Merge branch 'develop' into persistence_axes

.appveyor.yml

@@ -10,7 +10,7 @@ cache:
 environment:
     global:
         CONDA_CHANNELS: conda-forge
-        CONDA_DEPENDENCIES: pip setuptools wheel cython mock six biopython networkx joblib matplotlib scipy vs2015_runtime pytest mmtf-python GridDataFormats hypothesis pytest-cov codecov
+        CONDA_DEPENDENCIES: pip setuptools wheel cython mock six biopython networkx joblib matplotlib scipy vs2015_runtime pytest mmtf-python GridDataFormats hypothesis pytest-cov codecov chemfiles
         PIP_DEPENDENCIES: gsd==1.9.3 duecredit parmed
         DEBUG: "False"
         MINGW_64: C:\mingw-w64\x86_64-6.3.0-posix-seh-rt_v5-rev1\mingw64\bin

.travis.yml

@@ -28,7 +28,7 @@ env:
     - SETUP_CMD="${PYTEST_FLAGS}"
     - BUILD_CMD="pip install -e package/ && (cd testsuite/ && python setup.py build)"
     - CONDA_MIN_DEPENDENCIES="mmtf-python mock six biopython networkx cython matplotlib scipy griddataformats hypothesis gsd codecov"
-    - CONDA_DEPENDENCIES="${CONDA_MIN_DEPENDENCIES} seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12"
+    - CONDA_DEPENDENCIES="${CONDA_MIN_DEPENDENCIES} seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12 chemfiles"
     - CONDA_CHANNELS='biobuilds conda-forge'
     - CONDA_CHANNEL_PRIORITY=True
     - PIP_DEPENDENCIES="duecredit parmed"
@@ -66,7 +66,7 @@ matrix:
            INSTALL_HOLE="false"
 
     - env: NAME="python 2.7"
-           PYTHON_VERSION=2.7 
+           PYTHON_VERSION=2.7
            CODECOV="true"
            NUMPY_VERSION=1.16
            SETUP_CMD="${PYTEST_FLAGS} --cov=MDAnalysis"

package/AUTHORS

@@ -128,13 +128,15 @@ Chronological list of authors
 2020
   - Charlie Cook
   - Yuanyu Chang
+  - Guillaume Fraux
   - Ivan Hristov
   - Michael Quevillon
   - Hao Tian
   - Hugo MacDermott-Opeskin
   - Anshul Angaria
-
-
+  - Shubham Sharma
+  - Yuxuan Zhuang
+  - Abhishek Shandilya
 
 External code
 -------------

package/CHANGELOG

@@ -16,11 +16,17 @@ The rules for this file:
 mm/dd/yy richardjgowers, kain88-de, lilyminium, p-j-smith, bdice, joaomcteixeira,
          PicoCentauri, davidercruz, jbarnoud, RMeli, IAlibay, mtiberti, CCook96,
          Yuan-Yu, xiki-tempula, HTian1997, Iv-Hristov, hmacdope, AnshulAngaria,
-         ss62171
+         ss62171, Luthaf, yuxuanzhuang, abhishandy
 
   * 0.21.0
 
 Fixes
+  * Fixed the deprecation warning from `collections` library in `flatten_dict`
+    (Issue #2605)
+  * Fixed test for the `save_paths` and `load` methods of :class:`PSAnalysis`
+    (Issue #2593)
+  * Fixes outdated :class:`TRJReader` documentation on random frame access
+    (Issue #2398)
   * Fixed mda.Merge for Universes without coordinates (Issue #2470)(PR #2580)
   * PCA(align=True) now correctly aligns the trajectory and computes the
     correct means and covariance matrix (Issue #2561)
@@ -59,8 +65,11 @@ Fixes
     argument. The directives parsed into bonds, angles, impropers, and dihedrals now
     match TPRParser. (PR #2408)
   * Added parmed to setup.py
+  * Fixed example docs for polymer persistence length (#2582)
+  * Added missing selection module to leaflet.py (Issue #2612)
 
 Enhancements
+  * Added ability to use Chemfiles as a trajectory reader backend (PR #1862)
   * New analysis.hole2 module for HOLE interfacing. Contains a function (hole) 
     for running HOLE on singular PDB files and class (HoleAnalysis) for 
     trajectories (PR #2523)
@@ -96,6 +105,9 @@ Enhancements
   * PersistenceLength.plot() now create new axes if current axes not provided (Issue #2590)
 
