reciprocalspaceship 1.0.2__tar.gz → 1.0.4__tar.gz

{reciprocalspaceship-1.0.2/reciprocalspaceship.egg-info → reciprocalspaceship-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: reciprocalspaceship
-Version: 1.0.2
+Version: 1.0.4
 Summary: Tools for exploring reciprocal space
 Home-page: https://rs-station.github.io/reciprocalspaceship/
 Author: Kevin M. Dalton, Jack B. Greisman
@@ -18,9 +18,49 @@ Classifier: Topic :: Scientific/Engineering :: Physics
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Programming Language :: Python
 Requires-Python: >=3.9
+License-File: LICENSE
+Requires-Dist: gemmi<=0.7.1,>=0.7.0
+Requires-Dist: pandas<=2.2.3,>=2.2.2
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: ipython
+Requires-Dist: msgpack
 Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-xdist; extra == "dev"
+Requires-Dist: ray; extra == "dev"
+Requires-Dist: sphinx; extra == "dev"
+Requires-Dist: sphinx_rtd_theme; extra == "dev"
+Requires-Dist: nbsphinx; extra == "dev"
+Requires-Dist: sphinx-design; extra == "dev"
+Requires-Dist: sphinxcontrib-autoprogram; extra == "dev"
+Requires-Dist: autodocsumm; extra == "dev"
+Requires-Dist: jupyter; extra == "dev"
+Requires-Dist: tqdm; extra == "dev"
+Requires-Dist: matplotlib; extra == "dev"
+Requires-Dist: seaborn; extra == "dev"
+Requires-Dist: celluloid; extra == "dev"
+Requires-Dist: scikit-image; extra == "dev"
 Provides-Extra: examples
-License-File: LICENSE
+Requires-Dist: jupyter; extra == "examples"
+Requires-Dist: tqdm; extra == "examples"
+Requires-Dist: matplotlib; extra == "examples"
+Requires-Dist: seaborn; extra == "examples"
+Requires-Dist: celluloid; extra == "examples"
+Requires-Dist: scikit-image; extra == "examples"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 
 ``reciprocalspaceship`` provides a ``pandas``-style interface for

reciprocalspaceship-1.0.4/reciprocalspaceship/VERSION

@@ -0,0 +1 @@
+1.0.4

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/__init__.py

@@ -1,8 +1,15 @@
 # Version number for reciprocalspaceship
 def getVersionNumber():
-    import pkg_resources
+    version = None
+    try:
+        from setuptools.version import metadata
+
+        version = metadata.version("reciprocalspaceship")
+    except ImportError:
+        from setuptools.version import pkg_resources
+
+        version = pkg_resources.require("reciprocalspaceship")[0].version
 
-    version = pkg_resources.require("reciprocalspaceship")[0].version
     return version
 
 

