Merge branch 'refactor_24' into 48-fractional-binning

.github/workflows/test.yml

@@ -14,33 +14,22 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, ubuntu-latest, windows-latest]
-        python-version: ['3.9', '3.10', '3.11']
+        python-version: ['3.12']
       fail-fast: false
 
     steps:
 
     - name: Obtain SasData source from git
-      uses: actions/checkout@v1
+      uses: actions/checkout@v4
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
-
-    ### Caching of pip downloads and local wheel builds
-    - name: Get pip cache dir
-      id: pip-cache
-      run: |
-        echo "name={$(pip cache dir)}" >> $GITHUB_OUTPUT
-
-    - name: Obtain pip cache (Linux)
-      uses: actions/cache@v2
-      with:
-        path: ${{ steps.pip-cache.outputs.name }}
-        key: ${{ runner.os }}-pip-${{ matrix.python-version }}-${{ hashFiles('**/test.yml') }}
-        restore-keys: |
-          ${{ runner.os }}-pip-${{ matrix.python-version }}-
-          ${{ runner.os }}-pip-
+        cache: 'pip'
+        cache-dependency-path: |
+          **/test.yml
+          **/requirements*.txt
 
     ### Installation of build-dependencies
 

LICENSE.TXT

@@ -1,5 +1,4 @@
-Copyright (c) 2009-2022, SasView Developers
-
+Copyright (c) 2009-2024, SasView Developers
 
 All rights reserved.
 

docs/Makefile

@@ -1,14 +1,17 @@
 # Minimal makefile for Sphinx documentation
-#
 
 # Environment variables
 SPHINXOPTS    ?=
 SPHINXBUILD   ?= sphinx-build
 SPHINXAPIDOC  ?= sphinx-apidoc
 APIOPTS       = -d 8 -H SasData
+DOCSDIR       = docs
 SOURCEDIR     = source
 BUILDDIR      = build
-CD            = cd
+DEVDIR        = dev
+LIBDIR        = lib
+GENDIR        = generated
+UP            = ..
 
 ifdef ComSpec
     RMDIR   = rmdir /s/q
@@ -20,27 +23,31 @@ else
     PATHSEP = $(strip /)
 endif
 
-LIBDIR        = $(BUILDDIR)$(PATHSEP)lib
+SASDATABUILD  = $(UP)$(PATHSEP)$(BUILDDIR)$(PATHSEP)$(LIBDIR)
+DOCSSRC       = $(SOURCEDIR)
+DEV           = $(DOCSSRC)$(PATHSEP)$(DEVDIR)
+DEVGEN        = $(DEV)$(PATHSEP)$(GENDIR)
+DOCSBUILD     = $(DOCSSRC)$(PATHSEP)$(BUILDDIR)
 
 # Put it first so that "make" without argument is like "make help".
 help:
 	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 
 clean:
-	-$(RMDIR) "$(SOURCEDIR)$(PATHSEP)dev$(PATHSEP)generated/" "$(BUILDDIR)"
+	-$(RMDIR) "$(DEVGEN)" "$(DOCSBUILD)"
 
 dir:
-	-$(MKDIR) "$(BUILDDIR)"
-	-$(MKDIR) "$(LIBDIR)"
+	-$(MKDIR) "$(DEVGEN)"
+	-$(MKDIR) "$(DOCSBUILD)"
 
 .PHONY: help Makefile
 
 # Generate the api docs
 api:
-	$(SPHINXAPIDOC) -o "$(SOURCEDIR)$(PATHSEP)dev$(PATHSEP)generated/" $(APIOPTS) "$(LIBDIR)"
+	$(SPHINXAPIDOC) -o "$(DEVGEN)" $(APIOPTS) "$(SASDATABUILD)"
 
 html: dir api
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(DOCSSRC)" "$(DOCSBUILD)" $(SPHINXOPTS) $(O)
 
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).

docs/source/dev/dev.rst

@@ -6,6 +6,6 @@ Developer Documentation
 =======================
 
 .. toctree::
-    :maxdepth: 1
+    :maxdepth: 8
 
-    SasData <generated/modules>
+    SasData <generated/sasdata>

docs/source/rst_prolog

@@ -1,4 +1,5 @@
 .. Set up some substitutions to make life easier...
 
 .. |Ang| unicode:: U+212B
-.. |Ang^-1| replace:: |Ang|\ :sup:`-1`
+.. |Ang^-1| replace:: |Ang|\ :sup:`-1`
+.. |delta| unicode:: U+03B4

docs/source/user/RELEASE.rst

@@ -14,6 +14,43 @@ Features
 ========
 Wheel, egg, and tar.gz files are available on `pypi <https://pypi.org/project/sasdata/>`_.
 
