def load_tslearn_data():
""" Time series data with variable length """
X_train, y_train, X_test, y_test = CachedDatasets().load_dataset("Trace")
X_train = X_train[y_train < 4] # Keep first 3 classes
np.random.shuffle(X_train)
X_train = TimeSeriesScalerMeanVariance().fit_transform(X_train[:50]) # Keep only 50 time series
X_train = TimeSeriesResampler(sz=40).fit_transform(X_train) # Make time series shorter
X_train = X_train.reshape(50,-1)
return X_train
import numpy as np
from Sloth import cluster
seed = 0
numpy.random.seed(seed)
X_train, y_train, X_test, y_test = CachedDatasets().load_dataset("Trace")
X_train = X_train[y_train < 4] # Keep first 3 classes
numpy.random.shuffle(X_train)
#X_train = TimeSeriesScalerMeanVariance().fit_transform(X_train[:50]) # Keep only 50 time series
X_train = X_train[:50]
sz = X_train.shape[1]
X_train = X_train.reshape((X_train.shape[0], X_train.shape[1]))
#Sloth = Sloth()
eps = 20
min_samples = 2
LOAD = False # Flag for loading similarity matrix from file if it has been computed before
if (LOAD):
SimilarityMatrix = cluster.LoadSimilarityMatrix()
else:
SimilarityMatrix = cluster.GenerateSimilarityMatrix(X_train)
cluster.SaveSimilarityMatrix(SimilarityMatrix)
nclusters, labels, cnt = cluster.ClusterSimilarityMatrix(
SimilarityMatrix, eps, min_samples)
print("DEBUG::number of clusters found =")
print(nclusters)