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)
plt.figure()
for yi in range(nclusters):
plt.subplot(nclusters, 1, 1 + yi)
for xx in X_train[labels == yi]:
plt.plot(xx.ravel(), "k-")
plt.xlim(0, sz)
plt.ylim(-4, 4)
plt.title("Cluster %d" % (yi + 1))
plt.tight_layout()
plt.show()
def produce(self,
*,
inputs: Inputs,
timeout: float = None,
iterations: int = None) -> CallResult[Outputs]:
"""
Parameters
----------
inputs : numpy ndarray of size (number_of_time_series, time_series_length) containing new time series
Returns
----------
Outputs
The output is a dataframe containing a single column where each entry is the associated series' cluster number.
"""
# temporary (until Uncharted adds conversion primitive to repo)
if not self.hyperparams['long_format']:
inputs = TimeSeriesFormatterPrimitive(
hyperparams=self._hp).produce(inputs=inputs).value['0']
else:
hyperparams_class = DatasetToDataFrame.DatasetToDataFramePrimitive.metadata.query(
)['primitive_code']['class_type_arguments']['Hyperparams']
ds2df_client = DatasetToDataFrame.DatasetToDataFramePrimitive(
hyperparams=hyperparams_class.defaults().replace(
{"dataframe_resource": "learningData"}))
inputs = d3m_DataFrame(ds2df_client.produce(inputs=inputs).value)
# parse values from output of time series formatter
n_ts = len(inputs.d3mIndex.unique())
ts_sz = int(inputs.shape[0] / n_ts)
input_vals = np.array(inputs.value).reshape(n_ts, ts_sz)
# use HP to produce DBSCAN clustering
if self.hyperparams['algorithm'] == 'DBSCAN':
#SimilarityMatrix = cluster.GenerateSimilarityMatrix(input_vals)
_, labels, _ = cluster.ClusterSimilarityMatrix(
input_vals, self.hyperparams['eps'],
self.hyperparams['min_samples'])
else:
#SimilarityMatrix = cluster.GenerateSimilarityMatrix(input_vals)
_, labels, _ = cluster.HClusterSimilarityMatrix(
input_vals, self.hyperparams['min_cluster_size'],
self.hyperparams['min_samples'])
# transform labels for D3M classification task
labels = [x + 1 if x >= 0 else x + 2 for x in labels]
# add metadata to output
labels = pandas.DataFrame(labels)
out_df = pandas.concat(
[pandas.DataFrame(inputs.d3mIndex.unique()), labels], axis=1)
# get column names from metadata
out_df.columns = ['d3mIndex', 'label']
hdbscan_df = d3m_DataFrame(out_df)
# first column ('d3mIndex')
col_dict = dict(
hdbscan_df.metadata.query((metadata_base.ALL_ELEMENTS, 0)))
col_dict['structural_type'] = type("1")
# confirm that this metadata still exists
#index = inputs['0'].metadata.get_columns_with_semantic_type('https://metadata.datadrivendiscovery.org/types/PrimaryKey')
#col_dict['name'] = inputs.metadata.query_column(index[0])['name']
col_dict['name'] = 'd3mIndex'
col_dict['semantic_types'] = (
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/PrimaryKey',
)
hdbscan_df.metadata = hdbscan_df.metadata.update(
(metadata_base.ALL_ELEMENTS, 0), col_dict)
# second column ('labels')
col_dict = dict(
hdbscan_df.metadata.query((metadata_base.ALL_ELEMENTS, 1)))
col_dict['structural_type'] = type("1")
#index = inputs['0'].metadata.get_columns_with_semantic_type('https://metadata.datadrivendiscovery.org/types/SuggestedTarget')
#col_dict['name'] = inputs.metadata.query_column(index[0])['name']
col_dict['name'] = 'label'
col_dict['semantic_types'] = (
'http://schema.org/Integer',
'https://metadata.datadrivendiscovery.org/types/SuggestedTarget',
'https://metadata.datadrivendiscovery.org/types/TrueTarget',
'https://metadata.datadrivendiscovery.org/types/Target')
hdbscan_df.metadata = hdbscan_df.metadata.update(
(metadata_base.ALL_ELEMENTS, 1), col_dict)
return CallResult(hdbscan_df)