+New in Version 0.9.0
+--------------------
+This is an enhancement release with updates to the unit conversion routines, the ability to load data from URIs, the
+addition of a wedge slicer and other slicer enhancements.
+
+What's Changed
+^^^^^^^^^^^^^^
+
+Feature Enhancements
+____________________
+* Refactor nxsunit by @krzywon in https://github.com/SasView/sasdata/pull/13
+* Enable the sector slicing to allow both sides independantly by @butlerpd in https://github.com/SasView/sasdata/pull/36
+* Load data from URIs by @krzywon in https://github.com/SasView/sasdata/pull/37
+* SasData counterpart to SasView SlicerExtension_1344 by @jack-rooks in https://github.com/SasView/sasdata/pull/61
+
+Bug Fixes
+_________
+* Fixing Issue #40 (but properly this time) by @ehewins in https://github.com/SasView/sasdata/pull/42
+* changed xaxis label for updated SESANS nomenclature from z to delta by @caitwolf in https://github.com/SasView/sasdata/pull/60
+* Fix delta in sesans docs by @caitwolf in https://github.com/SasView/sasdata/pull/65
+
+Documentation Changes
+_____________________
+* Rework readme by @krzywon in https://github.com/SasView/sasdata/pull/15
+* Building sasdata documentation by @krzywon in https://github.com/SasView/sasdata/pull/53
+* Generate Developer Docs by @krzywon in https://github.com/SasView/sasdata/pull/56
+
+Infrastructure Changes
+______________________
+* Remove entry_point from setup.py by @krzywon in https://github.com/SasView/sasdata/pull/2
+* Dependency cleanup by @krzywon in https://github.com/SasView/sasdata/pull/33
+* Move example data to sasdata by @krzywon in https://github.com/SasView/sasdata/pull/49
+* CI updates by @krzywon in https://github.com/SasView/sasdata/pull/50
+* Restrict lxml to versions less than 5.0 by @krzywon in https://github.com/SasView/sasdata/pull/63
+* Update example data by @smk78 in https://github.com/SasView/sasdata/pull/58
+* Fix broken unit test(s) by @krzywon in https://github.com/SasView/sasdata/pull/68
+
 New in Version 0.8.1
 --------------------
 This is a point release to fix a build issue. The `sasdata.data_utils` package was omitted from setup.py causing an

docs/source/user/data/data_formats_help.rst

@@ -114,10 +114,10 @@ between users.
 Following the header are up to 8 space-delimited columns of experimental
 variables of which the first 4 columns are required. In order, these are:
 
-- Spin-echo length (z, in Angstroms)
-- Depolarization (:math:`log(P/P_0)/(lambda^2 * thickness)`, in Angstrom :sup:`-1` cm :sup:`-1`\ )
+- Spin-echo length (:math:`\delta`, in Angstroms)
+- Depolarization (:math:`log(P/P_0)/(\lambda^2 * thickness)`, in Angstrom :sup:`-1` cm :sup:`-1`\ )
 - Depolarization error (also in in Angstrom :sup:`-1` cm :sup:`-1`\ ) (i.e. the measurement error)
-- Spin-echo length error (:math:`\Delta`\ z, in Angstroms) (i.e. the experimental resolution)
+- Spin-echo length error (:math:`\Delta \delta`, in Angstroms) (i.e. the experimental resolution)
 - Neutron wavelength (:math:`\lambda`, in Angstroms)
 - Neutron wavelength error (:math:`\Delta \lambda`, in Angstroms)
 - Normalized polarization (:math:`P/P_0`, unitless)

requirements.txt

@@ -3,7 +3,7 @@ h5py
 lxml
 
 # Calculation
-numpy
+numpy==1.*
 scipy
 
 # Unit testing

sasdata/__init__.py

@@ -1,7 +1,7 @@
 import os
 from pathlib import Path
 
-__version__ = "0.8.1"
+__version__ = "0.9.0"
 
 # An importable path to the example data to
 data_path: Path = Path(os.path.join(Path(os.path.dirname(__file__)), 'example_data'))

sasdata/checklist.txt

@@ -0,0 +1,3 @@
+Things to check once everything is in place:
+
+1) Do any centigrade fields read in incorrectly?

sasdata/data.py

@@ -0,0 +1,42 @@
+from enum import Enum
+from typing import TypeVar, Any, Self
+from dataclasses import dataclass
+
+from quantities.quantity import NamedQuantity
+from sasdata.metadata import Metadata
+from sasdata.quantities.accessors import AccessorTarget
+from sasdata.data_backing import Group, key_tree
+
+
+class SasData:
+    def __init__(self, name: str, data_contents: list[NamedQuantity], raw_metadata: Group, verbose: bool=False):
+        self.name = name
+        self._data_contents = data_contents
+        self._raw_metadata = raw_metadata
+        self._verbose = verbose
+
+        self.metadata = Metadata(AccessorTarget(raw_metadata, verbose=verbose))
+
+        # TO IMPLEMENT
+
+        # abscissae: list[NamedQuantity[np.ndarray]]
+        # ordinate: NamedQuantity[np.ndarray]
+        # other: list[NamedQuantity[np.ndarray]]
+        #
+        # metadata: Metadata
+        # model_requirements: ModellingRequirements
+
+    def summary(self, indent = "  ", include_raw=False):
+        s = f"{self.name}\n"
+
+        for data in self._data_contents:
+            s += f"{indent}{data}\n"
+
+        s += f"Metadata:\n"
+        s += "\n"
+        s += self.metadata.summary()
+
+        if include_raw:
+            s += key_tree(self._raw_metadata)
+
+        return s

