IOHprofiler · Dinu23 · Apr 11, 2025 · Apr 11, 2025 · Apr 11, 2025 · Apr 11, 2025
diff --git a/README.md b/README.md
@@ -33,8 +33,6 @@ The following example shows how to get a benchmark clustering problem (by name o
 ```python
 from iohclustering import get_problem, download_benchmark_datasets
 
-# Download benchmark datasets
-download_benchmark_datasets()
 
 # Get benchmark problem by name (e.g., "iris_pca") with k=2 clusters
 clustering_problem, retransform = get_problem(fid="iris_pca", k=2)
@@ -85,7 +83,10 @@ This project is licensed under a standard BSD-3 clause License. See the LICENSE
 
 ## Acknowledgments
 
-
+This work has been estabilished as a collaboration between:
+* Diederick Vermetten 
+* Catalin-Viorel Dinu
+* Marcus Gallagher
 
 ## Cite Us
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "iohclustering"
-version = "0.0.1b"
+version = "0.0.2"
 authors = [
 ]
 description = "Package for IOH Clustering problems"
@@ -20,6 +20,14 @@ dependencies = [
   "numpy",
 ]
 
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+
+[tool.setuptools.package-data]
+"iohclustering" = ["static/*.txt"]
+
+
 [project.optional-dependencies]
 test = [
   "coverage",

diff --git a/src/iohclustering/cluster_base.py b/src/iohclustering/cluster_base.py
@@ -7,6 +7,7 @@
 import os
 from .cluster_metrics import *
 from .cluster_baseline_problems import *
+from importlib.resources import files
 
 
 def create_cluster_problem(dataset: str | np.ndarray, k: int, instance=1, error_metric="mse_euclidean") -> tuple[ioh.problem.RealSingleObjective, callable]:
@@ -17,8 +18,7 @@ def create_cluster_problem(dataset: str | np.ndarray, k: int, instance=1, error_
     ---------
         dataset : str or np.ndarray
             The dataset to be used for clustering. If a string is provided, it is assumed
-            to be the name of a file (without extension) located in the 'banchmark_datasets/' directory
-            with a '.txt' extension. If an np.ndarray is provided, it is used directly
+            to be the name of a banchmark dataset. If an np.ndarray is provided, it is used directly
             as the dataset.
         k : int
             The number of clusters to create.
@@ -53,11 +53,9 @@ def create_cluster_problem(dataset: str | np.ndarray, k: int, instance=1, error_
     """
     id = None
     if isinstance(dataset, str):
-        if os.path.exists(f'{dataset}.txt'):
-            data = np.loadtxt(f'{dataset}.txt', delimiter=',')
-        else:
-            id = get_problem_id(dataset)
-            data = np.loadtxt(f'banchmark_datasets/{dataset}.txt', delimiter=',')
+        id = get_problem_id(dataset)
+        dataset_path = files("iohclustering.static").joinpath(f"{dataset}.txt")
+        data = np.loadtxt(dataset_path, delimiter=',')
 
     else:
         data = dataset
@@ -71,7 +69,6 @@ def create_cluster_problem(dataset: str | np.ndarray, k: int, instance=1, error_
 
 
     data_np = np.array(data)
-
     # Normalize the data to the range [0, 1]
     data_min = np.tile(np.min(data_np, axis=0), k)
     data_max = np.tile(np.max(data_np, axis=0), k)
@@ -103,41 +100,6 @@ def retransform(X):
 
     return f, retransform
 
-def download_benchmark_datasets(warn = True) -> None:
-    """
-    Downloads and extracts benchmark datasets from a remote GitHub repository.
-    This function downloads a compressed tarball containing benchmark datasets 
-    from a specified branch of the IOHClustering GitHub repository and extracts 
-    its contents into a local directory named "banchmark_datasets". If the target 
-    directory already exists, a warning is issued (if `warn` is set to True) and 
-    the download is skipped.
-    Args:
-        warn (bool): If True, a warning is issued when the target directory 
-                        already exists. Defaults to True.
-    Raises:
-        urllib.error.URLError: If there is an issue with downloading the file 
-                                from the remote URL.
-        tarfile.TarError: If there is an issue with extracting the tarball.
-    Notes:
-        - The function assumes that the target directory is relative to the 
-            current working directory.
-        - The tarball is downloaded from the "main" branch of the repository.
