Merge remote-tracking branch 'upstream/develop' into get_connections_…

…develop
MDAnalysis · Apr 23, 2021 · c0f0f52 · c0f0f52
2 parents 981c22a + ec7d636
commit c0f0f52
Show file tree

Hide file tree

Showing 45 changed files with 1,059 additions and 134 deletions.
diff --git a/.disabled-travis.yml b/.disabled-travis.yml
@@ -30,7 +30,7 @@ env:
     - SETUP_CMD="${PYTEST_FLAGS}"
     - BUILD_CMD="pip install -e package/ && (cd testsuite/ && python setup.py build)"
     - CONDA_MIN_DEPENDENCIES="mmtf-python biopython networkx cython matplotlib scipy griddataformats hypothesis gsd codecov"
-    - CONDA_DEPENDENCIES="${CONDA_MIN_DEPENDENCIES} seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12 chemfiles tqdm>=4.43.0 tidynamics>=1.0.0 rdkit>=2020.03.1 h5py==2.10.0"
+    - CONDA_DEPENDENCIES="${CONDA_MIN_DEPENDENCIES} seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12 chemfiles tqdm>=4.43.0 tidynamics>=1.0.0 rdkit>=2020.03.1 h5py"
     - CONDA_CHANNELS='biobuilds conda-forge'
     - CONDA_CHANNEL_PRIORITY=True
     - PIP_DEPENDENCIES="duecredit parmed"

diff --git a/.github/workflows/gh-ci.yaml b/.github/workflows/gh-ci.yaml
@@ -14,8 +14,8 @@ defaults:
     shell: bash -l {0}
 
 env:
-  MDA_CONDA_MIN_DEPS: "pip pytest==6.1.2 mmtf-python biopython networkx cython matplotlib-base scipy griddataformats hypothesis gsd codecov"
-  MDA_CONDA_EXTRA_DEPS: "seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12 chemfiles tqdm>=4.43.0 tidynamics>=1.0.0 rdkit>=2020.03.1 h5py==2.10.0"
+  MDA_CONDA_MIN_DEPS: "pip pytest==6.1.2 mmtf-python biopython networkx cython matplotlib-base scipy griddataformats hypothesis gsd codecov threadpoolctl"
+  MDA_CONDA_EXTRA_DEPS: "seaborn>=0.7.0 clustalw=2.1 netcdf4 scikit-learn joblib>=0.12 chemfiles tqdm>=4.43.0 tidynamics>=1.0.0 rdkit>=2020.03.1 h5py"
   MDA_PIP_MIN_DEPS: 'coveralls coverage<5 pytest-cov pytest-xdist'
   MDA_PIP_EXTRA_DEPS: 'duecredit parmed'
 
@@ -80,6 +80,7 @@ jobs:
         echo "CXX=clang++" >> $GITHUB_ENV
         gfortran-9 -v
         echo "FC=gfortran-9" >> $GITHUB_ENV
+        echo "numprocs=3" >> $GITHUB_ENV
 
     - name: setup_linux
       if: startsWith(matrix.os, 'ubuntu')
@@ -92,17 +93,17 @@ jobs:
         echo "CXX=g++" >> $GITHUB_ENV
         gfortran -v
         echo "FC=gfortran" >> $GITHUB_ENV
+        echo "numprocs=2" >> $GITHUB_ENV
 
     - name: setup_miniconda
       uses: conda-incubator/setup-miniconda@v2
       with:
         python-version: ${{ matrix.python-version }}
         auto-update-conda: true
         channel-priority: flexible
-        channels: biobuilds, conda-forge
+        channels: conda-forge, biobuilds
         add-pip-as-python-dependency: true
-        # TODO: mamba causes pip to segfault, switch when fixed
-        #mamba-version: "*"
+        mamba-version: "*"
         architecture: x64
 
