dclab 0.67.0__cp314-cp314-macosx_10_13_x86_64.whl

dclab/definitions/meta_logic.py

@@ -0,0 +1,111 @@
+import numbers
+
+from . import feat_logic, meta_const, meta_parse
+
+
+def config_key_exists(section, key):
+    """Return `True` if the configuration key exists"""
+    valid = False
+    if section == "user":
+        if isinstance(key, str) and key.strip():  # sanity check
+            valid = True
+    elif meta_const.config_funcs.get(section, {}).get(key, False):
+        valid = True
+    elif section == "online_filter":
+        if (key.count(",")
+                and (key.endswith("soft limit")
+                     or key.endswith("polygon points"))):
+            # "online_filter:area_um,deform soft limit"
+            # "online_filter:area_um,deform polygon points"
+            f1, f2 = key.split(" ", 1)[0].split(",")
+            valid = (feat_logic.scalar_feature_exists(f1)
+                     and feat_logic.scalar_feature_exists(f2))
+        else:
+            feat = key.split(" ", 1)[0]
+            valid = feat_logic.scalar_feature_exists(feat)
+    return valid
+
+
+def get_config_value_descr(section, key):
+    """Return the description of a config value
+
+    Returns `key` if not defined anywhere
+    """
+    descr = key
+    if section == "user":
+        pass
+    elif meta_const.config_descr.get(section, {}).get(key, False):
+        descr = meta_const.config_descr[section][key]
+    elif section == "online_filter":
+        if (key.count(",")
+                and (key.endswith("soft limit")
+                     or key.endswith("polygon points"))):
+            # "online_filter:area_um,deform soft limit"
+            # "online_filter:area_um,deform polygon points"
+            f1, f2 = key.split(" ", 1)[0].split(",")
+            # do not include units
+            l1 = feat_logic.get_feature_label(f1, with_unit=False)
+            l2 = feat_logic.get_feature_label(f2, with_unit=False)
+            if key.endswith("soft limit"):
+                descr = f"Soft limit, polygon ({l1}, {l2})"
+            elif key.endswith("polygon points"):
+                descr = f"Polygon ({l1}, {l2})"
+        else:
+            feat = key.split(" ", 1)[0]
+            if feat_logic.scalar_feature_exists(feat):
+                if key.endswith("soft limit"):
+                    # "online_filter:area_um soft limit"
+                    label = feat_logic.get_feature_label(feat, with_unit=False)
+                    descr = f"Soft limit, {label}"
+                elif key.endswith("min"):
+                    # "online_filter:area_um min"
+                    descr = f"Min. {feat_logic.get_feature_label(feat)}"
+                elif key.endswith("max"):
+                    # "online_filter:area_um max"
+                    descr = f"Max. {feat_logic.get_feature_label(feat)}"
+
+    return descr
+
+
+def get_config_value_func(section, key):
+    """Return configuration type converter function"""
+    func = None
+    if section == "user":
+        pass
+    elif meta_const.config_funcs.get(section, {}).get(key, False):
+        func = meta_const.config_funcs[section][key]
+    elif section == "online_filter":
+        # Note that for "min" and "max" values we do nothing (None)
+        if key.endswith("soft limit"):
+            # "online_filter:area_um,deform soft limit"
+            func = meta_parse.fbool
+        elif key.endswith("polygon points"):
+            # "online_filter:area_um,deform polygon points"
+            func = meta_parse.f2dfloatarray
+
+    if func is None:
+        return lambda x: x
+    else:
+        return func
+
+
+def get_config_value_type(section, key):
+    """Return the expected type of a config value
+
+    Returns `None` if no type is defined
+    """
+    typ = None
+    if section == "user":
+        pass
+    elif meta_const.config_types.get(section, {}).get(key, False):
+        typ = meta_const.config_types[section][key]
+    elif section == "online_filter":
+        if key.endswith("soft limit"):
+            # "online_filter:area_um,deform soft limit"
+            typ = meta_parse.func_types[meta_parse.fbool]
+        elif key.endswith("polygon points"):
+            typ = meta_parse.func_types[meta_parse.f2dfloatarray]
+        elif key.endswith("min") or key.endswith("max"):
+            # most-general type is a number
+            typ = numbers.Number
+    return typ

