2021-07-05T14:45:50,745 DEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.
2021-07-05T14:45:51,461 Created temporary directory: /tmp/pip-ephem-wheel-cache-pq6792mh
2021-07-05T14:45:51,466 Created temporary directory: /tmp/pip-req-tracker-vnsiqyvf
2021-07-05T14:45:51,467 Initialized build tracking at /tmp/pip-req-tracker-vnsiqyvf
2021-07-05T14:45:51,468 Created build tracker: /tmp/pip-req-tracker-vnsiqyvf
2021-07-05T14:45:51,468 Entered build tracker: /tmp/pip-req-tracker-vnsiqyvf
2021-07-05T14:45:51,470 Created temporary directory: /tmp/pip-wheel-xro7nguy
2021-07-05T14:45:51,543 1 location(s) to search for versions of matrix-fact:
2021-07-05T14:45:51,543 * https://pypi.org/simple/matrix-fact/
2021-07-05T14:45:51,544 Fetching project page and analyzing links: https://pypi.org/simple/matrix-fact/
2021-07-05T14:45:51,546 Getting page https://pypi.org/simple/matrix-fact/
2021-07-05T14:45:51,551 Found index url https://pypi.org/simple
2021-07-05T14:45:51,873   Found link https://files.pythonhosted.org/packages/11/2e/c979994d0cff31bfb39218e8b5f26b632f651349582bd60a13a24955b285/matrix-fact-1.0.1.tar.gz#sha256=5488e7eca9842f32b0235ddf09c2678f27e900aefe7f00c3d6acf753b1a18c74 (from https://pypi.org/simple/matrix-fact/), version: 1.0.1
2021-07-05T14:45:51,874   Found link https://files.pythonhosted.org/packages/39/8a/e2d537aced3afacdb93d822823580f460ee95fc834d0b0f5ad25e21a1066/matrix-fact-1.1.0.tar.gz#sha256=850c6b9f4a3ca0d9e094e7691403779ed798afb9d0e2cc0c5221946769867e44 (from https://pypi.org/simple/matrix-fact/), version: 1.1.0
2021-07-05T14:45:51,875   Found link https://files.pythonhosted.org/packages/44/6d/a8144f7aa9e57d0de9278a6903f94cf771ba212608e089247fb098f78be7/matrix-fact-1.1.1.tar.gz#sha256=865250a0212fbe372e5c38c9d3979350517b0696def64a87eb6b35af33cbd0b6 (from https://pypi.org/simple/matrix-fact/), version: 1.1.1
2021-07-05T14:45:51,876   Found link https://files.pythonhosted.org/packages/e0/31/1221f472055654406d1c352f5110f031f4f255d5947692df73557b11f15f/matrix-fact-1.1.2.tar.gz#sha256=5ece899deafbb1912f8c01f92b54dddd889c5202447100044f335ccca52abc6e (from https://pypi.org/simple/matrix-fact/), version: 1.1.2
2021-07-05T14:45:51,906 Given no hashes to check 1 links for project 'matrix-fact': discarding no candidates
2021-07-05T14:45:51,939 Collecting matrix-fact==1.1.1
2021-07-05T14:45:51,943   Created temporary directory: /tmp/pip-unpack-0cvyson6
2021-07-05T14:45:52,174   Downloading matrix-fact-1.1.1.tar.gz (34 kB)
2021-07-05T14:45:52,497   Added matrix-fact==1.1.1 from https://files.pythonhosted.org/packages/44/6d/a8144f7aa9e57d0de9278a6903f94cf771ba212608e089247fb098f78be7/matrix-fact-1.1.1.tar.gz#sha256=865250a0212fbe372e5c38c9d3979350517b0696def64a87eb6b35af33cbd0b6 to build tracker '/tmp/pip-req-tracker-vnsiqyvf'
2021-07-05T14:45:52,499     Running setup.py (path:/tmp/pip-wheel-xro7nguy/matrix-fact_3e170dbf62784ade99e0a9cff08304c3/setup.py) egg_info for package matrix-fact
2021-07-05T14:45:52,500     Created temporary directory: /tmp/pip-pip-egg-info-dbfisdig
2021-07-05T14:45:52,501     Running command python setup.py egg_info
2021-07-05T14:45:54,820     ## MatrixFact