sasdata/data_backing.py

@@ -0,0 +1,126 @@
+from typing import TypeVar, Self
+from dataclasses import dataclass
+from enum import Enum
+
+from sasdata.quantities.quantity import NamedQuantity
+
+DataType = TypeVar("DataType")
+
+""" Sasdata metadata tree """
+
+def shorten_string(string):
+    lines = string.split("\n")
+    if len(lines) <= 1:
+        return string
+    else:
+        return lines[0][:30] + " ... " + lines[-1][-30:]
+
+@dataclass
+class Dataset[DataType]:
+    name: str
+    data: DataType
+    attributes: dict[str, Self | str]
+
+    def summary(self, indent_amount: int = 0, indent: str = "  ") -> str:
+
+        s = f"{indent*indent_amount}{self.name.split("/")[-1]}:\n"
+        s += f"{indent*(indent_amount+1)}{shorten_string(str(self.data))}\n"
+        for key in self.attributes:
+            value = self.attributes[key]
+            if isinstance(value, (Group, Dataset)):
+                value_string = value.summary(indent_amount+1, indent)
+            else:
+                value_string = f"{indent * (indent_amount+1)}{key}: {shorten_string(repr(value))}\n"
+
+            s += value_string
+
+        return s
+
+@dataclass
+class Group:
+    name: str
+    children: dict[str, Self | Dataset]
+
+    def summary(self, indent_amount: int=0, indent="  "):
+        s = f"{indent*indent_amount}{self.name.split("/")[-1]}:\n"
+        for key in self.children:
+            s += self.children[key].summary(indent_amount+1, indent)
+
+        return s
+
+class Function:
+    """ Representation of a (data driven) function, such as I vs Q """
+
+    def __init__(self, abscissae: list[NamedQuantity], ordinate: NamedQuantity):
+        self.abscissae = abscissae
+        self.ordinate = ordinate
+
+
+class FunctionType(Enum):
+    """ What kind of function is this, should not be relied upon to be perfectly descriptive
+
+    The functions might be parametrised by more variables than the specification
+    """
+    UNKNOWN = 0
+    SCATTERING_INTENSITY_VS_Q = 1
+    SCATTERING_INTENSITY_VS_Q_2D = 2
+    SCATTERING_INTENSITY_VS_Q_3D = 3
+    SCATTERING_INTENSITY_VS_ANGLE = 4
+    UNKNOWN_METADATA = 20
+    TRANSMISSION = 21
+    POLARISATION_EFFICIENCY = 22
+    UNKNOWN_REALSPACE = 30
+    SESANS = 31
+    CORRELATION_FUNCTION_1D = 32
+    CORRELATION_FUNCTION_2D = 33
+    CORRELATION_FUNCTION_3D = 34
+    INTERFACE_DISTRIBUTION_FUNCTION = 35
+    PROBABILITY_DISTRIBUTION = 40
+    PROBABILITY_DENSITY = 41
+
+def function_type_identification_key(names):
+    """ Create a key from the names of data objects that can be used to assign a function type"""
+    return ":".join([s.lower() for s in sorted(names)])
+
+function_fields_to_type = [
+    (["Q"], "I", FunctionType.SCATTERING_INTENSITY_VS_Q),
+    (["Qx", "Qy"], "I", FunctionType.SCATTERING_INTENSITY_VS_Q_2D),
+    (["Qx", "Qy", "Qz"], "I", FunctionType.SCATTERING_INTENSITY_VS_Q_3D),
+    (["Z"], "G", FunctionType.SESANS),
+    (["lambda"], "T", FunctionType.TRANSMISSION)
+]
+
+function_fields_lookup = {
+    function_type_identification_key(inputs + [output]): function_type for inputs, output, function_type in function_fields_to_type
+}
+
+def build_main_data(data: list[NamedQuantity]) -> Function:
+    names = [datum.name for datum in data]
+    identifier = function_type_identification_key(names)
+
+    if identifier in function_fields_lookup:
+        function_type = function_fields_lookup[identifier]
+    else:
+        function_type = FunctionType.UNKNOWN
+
+    match function_type:
+        case FunctionType.UNKNOWN:
+            pass
+        case _:
+            raise NotImplementedError("Unknown ")
+
+def key_tree(data: Group | Dataset, indent_amount=0, indent: str = "  ") -> str:
+    """ Show a metadata tree, showing the names of they keys used to access them"""
+    s = ""
+    if isinstance(data, Group):
+        for key in data.children:
+            s += indent*indent_amount + key + "\n"
+            s += key_tree(data.children[key], indent_amount=indent_amount+1, indent=indent)
+
+    if isinstance(data, Dataset):
+        s += indent*indent_amount + "[data]\n"
+        for key in data.attributes:
+            s += indent*indent_amount + key + "\n"
+            s += key_tree(data.attributes[key], indent_amount=indent_amount+1, indent=indent)
+
+    return s