-    """
-    target = os.path.realpath("banchmark_datasets")
-    branch = "main"
-
-    if os.path.isdir(target) and warn:
-        warnings.warn(f"Attempting to download static folder but path {target} already exists. Skipping...")
-        return 
-
-    os.makedirs(target, exist_ok=True)
-    github_static_folder = f"https://github.com/IOHprofiler/IOHClustering/blob/{branch}/static.tar.gz?raw=true" 
-    print(f"Downloading static folder from {github_static_folder} to {target}")
-    with urllib.request.urlopen(github_static_folder) as f:
-        thetarfile = tarfile.open(fileobj=f, mode="r|gz")
-        thetarfile.extractall(target)
-
-
 
 def get_problem_id(dataset_name: str) -> int:
     """
@@ -231,11 +193,13 @@ def load_problems():
               and the values are the corresponding clustering problem objects.
 
     """
-    download_benchmark_datasets(warn=False)
-    datasets_path = "banchmark_datasets"
+
+    folder = files("iohclustering.static")
+    datasets_names = [f.name for f in folder.iterdir() if f.suffix == ".txt"]
+
     problems = {}
     for dataset in CLUSTER_BASELINE_DATASETS.values():
-        if f"{dataset}.txt" in os.listdir(datasets_path):
+        if f"{dataset}.txt" in datasets_names:
             for k in BASELINE_K_DIMENTIONS[dataset]:
                 problem, retransform = create_cluster_problem(dataset, k)
                 problems[problem.meta_data.name] = problem, retransform

diff --git a/src/iohclustering/static/__init__.py b/src/iohclustering/static/__init__.py
diff --git a/src/iohclustering/static/breast_pca.txt b/src/iohclustering/static/breast_pca.txt
@@ -0,0 +1,106 @@
+-1.848982724994230331e-01,3.328202814139474275e-01
+-7.240586425684303329e-01,2.198421000584537488e+00
+4.286043357930507391e-01,1.138245782413504825e+00
+-2.587553981135277126e-01,2.609080554216371972e+00
+-6.741198420671984382e-01,1.805546179230361981e+00
+-9.583882252728245232e-01,3.555546797097947076e-01
+-1.440760389747365311e+00,4.134665947724535523e-02
+-1.182575545409856543e+00,9.573855329593937702e-01
+1.313382936248615185e-01,1.967459347507418910e+00
+-1.357556379326936846e-01,2.145026897195538851e+00
+2.792327651612147021e-01,3.349931330371387350e+00
+1.334131481525345775e-01,1.060229812989774256e+00
+-4.982280109676025526e-01,1.008252750470800763e+00
+-1.701871266934971150e-01,2.784371517488861247e+00
+3.285448519081174412e-02,1.379410631738837267e+00
+9.053543976519000391e-02,3.214270116569836411e+00
+-1.307072483517048411e+00,6.962660066452452945e-01
+-9.072018099584816531e-01,1.335096165696885162e+00
+-3.293908191184288237e-01,2.157144425402158117e+00
+-2.590113541161894184e-01,3.116490085081830674e+00
+-4.870285324051700226e-01,1.328666541844850002e+00
+-1.897761841740689182e+00,-6.788460407715413147e-01
+-1.960379205734269492e+00,-1.052842719736690302e+00
+-1.461179410029408210e+00,7.332827640061865271e-01
+-1.338919166880424783e+00,2.465845768346427297e-02
+-1.719960361286458905e+00,-1.021819709187707481e+00
+-1.756216957335545059e+00,-1.030355831297673053e+00
+-1.720687052485004420e+00,-1.141553282089176724e+00
+-1.831001209057610435e+00,-7.108522319812335954e-01
+-1.338121326600621774e+00,-6.655153851912668506e-01
+-1.668699527787910419e+00,-8.082490598305543950e-01
+-1.306586709088289666e+00,-3.893175779619356680e-01
+-1.810693602870551588e+00,1.017280820757553883e+00
+-1.518599609822518293e+00,-4.187633231521315502e-01
+-1.833762424400594560e+00,7.266122723606173173e-01
+-2.117976500422840136e+00,-2.732877688678871930e-01
+-1.661089426675247172e+00,1.269783905173813565e+00
