Skip to content

add everything to conda yml #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
markrobinsonuzh wants to merge 4 commits into
base: update-to-0.4
Choose a base branch
from
Open

add everything to conda yml #47

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a379497
add everything to conda yml
markrobinsonuzh Jan 20, 2026
ce838e2
updates to README.md + conda plan
markrobinsonuzh Jan 20, 2026
d2c4458
harmonize all three backends to have the same data/methods/metrics
markrobinsonuzh Jan 20, 2026
97bed63
few more harmonizations - naming mostly
markrobinsonuzh Jan 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
181 changes: 33 additions & 148 deletions Clustering_conda.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
id: clustering_example_conda
description: Clustering benchmark on Gagolewski's, true number of clusters plus minus 2.
id: omni-clustbench-conda
description: "Clustering benchmark on Gagolewski's, true number of clusters plus minus 2."
version: "1.5.0"
benchmarker: "Izaskun Mallona, Daniel Incicau, Ben Carrillo"
benchmarker: "Izaskun Mallona, Daniel Incicau, Ben Carrillo, Mark Robinson"
storage:
api: S3
endpoint: http://omnibenchmark.mls.uzh.ch:9000
Expand All @@ -11,25 +11,21 @@ software_environments:
clustbench:
description: "clustbench on py3.12.6"
conda: envs/clustbench.yml
envmodule: clustbench
apptainer: oras://quay.io/imallona/clustering_example/clustbench:latest
fcps:
description: "CRAN's FCPS"
conda: envs/fcps.yml
apptainer: oras://quay.io/imallona/clustering_example/fcps:latest
envmodule: fcps
metric_collectors:
- id: plotting
name: "Single-backend metric collector."
software_environment: "fcps"
repository:
url: https://github.com/imallona/clustering_report
commit: 040
inputs:
- metrics.scores
outputs:
- id: plotting.html
path: "{name}/plotting_report.html"
#metric_collectors:
# - id: plotting
# name: "Single-backend metric collector."
# software_environment: fcps
# repository:
# url: https://github.com/imallona/clustering_report
# commit: 040
# inputs:
# - metrics.scores
# outputs:
# - id: plotting.html
# path: "{name}/plotting_report.html"
stages:
## clustbench data ##########################################################