reciprocalspaceship-1.0.4/reciprocalspaceship/commandline/cifdump.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python
+"""
+Summarize the contents of a CIF file.
+
+Examples
+--------
+In order to summarize contents of file.cif::
+
+    > rs.cifdump file.cif
+
+If you would like to interactively inspect file.cif in an IPython
+shell, use the "--embed" argument::
+
+    > rs.cifdump file.cif --embed
+
+If multiple CIF files are listed, they will be summarized sequentially,
+and can be accessed in an IPython shell as a dictionary called `cifs`::
+
+    > rs.cifdump file1.cif file2.cif file3.cif --embed
+
+Usage Details
+-------------
+"""
+import argparse
+
+import pandas as pd
+
+import reciprocalspaceship as rs
+
+# If matplotlib is available, use pylab to setup IPython environment
+try:
+    from pylab import *
+except:
+    pass
+
+
+def parse_arguments():
+    """Parse commandline arguments"""
+
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.RawTextHelpFormatter, description=__doc__
+    )
+
+    # Required arguments
+    parser.add_argument("cif", nargs="+", help="CIF file(s) to summarize")
+
+    # Optional arguments
+    parser.add_argument(
+        "--embed",
+        action="store_true",
+        help=(
+            "CIF file(s) will be summarized, and an IPython " "shell will be started"
+        ),
+    )
+    parser.add_argument(
+        "-p",
+        "--precision",
+        type=int,
+        default=3,
+        help="Number of significant digits to output for floats",
+    )
+
+    return parser
+
+
+def summarize(cif, precision):
+    """Summarize contents of CIF file"""
+    with pd.option_context("display.precision", precision):
+        print(f"Spacegroup: {cif.spacegroup.short_name()}")
+        print(f"Extended Hermann-Mauguin name: {cif.spacegroup.xhm()}")
+        print(
+            (
+                f"Unit cell dimensions: {cif.cell.a:.3f} {cif.cell.b:.3f} {cif.cell.c:.3f} "
+                f"{cif.cell.alpha:.3f} {cif.cell.beta:.3f} {cif.cell.gamma:.3f}"
+            )
+        )
+        print(f"\ncif.head():\n\n{cif.head()}")
+        print(f"\ncif.describe():\n\n{cif.describe()}")
+        print(f"\ncif.dtypes:\n\n{cif.dtypes}")
+    return
+
+
+def main():
+    # Parse commandline arguments
+    parser = parse_arguments()
+    args = parser.parse_args()
+
+    if len(args.cif) == 1:
+        cif = rs.read_cif(args.cif[0])
+        summarize(cif, args.precision)
+    else:
+        cifs = dict(zip(args.cif, map(rs.read_cif, args.cif)))
+        for key, value in cifs.items():
+            print(f"CIF file: {key}\n")
+            summarize(value, args.precision)
+            print(f"{'-'*50}")
+
+    # Begin IPython shell
+    if args.embed:
+        from IPython import embed
+
+        bold = "\033[1m"
+        end = "\033[0m"
+        if "cifs" in locals():
+            header = f"rs.DataSets stored in {bold}cifs{end} dictionary"
+        else:
+            header = f"rs.DataSet stored as {bold}cif{end}"
+        print()
+        embed(colors="neutral", header=header)
+
+    return
+
+
+if __name__ == "__main__":
+    parser = main()

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/commandline/mtzdump.py

@@ -74,9 +74,13 @@ def summarize(mtz, precision):
                 f"{mtz.cell.alpha:.3f} {mtz.cell.beta:.3f} {mtz.cell.gamma:.3f}"
             )
         )
-        print(f"\nmtz.head():\n\n{mtz.head()}")
-        print(f"\nmtz.describe():\n\n{mtz.describe()}")
-        print(f"\nmtz.dtypes:\n\n{mtz.dtypes}")
+        if mtz.cell is not None:
+            dHKL = mtz.compute_dHKL().dHKL
+            print(f"Resolution range:  {dHKL.max():.3f} - {dHKL.min():.3f} Å")
+        with pd.option_context("display.max_rows", None):
+            print(f"\nmtz.head():\n\n{mtz.head()}")
+            print(f"\nmtz.describe().T:\n\n{mtz.describe().T}")
+            print(f"\nmtz.dtypes:\n\n{mtz.dtypes}")
     return
 
 

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/dataset.py

@@ -43,6 +43,23 @@ class DataSet(pd.DataFrame):
     and attributes, please see the `Pandas.DataFrame documentation`_.
 
