evomap.metrics
Contents
evomap.metrics#
Useful functions to evaluate maps.
Module Contents#
Functions#
|
Calculate misalignment of a sequence of maps. |
|
Calculate alignment of a sequence of maps. |
|
Calculate Hitrate of nearest neighbor recovery for a single map. The |
|
Calculate Hitrate of nearest neighbor recovery for a single map, adjusted |
|
Calculate average Hitrate of nearest neighbor recovery for a sequence of |
|
Calculate average Hitrate of nearest neighbor recovery for a sequence of |
Calculate persistence of a sequence of maps as the average Pearson |
- evomap.metrics.misalign_score(Ys, normalize=True)[source]#
Calculate misalignment of a sequence of maps.
Misaligned is measured as the average Euclidean distance between objects’ subsequent map positions. The final score is averaged across all objects.
- Parameters
Ys (list of ndarrays, each of shape (n_samples, d)) – Map coordinates.
normalize (bool, optional) –
If true, misalignment is normalized by the average interobject distance on the map. Useful for comparing maps across differently scaled coordinate
systems, by default True.
- Returns
Misalignment score, bounded within [0, inf). Lower values indicate better alignment.
- Return type
float
- evomap.metrics.align_score(Ys)[source]#
Calculate alignment of a sequence of maps.
Alignment is measured as the mean cosine similarity of objects’ subsequent map positions. The final score is averaged across all objects.
- Parameters
Ys (list of ndarrays, each of shape (n_samples, d)) – Map coordinates.
- Returns
Alignment score, bounded between [-1,1]. Higher values indicate better alignment.
- Return type
float
- evomap.metrics.hitrate_score(X, Y, n_neighbors=10, inc=None, input_type='similarity')[source]#
Calculate Hitrate of nearest neighbor recovery for a single map. The score is averaged across all objects.
- Parameters
X (ndarray) – Input data, either a similarity / distance matrix of shape (n_samples, n_samples), or a matrix of feature vectors of shape (n_samples, d_input).
Y (ndarray of shape (n_samples, d)) – Map coordinates.
n_neighbors (int, optional) – Number of neighbors considered when calculating the hitrate, by default 10
inc (ndarray of shape (n_samples,), optional) – Inclusion array, indicating if an object is present (via 0 and 1s), by default None
input_type (str, optional) – One of ‘vector’, ‘similarity’, or ‘distance’, by default ‘similarity’
- Returns
Hitrate of nearest neighbor recovery, bounded within [0,1]. Higher values indicate better recovery.
- Return type
float
- evomap.metrics.adjusted_hitrate_score(X, Y, n_neighbors=10, inc=None, input_type='similarity')[source]#
Calculate Hitrate of nearest neighbor recovery for a single map, adjusted for random agreement. The score is averaged across all objects.
- Parameters
X (ndarray) – Input data, either a similarity / distance matrix of shape (n_samples, n_samples), or a matrix of feature vectors of shape (n_samples, d_input).
Y (ndarray of shape (n_samples, d)) – Map coordinates.
n_neighbors (int, optional) – Number of neighbors considered when calculating the hitrate, by default 10
inc (ndarray of shape (n_samples,), optional) – Inclusion array, indicating if an object is present (via 0 and 1s), by default None
input_type (str, optional) – One of ‘vector’, ‘similarity’, or ‘distance’, by default ‘similarity’
- Returns
Adjusted Hitrate of nearest neighbor recovery, bounded within [0,1]. Higher values indicate better recovery.
- Return type
float
- evomap.metrics.avg_hitrate_score(Ys, Xs, n_neighbors=10, Inc_ts=None, input_type='distance')[source]#
Calculate average Hitrate of nearest neighbor recovery for a sequence of maps. The score is averaged across all maps within the sequence.
- Parameters
Xs (list of ndarrays) – Input data, either in the form of distance/similarity matrices, each of shape (n_samples, n_samples), or or feature vectors of shape (n_samples, d_input).
Ys (list of ndarays, each of shape (n_samples, d)) – _description_
n_neighbors (int, optional) – Number of neighbors considered when calculating the hitrate, by default 10
Inc_ts (list of ndarays, each of shape (n_samples,), optional) – List of inclusion arrays, indicating if an object is present in a given period (via 0 and 1s), by default None
input_type (str, optional) – One of ‘vector’, ‘similarity’, or ‘distance’, by default ‘similarity’
- Returns
Average hitrate, bounded between [0,1]. Higher values indicate better recovery.
- Return type
float
- evomap.metrics.avg_adjusted_hitrate_score(Ys, Xs, n_neighbors=10, Inc_ts=None, input_type='distance')[source]#
Calculate average Hitrate of nearest neighbor recovery for a sequence of maps, adjusted for random agreement. The score is averaged across all maps within the sequence.
- Parameters
Xs (list of ndarrays) – Input data, either in the form of distance/similarity matrices, each of shape (n_samples, n_samples), or or feature vectors of shape (n_samples, d_input).
Ys (list of ndarays, each of shape (n_samples, d)) – _description_
n_neighbors (int, optional) – Number of neighbors considered when calculating the hitrate, by default 10
Inc_ts (list of ndarays, each of shape (n_samples,), optional) – List of inclusion arrays, indicating if an object is present in a given period (via 0 and 1s), by default None
input_type (str, optional) – One of ‘vector’, ‘similarity’, or ‘distance’, by default ‘similarity’
- Returns
Average adjusted hitrate, bounded between [0,1]. Higher values indicate better recovery.
- Return type
float
- evomap.metrics.persistence_score(Ys)[source]#
Calculate persistence of a sequence of maps as the average Pearson correlation coefficient between objects’ subsequent map movements (i.e., the first differences of their map positions). The score is averaged across all objects.
- Parameters
Ys (list of ndarrays, each of shape (n_samples, 2)) – Map coordinates.
- Returns
Persistence score, bounded within (-1,1). Higher positive values indicate higher persistence.
- Return type
float