2021-07-05T14:45:54,822     ### Install
2021-07-05T14:45:54,822     ```
2021-07-05T14:45:54,823     pip install matrix-fact
2021-07-05T14:45:54,824     ```

2021-07-05T14:45:54,825     ### What is matrix-fact?
2021-07-05T14:45:54,825     matrix-fact contains modules for constrained/unconstrained matrix factorization (and related) methods for both sparse and dense matrices. The repository can be found at https://github.com/gentaiscool/matrix_fact. The code is based on https://github.com/ChrisSchinnerl/pymf3 and https://github.com/rikkhill/pymf. We updated the code to support the latest library. It requires cvxopt, numpy, scipy and torch. We just addded the support for PyTorch-based SNMF.

2021-07-05T14:45:54,827     ### Packages

2021-07-05T14:45:54,828     The package includes:
2021-07-05T14:45:54,829     * Non-negative matrix factorization (NMF) [three different optimizations used]
2021-07-05T14:45:54,829     * Convex non-negative matrix factorization (CNMF)
2021-07-05T14:45:54,830     * Semi non-negative matrix factorization (SNMF)
2021-07-05T14:45:54,831     * Archetypal analysis (AA)
2021-07-05T14:45:54,831     * Simplex volume maximization (SiVM) [and SiVM for CUR, GSAT, ... ]
2021-07-05T14:45:54,832     * Convex-hull non-negative matrix factorization (CHNMF)
2021-07-05T14:45:54,833     * Binary matrix factorization (BNMF)
2021-07-05T14:45:54,833     * Singular value decomposition (SVD)
2021-07-05T14:45:54,834     * Principal component analysis (PCA)
2021-07-05T14:45:54,834     * K-means clustering (Kmeans)
2021-07-05T14:45:54,835     * C-means clustering (Cmeans)
2021-07-05T14:45:54,836     * CUR decomposition (CUR)
2021-07-05T14:45:54,836     * Compaxt matrix decomposition (CMD)
2021-07-05T14:45:54,837     * PyTorch SNMF

2021-07-05T14:45:54,838     ### Usage
2021-07-05T14:45:54,839     Given a dataset, most factorization methods try to minimize the Frobenius norm <code>| data - W*H|</code> by finding a suitable set of basis vectors <code>W</code> and coefficients H. The syntax for calling the various methods is quite similar. Usually, one has to submit a desired number of basis vectors and the maximum number of iterations. For example, applying NMF to a dataset data aiming at 2 basis vectors within 10 iterations works as follows:

2021-07-05T14:45:54,840     ```python
2021-07-05T14:45:54,841     >>> import matrix_fact
2021-07-05T14:45:54,841     >>> import numpy as np
2021-07-05T14:45:54,842     >>> data = np.array([[1.0, 0.0, 2.0], [0.0, 1.0, 1.0]])
2021-07-05T14:45:54,842     >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2, niter=10)
2021-07-05T14:45:54,843     >>> nmf_mdl.initialization()
2021-07-05T14:45:54,844     >>> nmf_mdl.factorize()
2021-07-05T14:45:54,844     ```

2021-07-05T14:45:54,845     The basis vectors are now stored in <code>nmf_mdl.W</code>, the coefficients in <code>nmf_mdl.H</code>. To compute coefficients for an existing set of basis vectors simply copy W to nmf_mdl.W, and set compW to False:

2021-07-05T14:45:54,847     ```python
2021-07-05T14:45:54,847     >>> data = np.array([[1.5], [1.2]])
2021-07-05T14:45:54,848     >>> W = np.array([[1.0, 0.0], [0.0, 1.0]])
2021-07-05T14:45:54,849     >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2, niter=1, compW=False)
2021-07-05T14:45:54,849     >>> nmf_mdl.initialization()
2021-07-05T14:45:54,850     >>> nmf_mdl.W = W
2021-07-05T14:45:54,850     >>> nmf_mdl.factorize()
2021-07-05T14:45:54,851     ```

2021-07-05T14:45:54,852     By changing py_fact.NMF to e.g. py_fact.AA or py_fact.CNMF Archetypal Analysis or Convex-NMF can be applied. Some methods might allow other parameters, make sure to have a look at the corresponding <code>>>>help(py_fact.AA)</code> documentation. For example, CUR, CMD, and SVD are handled slightly differently, as they factorize into three submatrices which requires appropriate arguments for row and column sampling.