     - name: install_deps
@@ -114,7 +115,7 @@ jobs:
         # NOTE: set matrix.numpy to pin to a specific numpy version
         conda_deps="${{ matrix.numpy }} ${MDA_CONDA_${{ matrix.run_type }}_DEPS}"
         pip_deps=${MDA_PIP_${{ matrix.run_type }}_DEPS}
-        conda install ${conda_deps}
+        mamba install ${conda_deps}
         pip install ${pip_deps}
 
         # also install asv if required
@@ -158,7 +159,7 @@ jobs:
           PYTEST_FLAGS="${PYTEST_FLAGS} --cov=MDAnalysis --cov-report=xml"
         fi
         echo $PYTEST_FLAGS
-        pytest -n 2 testsuite/MDAnalysisTests $PYTEST_FLAGS
+        pytest -n $numprocs testsuite/MDAnalysisTests $PYTEST_FLAGS
 
     - name: run_asv
       if: contains(matrix.name, 'asv_check')
@@ -191,15 +192,16 @@ jobs:
         python-version: 3.7
         auto-update-conda: true
         channel-priority: flexible
-        channels: biobuilds, conda-forge
+        channels: conda-forge, biobuilds
         add-pip-as-python-dependency: true
         architecture: x64
+        mamba-version: "*"
 
     - name: install_deps
       run: |
         conda_deps="${{ env.MDA_CONDA_MIN_DEPS }} ${{ env.MDA_CONDA_EXTRA_DEPS}}"
         pip_deps="${{ env.MDA_PIP_MIN_DEPS}} ${{ env.MDA_PIP_EXTRA_DEPS }} sphinx==1.8.5 sphinx-sitemap sphinx_rtd_theme msmb_theme==1.2.0"
-        conda install ${conda_deps}
+        mamba install ${conda_deps}
         pip install ${pip_deps}
 
     - name: install_mda
@@ -280,7 +282,6 @@ jobs:
         channel-priority: flexible
         channels: conda-forge
         add-pip-as-python-dependency: true
-        mamba-version: "*"
         architecture: x64
 
     - name: install
@@ -311,7 +312,7 @@ jobs:
         channel-priority: flexible
         channels: conda-forge
         add-pip-as-python-dependency: true
-        mamba-version: "*"
+        # mamba not enabled as install longer than deps install
         architecture: x64
 
     - name: install_conda

diff --git a/.travis.yml b/.travis.yml
@@ -25,7 +25,7 @@ matrix:
         - conda activate base
         - conda update --yes conda
         - conda install --yes pip pytest==6.1.2 mmtf-python biopython networkx cython matplotlib-base "scipy>=1.6" griddataformats hypothesis gsd codecov -c conda-forge -c biobuilds
-        - pip install pytest-xdist
+        - pip install pytest-xdist threadpoolctl
         - conda info
       install:
         - (cd package/ && python setup.py develop) && (cd testsuite/ && python setup.py install)
@@ -45,7 +45,7 @@ matrix:
       if: type = cron
       before_install:
         - python -m pip install cython numpy scipy
-        - python -m pip install --no-build-isolation hypothesis matplotlib pytest pytest-cov pytest-xdist tqdm
+        - python -m pip install --no-build-isolation hypothesis matplotlib pytest pytest-cov pytest-xdist tqdm threadpoolctl
       install:
         - cd package
         - python setup.py install

diff --git a/README.rst b/README.rst
@@ -23,6 +23,9 @@ a `tax-deductible donation`_ to help the project pay for developer time, profess
 
 This project is bound by a `Code of Conduct`_.
 
+|powered_by_MDA|
+
+If you use MDAnalysis_ in your project consider lettting your users and the world know about it by displaying the MDAnalysis_ badge! `Embedding code`_ is available for different markups.
 
