ima-preparation/god-2022
Claudio Maggioni 0ee4bb302b renamed god-2022 project 2023-02-15 16:42:19 +01:00
..
clustering renamed god-2022 project 2023-02-15 16:42:19 +01:00
feature_vectors renamed god-2022 project 2023-02-15 16:42:19 +01:00
god_classes renamed god-2022 project 2023-02-15 16:42:19 +01:00
.gitignore renamed god-2022 project 2023-02-15 16:42:19 +01:00
README.md renamed god-2022 project 2023-02-15 16:42:19 +01:00
extract_feature_vectors.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
find_god_classes.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
ground_truth.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
hierarchical.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
k_means.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
keyword_list.txt renamed god-2022 project 2023-02-15 16:42:19 +01:00
prec_recall.py renamed god-2022 project 2023-02-15 16:42:19 +01:00
requirements.txt renamed god-2022 project 2023-02-15 16:42:19 +01:00
silhouette.py renamed god-2022 project 2023-02-15 16:42:19 +01:00

README.md

IMA - God classes project

Xerces2

Running

Part 3: clustering and silhouette metric

To compute optimal k-means and agglomerative clusterings using silhouette validation for all classes run:

./silhouette.py --validate --autorun

To compute k-means or agglomerative clustering for a specific number of clusters K and a specific class KLASS run respectively:

./k_means.py KLASS K
./hierarchical.py KLASS K

Then, to check their silhouette metric run:

./silhouette.py

Install dependencies

# create venv
python -m venv env
source env/bin/activate

pip3 install -r requirements.txt