2021-07-05T14:45:54,853     For PyTorch-SNMF
2021-07-05T14:45:54,854     ```python
2021-07-05T14:45:54,855     >>> data = torch.FloatTensor([[1.5], [1.2]])
2021-07-05T14:45:54,855     >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2)
2021-07-05T14:45:54,856     >>> nmf_mdl.factorize(niter=1000)
2021-07-05T14:45:54,856     ```

2021-07-05T14:45:54,858     ### Very large datasets
2021-07-05T14:45:54,858     For handling larger datasets py_fact supports hdf5 via h5py. Usage is straight forward as h5py allows to map large numpy matrices to disk. Thus, instead of passing data as a np.array, you can simply send the corresponding hdf5 table. The following example shows how to apply py_fact to a random matrix that is entirely stored on disk. In this example the dataset does not have to fit into memory, the resulting low-rank factors <code>W,H</code> have to.

2021-07-05T14:45:54,860     ```python
2021-07-05T14:45:54,860     >>> import h5py
2021-07-05T14:45:54,861     >>> import numpy as np
2021-07-05T14:45:54,861     >>> import matrix_fact
2021-07-05T14:45:54,862     >>>
2021-07-05T14:45:54,863     >>> file = h5py.File('myfile.hdf5', 'w')
2021-07-05T14:45:54,863     >>> file['dataset'] = np.random.random((100,1000))
2021-07-05T14:45:54,864     >>> sivm_mdl = matrix_fact.SIVM(file['dataset'], num_bases=10)
2021-07-05T14:45:54,865     >>> sivm_mdl.factorize()
2021-07-05T14:45:54,865     ```

2021-07-05T14:45:54,866     If the low-rank matrices <code>W,H</code> also do not fit into memory, they can be initialized as a h5py matrix.

2021-07-05T14:45:54,868     ```python
2021-07-05T14:45:54,868     >>> import h5py
2021-07-05T14:45:54,869     >>> import numpy as np
2021-07-05T14:45:54,869     >>> import matrix_fact
2021-07-05T14:45:54,870     >>>
2021-07-05T14:45:54,871     >>> file = h5py.File('myfile.hdf5', 'w')
2021-07-05T14:45:54,871     >>> file['dataset'] = np.random.random((100,1000))
2021-07-05T14:45:54,872     >>> file['W'] = np.random.random((100,10))
2021-07-05T14:45:54,872     >>> file['H'] = np.random.random((10,1000))
2021-07-05T14:45:54,873     >>> sivm_mdl = matrix_fact.SIVM(file['dataset'], num_bases=10)
2021-07-05T14:45:54,873     >>> sivm_mdl.W = file['W']
2021-07-05T14:45:54,874     >>> sivm_mdl.H = file['H']
2021-07-05T14:45:54,874     >>> sivm_mdl.factorize()
2021-07-05T14:45:54,875     ```

2021-07-05T14:45:54,876     Please note that currently not all methods work well with hdf5. While they all accept hdf5 input matrices, they sometimes lead to very high memory consumption on intermediate computation steps. This is difficult to avoid unless we switch to a completely disk-based storage.