     .. _Pandas.DataFrame documentation: https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html
+
+    Attributes
+    ----------
+    acentrics : rs.DataSet
+        Access only the acentric reflections in this dataset
+    cell : gemmi.UnitCell
+        The unit cell
+    centrics : rs.DataSet
+        Access only the centric reflections in this dataset
+    hkls : ndarray, shape=(n_reflections, 3)
+        Miller indices in DataSet.
+    merged : bool
+        Whether this is a merged dataset or unmerged
+    spacegroup : gemmi.SpaceGroup
+        The space group
+    reindexing_ops : list
+        Possible reindexing ops consistent with the cell and spacegroup
     """
 
     _metadata = ["_spacegroup", "_cell", "_index_dtypes", "_merged"]
@@ -131,6 +148,38 @@ class DataSet(pd.DataFrame):
     def merged(self, val):
         self._merged = val
 
+    @property
+    @range_indexed
+    def hkls(self):
+        """Miller indices"""
+        hkl = self[["H", "K", "L"]].to_numpy(dtype=np.int32)
+        return hkl
+
+    def get_hkls(self):
+        """Get the Miller indices of the dataset."""
+        return self.hkls
+
+    @hkls.setter
+    @range_indexed
+    def hkls(self, hkls):
+        if isinstance(hkls, DataSet):
+            """Convert to numpy if hkls is a dataset"""
+            hkls = hkls.hkls
+        if isinstance(hkls, np.ndarray):
+            h, k, l = hkls[..., 0], hkls[..., 1], hkls[..., 2]
+        else:
+            """Try coercing to numpy"""
+            try:
+                hkls = np.array(hkls)
+                h, k, l = hkls[..., 0], hkls[..., 1], hkls[..., 2]
+            except:
+                raise ValueError(
+                    "Unable to convert hkls to a suitable type. Please ensure hkls is a numpy array or rs.DataSet"
+                )
+        self["H"] = DataSeries(h, index=self.index, dtype="H")
+        self["K"] = DataSeries(k, index=self.index, dtype="H")
+        self["L"] = DataSeries(l, index=self.index, dtype="H")
+
     @property
     def centrics(self):
         """Access centric reflections in DataSet"""
@@ -258,7 +307,14 @@ class DataSet(pd.DataFrame):
         )
 
     def reset_index(
-        self, level=None, drop=False, inplace=False, col_level=0, col_fill=""
+        self,
+        level=None,
+        drop=False,
+        inplace=False,
+        col_level=0,
+        col_fill="",
+        allow_duplicates=lib.no_default,
+        names=None,
     ):
         """
         Reset the index or a specific level of a MultiIndex.
@@ -281,6 +337,12 @@ class DataSet(pd.DataFrame):
         col_fill : object
             If the columns have multiple levels, determines how the other
             levels are named. If None then the index name is repeated.
+        allow_duplicates : bool
+            Allow duplicate column labels to be created.
+        names : int, str, tuple, list
+            Using the given string, rename the DataSet column which contains the
+            index data. If the DataSet has a MultiIndex, this has to be a list or
+            tuple with length equal to the number of levels.
 
         Returns
         -------
@@ -317,6 +379,8 @@ class DataSet(pd.DataFrame):
                 inplace=inplace,
                 col_level=col_level,
                 col_fill=col_fill,
+                allow_duplicates=allow_duplicates,
+                names=names,
             )
             _handle_cached_dtypes(self, columns, drop)
             return
@@ -327,6 +391,8 @@ class DataSet(pd.DataFrame):
                 inplace=inplace,
                 col_level=col_level,
                 col_fill=col_fill,
+                allow_duplicates=allow_duplicates,
+                names=names,
             )
             dataset._index_dtypes = dataset._index_dtypes.copy()
             dataset = _handle_cached_dtypes(dataset, columns, drop)
@@ -406,6 +472,7 @@ class DataSet(pd.DataFrame):
         """
         return cls(gemmiMtz)
 
+    @range_indexed
     def to_gemmi(
         self,
         skip_problem_mtztypes=False,
@@ -575,6 +642,7 @@ class DataSet(pd.DataFrame):
         result = super().join(*args, **kwargs)
         return result.__finalize__(self)
 