 Changes
+  * Removed deprecated :meth:`PersistenceLength.perform_fit` (Issue #2596)
+  * Changed :meth:`PSAnalysis.generate_paths` keywords `store` and `filename`
+    defaults to `False` and `None` (Issue #2593)
   * Removed `format` keyword from :meth:`MemoryReader.timeseries` (Issue #1453,
     #2443)
   * Deprecated :class:`LAMMPSDataConverter` has now been removed (Issue #2564)

package/MDAnalysis/analysis/leaflet.py

@@ -79,6 +79,7 @@
 
 from .. import core
 from . import distances
+from .. import selections
 
 from ..due import due, Doi
 
@@ -174,7 +175,7 @@ def _get_graph(self):
             # only try distance array
             try:
                 adj = distances.contact_matrix(coord, cutoff=self.cutoff, returntype="numpy", box=box)
-            except ValueError:
+            except ValueError:      # pragma: no cover
                 warnings.warn('N x N matrix too big, use sparse=True or sparse=None', category=UserWarning,
                               stacklevel=2)
                 raise
@@ -186,7 +187,7 @@ def _get_graph(self):
             try:
                 # this works for small-ish systems and depends on system memory
                 adj = distances.contact_matrix(coord, cutoff=self.cutoff, returntype="numpy", box=box)
-            except ValueError:
+            except ValueError:       # pragma: no cover
                 # but use a sparse matrix method for larger systems for memory reasons
                 warnings.warn(
                     'N x N matrix too big - switching to sparse matrix method (works fine, but is currently rather '

package/MDAnalysis/analysis/polymer.py

@@ -48,16 +48,16 @@
   # so we can select the chains by using the .fragments attribute
   chains = u.atoms.fragments
   # select only the backbone atoms for each chain
-  backbones = [chain.select_atoms('not name O* H') for chain in chains]
+  backbones = [chain.select_atoms('not name O* H*') for chain in chains]
   # sort the chains, removing any non-backbone atoms
   sorted_backbones = [polymer.sort_backbone(bb) for bb in backbones]
-  lp = polymer.PersistenceLength(sorted_backbones)
+  persistence_length = polymer.PersistenceLength(sorted_backbones)
   # Run the analysis, this will average over all polymer chains
   # and all timesteps in trajectory
-  lp = lp.run()
-  print('The persistence length is: {}'.format(lp.pl))
+  persistence_length = persistence_length.run()
+  print('The persistence length is: {}'.format(persistence_length.lp))
   # always check the visualisation of this:
-  lp.plot()
+  persistence_length.plot()
 
 """
 from __future__ import division, absolute_import
@@ -189,6 +189,8 @@ class PersistenceLength(AnalysisBase):
     .. versionadded:: 0.13.0
     .. versionchanged:: 0.20.0
        The run method now automatically performs the exponential fit
+    .. versionchanged:: 1.0.0
+       Deprecated :meth:`PersistenceLength.perform_fit` has now been removed.
     """
     def __init__(self, atomgroups, **kwargs):
         super(PersistenceLength, self).__init__(
@@ -240,10 +242,6 @@ def _calc_bond_length(self):
             bs.append(b)
         self.lb = np.mean(bs)
 
-    def perform_fit(self):
-        warnings.warn("perform_fit is now called automatically from run",
-                      DeprecationWarning)
-
     def _perform_fit(self):
         """Fit the results to an exponential decay"""
         try:

package/MDAnalysis/analysis/psa.py

@@ -237,6 +237,7 @@
          cite_module=True)
 del Doi
 
+
 def get_path_metric_func(name):
     """Selects a path metric function by name.
 
@@ -835,7 +836,6 @@ def __init__(self, universe, reference, select='name CA',
         self.path = None
         self.natoms = None
 
-
     def fit_to_reference(self, filename=None, prefix='', postfix='_fit',
                          rmsdfile=None, targetdir=os.path.curdir,
                          weights=None, tol_mass=0.1):
@@ -894,7 +894,6 @@ def fit_to_reference(self, filename=None, prefix='', postfix='_fit',
             aligntrj.save(rmsdfile)
         return MDAnalysis.Universe(self.top_name, self.newtrj_name)
 
-
     def to_path(self, fitted=False, select=None, flat=False):
         r"""Generates a coordinate time series from the fitted universe
         trajectory.
@@ -947,7 +946,6 @@ def to_path(self, fitted=False, select=None, flat=False):
         else:
             return np.array([atoms.positions for _ in frames])
 
-
     def run(self, align=False, filename=None, postfix='_fit', rmsdfile=None,
             targetdir=os.path.curdir, weights=None, tol_mass=0.1,
             flat=False):
@@ -1018,7 +1016,6 @@ def run(self, align=False, filename=None, postfix='_fit', rmsdfile=None,
         self.path = self.to_path(fitted=align, flat=flat)
         return self.top_name, self.newtrj_name
 
-
     def get_num_atoms(self):
         """Return the number of atoms used to construct the :class:`Path`.
 
