make imports explicit and improve style

pensa/__init__.py

@@ -1,7 +0,0 @@
-from .preprocessing import *
-from .features import *
-from .statesinfo import *
-from .clusters import *
-from .comparison import *
-from .dimensionality import *
-

pensa/clusters/__init__.py

@@ -1,3 +1,12 @@
-from .clustering import *
-from .trajectory import *
-from .wss import *
+from .clustering import \
+    obtain_clusters, \
+    obtain_combined_clusters, \
+    obtain_mult_combined_clusters, \
+    find_closest_frames
+
+from .trajectory import \
+    write_cluster_traj
+
+from .wss import \
+    wss_over_number_of_clusters, \
+    wss_over_number_of_combined_clusters

pensa/comparison/__init__.py

@@ -1,6 +1,29 @@
-from .statistics import *
-from .relative_entropy import *
-from .statespecific import *
-from .visualization import *
-from .metrics import *
-from .uncertainty_analysis import *
+from .statistics import \
+    kolmogorov_smirnov_analysis, \
+    mean_difference_analysis, \
+    feature_correlation
+
+from .relative_entropy import \
+    relative_entropy_analysis
+
+from .statespecific import \
+    ssi_feature_analysis, \
+    ssi_ensemble_analysis, \
+    cossi_featens_analysis
+
+from .visualization import \
+    residue_visualization, \
+    distances_visualization, \
+    pair_features_heatmap, \
+    resnum_heatmap
+
+from .metrics import \
+    pca_sampling_efficiency, \
+    average_jsd, average_kld, average_ksp, average_kss, average_ssi, \
+    max_jsd, max_kld, max_ksp, max_kss, max_ssi, min_ksp
+
+from .uncertainty_analysis import \
+    relen_block_analysis, \
+    relen_sem_analysis, \
+    ssi_block_analysis, \
+    ssi_sem_analysis

pensa/comparison/metrics.py

@@ -8,7 +8,9 @@
 
 
 """
-    Calculates the average and maximum Jensen-Shannon distance and the Kullback-Leibler divergences for each feature from two ensembles. Each of four functions uses the relative_entropy_analysis function with the same parameters.
+    Calculates the average and maximum Jensen-Shannon distance and the Kullback-Leibler divergences
+    for each feature from two ensembles.
+    Each of the four functions uses the relative_entropy_analysis function with the same parameters.
 
     Parameters
     ----------
@@ -20,16 +22,19 @@
             Can be obtained from features object via .describe().
             Must be the same as features_a. Provided as a sanity check.
         all_data_a : float array
-            Trajectory data from the first ensemble. Format: [frames, frame_data].
+            Trajectory data from the first ensemble.
+            Format: [frames, frame_data].
         all_data_b : float array
             Trajectory data from the second ensemble.
             For kld functions, the second ensemble should be the reference ensemble.
             Format: [frames, frame_data].
         bin_width : float, default=None
             Bin width for the axis to compare the distributions on.
-            If bin_width is None, bin_num (see below) bins are used and the width is determined from the common histogram.
+            If bin_width is None, bin_num (see below) bins are used
+            and the width is determined from the common histogram.
         bin_num : int, default=10
-            Number of bins for the axis to compare the distributions on (only if bin_width=None).
+            Number of bins for the axis to compare the distributions on
+            (only if bin_width=None).
         verbose : bool, default=True
             Print intermediate results.
         override_name_check : bool, default=False
@@ -50,28 +55,52 @@
 """
 
 
-def average_jsd(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_num=10, verbose=True, override_name_check=False):
-    _, data_jsdist, _, _ = relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b, bin_width=bin_width, bin_num=bin_num, verbose=verbose, override_name_check=override_name_check)
+def average_jsd(features_a, features_b, all_data_a, all_data_b,
+                bin_width=None, bin_num=10, verbose=True,
+                override_name_check=False):
+    _, data_jsdist, _, _ = relative_entropy_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        bin_width=bin_width, bin_num=bin_num, verbose=verbose,
+        override_name_check=override_name_check
+    )
     return np.mean(data_jsdist)
 
