dclab 0.62.11__tar.gz → 2.18.0__tar.gz

{dclab-0.62.11 → dclab-2.18.0}/.readthedocs.yml

@@ -8,6 +8,8 @@ build:
   jobs:
     post_checkout:
       - git fetch --unshallow || true
+    pre_install:
+      - RPY2_CFFI_MODE=ABI
 python:
   install:
     - requirements: docs/requirements.txt

{dclab-0.62.11 → dclab-2.18.0}/CHANGELOG

@@ -1,60 +1,3 @@
-0.62.11
- - enh: support plain `numpy.array` tables
-0.62.10
- - fix: `basin_definition_copy` failed when more than one basins defined
-   due to redundant loop
- - fix: JSON logs during export were not sorted and indented
-0.62.9
- - enh: sort basin definition before exporting to JSON; the side-effect
-   is that the unique key for a basin changes, possibly resulting in
-   duplicated basin definitions for existing datasets
- - enh: make sure every basin can be identified with a key created from
-   its definition; important for connecting the basin dictionaries
-   with the instantiated basins
-0.62.8
- - fix: metadata of tables not copied by `copier.py`
- - docs: formatting typo (#270)
-0.62.7
- - fix: IntegrityChecker must not load basins
- - fix: KeyError in IntegrityChecker when "basin_events" group missing (#268)
- - fix: warn user about missing internal basin features while still loading
-   those that are available (#268)
- - fix: do not copy internal basin definitions for non-existent features (#269)
- - docs: clarify interpretation of [qpi]: "filter size" metadata (#267)
- - tests: avoid architecture and Python-version dependent test
-0.62.6
- - enh: support passing pathlib.Path to lme4.rsetup.set_*_path methods
- - docs: correct keyword arguments for advanced section on S3
-0.62.5
- - enh: make set_r_lib_path available in lme4 submodule
-0.62.4
- - enh: honor R_LIBS_USER environment variable when running R
-0.62.3
- - fix: get_r_version string conversion not necessary
-0.62.2
- - fix: use full path to R executable when running lme4 analysis in rsetup
- - enh: properly catch CalledProcessError in run_command
- - enh: improve search for R executable path
- - ref: replace sp.check_output with run_command in lme4 submodule
-0.62.1
- - fix: numpy-version-specific default for `copy` in `__array__()`
-0.62.0
- - BREAKING: removed the `rtdc_dataset.linker` module, because it is not
-   used by any other piece of software and because combining file-like
-   objects external links are quirky and their combination finally broke
-   with h5py 3.12
- - enh: added integrity check for external links
- - tests: reduce warnings
-0.61.5
- - fix: integrity check failed for empty datasets
-0.61.4
- - docs: update basins section
- - docs: cleanup build process
-0.61.3
- - fix: TypeError when of R_HOME is not set
-0.61.2
- - ref: migrate from rpy2 to custom wrapper around R and Rscript binary
- - setup: remove extra [lme4] and rpy2 requirement
 0.61.1
  - fix: properly catch warnings for determining bad event image for fmt_tdms
  - fix: make sure integer features are always written as uint,
@@ -70,7 +13,7 @@
  - enh: improve availability check for HDF5 basin data
  - enh: cache list of features available via all basins
  - enh: speed up feature retrieval for non-ancillary features
- - ref: replace `np.string_` with `np.bytes_`
+ - ref: replace np.string_ with np.bytes_
 0.60.9
  - build: build with macos-latest and macos-13 images
 0.60.8
@@ -302,7 +245,7 @@
  - ref: HDF5Basin gets its own submodule
  - setup: oldest-supported-numpy is not required anymore, since numpy
    is backwards-compatible now
-0.52.3
+ 0.52.3
  - maintenance release
 0.52.2
  - maintenance release
@@ -427,7 +370,7 @@
 0.47.3
  - fix: np.histrogram2d does not expect broken normed argument
  - docs: fixed GH Actions badge
- - enh: implement `RTDC_HDF5.__len__`
+ - enh: implement RTDC_HDF5.__len__
 0.47.2
  - enh: add --version flag to CLI
 0.47.1