2021-07-05T14:45:54,878     running egg_info
2021-07-05T14:45:54,878     creating /tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info
2021-07-05T14:45:54,880     writing top-level names to /tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/top_level.txt
2021-07-05T14:45:54,882     writing requirements to /tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/requires.txt
2021-07-05T14:45:54,885     writing dependency_links to /tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/dependency_links.txt
2021-07-05T14:45:54,887     writing /tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/PKG-INFO
2021-07-05T14:45:54,894     writing manifest file '/tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/SOURCES.txt'
2021-07-05T14:45:55,263     reading manifest file '/tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/SOURCES.txt'
2021-07-05T14:45:55,274     writing manifest file '/tmp/pip-pip-egg-info-dbfisdig/matrix_fact.egg-info/SOURCES.txt'
2021-07-05T14:45:55,411   Source in /tmp/pip-wheel-xro7nguy/matrix-fact_3e170dbf62784ade99e0a9cff08304c3 has version 1.1.1, which satisfies requirement matrix-fact==1.1.1 from https://files.pythonhosted.org/packages/44/6d/a8144f7aa9e57d0de9278a6903f94cf771ba212608e089247fb098f78be7/matrix-fact-1.1.1.tar.gz#sha256=865250a0212fbe372e5c38c9d3979350517b0696def64a87eb6b35af33cbd0b6
2021-07-05T14:45:55,413   Removed matrix-fact==1.1.1 from https://files.pythonhosted.org/packages/44/6d/a8144f7aa9e57d0de9278a6903f94cf771ba212608e089247fb098f78be7/matrix-fact-1.1.1.tar.gz#sha256=865250a0212fbe372e5c38c9d3979350517b0696def64a87eb6b35af33cbd0b6 from build tracker '/tmp/pip-req-tracker-vnsiqyvf'
2021-07-05T14:45:55,422 Created temporary directory: /tmp/pip-unpack-hu8s0p5d
2021-07-05T14:45:55,423 Building wheels for collected packages: matrix-fact
2021-07-05T14:45:55,432   Created temporary directory: /tmp/pip-wheel-d3vknf4r
2021-07-05T14:45:55,433   Building wheel for matrix-fact (setup.py): started
2021-07-05T14:45:55,433   Destination directory: /tmp/pip-wheel-d3vknf4r
2021-07-05T14:45:55,434   Running command /usr/bin/python3 -u -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-wheel-xro7nguy/matrix-fact_3e170dbf62784ade99e0a9cff08304c3/setup.py'"'"'; __file__='"'"'/tmp/pip-wheel-xro7nguy/matrix-fact_3e170dbf62784ade99e0a9cff08304c3/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' bdist_wheel -d /tmp/pip-wheel-d3vknf4r
2021-07-05T14:45:57,291   ## MatrixFact

2021-07-05T14:45:57,293   ### Install
2021-07-05T14:45:57,293   ```
2021-07-05T14:45:57,294   pip install matrix-fact
2021-07-05T14:45:57,294   ```

2021-07-05T14:45:57,295   ### What is matrix-fact?
2021-07-05T14:45:57,296   matrix-fact contains modules for constrained/unconstrained matrix factorization (and related) methods for both sparse and dense matrices. The repository can be found at https://github.com/gentaiscool/matrix_fact. The code is based on https://github.com/ChrisSchinnerl/pymf3 and https://github.com/rikkhill/pymf. We updated the code to support the latest library. It requires cvxopt, numpy, scipy and torch. We just addded the support for PyTorch-based SNMF.

2021-07-05T14:45:57,297   ### Packages

2021-07-05T14:45:57,299   The package includes:
2021-07-05T14:45:57,299   * Non-negative matrix factorization (NMF) [three different optimizations used]
2021-07-05T14:45:57,300   * Convex non-negative matrix factorization (CNMF)
2021-07-05T14:45:57,300   * Semi non-negative matrix factorization (SNMF)
2021-07-05T14:45:57,301   * Archetypal analysis (AA)
2021-07-05T14:45:57,302   * Simplex volume maximization (SiVM) [and SiVM for CUR, GSAT, ... ]
2021-07-05T14:45:57,302   * Convex-hull non-negative matrix factorization (CHNMF)
2021-07-05T14:45:57,303   * Binary matrix factorization (BNMF)
2021-07-05T14:45:57,303   * Singular value decomposition (SVD)
2021-07-05T14:45:57,304   * Principal component analysis (PCA)
2021-07-05T14:45:57,305   * K-means clustering (Kmeans)
2021-07-05T14:45:57,305   * C-means clustering (Cmeans)
2021-07-05T14:45:57,306   * CUR decomposition (CUR)
2021-07-05T14:45:57,306   * Compaxt matrix decomposition (CMD)
2021-07-05T14:45:57,307   * PyTorch SNMF

2021-07-05T14:45:57,308   ### Usage
2021-07-05T14:45:57,309   Given a dataset, most factorization methods try to minimize the Frobenius norm <code>| data - W*H|</code> by finding a suitable set of basis vectors <code>W</code> and coefficients H. The syntax for calling the various methods is quite similar. Usually, one has to submit a desired number of basis vectors and the maximum number of iterations. For example, applying NMF to a dataset data aiming at 2 basis vectors within 10 iterations works as follows:

