Skip to main content
Join the official 2019 Python Developers SurveyStart the survey!

Unsupervised Random Forest (Random Forest Clustering)

Project description

URF (Unsupervised Random Forest, or Random Forest Clustering) is a python implementation of the paper: Shi, T., & Horvath, S. (2006). Unsupervised learning with random forest predictors. Journal of Computational and Graphical Statistics, 15(1), 118-138.

Prerequisite

conda install -c bioconda pycluster

or:

wget http://bonsai.hgc.jp/~mdehoon/software/cluster/Pycluster-1.54.tar.gz
tar -zxvf Pycluster-1.54.tar.gz
cd Pycluster-1.54
python setup.py install

Installation

pip install URF

Usage

from sklearn.datasets import load_iris
from URF.main import random_forest_cluster, plot_cluster_result
iris = load_iris()
X = iris.data
y = iris.target
print(len(list(set(y))))

clf, prox_mat, cluster_ids = random_forest_cluster(X, k=3, max_depth=20, random_state=0)
plot_cluster_result(prox_mat, cluster_ids, marker=y)

If you encountered an error like

> QXcbConnection: Could not connect to display

then you need to add these codes to the very beginning of your file:

import matplotlib as mpl
mpl.use("Agg")

and you must assign the output file when you call plot_cluster_result, like this:

plot_cluster_result(prox_mat, cluster_ids, marker=y, output="test_123.png")

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for URF, version 0.0.5
Filename, size File type Python version Upload date Hashes
Filename, size URF-0.0.5.tar.gz (3.7 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page