 Example analysis script
 =======================
@@ -144,6 +147,7 @@ For citations of included algorithms and sub-modules please see the references_.
 .. _`10.1002/jcc.21787`: https://dx.doi.org/10.1002/jcc.21787
 .. _`10.25080/Majora-629e541a-00e`: https://doi.org/10.25080/Majora-629e541a-00e
 .. _references: https://docs.mdanalysis.org/documentation_pages/references.html
+.. _Embedding code: https://www.mdanalysis.org/pages/citations/#powered-by-mdanalysis
 
 
 .. |usergroup| image:: https://img.shields.io/badge/Google%20Group-Users-lightgrey.svg
@@ -185,3 +189,7 @@ For citations of included algorithms and sub-modules please see the references_.
 .. |mybinder| image:: https://mybinder.org/badge.svg
    :alt: My Binder
    :target: https://mybinder.org/v2/gh/MDAnalysis/binder-notebook/master
+
+.. |powered_by_MDA| image:: https://img.shields.io/badge/Powered%20by-MDAnalysis-orange.svg?logoWidth=15&logo=data:image/x-icon;base64,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
+   :alt: Powered by MDAnalysis
+   :target: https://www.mdanalysis.org
diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -35,6 +35,9 @@ jobs:
         Python38-64bit-full:
           PYTHON_VERSION: '3.8'
           PYTHON_ARCH: 'x64'
+        Python39-64bit-full:
+          PYTHON_VERSION: '3.9'
+          PYTHON_ARCH: 'x64'
   steps:
   - task: UsePythonVersion@0
     inputs:
@@ -44,7 +47,7 @@ jobs:
   - script: python -m pip install --upgrade pip setuptools wheel
     displayName: 'Install tools'
   - script: >-
-      python -m pip install
+      python -m pip install --only-binary=h5py
       cython
       hypothesis
       matplotlib
@@ -54,11 +57,11 @@ jobs:
       pytest-xdist
       scikit-learn
       scipy
-      h5py==2.10.0
+      h5py
       tqdm
+      threadpoolctl
     displayName: 'Install dependencies'
   # TODO: recent rdkit is not on PyPI
-  # NOTE: h5py pinned because of gh-3019
   - script: >-
       python -m pip install
       biopython

diff --git a/maintainer/conda/environment.yml b/maintainer/conda/environment.yml
@@ -8,7 +8,7 @@ dependencies:
   - cython
   - griddataformats
   - gsd
-  - h5py==2.10.0
+  - h5py
   - hypothesis
   - joblib>=0.12
   - matplotlib==3.2.2
@@ -31,4 +31,4 @@ dependencies:
       - duecredit
       - parmed
       - msmb_theme==1.2.0
-      - sphinx-sitemap==1.0.2
+      - sphinx-sitemap==1.0.2
diff --git a/package/AUTHORS b/package/AUTHORS
@@ -157,6 +157,14 @@ Chronological list of authors
   - Leonardo Barneschi
   - Henrik Jäger
   - Jan Stevens
+  - Orion Cohen
+  - Dimitrios Papageorgiou
+  - Hannah Pollak
+  - Estefania Barreto-Ojeda
+  - Paarth Thadani
+  - Henry Kobin
+  - Kosuke Kudo
+  - Sulay Shah
 
 External code
 -------------

diff --git a/package/CHANGELOG b/package/CHANGELOG
@@ -17,13 +17,28 @@ The rules for this file:
          lilyminium, daveminh, jbarnoud, yuxuanzhuang, VOD555, ianmkenney,
          calcraven，xiki-tempula, mieczyslaw, manuel.nuno.melo, PicoCentauri,
          hanatok, rmeli, aditya-kamath, tirkarthi, LeonardoBarneschi, hejamu,
-         biogen98
+         biogen98, orioncohen, z3y50n, hp115, ojeda-e, thadanipaarth, HenryKobin,
+         1ut, sulays
 