dclab/definitions/meta_parse.py

@@ -0,0 +1,94 @@
+import numbers
+
+import numpy as np
+
+
+def f1dfloatduple(value):
+    """Tuple of two floats (duple)"""
+    if np.array(value).ndim != 1:
+        raise ValueError(f"Value is not 1 dimensional, got {value}!")
+    value = tuple(float(i) for i in value)
+    if len(value) != 2:
+        raise ValueError(f"Value must be of length two, "
+                         f"got length {len(value)}!")
+    return value
+
+
+def f2dfloatarray(value):
+    """numpy floating point array"""
+    return np.array(value, dtype=np.float64)
+
+
+def fbool(value):
+    """boolean"""
+    if isinstance(value, str):
+        value = value.lower()
+        if value == "false":
+            value = False
+        elif value == "true":
+            value = True
+        elif value:
+            value = bool(float(value))
+        else:
+            raise ValueError("Empty string provided for fbool!")
+    else:
+        value = bool(float(value))
+    return value
+
+
+def fboolorfloat(value):
+    """Bool or float"""
+    if isinstance(value, (str, bool)) or value == 0:
+        return fbool(value)
+    elif isinstance(value, (int, float)):
+        return float(value)
+    else:
+        raise ValueError(f"Value could not be converted to bool "
+                         f"or float, got {value}!")
+
+
+def fint(value):
+    """integer"""
+    if isinstance(value, str):
+        # strings might have been saved wrongly as booleans
+        value = value.lower()
+        if value == "false":
+            value = 0
+        elif value == "true":
+            value = 1
+        elif value:
+            value = int(float(value))
+        else:
+            raise ValueError("Empty string provided for fint!")
+    else:
+        value = int(float(value))
+    return value
+
+
+def fintlist(alist):
+    """A list of integers"""
+    outlist = []
+    if not isinstance(alist, (list, tuple)):
+        # we have a string (comma-separated integers)
+        alist = alist.strip().strip("[] ").split(",")
+    for it in alist:
+        if it:
+            outlist.append(fint(it))
+    return outlist
+
+
+def lcstr(astr):
+    """lower-case string"""
+    return astr.lower()
+
+
+#: maps functions to their expected output types
+func_types = {
+    f1dfloatduple: (tuple, np.ndarray),
+    f2dfloatarray: np.ndarray,
+    fbool: (bool, np.bool_),
+    fboolorfloat: (bool, np.bool_, float),
+    fint: numbers.Integral,
+    fintlist: list,
+    float: numbers.Number,
+    lcstr: str}