+-1.705605360112204760e+00,8.736995842165060644e-01
+-1.027398046313792834e+00,-1.536998190669197906e-01
+-1.821426314340875319e+00,-1.288451764200204908e+00
+-1.586494447697767152e+00,-1.252101928973064826e+00
+-1.666663372189262082e+00,6.375568565917143493e-01
+-1.251977948680964348e+00,-9.366293955148259354e-01
+-1.737787577977409903e+00,-4.566908458241893398e-01
+-1.989894224328545569e+00,-2.631684801776546512e-01
+-2.063309917689361672e+00,5.495878944476452199e-01
+-1.588416907416133395e+00,9.959153230694850478e-01
+-1.313374358093098326e+00,-7.809945608952784113e-01
+-1.798707107745871614e+00,-8.345764688375999496e-01
+-1.164517220578309420e+00,-1.252440641544600108e+00
+-9.517084371850630387e-01,1.125503905569050778e+00
+-1.355081211389860707e+00,6.102861192882447217e-01
+-3.723751054650796255e-01,3.310338913216768209e+00
+-1.232097817416121233e+00,2.543804857884927606e-01
+-8.192274194272235466e-01,-1.544016712190948160e-01
+-1.864434872752001704e+00,-5.434264122612918191e-02
+-1.872130416393183783e+00,1.212130799227967071e+00
+-1.883941879715140155e+00,-9.397691390430359393e-01
+-1.822584971178903501e+00,-3.558291676287129168e-01
+-1.801957677902964461e+00,7.845162594995971905e-02
+-1.801957677902964461e+00,7.845162594995971905e-02
+-1.826174177238950147e+00,-2.111250840323902200e-01
+-1.786696400415751285e+00,3.865838482934754738e-01
+-1.838065021858341197e+00,2.735524093524348554e-01
+-1.700536886262037584e+00,-1.183405526887598480e+00
+-1.305311735438024368e+00,-9.810663375105362904e-01
+-2.024550740829507145e+00,-4.094014355141412098e-01
+-2.038911767639823402e+00,7.649757410821866888e-02
+-2.080713790785273964e+00,2.163542585430171250e-01
+-1.929714750690816105e+00,1.540573504668079519e+00
+1.315627774196893807e+00,-2.321166507067586871e+00
+1.309647032240341291e+00,-4.382160731653361729e-01
+-1.131173640425042586e-02,-1.430295156545804414e+00
+-4.512478618865424784e-01,-7.679638055363463556e-01
+1.204995641059246170e+00,-1.652294829907287488e+00
+-8.604746493734681811e-01,-1.752586179191983451e+00
+-6.430304809442323188e-01,-8.842406976130920970e-01
+-7.912717456025313290e-01,-1.396406587600655946e+00
+1.255279830703438959e+00,-1.834918358860255561e+00
+2.530591583927060295e+00,-1.035789568344203548e+00
+1.064021637611846094e+00,-8.033762235686184860e-01
+1.437386531535752798e+00,-1.413480160120521578e+00
+2.561741313062207315e+00,-1.232969373175034633e+00
+2.428573734826210639e+00,-1.676462352493848229e+00
+2.771762714558825724e+00,-2.012017974113212038e+00
+1.246933239809339788e+00,-2.038916716734023638e+00
+5.339009058023971299e+00,2.035030175046296463e+00
+2.058310088388645986e-01,-1.919046539542039298e+00
+2.254157075286578049e+00,-2.742345656143270749e-01
+1.012412519827168289e+00,-1.912984036199320226e+00
+2.244938588880122765e+00,-8.075015492813163442e-01
+4.904499131031587744e+00,2.191618171074125321e-01
+2.895809649155808518e+00,1.092106248452114937e-02
+1.865368928339548482e+00,-1.198873471915568700e+00
+2.601525586030091652e+00,-6.627592695917537968e-01
+2.409816772711398158e+00,-2.847229478713268480e-01
+1.165702398319113486e+00,-1.691515548002207936e+00
+5.681183623804933802e+00,-5.355353757934687708e-01
+4.688831082575416254e+00,8.628985692809039154e-01
+5.467613980210909830e+00,2.808147193715014589e-02
+2.797188845073364849e+00,-7.854488349066930386e-01
+4.651591113628814611e+00,-4.414534766912490277e-02
+1.233099334668400004e+01,3.220132363746897486e+00
+1.988619122429610808e+00,-2.001715569536710149e+00
+1.984934095409382371e+00,-1.266944911062789725e+00
+5.527583030387858365e+00,-1.572698337686180947e+00