Coordinates package (pyemma.coordinates)¶
The coordinates package contains tools to select features from MD-trajectories. It also assigns them to a discrete state space, which will be later used in Markov modeling.
It supports reading from MD-trajectories, comma separated value ASCII files and NumPy arrays. The discretized trajectories are being stored as NumPy arrays of integers.
User API¶
Trajectory input/output and featurization
featurizer (topfile) |
Featurizer to select features from MD data. |
load (trajfiles[, features, top, stride, …]) |
Loads coordinate features into memory. |
source (inp[, features, top, chunksize]) |
Defines trajectory data source |
combine_sources (sources[, chunksize]) |
Combines multiple data sources to stream from. |
pipeline (stages[, run, stride, chunksize]) |
Data analysis pipeline. |
discretizer (reader[, transform, cluster, …]) |
Specialized pipeline: From trajectories to clustering. |
save_traj (traj_inp, indexes, outfile[, top, …]) |
Saves a sequence of frames as a single trajectory. |
save_trajs (traj_inp, indexes[, prefix, fmt, …]) |
Saves sequences of frames as multiple trajectories. |
Covariance estimation
covariance_lagged ([data, c00, c0t, ctt, …]) |
Compute lagged covariances between time series. |
Coordinate and feature transformations
pca ([data, dim, var_cutoff, stride, mean, …]) |
Principal Component Analysis (PCA). |
tica ([data, lag, dim, var_cutoff, …]) |
Time-lagged independent component analysis (TICA). |
vamp ([data, lag, dim, scaling, right, …]) |
Variational approach for Markov processes (VAMP) [1]_. |
Clustering Algorithms
cluster_kmeans ([data, k, max_iter, …]) |
k-means clustering |
cluster_mini_batch_kmeans ([data, k, …]) |
k-means clustering with mini-batch strategy |
cluster_regspace ([data, dmin, max_centers, …]) |
Regular space clustering |
cluster_uniform_time ([data, k, stride, …]) |
Uniform time clustering |
assign_to_centers ([data, centers, stride, …]) |
Assigns data to the nearest cluster centers |
Classes¶
Coordinate classes encapsulating complex functionality. You don’t need to construct these classes yourself, as this is done by the user API functions above. Find here a documentation how to extract features from them.
I/O and Featurization
data.MDFeaturizer (topfile, **kwargs) |
Extracts features from MD trajectories. |
data.CustomFeature (fun, dim[, description, …]) |
A CustomFeature is the base class for user-defined features. |
Transformation estimators
transform.PCA ([dim, var_cutoff, mean, …]) |
Principal component analysis. |
transform.TICA (lag[, dim, var_cutoff, …]) |
Time-lagged independent component analysis (TICA) |
transform.VAMP (lag[, dim, scaling, right, …]) |
Variational approach for Markov processes (VAMP) |
Covariance estimation
estimation.covariance.LaggedCovariance ([…]) |
Clustering algorithms
clustering.KmeansClustering (n_clusters[, …]) |
k-means clustering |
clustering.MiniBatchKmeansClustering (n_clusters) |
Mini-batch k-means clustering |
clustering.RegularSpaceClustering (dmin[, …]) |
Regular space clustering |
clustering.UniformTimeClustering ([…]) |
Uniform time clustering |
Transformers
data._base.transformer.StreamingTransformer ([…]) |
Basis class for pipelined Transformers. |
pipelines.Pipeline (chain[, chunksize, …]) |
Data processing pipeline. |
Discretization
clustering.AssignCenters (clustercenters[, …]) |
Assigns given (pre-calculated) cluster centers. |