dclab/downsampling.pyx

@@ -0,0 +1,230 @@
+"""Content-based downsampling of ndarrays"""
+import numpy as np
+cimport numpy as cnp
+
+from .cached import Cache
+
+# We are using the numpy array API
+cnp.import_array()
+ctypedef cnp.uint8_t uint8
+ctypedef cnp.uint32_t uint32
+ctypedef cnp.int64_t int64
+
+def downsample_rand(a, samples, remove_invalid=False, ret_idx=False):
+    """Downsampling by randomly removing points
+
+    Parameters
+    ----------
+    a: 1d ndarray
+        The input array to downsample
+    samples: int
+        The desired number of samples
+    remove_invalid: bool
+        Remove nan and inf values before downsampling
+    ret_idx: bool
+        Also return a boolean array that corresponds to the
+        downsampled indices in `a`.
+
+    Returns
+    -------
+    dsa: 1d ndarray of size `samples`
+        The pseudo-randomly downsampled array `a`
+    idx: 1d boolean array with same shape as `a`
+        Only returned if `ret_idx` is True.
+        A boolean array such that `a[idx] == dsa`
+    """
+    # fixed random state for this method
+    rs = np.random.RandomState(seed=47).get_state()
+    np.random.set_state(rs)
+
+    cdef uint32 samples_int = np.uint32(samples)
+
+    if remove_invalid:
+        # slice out nans and infs
+        bad = np.isnan(a) | np.isinf(a)
+        pool = a[~bad]
+    else:
+        pool = a
+
+    if samples_int and (samples_int < pool.shape[0]):
+        keep = np.zeros_like(pool, dtype=bool)
+        keep_ids = np.random.choice(np.arange(pool.size),
+                                    size=samples_int,
+                                    replace=False)
+        keep[keep_ids] = True
+        dsa = pool[keep]
+    else:
+        keep = np.ones_like(pool, dtype=bool)
+        dsa = pool
+
+    if remove_invalid:
+        # translate the kept values back to the original array
+        idx = np.zeros(a.size, dtype=bool)
+        idx[~bad] = keep
+    else:
+        idx = keep
+
+    if ret_idx:
+        return dsa, idx
+    else:
+        return dsa
+
+
+@Cache
+def downsample_grid(a, b, samples, remove_invalid=False, ret_idx=False):
+    """Content-based downsampling for faster visualization
+
+    The arrays `a` and `b` make up a 2D scatter plot with high
+    and low density values. This method takes out points at
+    indices with high density.
+
+    Parameters
+    ----------
+    a, b: 1d ndarrays
+        The input arrays to downsample
+    samples: int
+        The desired number of samples
+    remove_invalid: bool
+        Remove nan and inf values before downsampling; if set to
+        `True`, the actual number of samples returned might be
+        smaller than `samples` due to infinite or nan values.
+    ret_idx: bool
+        Also return a boolean array that corresponds to the
+        downsampled indices in `a` and `b`.
+
+    Returns
+    -------
+    dsa, dsb: 1d ndarrays of shape (samples,)
+        The arrays `a` and `b` downsampled by evenly selecting
+        points and pseudo-randomly adding or removing points
+        to match `samples`.
+    idx: 1d boolean array with same shape as `a`
+        Only returned if `ret_idx` is True.
+        A boolean array such that `a[idx] == dsa`
+    """
+    cdef uint32 samples_int = np.uint32(samples)
+
+    # fixed random state for this method
+    rs = np.random.RandomState(seed=47).get_state()
+
+    keep = np.ones_like(a, dtype=bool)
+    bad = np.isnan(a) | np.isinf(a) | np.isnan(b) | np.isinf(b)
+    good = ~bad
+
+    # We are generally not interested in bad data.
+    keep[bad] = False
+    bd = b[good]
+    ad = a[good]
+
+    cdef int64 diff
+
+    if samples_int and samples_int < ad.size:
+        # 1. Produce evenly distributed samples
+        # Choosing grid-size:
+        # - large numbers tend to show actual structures of the sample,
+        #   which is not desired for plotting
+        # - small numbers tend will not result in too few samples and,
+        #   in order to reach the desired samples, the data must be
+        #   upsampled again.
+        # 300 is about the size of the plot in marker sizes and yields
+        # good results.
+        grid_size = 300
+        # The events on the grid to process
+        toproc = np.ones((grid_size, grid_size), dtype=np.uint8)
+
+        x_discrete = np.array(norm(ad) * (grid_size - 1), dtype=np.uint32)