2021-07-05T14:45:57,310   ```python
2021-07-05T14:45:57,311   >>> import matrix_fact
2021-07-05T14:45:57,311   >>> import numpy as np
2021-07-05T14:45:57,312   >>> data = np.array([[1.0, 0.0, 2.0], [0.0, 1.0, 1.0]])
2021-07-05T14:45:57,313   >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2, niter=10)
2021-07-05T14:45:57,313   >>> nmf_mdl.initialization()
2021-07-05T14:45:57,314   >>> nmf_mdl.factorize()
2021-07-05T14:45:57,314   ```

2021-07-05T14:45:57,315   The basis vectors are now stored in <code>nmf_mdl.W</code>, the coefficients in <code>nmf_mdl.H</code>. To compute coefficients for an existing set of basis vectors simply copy W to nmf_mdl.W, and set compW to False:

2021-07-05T14:45:57,316   ```python
2021-07-05T14:45:57,317   >>> data = np.array([[1.5], [1.2]])
2021-07-05T14:45:57,318   >>> W = np.array([[1.0, 0.0], [0.0, 1.0]])
2021-07-05T14:45:57,318   >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2, niter=1, compW=False)
2021-07-05T14:45:57,319   >>> nmf_mdl.initialization()
2021-07-05T14:45:57,319   >>> nmf_mdl.W = W
2021-07-05T14:45:57,320   >>> nmf_mdl.factorize()
2021-07-05T14:45:57,320   ```

2021-07-05T14:45:57,322   By changing py_fact.NMF to e.g. py_fact.AA or py_fact.CNMF Archetypal Analysis or Convex-NMF can be applied. Some methods might allow other parameters, make sure to have a look at the corresponding <code>>>>help(py_fact.AA)</code> documentation. For example, CUR, CMD, and SVD are handled slightly differently, as they factorize into three submatrices which requires appropriate arguments for row and column sampling.

2021-07-05T14:45:57,323   For PyTorch-SNMF
2021-07-05T14:45:57,323   ```python
2021-07-05T14:45:57,324   >>> data = torch.FloatTensor([[1.5], [1.2]])
2021-07-05T14:45:57,324   >>> nmf_mdl = matrix_fact.NMF(data, num_bases=2)
2021-07-05T14:45:57,325   >>> nmf_mdl.factorize(niter=1000)
2021-07-05T14:45:57,325   ```

2021-07-05T14:45:57,327   ### Very large datasets
2021-07-05T14:45:57,327   For handling larger datasets py_fact supports hdf5 via h5py. Usage is straight forward as h5py allows to map large numpy matrices to disk. Thus, instead of passing data as a np.array, you can simply send the corresponding hdf5 table. The following example shows how to apply py_fact to a random matrix that is entirely stored on disk. In this example the dataset does not have to fit into memory, the resulting low-rank factors <code>W,H</code> have to.

2021-07-05T14:45:57,328   ```python
2021-07-05T14:45:57,329   >>> import h5py
2021-07-05T14:45:57,329   >>> import numpy as np
2021-07-05T14:45:57,330   >>> import matrix_fact
2021-07-05T14:45:57,330   >>>
2021-07-05T14:45:57,331   >>> file = h5py.File('myfile.hdf5', 'w')
2021-07-05T14:45:57,332   >>> file['dataset'] = np.random.random((100,1000))
2021-07-05T14:45:57,332   >>> sivm_mdl = matrix_fact.SIVM(file['dataset'], num_bases=10)
2021-07-05T14:45:57,333   >>> sivm_mdl.factorize()
2021-07-05T14:45:57,333   ```

2021-07-05T14:45:57,335   If the low-rank matrices <code>W,H</code> also do not fit into memory, they can be initialized as a h5py matrix.