+    @range_indexed
     def write_mtz(
         self,
         mtzfile,
@@ -1158,7 +1226,7 @@ class DataSet(pd.DataFrame):
 
         return result
 
-    def is_isomorphous(self, other, cell_threshold=0.05):
+    def is_isomorphous(self, other, cell_threshold=0.5):
         """
         Determine whether DataSet is isomorphous to another DataSet. This
         method confirms isomorphism by ensuring the spacegroups are equivalent,
@@ -1195,7 +1263,8 @@ class DataSet(pd.DataFrame):
         for param in params:
             param1 = self.cell.__getattribute__(param)
             param2 = other.cell.__getattribute__(param)
-            if (np.abs((param1 - param2)) / 100.0) > cell_threshold:
+            diff = 200.0 * np.abs(param1 - param2) / (param1 + param2)
+            if diff > cell_threshold:
                 return False
 
         return True
@@ -1565,24 +1634,6 @@ class DataSet(pd.DataFrame):
         warnings.simplefilter("always")
         warnings.warn(message, DeprecationWarning)
 
-        if dmin is not None:
-            ds = self.loc[self.compute_dHKL().dHKL >= dmin, [key]]
-        else:
-            ds = self.loc[:, [key]]
-
-        if gridsize is None:
-            gridsize = self.get_reciprocal_grid_size(dmin=dmin, sample_rate=sample_rate)
-
-        # Set up P1 unit cell
-        p1 = ds.expand_to_p1()
-        p1 = p1.expand_anomalous()
-
-        # Get data and indices
-        data = p1[key].to_numpy()
-        H = p1.get_hkls()
-
-        # Populate grid
-        grid = np.zeros(gridsize, dtype=data.dtype)
-        grid[H[:, 0], H[:, 1], H[:, 2]] = data
-
-        return grid
+        return self.to_reciprocal_grid(
+            key, sample_rate=sample_rate, dmin=dmin, grid_size=gridsize
+        )

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/decorators.py

@@ -4,6 +4,8 @@ from inspect import signature
 import gemmi
 import numpy as np
 
+import reciprocalspaceship as rs
+
 
 def inplace(f):
     """
@@ -46,9 +48,11 @@ def range_indexed(f):
         names = ds.index.names
         ds = ds._index_from_names([None], inplace=True)
         result = f(ds, *args, **kwargs)
-        result = result._index_from_names(names, inplace=True)
         ds = ds._index_from_names(names, inplace=True)
-        return result.__finalize__(ds)
+        if isinstance(result, rs.DataSet):
+            result = result._index_from_names(names, inplace=True)
+            result = result.__finalize__(ds)
+        return result
 
     return wrapped
 

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/dtypes/internals.py

@@ -1359,7 +1359,7 @@ class NumericArray(BaseMaskedArray):
 
 @wraps(libmissing.is_numeric_na)
 def is_numeric_na(values):
-    allowed_dtypes = ("float32", "int32")
+    allowed_dtypes = ("float64", "float32", "int32")
     if isinstance(values, np.ndarray) and values.dtype in allowed_dtypes:
         return np.isnan(values)
     return libmissing.is_numeric_na(values)

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/io/__init__.py

@@ -1,6 +1,7 @@
 from reciprocalspaceship.io.ccp4map import write_ccp4_map
 from reciprocalspaceship.io.crystfel import read_crystfel
 from reciprocalspaceship.io.csv import read_csv
+from reciprocalspaceship.io.dials import print_refl_info, read_dials_stills
 from reciprocalspaceship.io.mtz import (
     from_gemmi,
     read_cif,