+        y_discrete = np.array(norm(bd) * (grid_size - 1), dtype=np.uint32)
+
+        # The events to keep
+        keepd = np.zeros_like(ad, dtype=np.uint8)
+        populate_grid(x_discrete=x_discrete,
+                      y_discrete=y_discrete,
+                      toproc=toproc,
+                      keepd=keepd
+                      )
+
+        keepdb = np.array(keepd, dtype=bool)
+
+        # 2. Make sure that we reach `samples` by adding or
+        # removing events.
+        diff = np.sum(keepdb) - samples_int
+        if diff > 0:
+            # Too many samples
+            rem_indices = np.where(keepdb)[0]
+            np.random.set_state(rs)
+            rem = np.random.choice(rem_indices,
+                                   size=diff,
+                                   replace=False)
+            keepdb[rem] = False
+        elif diff < 0:
+            # Not enough samples
+            add_indices = np.where(~keepdb)[0]
+            np.random.set_state(rs)
+            add = np.random.choice(add_indices,
+                                   size=abs(diff),
+                                   replace=False)
+            keepdb[add] = True
+
+        # paulmueller 2024-01-03
+        # assert np.sum(keepdb) <= samples_int, "sanity check"
+
+        keep[good] = keepdb
+
+        # paulmueller 2024-01-03
+        # assert np.sum(keep) <= samples_int, "sanity check"
+
+    if not remove_invalid:
+        diff_bad = (samples_int or keep.size) - np.sum(keep)
+        if diff_bad > 0:
+            # Add a few of the invalid values so that in the end
+            # we have the desired array size.
+            add_indices_bad = np.where(bad)[0]
+            np.random.set_state(rs)
+            add_bad = np.random.choice(add_indices_bad,
+                                       size=diff_bad,
+                                       replace=False)
+            keep[add_bad] = True
+
+    # paulmueller 2024-01-03
+    # if samples_int and not remove_invalid:
+    #     assert np.sum(keep) == samples_int, "sanity check"
+
+    asd = a[keep]
+    bsd = b[keep]
+
+    if ret_idx:
+        return asd, bsd, keep
+    else:
+        return asd, bsd
+
+
+def populate_grid(x_discrete, y_discrete, keepd, toproc):
+    # Py_ssize_t is the proper C type for Python array indices.
+    cdef int iter_size = x_discrete.size
+    cdef Py_ssize_t ii
+    cdef uint32[:] x_view = x_discrete
+    cdef uint32[:] y_view = y_discrete
+    # Numpy uses uint8 internally to represent boolean arrays
+    cdef uint8[:] keepd_view = keepd
+    cdef uint8[:, :] toproc_view = toproc
+
+    for ii in range(iter_size):
+        # filter for overlapping events
+        xi = x_view[ii]
+        yi = y_view[ii]
+        if toproc_view[xi, yi]:
+            toproc_view[xi, yi] = 0
+            # include event
+            keepd_view[ii] = 1
+
+
+def valid(a, b):
+    """Check whether `a` and `b` are not inf or nan"""
+    return ~(np.isnan(a) | np.isinf(a) | np.isnan(b) | np.isinf(b))
+
+
+def norm(a):
+    """Normalize `a` with its min/max values"""
+    rmin = a.min()
+    rptp = a.max() - rmin
+    return (a - rmin) / rptp

dclab/external/__init__.py

@@ -0,0 +1,4 @@
+# flake8: noqa: F401
+from . import packaging
+from . import statsmodels
+from . import skimage

dclab/external/packaging/LICENSE

@@ -0,0 +1,3 @@
+This software is made available under the terms of *either* of the licenses
+found in LICENSE.APACHE or LICENSE.BSD. Contributions to this software is made
+under the terms of *both* these licenses.

dclab/external/packaging/LICENSE.APACHE

@@ -0,0 +1,177 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

dclab/external/packaging/LICENSE.BSD

@@ -0,0 +1,23 @@
+Copyright (c) Donald Stufft and individual contributors.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    1. Redistributions of source code must retain the above copyright notice,
+       this list of conditions and the following disclaimer.
+
+    2. Redistributions in binary form must reproduce the above copyright
+       notice, this list of conditions and the following disclaimer in the
+       documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

dclab/external/packaging/__init__.py

@@ -0,0 +1,6 @@
+# flake8: noqa: F401
+"""packaging.version
+
+Since distutils is deprecated, we keep our own copy of version parsing.
+"""
+from .version import parse