diff --git a/.travis.yml b/.travis.yml index 4af264e0bc..94539674f1 100644 --- a/.travis.yml +++ b/.travis.yml @@ -18,7 +18,7 @@ install: - > conda create -q -c synthicity -n test-environment python=$TRAVIS_PYTHON_VERSION - numpy pandas pip pytest urbansim + numpy pandas pip pytables pytest urbansim - source activate test-environment - pip install pytest-cov coveralls pep8 - pip install . diff --git a/activitysim/omx/LICENSE.TXT b/activitysim/omx/LICENSE.TXT new file mode 100644 index 0000000000..d645695673 --- /dev/null +++ b/activitysim/omx/LICENSE.TXT @@ -0,0 +1,202 @@ + + 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 + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/activitysim/omx/__init__.py b/activitysim/omx/__init__.py new file mode 100644 index 0000000000..ab6663217f --- /dev/null +++ b/activitysim/omx/__init__.py @@ -0,0 +1,7 @@ +# Licensed under the Apache License, v2.0 +# See activitysim/omx/LICENSE.txt +# Modified from the original OMX library available at +# https://github.com/osPlanning/omx/tree/dev/api/python/omx + +from .omxfile import OMXFile, open_omxfile, OMX_VERSION +from .exceptions import ShapeError diff --git a/activitysim/omx/exceptions.py b/activitysim/omx/exceptions.py new file mode 100644 index 0000000000..f7220e21bb --- /dev/null +++ b/activitysim/omx/exceptions.py @@ -0,0 +1,8 @@ +# Licensed under the Apache License, v2.0 +# See activitysim/omx/LICENSE.txt +# Modified from the original OMX library available at +# https://github.com/osPlanning/omx/tree/dev/api/python/omx + + +class ShapeError(Exception): + pass diff --git a/activitysim/omx/omxfile.py b/activitysim/omx/omxfile.py new file mode 100644 index 0000000000..182d0d5362 --- /dev/null +++ b/activitysim/omx/omxfile.py @@ -0,0 +1,246 @@ +# Licensed under the Apache License, v2.0 +# See activitysim/omx/LICENSE.txt +# Modified from the original OMX library available at +# https://github.com/osPlanning/omx/tree/dev/api/python/omx + +import numpy as np +import tables + +from .exceptions import ShapeError + +OMX_VERSION = '0.2' + + +class OMXFile(tables.File): + def __init__(self, *args, **kwargs): + super(OMXFile, self).__init__(*args, **kwargs) + self._shape = None + + def version(self): + if 'OMX_VERSION' in self.root._v_attrs: + return self.root._v_attrs['OMX_VERSION'] + else: + return None + + def create_matrix( + self, name, atom=None, shape=None, title='', filters=None, + chunkshape=None, byteorder=None, createparents=False, obj=None, + attrs=None): + """Create OMX Matrix (CArray) at root level. User must pass in either + an existing numpy matrix, or a shape and an atom type.""" + + # If object was passed in, make sure its shape is correct + if (self.shape() is not None and + obj is not None and + obj.shape != self.shape()): + raise ShapeError( + '%s has shape %s but this file requires shape %s' % + (name, obj.shape, self.shape())) + + # Create the HDF5 array + if tables.__version__.startswith('3'): + matrix = self.create_carray( + self.root.data, name, atom, shape, title, filters, + chunkshape, byteorder, createparents, obj) + + # Store shape if we don't have one yet + if self._shape is None: + storeshape = np.array(matrix.shape, dtype='int32') + self.root._v_attrs['SHAPE'] = storeshape + self._shape = matrix.shape + + # attributes + if attrs: + for key in attrs: + matrix.attrs[key] = attrs[key] + + return matrix + + def shape(self): + """Return the one and only shape of all matrices in this File""" + + # If we already have the shape, just return it + if self._shape: + return self._shape + + # If shape is already set in root node attributes, grab it + if 'SHAPE' in self.root._v_attrs: + # Shape is stored as a numpy.array: + arrayshape = self.root._v_attrs['SHAPE'] + # which must be converted to a tuple: + realshape = tuple(arrayshape) + self._shape = realshape + return self._shape + + # Inspect the first CArray object to determine its shape + if len(self) > 0: + self._shape = self.iter_nodes( + self.root.data, 'CArray').next().shape + + # Store it if we can + if self._iswritable(): + storeshape = np.array(self._shape, dtype='int32') + self.root._v_attrs['SHAPE'] = storeshape + + return self._shape + + else: + return None + + def list_matrices(self): + """Return list of Matrix names in this File""" + return [ + node.name for node in self.list_nodes(self.root.data, 'CArray')] + + def list_all_attributes(self): + """ + Return combined list of all attributes used for + any Matrix in this File + + """ + all_tags = set() + for m in self.iter_nodes(self.root.data, 'CArray'): + all_tags.update(m.attrs._v_attrnamesuser) + return sorted(all_tags) + + # MAPPINGS ----------------------------------------------- + def list_mappings(self): + try: + return [m.name for m in self.list_nodes(self.root.lookup)] + except: + return [] + + def delete_mapping(self, title): + try: + self.remove_node(self.root.lookup, title) + except: + raise LookupError('No such mapping: ' + title) + + def mapping(self, title): + """Return dict containing key:value pairs for specified mapping. Keys + represent the map item and value represents the array offset.""" + try: + # fetch entries + entries = [] + entries.extend(self.get_node(self.root.lookup, title)[:]) + + # build reverse key-lookup + keymap = {} + for i in range(len(entries)): + keymap[entries[i]] = i + + return keymap + + except: + raise LookupError('No such mapping: ' + title) + + def create_mapping(self, title, entries, overwrite=False): + """Create an equivalency index, which maps a raw data dimension to + another integer value. Once created, mappings can be referenced by + offset or by key.""" + + # Enforce shape-checking + if self.shape(): + if not len(entries) in self._shape: + raise ShapeError('Mapping must match one data dimension') + + # Handle case where mapping already exists: + if title in self.list_mappings(): + if overwrite: + self.delete_mapping(title) + else: + raise LookupError(title + ' mapping already exists.') + + # Create lookup group under root if it doesn't already exist. + if 'lookup' not in self.root: + self.create_group(self.root, 'lookup') + + # Write the mapping! + mymap = self.create_array( + self.root.lookup, title, atom=tables.UInt16Atom(), + shape=(len(entries),)) + mymap[:] = entries + + return mymap + + def __getitem__(self, key): + """Return a matrix by name, or a list of matrices by attributes""" + return self.get_node(self.root.data, key) + + def get_matrices_by_attr(self, key, value): + """ + Returns a list of matrices that have an attribute matching + a certain value. + + Parameters + ---------- + key : str + Attribute name to match. + value : object + Attribute value to match. + + Returns + ------- + matrices : list + + """ + return [ + m for m in self + if key in m.attrs and m.attrs[key] == value] + + def __len__(self): + return len(self.list_nodes(self.root.data, 'CArray')) + + def __setitem__(self, key, dataset): + # checks to see if it is already a tables instance, and if so, + # copies it + if isinstance(dataset, tables.CArray): + return dataset.copy(self.root.data, key) + else: + # We need to determine atom and shape from the object that's + # been passed in. + # This assumes 'dataset' is a numpy object. + atom = tables.Atom.from_dtype(dataset.dtype) + shape = dataset.shape + + return self.create_matrix(key, atom, shape, obj=dataset) + + def __delitem__(self, key): + self.remove_node(self.root.data, key) + + def __iter__(self): + """Iterate over the keys in this container""" + return self.iter_nodes(self.root.data, 'CArray') + + def __contains__(self, item): + return item in self.root.data + + +def open_omxfile( + filename, mode='r', title='', root_uep='/', + filters=tables.Filters( + complevel=1, shuffle=True, fletcher32=False, complib='zlib'), + shape=None, **kwargs): + """Open or create a new OMX file. New files will be created with default + zlib compression enabled.""" + + f = OMXFile(filename, mode, title, root_uep, filters, **kwargs) + + # add omx structure if file is writable + if mode != 'r': + # version number + if 'OMX_VERSION' not in f.root._v_attrs: + f.root._v_attrs['OMX_VERSION'] = OMX_VERSION + + # shape + if shape: + storeshape = np.array(shape, dtype='int32') + f.root._v_attrs['SHAPE'] = storeshape + + # /data and /lookup folders + if 'data' not in f.root: + f.create_group(f.root, "data") + if 'lookup' not in f.root: + f.create_group(f.root, "lookup") + + return f diff --git a/activitysim/omx/tests/__init__.py b/activitysim/omx/tests/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/activitysim/omx/tests/test_omxfile.py b/activitysim/omx/tests/test_omxfile.py new file mode 100644 index 0000000000..7f8b6ac23a --- /dev/null +++ b/activitysim/omx/tests/test_omxfile.py @@ -0,0 +1,153 @@ +# Licensed under the Apache License, v2.0 +# See activitysim/omx/LICENSE.txt +# Modified from the original OMX library available at +# https://github.com/osPlanning/omx/tree/dev/api/python/omx + +import os +import tempfile + +import numpy as np +import numpy.testing as npt +import pytest +import tables + +from .. import open_omxfile, ShapeError + + +@pytest.fixture +def tmpomx(request): + with tempfile.NamedTemporaryFile() as f: + fname = f.name + + def cleanup(): + if os.path.exists(fname): + os.remove(fname) + request.addfinalizer(cleanup) + + return fname + + +@pytest.fixture +def ones5x5(): + return np.ones((5, 5)) + + +@pytest.fixture +def basic_omx(request, tmpomx, ones5x5): + f = open_omxfile(tmpomx, mode='w') + f['m1'] = ones5x5 + + def fin(): + f.close() + request.addfinalizer(fin) + + return f + + +def test_open_readonly_hdf5_file(tmpomx): + f = tables.open_file(tmpomx, 'w') + f.close() + assert os.path.exists(tmpomx) + f = open_omxfile(tmpomx, 'r') + f.close() + + +def test_set_get_del(tmpomx, ones5x5): + with open_omxfile(tmpomx, 'w') as f: + f['m1'] = ones5x5 + npt.assert_array_equal(f['m1'], ones5x5) + assert f.shape() == (5, 5) + del f['m1'] + assert 'm1' not in f + + +def test_create_matrix(tmpomx, ones5x5): + with open_omxfile(tmpomx, 'w') as f: + f.create_matrix('m1', obj=ones5x5) + npt.assert_array_equal(f['m1'], ones5x5) + assert f.shape() == (5, 5) + + # test check for shape matching + with pytest.raises(ShapeError): + f.create_matrix('m2', obj=np.ones((8, 8))) + + +def test_add_matrix_to_readonly_file(tmpomx, ones5x5): + with open_omxfile(tmpomx, 'w') as f: + f['m2'] = ones5x5 + + with open_omxfile(tmpomx, 'r') as f: + with pytest.raises(tables.FileModeError): + f['m1'] = ones5x5 + + +def test_add_matrix_with_same_name(tmpomx, ones5x5): + with open_omxfile(tmpomx, 'w') as f: + f['m1'] = ones5x5 + + # now add m1 again: + with pytest.raises(tables.NodeError): + f['m1'] = ones5x5 + + +def test_len_list_iter(tmpomx, ones5x5): + names = ['m{}'.format(x) for x in range(5)] + with open_omxfile(tmpomx, 'w') as f: + for m in names: + f[m] = ones5x5 + + for mat in f: + npt.assert_array_equal(mat, ones5x5) + + assert len(f) == len(names) + assert f.list_matrices() == names + + +def test_shape(tmpomx): + with open_omxfile(tmpomx, mode='w', shape=(5, 5)) as f: + assert f.shape() == (5, 5) + + with pytest.raises(ShapeError): + f['test'] = np.ones(10) + + +def test_contains(basic_omx): + assert 'm1' in basic_omx + + +def test_list_all_attrs(basic_omx, ones5x5): + basic_omx['m2'] = ones5x5 + + assert basic_omx.list_all_attributes() == [] + + basic_omx['m1'].attrs['a1'] = 'a1' + basic_omx['m1'].attrs['a2'] = 'a2' + basic_omx['m2'].attrs['a2'] = 'a2' + basic_omx['m2'].attrs['a3'] = 'a3' + + assert basic_omx.list_all_attributes() == ['a1', 'a2', 'a3'] + + +def test_matrices_by_attr(basic_omx, ones5x5): + bo = basic_omx + bo['m2'] = ones5x5 + bo['m3'] = ones5x5 + + for m in bo: + m.attrs['a1'] = 'a1' + m.attrs['a2'] = 'a2' + bo['m3'].attrs['a2'] = 'a22' + bo['m3'].attrs['a3'] = 'a3' + + gmba = bo.get_matrices_by_attr + + assert gmba('zz', 'zz') == [] + assert gmba('a1', 'a1') == [bo['m1'], bo['m2'], bo['m3']] + assert gmba('a2', 'a2') == [bo['m1'], bo['m2']] + assert gmba('a2', 'a22') == [bo['m3']] + assert gmba('a3', 'a3') == [bo['m3']] + + +def test_set_with_carray(basic_omx): + basic_omx['m2'] = basic_omx['m1'] + npt.assert_array_equal(basic_omx['m2'], basic_omx['m1']) diff --git a/setup.py b/setup.py index 2bbe07261e..d88ecdb149 100644 --- a/setup.py +++ b/setup.py @@ -20,5 +20,7 @@ install_requires=[ 'numpy>=1.8.0', 'pandas>=0.13.1', + 'tables>=3.1.0', + 'urbansim>=1.3' ] )