💖✨