{dclab-0.62.11 → dclab-2.18.0}/MANIFEST.in

@@ -3,7 +3,7 @@ include CREDITS
 include LICENSE
 include README.rst
 include pyproject.toml
-recursive-include dclab *.txt *.md *.pxd *.R
+recursive-include dclab *.txt *.md *.pxd
 recursive-include docs *.py *.md *.txt *.rst *.bib *.gif *.jpg
 recursive-include examples *.py *.jpg *.npy *.npz
 recursive-include tests *.zip *.md *.py *.txt

{dclab-0.62.11 → dclab-2.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.1
 Name: dclab
-Version: 0.62.11
+Version: 2.18.0
 Summary: Library for real-time deformability cytometry (RT-DC)
 Author: Benedikt Hartmann, Eoghan O'Connell, Maik Herbig, Maximilian Schlögel, Nadia Sbaa, Paul Müller, Philipp Rosendahl, Raghava Alajangi
 Maintainer-email: Paul Müller <dev@craban.de>
@@ -23,7 +23,7 @@ Requires-Dist: importlib-resources>=6.0
 Requires-Dist: numpy<3,>=1.21
 Requires-Dist: scipy<2,>=1.10.0
 Provides-Extra: all
-Requires-Dist: dclab[dcor,export,http,s3,tdms]; extra == "all"
+Requires-Dist: dclab[dcor,export,http,lme4,s3,tdms]; extra == "all"
 Provides-Extra: dcor
 Requires-Dist: requests<3,>=2.31.0; extra == "dcor"
 Provides-Extra: export
@@ -31,6 +31,8 @@ Requires-Dist: fcswrite>=0.5.0; extra == "export"
 Requires-Dist: imageio[ffmpeg]; extra == "export"
 Provides-Extra: http
 Requires-Dist: requests<3,>=2.31.0; extra == "http"
+Provides-Extra: lme4
+Requires-Dist: rpy2>=2.9.4; extra == "lme4"
 Provides-Extra: s3
 Requires-Dist: boto3>=1.34.31; extra == "s3"
 Provides-Extra: tdms

{dclab-0.62.11 → dclab-2.18.0}/dclab/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.62.11'
-__version_tuple__ = version_tuple = (0, 62, 11)
+__version__ = version = '2.18.0'
+__version_tuple__ = version_tuple = (2, 18, 0)

{dclab-0.62.11 → dclab-2.18.0}/dclab/definitions/meta_const.py

@@ -161,17 +161,7 @@ CFG_METADATA = {
         ["subtract mean", fbool, "Subtract mean before processing"],
         # pipeline_kws
         ["filter name", str, "Fourier filter used"],
-        # qpretrieve defines the keyword argument `filter_size_interpretation`
-        # for determining the filter size in Fourier space. In DC, we
-        # need a well-defined value for the filter size. The most logical
-        # choice is to interpret the filter size as "frequency index", which
-        # is independent of the image shape and yields a good approximation
-        # of the actual resolution one can expect. The default value
-        # ("sideband distance") is a good choice for general QPI analysis,
-        # but there is no meaningful information one could extract from it
-        # by just looking at the number. Thus, the "filter size" that we
-        # see here corresponds to a filter size set in qpretrieve where
-        # `filter_size_interpretation="frequency index"`.
+        # Corresponds to `filter_size_interpretation="frequency index"`
         ["filter size", float, "Fourier filter size [1/pix]"],
         ["scale to filter", fboolorfloat, "Scale QPI data to filter size"],
         # x, y coordinates, don't set if you wish None to be the default

{dclab-0.62.11 → dclab-2.18.0}/dclab/http_utils.py

@@ -27,14 +27,6 @@ REGEXP_HTTP_URL = re.compile(
 )
 