   * 2.0.0
 
 Fixes
+  * Fixed issue with unassigned 'GAP' variable in fasta2algin function when
+    resids are provided in input (Issue #3124)
+  * Improve diffusionmap coverage (Issue #3208)
+  * Removed deprecated parameters `n_jobs` and `precompute_distances` of
+    sklearn.cluster.KMeans (Issue #2986)
+  * Helix_analysis coverage raised to 100% and `from __future__ import`
+    removed (Issue #3209)
+  * Fixed 'sphzone', 'sphlayer', 'cyzone', and 'cylayer' to return empty if the
+   zone/layer is empty, consistent with 'around' (Issue #2915)
   * A Universe created from an ROMol with no atoms returns now a Universe 
     with 0 atoms (Issue #3142)
+  * PDBParser will check for the presence of the chainID attribute of an
+    atom group and use these values instead of just using the end of segid.
+    If no chainID attribute is present, then a default value will be
+    provided. If the chainID for an atom is invalid (longer than one character,
+    not alpha-numeric, blank) it will be replaced with a default. (Issue #3144)
   * ValueError raised when empty atomgroup is given to DensityAnalysis
     without a user defined grid. UserWarning displayed when user defined
     grid is provided. (Issue #3055)
@@ -90,6 +105,12 @@ Enhancements
   * Added intra_bonds, intra_angles, intra_dihedrals etc. to return only
     the connections involving atoms within the AtomGroup, instead of
     including atoms outside the AtomGroup (Issue #1264, #2821, PR #3200)
+  * Added an MDAnalysis shields.io badge to the README (Issue #3227, PR #3229)
+  * Added sort method to the atomgroup (Issue #2976, PR #3188) 
+  * ITPParser now reads [ atomtypes ] sections in ITP files, used for charges
+    and masses not defined in the [ atoms ] sections
+  * Add `set_dimensions` transformation class for setting constant 
+    box dimensions for all timesteps in trajectory (Issue #2691)
   * Added a ValueError raised when not given a gridcenter while
     providing grid dimensions to DensityAnalysis, also added
     check for NaN in the input (Issue #3148, PR #3154)
@@ -141,9 +162,11 @@ Enhancements
     'protein' selection (#2751 PR #2755)
   * Added an RDKit converter that works for any input with all hydrogens
     explicit in the topology (Issue #2468, PR #2775)
-
+  * Added `TransformationBase`. Implemented threadlimit and add an attribute for
+    checking if it can be used in parallel analysis. (Issue #2996, PR #2950)
 
 Changes
+  * Fixed inaccurate docstring inside the RMSD class (Issue #2796, PR #3134) 
   * TPRParser now loads TPR files with `tpr_resid_from_one=True` by default,
     which starts TPR resid indexing from 1 (instead of 0 as in 1.x) (Issue #2364, PR #3152)
   * Introduces encore specific C compiler arguments to allow for lowering of
@@ -183,6 +206,7 @@ Changes
   * deprecated ``analysis.helanal`` module has been removed in favour of
     ``analysis.helix_analysis`` (PR #2929)
   * Move water bridge analysis from hbonds to hydrogenbonds (Issue #2739 PR #2913)
+  * `threadpoolctl` is required for installation (Issue #2860)
 
 Deprecations
 

diff --git a/package/MDAnalysis/analysis/align.py b/package/MDAnalysis/analysis/align.py
@@ -1073,12 +1073,12 @@ def fasta2select(fastafilename, is_aligned=False,
     # implict assertion that we only have two sequences in the alignment
     orig_resids = [ref_resids, target_resids]
     offsets = [ref_offset, target_offset]
+    GAP = "-"
     for iseq, a in enumerate(alignment):
         # need iseq index to change orig_resids
         if orig_resids[iseq] is None:
             # build default: assume consecutive numbering of all
             # residues in the alignment
-            GAP = "-"
             length = len(a.seq) - a.seq.count(GAP)
             orig_resids[iseq] = np.arange(1, length + 1)
         else:

diff --git a/package/MDAnalysis/analysis/encore/clustering/ClusteringMethod.py b/package/MDAnalysis/analysis/encore/clustering/ClusteringMethod.py
@@ -195,6 +195,9 @@ def __init__(self,
                 (default is 50). Parameter in the Affinity Propagation for
                 clustering.
 