 
-def max_jsd(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_num=10, verbose=True, override_name_check=False):
-    _, data_jsdist, _, _ = relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b, bin_width=bin_width, bin_num=bin_num, verbose=verbose, override_name_check=override_name_check)
+def max_jsd(features_a, features_b, all_data_a, all_data_b,
+            bin_width=None, bin_num=10, verbose=True,
+            override_name_check=False):
+    _, data_jsdist, _, _ = relative_entropy_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        bin_width=bin_width, bin_num=bin_num, verbose=verbose,
+        override_name_check=override_name_check
+    )
     return np.max(data_jsdist)
 
 
-def average_kld(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_num=10, verbose=True, override_name_check=False):
-    _, _, data_kld_ab, _ = relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b, bin_width=bin_width, bin_num=bin_num, verbose=verbose, override_name_check=override_name_check)
+def average_kld(features_a, features_b, all_data_a, all_data_b,
+                bin_width=None, bin_num=10, verbose=True,
+                override_name_check=False):
+    _, _, data_kld_ab, _ = relative_entropy_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        bin_width=bin_width, bin_num=bin_num, verbose=verbose,
+        override_name_check=override_name_check
+    )
     return np.mean(data_kld_ab)
 
 
-def max_kld(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_num=10, verbose=True, override_name_check=False):
-    _, _, data_kld_ab, _ = relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b, bin_width=bin_width, bin_num=bin_num, verbose=verbose, override_name_check=override_name_check)
+def max_kld(features_a, features_b, all_data_a, all_data_b,
+            bin_width=None, bin_num=10, verbose=True,
+            override_name_check=False):
+    _, _, data_kld_ab, _ = relative_entropy_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        bin_width=bin_width, bin_num=bin_num, verbose=verbose,
+        override_name_check=override_name_check)
     return np.max(data_kld_ab)
 
 
 """
-    Calculates the average and maximum Kolmogorov-Smirnov statistic for two distributions. Each of five functions uses the kolmogorov_smirnov_analysis function with the same parameters.
+    Calculates the average and maximum Kolmogorov-Smirnov statistic for two distributions.
+    Each of the five functions uses the kolmogorov_smirnov_analysis function with the same parameters.
 
     Parameters
     ----------
@@ -108,33 +137,54 @@ def max_kld(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_
 """
 
 
-def average_kss(features_a, features_b, all_data_a, all_data_b, verbose=True, override_name_check=False):
-    _, data_kss, _ = kolmogorov_smirnov_analysis(features_a, features_b, all_data_a, all_data_b, verbose=verbose, override_name_check=override_name_check)
+def average_kss(features_a, features_b, all_data_a, all_data_b,
+                verbose=True, override_name_check=False):
+    _, data_kss, _ = kolmogorov_smirnov_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        verbose=verbose, override_name_check=override_name_check
+    )
     return np.mean(data_kss)
 
 
-def max_kss(features_a, features_b, all_data_a, all_data_b, verbose=True, override_name_check=False):
-    _, data_kss, _ = kolmogorov_smirnov_analysis(features_a, features_b, all_data_a, all_data_b, verbose=verbose, override_name_check=override_name_check)
+def max_kss(features_a, features_b, all_data_a, all_data_b,
+            verbose=True, override_name_check=False):
+    _, data_kss, _ = kolmogorov_smirnov_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        verbose=verbose, override_name_check=override_name_check
+    )
     return np.max(data_kss)
 
 
-def average_ksp(features_a, features_b, all_data_a, all_data_b, verbose=True, override_name_check=False):
-    _, _, data_ksp = kolmogorov_smirnov_analysis(features_a, features_b, all_data_a, all_data_b, verbose=verbose, override_name_check=override_name_check)
+def average_ksp(features_a, features_b, all_data_a, all_data_b,
+                verbose=True, override_name_check=False):
+    _, _, data_ksp = kolmogorov_smirnov_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        verbose=verbose, override_name_check=override_name_check
+    )
     return np.mean(data_ksp)
 
