def compute_distance_matrix_datasets(self, datasets: List[pd.DataFrame],
distance_metric: str) -> pd.DataFrame:
"""
Compute the pairwise distance matrix for a list of datasets. The distance matrix is used for the implementation
of k-medoids.
:param datasets: List of DataFrames.
:param distance_metric: Distance metric to use for calculating distance between datasets.
:return: Pairwise distance matrix.
"""
distances = pd.DataFrame(index=range(0, len(datasets)),
columns=range(0, len(datasets)))
DMNoOrdering = PersonDistanceMetricsNoOrdering()
DMOrdering = PersonDistanceMetricsOrdering()
# Compute the distances for each pair. Distanced are assumed to be symmetric
for i in range(0, len(datasets)):
for j in range(i, len(datasets)):
if distance_metric == self.abstraction_p:
distances.iloc[i, j] = DMNoOrdering.p_distance(
datasets[i], datasets[j])
elif distance_metric == self.abstraction_euclidean:
distances.iloc[i, j] = DMOrdering.euclidean_distance(
datasets[i], datasets[j])
elif distance_metric == self.abstraction_lag:
distances.iloc[i, j] = DMOrdering.lag_correlation(
datasets[i], datasets[j], self.max_lag)
elif distance_metric == self.abstraction_dtw:
distances.iloc[i, j] = DMOrdering.dynamic_time_warping(
datasets[i], datasets[j])
distances.iloc[j, i] = distances.iloc[i, j]
return distances
def aggregate_datasets(self, datasets, cols, abstraction_method):
temp_datasets = []
DM = PersonDistanceMetricsNoOrdering()
# Flatten all datasets and add them to the newly formed dataset.
for i in range(0, len(datasets)):
temp_dataset = datasets[i][cols]
temp_datasets.append(temp_dataset)
if abstraction_method == self.abstraction_normal:
return DM.create_instances_normal_distribution(temp_datasets)
else:
return DM.create_instances_mean(temp_datasets)
def compute_distance_matrix_datasets(self, datasets, distance_metric):
distances = pd.DataFrame(index=range(0, len(datasets)), columns=range(0, len(datasets)))
DMNoOrdering = PersonDistanceMetricsNoOrdering()
DMOrdering = PersonDistanceMetricsOrdering()
# And compute the distances for each pair. Note that we assume the distances to be symmetric.
for i in range(0, len(datasets)):
for j in range(i, len(datasets)):
if distance_metric == self.abstraction_p:
distances.iloc[i,j] = DMNoOrdering.p_distance(datasets[i], datasets[j])
elif distance_metric == self.abstraction_euclidean:
distances.iloc[i,j] = DMOrdering.euclidean_distance(datasets[i], datasets[j])
elif distance_metric == self.abstraction_lag:
distances.iloc[i,j] = DMOrdering.lag_correlation(datasets[i], datasets[j], self.max_lag)
elif distance_metric == self.abstraction_dtw:
distances.iloc[i,j] = DMOrdering.dynamic_time_warping(datasets[i], datasets[j])
distances.iloc[j,i] = distances.iloc[i,j]
return distances
def aggregate_datasets(self, datasets: List[pd.DataFrame], cols: List[str], abstraction_method: str) \
-> pd.DataFrame:
"""
Flatten each dataset to a single record/instance for comparing datasets between persons. This is done based on
the approaches defined in the distance metrics file.
:param datasets: List of DataFrames to aggregate.
:param cols: Columns to keep while aggregating.
:param abstraction_method: Abstraction method to use for aggregation.
:return: Aggregated DataFrame.
"""
temp_datasets = []
DM = PersonDistanceMetricsNoOrdering()
# Flatten all datasets and add them to the newly formed dataset
for i in range(0, len(datasets)):
temp_dataset = datasets[i][cols]
temp_datasets.append(temp_dataset)
if abstraction_method == self.abstraction_normal:
return DM.create_instances_normal_distribution(temp_datasets)
else:
return DM.create_instances_mean(temp_datasets)