def test_run_clustering_experiment():
"""Test running and saving results for clustering.
Currently it just checks the files have been created, then deletes them.
"""
dataset = "UnitTest"
train_X, train_Y = load_unit_test("TRAIN", return_X_y=True)
test_X, test_Y = load_unit_test("TEST", return_X_y=True)
run_clustering_experiment(
train_X,
TimeSeriesKMeans(n_clusters=2),
results_path="../Temp/",
trainY=train_Y,
testX=test_X,
testY=test_Y,
cls_name="kmeans",
dataset_name=dataset,
resample_id=0,
)
test_path = f"../Temp/kmeans/Predictions/{dataset}/testResample0.csv"
train_path = f"../Temp/kmeans/Predictions/{dataset}/trainResample0.csv"
assert os.path.isfile(test_path)
assert os.path.isfile(train_path)
os.remove(test_path)
os.remove(train_path)
def test_run_clustering_experiment(tmp_path):
"""Test running and saving results for clustering.
Currently it just checks the files have been created, then deletes them.
"""
dataset = "UnitTest"
train_X, train_Y = load_unit_test("TRAIN")
test_X, test_Y = load_unit_test("TEST")
run_clustering_experiment(
train_X,
TimeSeriesKMeans(n_clusters=2),
results_path=tmp_path,
trainY=train_Y,
testX=test_X,
testY=test_Y,
cls_name="kmeans",
dataset_name=dataset,
resample_id=0,
)
test_path = tmp_path.joinpath(
f"kmeans/Predictions/{dataset}/testResample0.csv")
train_path = tmp_path.joinpath(
f"kmeans/Predictions/{dataset}/trainResample0.csv")
assert test_path.is_file()
assert train_path.is_file()
# remove files
test_path.unlink()
train_path.unlink()
data_dir = "../datasets/data/"
results_dir = "C:/Temp/Clusterers/"
dataset = "UnitTest"
clusterer = "kmeans"
resample = 0
tf = True
clst = TimeSeriesKMeans(n_clusters=2)
load_and_run_clustering_experiment(
overwrite=True,
problem_path=data_dir,
results_path=results_dir,
cls_name=clusterer,
dataset=dataset,
resample_id=resample,
train_file=tf,
clusterer=clst,
)
train_X, train_Y = load_ts(data_dir + dataset + "/" + dataset +
"_TRAIN.ts")
test_X, test_Y = load_ts(data_dir + dataset + "/" + dataset +
"_TEST.ts")
run_clustering_experiment(
train_X,
clst,
results_path=results_dir + "Temp/",
trainY=train_Y,
testX=test_X,
testY=test_Y,
cls_name=clusterer,
)
window = tune_window(distance, train_X)
name = clusterer + "-" + distance + "-tuned"
else:
name = clusterer + "-" + distance
if (distance == "wdtw" or distance == "dwdtw" or distance == "dtw"
or distance == "wdtw"):
parameters = {"window": 0.2, "epsilon": 0.05, "g": 0.05, "c": 1}
else:
parameters = {"window": 1.0, "epsilon": 0.05, "g": 0.05, "c": 1}
clst = TimeSeriesKMeans(
averaging_method="dba",
average_params={"averaging_distance_metric": distance},
metric=distance,
distance_params=parameters,
n_clusters=len(set(train_Y)),
random_state=resample + 1,
)
run_clustering_experiment(
train_X,
clst,
results_path=results_dir,
trainY=train_Y,
testX=test_X,
testY=test_Y,
cls_name=name,
dataset_name=dataset,
resample_id=resample,
overwrite=True,
)
print("done")