@@ -1103,7 +1100,6 @@ def __init__(self, npaths, i, j):
         # Set by self.getHausdorffPair
         self.hausdorff_pair = {'frames' : (None, None), 'distance' : None}
 
-
     def _dvec_idx(self, i, j):
         """Convert distance matrix indices (in the upper triangle) to the index
         of the corresponding distance vector.
@@ -1127,7 +1123,6 @@ def _dvec_idx(self, i, j):
         """
         return (self.npaths*i) + j - (i+2)*(i+1)/2
 
-
     def compute_nearest_neighbors(self, P,Q, N=None):
         """Generates Hausdorff nearest neighbor lists of *frames* (by index) and
         *distances* for *this* pair of paths corresponding to distance matrix
@@ -1155,7 +1150,6 @@ def compute_nearest_neighbors(self, P,Q, N=None):
         self.nearest_neighbors['frames'] = hn['frames']
         self.nearest_neighbors['distances'] = hn['distances']
 
-
     def find_hausdorff_pair(self):
         r"""Find the Hausdorff pair (of frames) for *this* pair of paths.
 
@@ -1183,7 +1177,6 @@ def find_hausdorff_pair(self):
             self.hausdorff_pair['frames'] = nn_idx_Q[max_nn_idx_Q], max_nn_idx_Q
             self.hausdorff_pair['distance'] = max_nn_dist_Q
 
-
     def get_nearest_neighbors(self, frames=True, distances=True):
         """Returns the nearest neighbor frame indices, distances, or both, for
         each path in *this* :class:`PSAPair`.
@@ -1403,9 +1396,8 @@ def __init__(self, universes, reference=None, select='name CA',
         self._NN = None # (distance vector order) list of all nearest neighbors
         self._psa_pairs = None # (distance vector order) list of all PSAPairs
 
-
-    def generate_paths(self, align=False, filename='fitted', infix='', weights=None,
-                       tol_mass=False, ref_frame=None, flat=False, save=True, store=True):
+    def generate_paths(self, align=False, filename=None, infix='', weights=None,
+                       tol_mass=False, ref_frame=None, flat=False, save=True, store=False):
         """Generate paths, aligning each to reference structure if necessary.
 
         Parameters
@@ -1424,12 +1416,12 @@ def generate_paths(self, align=False, filename='fitted', infix='', weights=None,
              ``None`` weigh each atom equally. If a float array of the same
              length as the selected AtomGroup is provided, use each element of
              the `array_like` as a weight for the corresponding atom in the
-             AtomGroup.
+             AtomGroup [``None``]
         tol_mass : float
              Reject match if the atomic masses for matched atoms differ by more
-             than *tol_mass*
+             than *tol_mass* [``False``]
         ref_frame : int
-             frame index to select frame from *reference*
+             frame index to select frame from *reference* [``None``]
         flat : bool
              represent :attr:`Path.path` as a 2D (|2D|) :class:`numpy.ndarray`;
              if ``False`` then :attr:`Path.path` is a 3D (|3D|)
@@ -1459,6 +1451,11 @@ def generate_paths(self, align=False, filename='fitted', infix='', weights=None,
 
         .. versionchanged:: 0.17.0
            Deprecated keyword `mass_weighted` was removed.
+
+        .. versionchanged:: 1.0.0
+           Defaults for the `store` and `filename` keywords have been changed
+           from `True` and `fitted` to `False` and `None` respectively. These
+           now match the docstring documented defaults.
         """
         if ref_frame is None:
             ref_frame = self.ref_frame
@@ -1487,7 +1484,6 @@ def generate_paths(self, align=False, filename='fitted', infix='', weights=None,
         if store:
             self.save_paths(filename=filename)
 
-
     def run(self, **kwargs):
         """Perform path similarity analysis on the trajectories to compute
         the distance matrix.
@@ -1590,7 +1586,6 @@ def run_pairs_analysis(self, **kwargs):
                     self._HP.append(pp.get_hausdorff_pair())
         self.D = D
 
-
     def save_paths(self, filename=None):
         """Save fitted :attr:`PSAnalysis.paths` to numpy compressed npz files.
 
