heavyedge-dataset 0.1.0__py3-none-any.whl

heavyedge_dataset/__init__.py

@@ -0,0 +1,15 @@
+"""PyTorch-compatiable dataset API for edge profiles."""
+
+__all__ = [
+    "ProfileDataset",
+    "PseudoLmDataset",
+    "MathLm1dDataset",
+    "MathLm2dDataset",
+]
+
+from .datasets import (
+    MathLm1dDataset,
+    MathLm2dDataset,
+    ProfileDataset,
+    PseudoLmDataset,
+)

heavyedge_dataset/datasets.py

@@ -0,0 +1,293 @@
+"""
+Dataset classes
+---------------
+
+PyTorch dataset classes for edge profiles.
+"""
+
+import abc
+import numbers
+from collections.abc import Sequence
+
+import numpy as np
+from heavyedge.api import landmarks_type3
+from torch.utils.data import Dataset
+
+from .landmarks import math_landmarks_1d, pseudo_landmarks_1d, pseudo_landmarks_2d
+
+__all__ = [
+    "ProfileDataset",
+    "PseudoLmDataset",
+    "MathLm1dDataset",
+    "MathLm2dDataset",
+]
+
+
+class ProfileDatasetBase(abc.ABC):
+    """Abstract base class for profile dataset."""
+
+    @property
+    @abc.abstractmethod
+    def file(self):
+        """Profile data file.
+
+        Returns
+        -------
+        heavyedge.ProfileData
+        """
+
+    @abc.abstractmethod
+    def default_transform(self, profiles, lengths):
+        """Default transform by the dataset class.
+
+        Parameters
+        ----------
+        profiles : (N, M) array
+            Profile data.
+        lengths : (N,) array
+            Length of each profile.
+        """
+        pass
+
+    @property
+    @abc.abstractmethod
+    def transform(self):
+        """Optional transformation passed to the dataset instance.
+
+        Returns
+        -------
+        Callable
+        """
+
+    def __len__(self):
+        return len(self.file)
+
+    def __getitem__(self, idx):
+        if isinstance(idx, numbers.Integral):
+            Y, L, _ = self.file[idx]
+            ret = self.default_transform([Y], [L])
+            if self.transform:
+                ret = self.transform(ret)
+            ret = ret[0]
+        else:
+            ret = self.__getitems__(idx)
+        return ret
+
+    def __getitems__(self, idxs):
+        # PyTorch API
+        needs_sort = isinstance(idxs, (Sequence, np.ndarray))
+        if needs_sort:
+            # idxs must be sorted for h5py
+            idxs = np.array(idxs)
+            sort_idx = np.argsort(idxs)
+            idxs = idxs[sort_idx]
+        else:
+            pass
+        Ys, Ls, _ = self.file[idxs]
+        if needs_sort:
+            reverse_idx = np.argsort(sort_idx)
+            Ys = Ys[reverse_idx]
+            Ls = Ls[reverse_idx]
+        ret = self.default_transform(Ys, Ls)
+        if self.transform:
+            ret = self.transform(ret)
+        return ret
+
+
+class ProfileDataset(ProfileDatasetBase, Dataset):
+    """Full profile dataset.
+
+    Parameters
+    ----------
+    file : heavyedge.ProfileData
+        Open hdf5 file.
+    m : {1, 2}
+        Profile data dimension.
+        1 means only y coordinates, and 2 means both x and y coordinates.
+    transform : callable, optional
+        Optional transform to be applied on a sample.
+
+    Examples
+    --------
+    >>> from heavyedge import get_sample_path, ProfileData
+    >>> from heavyedge_dataset import ProfileDataset
+    >>> with ProfileData(get_sample_path("Prep-Type2.h5")) as file:
+    ...     data = ProfileDataset(file, 2)[:]
+    >>> import matplotlib.pyplot as plt  # doctest: +SKIP
+    ... for coords in data:
+    ...     plt.plot(*coords, color="gray")
+    """
+
+    def __init__(self, file, m, transform=None):
+        self._file = file
+        self.m = m
+        self._transform = transform
+
+        self.x = file.x()
+
+    @property
+    def file(self):
+        return self._file
+
+    def default_transform(self, profiles, lengths):
+        if self.m == 1:
+            ret = [Y[:L].reshape(1, -1) for Y, L in zip(profiles, lengths)]
+        elif self.m == 2:
+            ret = [np.stack([self.x[:L], Y[:L]]) for Y, L in zip(profiles, lengths)]
+        else:
+            raise ValueError(f"Invalid dimension: {self.m}")
+        return ret
+
+    @property
+    def transform(self):
+        return self._transform
+
+
+class PseudoLmDataset(ProfileDatasetBase, Dataset):
+    """Pseudo-landmark dataset.
+
+    Parameters
+    ----------
+    file : heavyedge.ProfileData
+        Open hdf5 file.
+    k : int
+        Number of landmarks to sample.