reciprocalspaceship-1.0.4/reciprocalspaceship/io/common.py

@@ -0,0 +1,48 @@
+import logging
+import warnings
+from contextlib import contextmanager
+from importlib.util import find_spec
+
+
+def set_ray_loglevel(level):
+    logger = logging.getLogger("ray")
+    logger.setLevel(level)
+    for handler in logger.handlers:
+        handler.setLevel(level)
+
+
+def check_for_ray():
+    has_ray = True
+    if find_spec("ray") is None:
+        has_ray = False
+
+        message = (
+            "ray (https://www.ray.io/) is not available..." "Falling back to serial."
+        )
+        warnings.warn(message, ImportWarning)
+    return has_ray
+
+
+def check_for_mpi():
+    try:
+        from mpi4py import MPI
+
+        return True
+    except Exception as err:
+        message = (
+            f"Failed `from mpi4py import MPI` with {err}. Falling back to serial mode."
+        )
+        warnings.warn(message, ImportWarning)
+        return False
+
+
+@contextmanager
+def ray_context(log_level="DEBUG", **ray_kwargs):
+    import ray
+
+    set_ray_loglevel(log_level)
+    ray.init(**ray_kwargs)
+    try:
+        yield ray
+    finally:
+        ray.shutdown()

{reciprocalspaceship-1.0.2 → reciprocalspaceship-1.0.4}/reciprocalspaceship/io/crystfel.py

@@ -1,13 +1,12 @@
 import mmap
 import re
-from contextlib import contextmanager
-from importlib.util import find_spec
 from typing import Union
 
 import gemmi
 import numpy as np
 
 from reciprocalspaceship import DataSet, concat
+from reciprocalspaceship.io.common import check_for_ray, ray_context
 from reciprocalspaceship.utils import angle_between, eV2Angstroms
 
 # See Rupp Table 5-2
@@ -60,17 +59,6 @@ _block_markers = {
 }
 
 
-@contextmanager
-def ray_context(**ray_kwargs):
-    import ray
-
-    ray.init(**ray_kwargs)
-    try:
-        yield ray
-    finally:
-        ray.shutdown()
-
-
 class StreamLoader(object):
     """
     An object that loads stream files into rs.DataSet objects in parallel.
@@ -304,15 +292,7 @@ class StreamLoader(object):
 
         # Check whether ray is available
         if use_ray:
-            if find_spec("ray") is None:
-                use_ray = False
-                import warnings
-
-                message = (
-                    "ray (https://www.ray.io/) is not available..."
-                    "Falling back to serial stream file parser."
-                )
-                warnings.warn(message, ImportWarning)
+            use_ray = check_for_ray()
 
         with open(self.filename, "r") as f:
             memfile = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)
@@ -507,10 +487,9 @@ def read_crystfel(
         The type of byte-encoding (optional, 'utf-8').
     columns : list (optional)
         Optionally specify the columns of the output by a list of strings.
-        The default list is:
-            [ "H", "K", "L", "I", "SigI", "BATCH", "s1x", "s1y", "s1z", "ewald_offset",
-            "angular_ewald_offset", "XDET", "YDET" ]
-        See `rs.io.crystfel.StreamLoader().available_column_names` for a list of available column names.
+        The default list is: [ "H", "K", "L", "I", "SigI", "BATCH", "s1x", "s1y", "s1z", "ewald_offset", "angular_ewald_offset", "XDET", "YDET" ]
+        See `rs.io.crystfel.StreamLoader().available_column_names` for a list of available
+        column names and *Notes* for a description of the returned columns
     parallel : bool (optional)
         Read the stream file in parallel using [ray.io](https://docs.ray.io) if it is available.
     num_cpus : int (optional)
@@ -524,6 +503,18 @@ def read_crystfel(
     Returns
     --------
     rs.DataSet
+
+    Notes
+    -----
+    The following columns are included in the returned DataSet object:
+
+        - H, K, L: Miller indices of each reflection
+        - I, SigI: Intensity and associated uncertainty
+        - BATCH: Image number
+        - s1x, s1y, s1z: scattered beam wavevector which points from the sample to the bragg peak
+        - ewald_offset: the distance in cartesian space (1/angstroms) between the observed reflection and the ewald sphere
+        - angular_ewald_offset: the distance in polar coordinates (degrees) between the observed reflection and the ewald sphere
+        - XDET, YDET: Internal detector panel coordinates
     """
     if not streamfile.endswith(".stream"):
         raise ValueError("Stream file should end with .stream")