 
-class ETagNotInResponseHeaderWarning(UserWarning):
-    """Used for cases where the requests.Response does not contain an ETag"""
-
-
-class ConnectionTimeoutWarning(UserWarning):
-    """Used when a connection fails or times out"""
-
-
 class HTTPFile(io.IOBase):
     def __init__(self, url, chunk_size=2**18, keep_chunks=200):
         """Chunk-cached access to a URL supporting range requests
@@ -86,8 +78,7 @@ class HTTPFile(io.IOBase):
             etag = resp.headers.get("etag", "").strip("'").strip('"')
             if len(etag) < 5:
                 etag = None
-                warnings.warn(f"Got empty ETag header for {self.url}",
-                              ETagNotInResponseHeaderWarning)
+                warnings.warn(f"Got empty ETag header for {self.url}")
             self._etag = etag
 
     @property
@@ -247,8 +238,7 @@ class ResoluteRequestsSession(requests.Session):
                     requests.exceptions.ConnectTimeout,
                     requests.urllib3.exceptions.ConnectionError,
                     requests.urllib3.exceptions.ReadTimeoutError) as e:
-                warnings.warn(f"Encountered {e} for {args} {kwargs}",
-                              ConnectionTimeoutWarning)
+                warnings.warn(f"Encountered {e} for {args} {kwargs}")
                 continue
             else:
                 break

dclab-2.18.0/dclab/lme4/__init__.py

@@ -0,0 +1,5 @@
+"""A wrapper around R with the lme4 package"""
+# flake8: noqa: F401
+from . import rlibs, rsetup, wrapr
+from .wrapr import Rlme4, bootstrapped_median_distributions
+from .rsetup import get_r_path, get_r_version, install_lme4, set_r_path

dclab-2.18.0/dclab/lme4/rlibs.py

@@ -0,0 +1,93 @@
+import importlib
+import os
+import warnings
+
+from ..external.packaging import parse as parse_version
+
+#: Minimum R version
+#: This is actually a dependency for rpy2, because the API changed then
+#: (ffi.error: symbol 'R_tryCatchError' not found in library).
+R_MIN_VERSION = "3.6.0"
+
+#: Minimum rpy2 version
+RPY2_MIN_VERSION = "2.9.4"
+
+R_SUBMODULES = [
+    "rpy2.robjects.packages",
+    "rpy2.situation",
+    "rpy2.robjects.vectors",
+]
+
+R_SUBMODULES_3 = [
+    "rpy2.rinterface_lib.callbacks",
+]
+
+
+class RPY2UnavailableError(BaseException):
+    pass
+
+
+class RPY2ImportError(RPY2UnavailableError):
+    pass
+
+
+class RPY2OutdatedError(RPY2UnavailableError):
+    pass
+
+
+class RUnavailableError(BaseException):
+    pass
+
+
+class ROutdatedError(RUnavailableError):
+    pass
+
+
+class MockRPackage:
+    def __init__(self, exception):
+        self.exception = exception
+
+    def __getattr__(self, item):
+        raise self.exception
+
+
+def import_r_submodules():
+    importlib.import_module("rpy2.situation")
+    r_home = rpy2.situation.get_r_home()
+    if r_home is not None:
+        if os.environ.get("R_HOME", None) is None:
+            # set R_HOME globally (https://github.com/rpy2/rpy2/issues/796)
+            os.environ["R_HOME"] = r_home
+        if rpy2_is_version_3:
+            mods = R_SUBMODULES + R_SUBMODULES_3
+        else:
+            mods = R_SUBMODULES
+        try:
+            for sm in mods:
+                importlib.import_module(sm)
+        except rpy2.rinterface_lib.openrlib.ffi.error as exc:
+            # This error happens when the installed R version is too old:
+            # "ffi.error: symbol 'R_tryCatchError' not found in library"
+            raise ROutdatedError(
+                f"Encountered '{exc.__class__.__name__}: {exc}'. "
+                f"Please make sure you have 'R>={R_MIN_VERSION}'!")
+
+
+try:
+    rpy2 = importlib.import_module("rpy2")
+    if parse_version(rpy2.__version__) < parse_version(RPY2_MIN_VERSION):
+        raise RPY2OutdatedError(f"Please install 'rpy2>={RPY2_MIN_VERSION}'!")
+except ImportError:
+    rpy2 = MockRPackage(
+        RPY2ImportError(f"Please install 'rpy2>={RPY2_MIN_VERSION}'!"))
+    rpy2_is_version_3 = False
+except BaseException as e:
+    rpy2 = MockRPackage(e)
+    rpy2_is_version_3 = False
+else:
+    rpy2_is_version_3 = parse_version(rpy2.__version__) >= parse_version("3.0")
+    try:
+        import_r_submodules()
+    except RUnavailableError as e:
+        warnings.warn("There is an issue with the linked R version: "
+                      + f"{e.__class__.__name__}: {e}")