Expand All @@ -43,115 +39,17 @@ stages:
commit: fc67ebd
parameters: # comments depict the possible cardinalities and the number of curated labelsets
- dataset_generator: "fcps"
dataset_name: ["atom", "chainlink"] # 2 1
# - dataset_generator: "fcps"
# dataset_name: ["engytime", "hepta", "lsun", "target", "tetra", "twodiamonds", "wingnut"] # 7 1, 3 1, 2,6 2, 4 1, 2 1, 2 1
# - dataset_generator: "graves"
# dataset_name: ["dense"] # 2 1
# - dataset_generator: "graves"
# dataset_name: ["fuzzyx"] # 2,4,5 6
# - dataset_generator: "graves"
# dataset_name: ["line"] # 2 1
# - dataset_generator: "graves"
# dataset_name: ["parabolic"] # 2,4 2
# - dataset_generator: "graves"
# dataset_name: ["ring"] # 2 1
# - dataset_generator: "graves"
# dataset_name: ["ring_noisy"] # 2 1
# - dataset_generator: "graves"
# dataset_name: ["ring_outliers"] # 2,5 2
# - dataset_generator: "graves"
# dataset_name: ["zigzag"] # 3,5 2
# - dataset_generator: "graves"
# dataset_name: ["zigzag_noisy"] # 3,5 2
# - dataset_generator: "graves"
# dataset_name: ["zigzag_outliers"] # 3,5 2
# - dataset_generator: "other"
# dataset_name: ["chameleon_t4_8k"] # 6 1
# - dataset_generator: "other"
# dataset_name: ["chameleon_t5_8k"] # 6 1
# - dataset_generator: "other"
# dataset_name: ["hdbscan"] # 6 1
# - dataset_generator: "other"
# dataset_name: ["iris"] # 3 1
# - dataset_generator: "other"
# dataset_name: ["iris5"] # 3 1
# - dataset_generator: "other"
# dataset_name: ["square"] # 2 1
# - dataset_generator: "sipu"
# dataset_name: ["aggregation"] # 7 1
# - dataset_generator: "sipu"
# dataset_name: ["compound"] # 4,5,6 5
# - dataset_generator: "sipu"
# dataset_name: ["flame"] # 2 2
# - dataset_generator: "sipu"
# dataset_name: ["jain"] # 2 1
# - dataset_generator: "sipu"
# dataset_name: ["pathbased"] # 3,4 2
# - dataset_generator: "sipu"
# dataset_name: ["r15"] # 8,9,15 3
# - dataset_generator: "sipu"
# dataset_name: ["spiral"] # 3 1
# - dataset_generator: "sipu"
# dataset_name: ["unbalance"] # 8 1
# - dataset_generator: "uci"
# dataset_name: ["ecoli"] # 8 1
# - dataset_generator: "uci"
# dataset_name: ["ionosphere"] # 2 1
# - dataset_generator: "uci"
# dataset_name: ["sonar"] # 2 1
# - dataset_generator: "uci"
# dataset_name: ["statlog"] # 7 1
# - dataset_generator: "uci"
# dataset_name: ["wdbc"] # 2 1
# - dataset_generator: "uci"
# dataset_name: ["wine"] # 3 1
# - dataset_generator: "uci"
# dataset_name: ["yeast"] # 10 1
# - dataset_generator: "wut"
# dataset_name: ["circles"] # 4 1
# - dataset_generator: "wut"
# dataset_name: ["cross"] # 4 1
# - dataset_generator: "wut"
# dataset_name: ["graph"] # 10 1
# - dataset_generator: "wut"
# dataset_name: ["isolation"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["labirynth"] # 6 1
# - dataset_generator: "wut"
# dataset_name: ["mk1"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["mk2"] # 2 1
# - dataset_generator: "wut"
# dataset_name: ["mk3"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["mk4"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["olympic"] # 5 1
# - dataset_generator: "wut"
# dataset_name: ["smile"] # 4,6 2
# - dataset_generator: "wut"
# dataset_name: ["stripes"] # 2 1
# - dataset_generator: "wut"
# dataset_name: ["trajectories"] # 4 1
# - dataset_generator: "wut"
# dataset_name: ["trapped_lovers"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["twosplashes"] # 2 1
# - dataset_generator: "wut"
# dataset_name: ["windows"] # 5 1
# - dataset_generator: "wut"
# dataset_name: ["x1"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["x2"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["x3"] # 4 1
# - dataset_generator: "wut"
# dataset_name: ["z1"] # 3 1
# - dataset_generator: "wut"
# dataset_name: ["z2"] # 5 1
# - dataset_generator: "wut"
# dataset_name: ["z3"] # 4 1
dataset_name: ["atom", "chainlink", "engytime", "hepta", "lsun", "target", "tetra", "twodiamonds", "wingnut"]
- dataset_generator: "graves"
dataset_name: ["dense", "fuzzyx", "line", "parabolic", "ring", "ring_noisy", "ring_outliers", "zigzag", "zigzag_noisy", "zigzag_outliers"]
- dataset_generator: "other"
dataset_name: ["chameleon_t4_8k", "chameleon_t5_8k", "hdbscan", "iris", "iris5", "square"]
- dataset_generator: "sipu"
dataset_name: ["aggregation", "compound", "flame", "jain", "pathbased", "r15", "spiral", "unbalance"]
- dataset_generator: "uci"
dataset_name: ["ecoli", "ionosphere", "sonar", "statlog", "wdbc", "wine", "yeast"]
- dataset_generator: "wut"
dataset_name: ["circles", "cross", "graph", "isolation", "labirynth", "mk1", "mk2", "mk3", "mk4", "olympic", "smile", "stripes", "trajectories", "trapped_lovers", "twosplashes", "windows", "x1", "x2", "x3", "z1", "z2", "z3"]
outputs:
- id: data.matrix
path: "{dataset}.data.gz"
Expand All @@ -169,27 +67,24 @@ stages:
url: https://github.com/imallona/clustbench_fastcluster
commit: e644ce5
parameters:
- linkage: "complete"
#- linkage: ["ward", "average", "weighted", "median", "centroid"]
- linkage: ["complete", "ward", "average", "weighted", "median", "centroid"]
- id: sklearn
name: "sklearn"
software_environment: "clustbench"
repository:
url: https://github.com/imallona/clustbench_sklearn
commit: dcf35e1
parameters:
- method: "birch"
# ["kmeans, "gm"]
# ["spectral"] ## too slow
- method: ["birch", "kmeans", "gm"]
# "spectral" ## too slow
- id: agglomerative
name: "agglomerative"
software_environment: "clustbench"
repository:
url: https://github.com/imallona/clustbench_agglomerative
commit: 9d086a9
parameters:
- linkage: "average"
# ["complete", "ward"]
- linkage: ["average", "complete", "ward"]
- id: genieclust
name: "genieclust"
software_environment: "clustbench"
Expand All @@ -198,28 +93,18 @@ stages:
commit: 7d9e799
parameters:
- method: "genie"
# method: ["gic", "ica"]
gini_threshold: 0.5
- method: ["gic", "ica"]
- id: fcps
name: "fcps"
software_environment: "fcps"
repository:
url: https://github.com/imallona/clustbench_fcps
commit: e780fed
parameters:
- method: "FCPS_Minimax"
- method: ["FCPS_Minimax", "FCPS_MinEnergy", "FCPS_HDBSCAN_2", "FCPS_HDBSCAN_4", "FCPS_HDBSCAN_8", "FCPS_Diana", "FCPS_Fanny", "FCPS_Hardcl", "FCPS_Softcl", "FCPS_Clara", "FCPS_PAM"]
seed: 2
# - "FCPS_AdaptiveDensityPeak" # not in Conda
# - "FCPS_MinEnergy",
# - "FCPS_HDBSCAN_2",
# - "FCPS_HDBSCAN_4",
# - "FCPS_HDBSCAN_8",
# - "FCPS_Diana",
# - "FCPS_Fanny",
# - "FCPS_Hardcl",
# - "FCPS_Softcl",
# - "FCPS_Clara",
# - "FCPS_PAM"
inputs:
- data.matrix
- data.true_labels
Expand All @@ -236,7 +121,7 @@ stages:
url: https://github.com/imallona/clustbench_metrics
commit: c4eda85
parameters:
- metric: ["normalized_clustering_accuracy", "adjusted_fm_score"]
- metric: ["normalized_clustering_accuracy", "adjusted_fm_score", "adjusted_rand_score"]
# - "adjusted_mi_score"
# - "adjusted_rand_score"
# - "fm_score"
Expand Down
Loading
Loading