aaanalysis.AAclust.comp_centers

static AAclust.comp_centers(X, labels=None)

Computes the center of each cluster based on the given labels.

Parameters:

• X (array-like, shape (n_samples, n_features)) – Feature matrix. Rows typically correspond to scales and columns to amino acids.

• labels (array-like, shape (n_samples,)) – Cluster labels for each sample in X.

Returns:

• centers (array-like, shape (n_clusters,)) – The computed center for each cluster.

• labels_centers (array-like, shape (n_clusters,)) – The labels associated with each computed center.

Examples

The cluster centers can be computed using the AAclust().comp_centers() method:

import aaanalysis as aa
import pandas as pd
# Create example dataset comprising 100 scales
df_scales = aa.load_scales().T.sample(100).T
X = df_scales.T
# Fit AAclust model and obtain clustering centers for 5 clusters
aac = aa.AAclust()
labels = aac.fit(X, n_clusters=5).labels_
centers, labels_centers = aac.comp_centers(X=X, labels=labels)
# Create DataFrame with cluster centers
columns = [f"Cluster {i}" for i in labels_centers]
df_centers = pd.DataFrame(centers.T, columns=columns, index=df_scales.index)
aa.display_df(df_centers)

	Cluster 2	Cluster 1	Cluster 3	Cluster 0	Cluster 4
AA
A	0.519000	0.437000	0.420000	0.198000	0.477000
C	0.133000	0.432000	0.248000	0.393000	0.627000
D	0.515000	0.420000	0.840000	0.564000	0.228000
E	0.637000	0.609000	0.782000	0.265000	0.214000
F	0.254000	0.627000	0.133000	0.216000	0.790000
G	0.422000	0.068000	0.616000	0.843000	0.383000
H	0.330000	0.569000	0.560000	0.361000	0.415000
I	0.331000	0.544000	0.121000	0.093000	0.854000
K	0.695000	0.674000	0.795000	0.346000	0.240000
L	0.452000	0.646000	0.211000	0.139000	0.746000
M	0.231000	0.710000	0.175000	0.199000	0.726000
N	0.418000	0.392000	0.745000	0.603000	0.243000
P	0.426000	0.223000	0.771000	0.628000	0.353000
Q	0.439000	0.559000	0.746000	0.356000	0.308000
R	0.596000	0.594000	0.690000	0.381000	0.218000
S	0.504000	0.288000	0.694000	0.546000	0.337000
T	0.444000	0.360000	0.599000	0.393000	0.425000
V	0.403000	0.481000	0.244000	0.089000	0.769000
W	0.125000	0.729000	0.202000	0.415000	0.709000
Y	0.291000	0.520000	0.402000	0.387000	0.651000