mlpack_mean_shift(1)

💖 mlpack_mean_shift 💖

okay bestie, welcome to mlpack_mean_shift — she's a User Command from the mlpack family and she does mean shift clustering. yes. that. let's get into it 🦋

---

✨ SYNOPSIS ✨

mlpack_mean_shift -i unknown [-f bool] [-P bool] [-l bool] [-m int] [-r double] [-V bool] [-C unknown] [-o unknown] [-h -v]

---

🌸 DESCRIPTION 🌸

so this program does mean shift clustering on the dataset you hand her, and then she stores the learned cluster assignments either as a column of labels dropped right into the input dataset, or separately. your choice, queen 👑

the input dataset goes in with the --input_file (-i) parameter, and the radius used for the search is set with --radius (-r). the max number of iterations before she just calls it and terminates is controlled by --max_iterations (-m) ✨

the output labels can be saved with the --output_file (-o) output parameter, and the centroids of each cluster go to --centroid_file (-C).

like, for an actual example — to run mean shift clustering on the dataset data.csv and store the centroids to centroids.csv, you'd literally just do:

$ mlpack_mean_shift --input_file data.csv --centroid_file centroids.csv

ate. periodt 💅

---

🎀 REQUIRED INPUT OPTIONS 🎀

• --input_file (-i) [unknown] — the input dataset she's gonna perform clustering on. no dataset, no clustering, no vibes. this one's mandatory fr fr.

---

🌈 OPTIONAL INPUT OPTIONS 🌈

• --force_convergence (-f) [bool] — if you specify this, the mean shift algorithm keeps running regardless of max_iterations until the clusters converge. yes she's stubborn. no she will not be stopped 😤
• --help (-h) [bool] — the default help info. your lil safety net 🫶
• --in_place (-P) [bool] — if specified, a column containing the learned cluster assignments gets added to the input dataset file. and in that case, --output_file is overridden, so don't even bother. (Do not use with Python.) 🚨
• --info [string] — print help on one specific option. default value is ''.
• --labels_only (-l) [bool] — if specified, only the output labels get written to the file you gave --output_file. nothing else, just the labels ✨
• --max_iterations (-m) [int] — maximum number of iterations before mean shift terminates. default value 1000.
• --radius (-r) [double] — if the distance between two centroids is less than the given radius, one of them gets removed. a radius of 0 or less means an estimate will be calculated and used for the radius instead. default value 0.
• --verbose (-v) [bool] — display informational messages plus the full list of parameters and timers at the end of execution. she's a talker 💬
• --version (-V) [bool] — display the version of mlpack.

---

👑 OPTIONAL OUTPUT OPTIONS 👑

• --centroid_file (-C) [unknown] — if specified, the centroids of each cluster get written to the given matrix.
• --output_file (-o) [unknown] — the matrix to write output labels or labeled data to.

---

🧚 ADDITIONAL INFORMATION 🧚

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

---

lowkey obsessed with you for reading the whole thing. now go cluster something 💜

mlpack-4.8.0 · 22 June 2026 · mwah, that's the version, that's the date, that's the whole manual page bestie, slay 🎀✨