 
-def max_ksp(features_a, features_b, all_data_a, all_data_b, verbose=True, override_name_check=False):
-    _, _, data_ksp = kolmogorov_smirnov_analysis(features_a, features_b, all_data_a, all_data_b, verbose=verbose, override_name_check=override_name_check)
+def max_ksp(features_a, features_b, all_data_a, all_data_b,
+            verbose=True, override_name_check=False):
+    _, _, data_ksp = kolmogorov_smirnov_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        verbose=verbose, override_name_check=override_name_check
+    )
     return np.max(data_ksp)
 
 
-def min_ksp(features_a, features_b, all_data_a, all_data_b, verbose=True, override_name_check=False):
-    _, _, data_ksp = kolmogorov_smirnov_analysis(features_a, features_b, all_data_a, all_data_b, verbose=verbose, override_name_check=override_name_check)
+def min_ksp(features_a, features_b, all_data_a, all_data_b,
+            verbose=True, override_name_check=False):
+    _, _, data_ksp = kolmogorov_smirnov_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        verbose=verbose, override_name_check=override_name_check
+    )
     return np.min(data_ksp)
 
 
 """
-    Calculates average and maximum State Specific Information statistic for a feature across two ensembles. Each of two functions uses the ssi_ensemble_analysis function with the same parameters.
+    Calculates average and maximum State Specific Information statistic for a feature across two ensembles.
+    Each of two functions uses the ssi_ensemble_analysis function with the same parameters.
 
     Parameters
     ----------
@@ -174,13 +224,27 @@ def min_ksp(features_a, features_b, all_data_a, all_data_b, verbose=True, overri
 """
 
 
-def average_ssi(features_a, features_b, all_data_a, all_data_b, torsions=None, pocket_occupancy=None, pbc=True, verbose=True, write_plots=None, override_name_check=False):
-    _, data_ssi = ssi_ensemble_analysis(features_a, features_b, all_data_a, all_data_b, torsions=torsions, pocket_occupancy=pocket_occupancy, pbc=pbc, verbose=verbose, write_plots=write_plots, override_name_check=override_name_check)
+def average_ssi(features_a, features_b, all_data_a, all_data_b,
+                torsions=None, pocket_occupancy=None, pbc=True,
+                verbose=True, write_plots=None, override_name_check=False):
+    _, data_ssi = ssi_ensemble_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        torsions=torsions, pocket_occupancy=pocket_occupancy,
+        pbc=pbc, verbose=verbose, write_plots=write_plots,
+        override_name_check=override_name_check
+    )
     return np.mean(data_ssi)
 
 
-def max_ssi(features_a, features_b, all_data_a, all_data_b, torsions=None, pocket_occupancy=None, pbc=True, verbose=True, write_plots=None, override_name_check=False):
-    _, data_ssi = ssi_ensemble_analysis(features_a, features_b, all_data_a, all_data_b, torsions=torsions, pocket_occupancy=pocket_occupancy, pbc=pbc, verbose=verbose, write_plots=write_plots, override_name_check=override_name_check)
+def max_ssi(features_a, features_b, all_data_a, all_data_b,
+            torsions=None, pocket_occupancy=None, pbc=True,
+            verbose=True, write_plots=None, override_name_check=False):
+    _, data_ssi = ssi_ensemble_analysis(
+        features_a, features_b, all_data_a, all_data_b,
+        torsions=torsions, pocket_occupancy=pocket_occupancy,
+        pbc=pbc, verbose=verbose, write_plots=write_plots,
+        override_name_check=override_name_check
+    )
     return np.max(data_ssi)
 
 

pensa/comparison/relative_entropy.py

@@ -5,7 +5,8 @@
 import scipy.spatial.distance
 
 
-def relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b, bin_width=None, bin_num=10, verbose=True, override_name_check=False):
+def relative_entropy_analysis(features_a, features_b, all_data_a, all_data_b,
+                              bin_width=None, bin_num=10, verbose=True, override_name_check=False):
     """
     Calculates the Jensen-Shannon distance and the Kullback-Leibler divergences for each feature from two ensembles.