+    m : {1, 2}
+        Profile data dimension.
+        1 means only y coordinates, and 2 means both x and y coordinates.
+    transform : callable, optional
+        Optional transform to be applied on a sample.
+
+    Examples
+    --------
+    >>> from heavyedge import get_sample_path, ProfileData
+    >>> from heavyedge_dataset import PseudoLmDataset
+    >>> with ProfileData(get_sample_path("Prep-Type2.h5")) as file:
+    ...     data = PseudoLmDataset(file, 10, 2)[:]
+    >>> import matplotlib.pyplot as plt  # doctest: +SKIP
+    ... plt.plot(*data.transpose(1, 2, 0), color="gray")
+    """
+
+    def __init__(self, file, k, m, transform=None):
+        self._file = file
+        self.k = k
+        self.m = m
+        self._transform = transform
+
+        self.x = file.x()
+
+    @property
+    def file(self):
+        return self._file
+
+    def default_transform(self, profiles, lengths):
+        if self.m == 1:
+            ret = pseudo_landmarks_1d(profiles, lengths, self.k)
+        elif self.m == 2:
+            ret = pseudo_landmarks_2d(self.x, profiles, lengths, self.k)
+        else:
+            raise ValueError(f"Invalid dimension: {self.m}")
+        return ret
+
+    @property
+    def transform(self):
+        return self._transform
+
+
+class MathLm1dDataset(ProfileDatasetBase, Dataset):
+    """1-D mathematical landmarks dataset.
+
+    Parameters
+    ----------
+    file : heavyedge.ProfileData
+        Open hdf5 file.
+    sigma : scalar
+        Standard deviation of Gaussian kernel for landmark detection.
+    transform : callable, optional
+        Optional transform to be applied on a sample.
+
+    Examples
+    --------
+    >>> from heavyedge import get_sample_path, ProfileData
+    >>> from heavyedge_dataset import MathLm1dDataset
+    >>> with ProfileData(get_sample_path("Prep-Type2.h5")) as file:
+    ...     data = MathLm1dDataset(file, 32)[:]
+    >>> import matplotlib.pyplot as plt  # doctest: +SKIP
+    ... plt.plot(*data.transpose(1, 2, 0), color="gray")
+    """
+
+    def __init__(self, file, sigma, transform=None):
+        self._file = file
+        self.sigma = sigma
+        self._transform = transform
+
+    @property
+    def file(self):
+        return self._file
+
+    def default_transform(self, profiles, lengths):
+        return math_landmarks_1d(profiles, lengths, self.sigma)
+
+    @property
+    def transform(self):
+        return self._transform
+
+
+class MathLm2dDataset(ProfileDatasetBase, Dataset):
+    """2-D mathematical landmarks dataset.
+
+    Parameters
+    ----------
+    file : heavyedge.ProfileData
+        Open hdf5 file.
+    sigma : scalar
+        Standard deviation of Gaussian kernel for landmark detection.
+    transform : callable, optional
+        Optional transform to be applied on a sample.
+
+    Examples
+    --------
+    >>> from heavyedge import get_sample_path, ProfileData
+    >>> from heavyedge_dataset import MathLm2dDataset
+    >>> with ProfileData(get_sample_path("Prep-Type2.h5")) as file:
+    ...     lm, _ = MathLm2dDataset(file, 32)[:]
+    >>> import matplotlib.pyplot as plt  # doctest: +SKIP
+    ... plt.plot(*lm.transpose(1, 2, 0), color="gray")
+    """
+
+    def __init__(self, file, sigma, transform=None):
+        self._file = file
+        self.sigma = sigma
+        self._transform = transform
+
+        self.x = file.x()
+
+    @property
+    def file(self):
+        return self._file
+
+    def default_transform(self, profiles, lengths):
+        # Todo: cythonize this method to avoid python loop.
+        # This will require cythonizing landmarks_type3().
+        lm, center_height = [], []
+        for Y, L in zip(profiles, lengths):
+            Y = Y[:L]
+            indices = np.flip(landmarks_type3(Y, self.sigma))
+            lm.append(np.stack([self.x[indices], Y[indices]]))
+            center_height.append(np.mean(Y[: indices[0]]))
+        return np.array(lm), np.array(center_height)
+
+    def __getitem__(self, idx):
+        if isinstance(idx, numbers.Integral):
+            Y, L, _ = self.file[idx]
+            lm, ch = self.default_transform([Y], [L])
+            if self.transform:
+                lm, ch = self.transform(lm, ch)
+            lm, ch = lm[0], ch[0]
+        else:
+            lm, ch = self.__getitems__(idx)
+        return (lm, ch)
+
+    @property
+    def transform(self):
+        return self._transform