@@ -1627,7 +1622,6 @@ def save_paths(self, filename=None):
             cPickle.dump(self.path_names, output)
         return filename
 
-
     def load(self):
         """Load fitted paths specified by 'psa_path-names.pkl' in
         :attr:`PSAnalysis.targetdir`.
@@ -1642,13 +1636,12 @@ def load(self):
         if not os.path.exists(self._paths_pkl):
             raise NoDataError("Fitted trajectories cannot be loaded; save file" +
                               "{0} does not exist.".format(self._paths_pkl))
-        self.path_names = np.load(self._paths_pkl)
+        self.path_names = np.load(self._paths_pkl, allow_pickle=True)
         self.paths = [np.load(pname) for pname in self.path_names]
         if os.path.exists(self._labels_pkl):
-            self.labels = np.load(self._labels_pkl)
+            self.labels = np.load(self._labels_pkl, allow_pickle=True)
         logger.info("Loaded paths from %r", self._paths_pkl)
 
-
     def plot(self, filename=None, linkage='ward', count_sort=False,
              distance_sort=False, figsize=4.5, labelsize=12):
         """Plot a clustered distance matrix.
@@ -1769,7 +1762,6 @@ def plot(self, filename=None, linkage='ward', count_sort=False,
 
         return Z, dgram, dist_matrix_clus
 
-
     def plot_annotated_heatmap(self, filename=None, linkage='ward',             \
                                count_sort=False, distance_sort=False,           \
                                figsize=8, annot_size=6.5):
@@ -1893,7 +1885,6 @@ def plot_annotated_heatmap(self, filename=None, linkage='ward',             \
 
         return Z, dgram, dist_matrix_clus
 
-
     def plot_nearest_neighbors(self, filename=None, idx=0,                      \
                                labels=('Path 1', 'Path 2'), figsize=4.5,        \
                                multiplot=False, aspect_ratio=1.75,              \
@@ -1999,7 +1990,6 @@ def plot_nearest_neighbors(self, filename=None, idx=0,                      \
 
         return ax
 
-
     def cluster(self, dist_mat=None, method='ward', count_sort=False,           \
                 distance_sort=False, no_plot=False, no_labels=True,             \
                 color_threshold=4):
@@ -2091,7 +2081,6 @@ def _get_plot_obj_locs(self):
 
         return dgram_loc, hmap_loc, cbar_loc
 
-
     def get_num_atoms(self):
         """Return the number of atoms used to construct the :class:`Path` instances in
         :class:`PSA`.
@@ -2111,7 +2100,6 @@ def get_num_atoms(self):
                 "No path data; do 'PSAnalysis.generate_paths()' first.")
         return self.natoms
 
-
     def get_num_paths(self):
         """Return the number of paths in :class:`PSA`.
 
@@ -2129,7 +2117,6 @@ def get_num_paths(self):
                 "No path data; do 'PSAnalysis.generate_paths()' first.")
         return self.npaths
 
-
     def get_paths(self):
         """Return the paths in :class:`PSA`.
 
@@ -2149,7 +2136,6 @@ def get_paths(self):
                 "No path data; do 'PSAnalysis.generate_paths()' first.")
         return self.paths
 
-
     def get_pairwise_distances(self, vectorform=False, checks=False):
         """Return the distance matrix (or vector) of pairwise path distances.
 
@@ -2180,7 +2166,6 @@ def get_pairwise_distances(self, vectorform=False, checks=False):
         else:
             return self.D
 
-
     @property
     def psa_pairs(self):
         """The list of :class:`PSAPair` instances for each pair of paths.
@@ -2210,7 +2195,6 @@ def psa_pairs(self):
                              " 'PSAnalysis.run_pairs_analysis()' first.")
         return self._psa_pairs
 
-
     @property
     def hausdorff_pairs(self):
         """The Hausdorff pair for each (unique) pairs of paths.

package/MDAnalysis/coordinates/TRJ.py

@@ -120,9 +120,6 @@
 * The trajectory does not contain time information so we simply set
   the time step to 1 ps (or the user could provide it as kwarg *dt*)
 
-* **No direct access of frames is implemented, only iteration through
-  the trajectory.**
-
 * Trajectories with fewer than 4 atoms probably fail to be read (BUG).
 
 * If the trajectory contains exactly *one* atom then it is always
@@ -204,9 +201,6 @@ class TRJReader(base.ReaderBase):
     be set by passing the `dt` keyword argument to the constructor; it
     is assumed to be in ps. The default value is 1 ps.
 
-    Functionality is currently limited to simple iteration over the
-    trajectory.
-
     .. _AMBER TRJ format: http://ambermd.org/formats.html#trajectory
 
     .. versionchanged:: 0.11.0