+            **kwargs : optional
+                Other keyword arguments are passed to :class:`sklearn.cluster.AffinityPropagation`.
+
             """
             self.ap = \
                 sklearn.cluster.AffinityPropagation(
@@ -331,7 +334,6 @@ def __init__(self,
                      verbose=False,
                      random_state=None,
                      copy_x=True,
-                     n_jobs=1,
                      **kwargs):
             """
             Parameters
@@ -360,14 +362,6 @@ def __init__(self,
                 If a callable is passed, it should take arguments X, k and
                 and a random state and return an initialization.
 
-            precompute_distances : {'auto', True, False}
-                Precompute distances (faster but takes more memory).
-                'auto' : do not precompute distances if
-                n_samples * n_clusters > 12 million. This corresponds to about
-                100MB overhead per job using double precision.
-                True : always precompute distances
-                False : never precompute distances
-
             tol : float, optional (default 1e-4)
                 The relative increment in the results before declaring
                 convergence.
@@ -388,25 +382,15 @@ def __init__(self,
                 differences may be introduced by subtracting and then adding
                 the data mean.
 
-            n_jobs : int
-                The number of jobs to use for the computation. This works by
-                computing each of the n_init runs in parallel. If -1 all CPUs
-                are used. If 1 is given, no parallel computing code is used at
-                all, which is useful for debugging. For n_jobs below -1,
-                (n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs
-                but one are used.
-
             """
             self.kmeans = sklearn.cluster.KMeans(n_clusters=n_clusters,
                                                  max_iter=max_iter,
                                                  n_init=n_init,
                                                  init=init,
-                                                 precompute_distances='auto',
                                                  tol=tol,
                                                  verbose=verbose,
                                                  random_state=random_state,
                                                  copy_x=copy_x,
-                                                 n_jobs=n_jobs,
                                                  **kwargs)
 
         def __call__(self, coordinates):

diff --git a/package/MDAnalysis/analysis/helix_analysis.py b/package/MDAnalysis/analysis/helix_analysis.py
@@ -78,7 +78,6 @@
     hel_xyz = hel.helix_analysis(u.atoms.positions, ref_axis=[0, 0, 1])
 
 """
-from __future__ import division, absolute_import
 
 import warnings
 import numpy as np

diff --git a/package/MDAnalysis/analysis/rms.py b/package/MDAnalysis/analysis/rms.py
@@ -380,7 +380,10 @@ def __init__(self, atomgroup, reference=None, select='all',
              corresponding atom in `select`, and assumes ``None`` for `groupselections`.
 
         weights_groupselections : False or list of {"mass", ``None`` or array_like} (optional)
-             1. ``False`` will apply imposed weights to `groupselections` from ``weights`` option.
+             1. ``False`` will apply imposed weights to `groupselections` from
+             ``weights`` option if ``weights`` is either ``"mass"`` or ``None``. 
+             Otherwise will assume a list of length equal to length of 
+             `groupselections` filled with ``None`` values.
 
              2. A list of {"mass", ``None`` or array_like} with the length of `groupselections`
              will apply the weights to `groupselections` correspondingly.

diff --git a/package/MDAnalysis/analysis/utils/__init__.py b/package/MDAnalysis/analysis/utils/__init__.py
diff --git a/package/MDAnalysis/coordinates/H5MD.py b/package/MDAnalysis/coordinates/H5MD.py
@@ -600,7 +600,7 @@ def _read_frame(self, frame):
             else:
                 raise NoDataError("Provide at least a position, velocity"
                                   " or force group in the h5md file.")
-        except ValueError:
+        except (ValueError, IndexError):
             raise IOError from None
 
         self._frame = frame