dclab-2.18.0/dclab/lme4/rsetup.py

@@ -0,0 +1,207 @@
+import logging
+import os
+import subprocess as sp
+
+from .rlibs import (
+    RUnavailableError, rpy2, rpy2_is_version_3, import_r_submodules)
+
+# Disable rpy2 logger because of unnecessary prints to stdout
+logging.getLogger("rpy2.rinterface_lib.callbacks").disabled = True
+
+
+class RNotFoundError(BaseException):
+    pass
+
+
+class AutoRConsole(object):
+    """Helper class for catching R console output"""
+    lock = False
+    perform_lock = rpy2_is_version_3
+
+    def __init__(self):
+        """
+        By default, this console always returns "yes" when asked a
+        question. If you need something different, you can subclass
+        and override `consoleread` fucntion. The console stream is
+        recorded in `self.stream`.
+        """
+        self.stream = [["init", "Starting RConsole class\n"]]
+        if AutoRConsole.perform_lock:
+            if AutoRConsole.lock:
+                raise ValueError("Only one RConsole instance allowed!")
+            AutoRConsole.lock = True
+            self.original_funcs = {
+                "consoleread": rpy2.rinterface_lib.callbacks.consoleread,
+                "consolewrite_print":
+                    rpy2.rinterface_lib.callbacks.consolewrite_print,
+                "consolewrite_warnerror":
+                    rpy2.rinterface_lib.callbacks.consolewrite_warnerror,
+            }
+            rpy2.rinterface_lib.callbacks.consoleread = self.consoleread
+            rpy2.rinterface_lib.callbacks.consolewrite_print = \
+                self.consolewrite_print
+            rpy2.rinterface_lib.callbacks.showmessage = \
+                self.consolewrite_print
+
+            rpy2.rinterface_lib.callbacks.consolewrite_warnerror = \
+                self.consolewrite_warnerror
+        # Set locale (to get always English messages)
+        rpy2.robjects.r('Sys.setlocale("LC_MESSAGES", "C")')
+        rpy2.robjects.r('Sys.setlocale("LC_CTYPE", "C")')
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *args):
+        if AutoRConsole.perform_lock:
+            AutoRConsole.lock = False
+            rpy2.rinterface_lib.callbacks.consoleread = \
+                self.original_funcs["consoleread"]
+            rpy2.rinterface_lib.callbacks.consolewrite_print = \
+                self.original_funcs["consolewrite_print"]
+            rpy2.rinterface_lib.callbacks.consolewrite_warnerror = \
+                self.original_funcs["consolewrite_warnerror"]
+
+    def close(self):
+        """Remove the rpy2 monkeypatches"""
+        self.__exit__()
+
+    def consoleread(self, prompt):
+        """Read user input, returns "yes" by default"""
+        self.write_to_stream("consoleread", prompt + "YES")
+        return "yes"
+
+    def consolewrite_print(self, s):
+        self.write_to_stream("consolewrite_print", s)
+
+    def consolewrite_warnerror(self, s):
+        self.write_to_stream("consolewrite_warnerror", s)
+
+    def write_to_stream(self, topic, s):
+        prev_topic = self.stream[-1][0]
+        same_topic = prev_topic == topic
+        unfinished_line = self.stream[-1][1][-1] not in ["\n", "\r"]
+        if same_topic and unfinished_line:
+            # append to previous line
+            self.stream[-1][1] += s
+        else:
+            self.stream.append([topic, s])
+
+    def get_prints(self):
+        prints = []
+        for line in self.stream:
+            if line[0] == "consolewrite_print":
+                prints.append(line[1].strip())
+        return prints
+
+    def get_warnerrors(self):