heavyedge_dataset/landmarks.py

@@ -0,0 +1,41 @@
+"""
+Landmark locators
+-----------------
+
+Functions to locate landmarks from edge profiles.
+"""
+
+import numpy as np
+from heavyedge.api import landmarks_type3
+
+__all__ = [
+    "pseudo_landmarks_1d",
+    "pseudo_landmarks_2d",
+    "math_landmarks_1d",
+]
+
+
+def pseudo_landmarks_1d(Ys, Ls, k):
+    ret = []
+    for Y, L in zip(Ys, Ls):
+        idxs = np.linspace(0, L - 1, k, dtype=int)
+        ret.append(Y[idxs].reshape(1, -1))
+    return np.array(ret)
+
+
+def pseudo_landmarks_2d(x, Ys, Ls, k):
+    ret = []
+    for Y, L in zip(Ys, Ls):
+        idxs = np.linspace(0, L - 1, k, dtype=int)
+        ret.append(np.stack([x[idxs], Y[idxs]]))
+    return np.array(ret)
+
+
+def math_landmarks_1d(Ys, Ls, sigma):
+    ret = []
+    for Y, L in zip(Ys, Ls):
+        Y = Y[:L]
+        indices = np.flip(landmarks_type3(Y, sigma))
+        y = np.concat([[np.mean(Y[: indices[0]])], Y[indices]])
+        ret.append(y.reshape(1, -1))
+    return np.array(ret)

heavyedge_dataset-0.1.0.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: heavyedge-dataset
+Version: 0.1.0
+Summary: PyTorch-compatible edge profile dataset API
+Author-email: Jisoo Song <jeesoo9595@snu.ac.kr>
+License-Expression: MIT
+Project-URL: homepage, https://pypi.python.org/pypi/heavyedge-dataset/
+Project-URL: source, https://github.com/heavyedge/heavyedge-dataset
+Project-URL: documentation, https://heavyedge-dataset.readthedocs.io
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: heavyedge>=1.1.2
+Requires-Dist: torch
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Provides-Extra: doc
+Requires-Dist: sphinx; extra == "doc"
+Requires-Dist: numpydoc; extra == "doc"
+Requires-Dist: pydata_sphinx_theme; extra == "doc"
+Requires-Dist: matplotlib; extra == "doc"
+Provides-Extra: dev
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Requires-Dist: heavyedge-dataset[doc,test]; extra == "dev"
+Dynamic: license-file
+
+# HeavyEdge-Dataset

heavyedge_dataset-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+heavyedge_dataset/__init__.py,sha256=X9li4ScLZs9TSlbH4ApoctQa6g7vglH0nkQadcb7Gq4,273
+heavyedge_dataset/datasets.py,sha256=j8a3KRXzWd0QpceAvP7ATvNUj5VSjyx445ksMMMdJio,8150
+heavyedge_dataset/landmarks.py,sha256=Tn7Pd91cWLs9txYu9mkNxC6OX-Y6VTNMzwTNzzCE4Bo,937
+heavyedge_dataset-0.1.0.dist-info/licenses/LICENSE,sha256=pBq2E7YJkUcEINdYeERL4RVFOQICd_MwJq6OusuAPGc,1066
+heavyedge_dataset-0.1.0.dist-info/METADATA,sha256=QsFgB89UjLFlONWWcgWvCaxhlSCgK535OxBXeB_oMrg,1515
+heavyedge_dataset-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+heavyedge_dataset-0.1.0.dist-info/top_level.txt,sha256=wpRFI8TlkYFGetc17appkyybauBvzhGGvyueunsdJTc,18
+heavyedge_dataset-0.1.0.dist-info/RECORD,,

heavyedge_dataset-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

heavyedge_dataset-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 heavyedge
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

heavyedge_dataset-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+heavyedge_dataset