+        warnerrors = []
+        for line in self.stream:
+            if line[0] == "consolewrite_warnerror":
+                warnerrors.append(line[1].strip())
+        return warnerrors
+
+
+def check_r():
+    """Make sure R is installed an R HOME is set"""
+    if not has_r():
+        raise RNotFoundError("Cannot find R, please set its path with the "
+                             + "`set_r_path` function.")
+
+
+def get_r_path():
+    """Get the path of the R executable/binary from rpy2"""
+    r_home = rpy2.situation.get_r_home()
+    return rpy2.situation.get_r_exec(r_home)
+
+
+def get_r_version():
+    check_r()
+    ver_string = rpy2.situation.r_version_from_subprocess().strip()
+    if ver_string:
+        # get the actual version string
+        if ver_string.startswith("R version "):
+            ver_string = ver_string.split(" ")[2]
+    return ver_string
+
+
+def has_lme4():
+    """Return True if the lme4 package is installed"""
+    check_r()
+    lme4_there = rpy2.robjects.packages.isinstalled("lme4")
+    statmod_there = rpy2.robjects.packages.isinstalled("statmod")
+    nloptr_there = rpy2.robjects.packages.isinstalled("nloptr")
+    return lme4_there and statmod_there and nloptr_there
+
+
+def has_r():
+    """Return True if R is available"""
+    try:
+        hasr = rpy2.situation.get_r_home() is not None
+    except RUnavailableError:
+        hasr = False
+    return hasr
+
+
+def import_lme4():
+    check_r()
+    if has_lme4():
+        lme4pkg = rpy2.robjects.packages.importr("lme4")
+    else:
+        raise ValueError(
+            "The R package 'lme4' is not installed, please install it via "
+            + "`dclab.lme4.rsetup.install_lme4()` or by executing "
+            + "in a shell: R -e " + '"install.packages(' + "'lme4', "
+            + "repos='http://cran.rstudio.org')" + '"')
+    return lme4pkg
+
+
+def install_lme4():
+    """Install the lme4 package (if not already installed)
+
+    The packages are installed to the user data directory
+    given in :const:`lib_path`.
+    """
+    check_r()
+    if not has_lme4():
+        # import R's utility package
+        utils = rpy2.robjects.packages.importr('utils')
+        # select the first mirror in the list
+        utils.chooseCRANmirror(ind=1)
+        # install lme4 to user data directory (say yes to user dir install)
+        with AutoRConsole() as rc:
+            # install statmod and nloptr first
+            # (Doesn't R have package dependencies?!)
+            utils.install_packages(
+                rpy2.robjects.vectors.StrVector(["statmod", "nloptr", "lme4"]))
+        return rc
+
+
+def set_r_path(r_path):
+    """Set the path of the R executable/binary for rpy2"""
+    if hasattr(sp, 'STARTUPINFO'):
+        # On Windows, subprocess calls will pop up a command window by
+        # default when run from Pyinstaller with the ``--noconsole``
+        # option. Avoid this distraction.
+        si = sp.STARTUPINFO()
+        si.dwFlags |= sp.STARTF_USESHOWWINDOW
+        # Windows doesn't search the path by default. Pass it an
+        # environment so it will.
+        env = os.environ
+    else:
+        si = None
+        env = None
+
+    tmp = sp.check_output((r_path, 'RHOME'),
+                          startupinfo=si,
+                          env=env,
+                          text=True,
+                          )
+
+    r_home = tmp.split(os.linesep)
+    if r_home[0].startswith('WARNING'):
+        res = r_home[1]
+    else:
+        res = r_home[0].strip()
+    os.environ["R_HOME"] = res
+    import_r_submodules()