2021-07-05T14:45:57,336   ```python
2021-07-05T14:45:57,336   >>> import h5py
2021-07-05T14:45:57,337   >>> import numpy as np
2021-07-05T14:45:57,338   >>> import matrix_fact
2021-07-05T14:45:57,338   >>>
2021-07-05T14:45:57,339   >>> file = h5py.File('myfile.hdf5', 'w')
2021-07-05T14:45:57,339   >>> file['dataset'] = np.random.random((100,1000))
2021-07-05T14:45:57,340   >>> file['W'] = np.random.random((100,10))
2021-07-05T14:45:57,341   >>> file['H'] = np.random.random((10,1000))
2021-07-05T14:45:57,341   >>> sivm_mdl = matrix_fact.SIVM(file['dataset'], num_bases=10)
2021-07-05T14:45:57,342   >>> sivm_mdl.W = file['W']
2021-07-05T14:45:57,342   >>> sivm_mdl.H = file['H']
2021-07-05T14:45:57,343   >>> sivm_mdl.factorize()
2021-07-05T14:45:57,343   ```

2021-07-05T14:45:57,344   Please note that currently not all methods work well with hdf5. While they all accept hdf5 input matrices, they sometimes lead to very high memory consumption on intermediate computation steps. This is difficult to avoid unless we switch to a completely disk-based storage.

2021-07-05T14:45:57,743   running bdist_wheel
2021-07-05T14:45:57,759   running build
2021-07-05T14:45:57,760   running build_py
2021-07-05T14:45:58,096   creating build
2021-07-05T14:45:58,097   creating build/lib
2021-07-05T14:45:58,099   creating build/lib/matrix_fact
2021-07-05T14:45:58,101   copying matrix_fact/greedy.py -> build/lib/matrix_fact
2021-07-05T14:45:58,106   copying matrix_fact/cmde.py -> build/lib/matrix_fact
2021-07-05T14:45:58,110   copying matrix_fact/sivm.py -> build/lib/matrix_fact
2021-07-05T14:45:58,115   copying matrix_fact/cur.py -> build/lib/matrix_fact
2021-07-05T14:45:58,119   copying matrix_fact/dist.py -> build/lib/matrix_fact
2021-07-05T14:45:58,124   copying matrix_fact/__init__.py -> build/lib/matrix_fact
2021-07-05T14:45:58,127   copying matrix_fact/greedycur.py -> build/lib/matrix_fact
2021-07-05T14:45:58,132   copying matrix_fact/pmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,138   copying matrix_fact/base.py -> build/lib/matrix_fact
2021-07-05T14:45:58,145   copying matrix_fact/aa.py -> build/lib/matrix_fact
2021-07-05T14:45:58,151   copying matrix_fact/awnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,156   copying matrix_fact/snmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,162   copying matrix_fact/nndsvd.py -> build/lib/matrix_fact
2021-07-05T14:45:58,167   copying matrix_fact/abnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,173   copying matrix_fact/kmeans.py -> build/lib/matrix_fact
2021-07-05T14:45:58,178   copying matrix_fact/sivm_gsat.py -> build/lib/matrix_fact
2021-07-05T14:45:58,184   copying matrix_fact/laesa.py -> build/lib/matrix_fact
2021-07-05T14:45:58,190   copying matrix_fact/sivm_cur.py -> build/lib/matrix_fact
2021-07-05T14:45:58,195   copying matrix_fact/wnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,200   copying matrix_fact/cursl.py -> build/lib/matrix_fact
2021-07-05T14:45:58,206   copying matrix_fact/svd.py -> build/lib/matrix_fact
2021-07-05T14:45:58,212   copying matrix_fact/torch_snmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,217   copying matrix_fact/bnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,223   copying matrix_fact/cmeans.py -> build/lib/matrix_fact
2021-07-05T14:45:58,228   copying matrix_fact/cnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,234   copying matrix_fact/nmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,241   copying matrix_fact/sivm_search.py -> build/lib/matrix_fact
2021-07-05T14:45:58,247   copying matrix_fact/pca.py -> build/lib/matrix_fact
2021-07-05T14:45:58,253   copying matrix_fact/chnmf.py -> build/lib/matrix_fact
2021-07-05T14:45:58,260   copying matrix_fact/sivm_sgreedy.py -> build/lib/matrix_fact
2021-07-05T14:45:58,282   installing to build/bdist.linux-armv7l/wheel
2021-07-05T14:45:58,283   running install
2021-07-05T14:45:58,285   running install_lib
2021-07-05T14:45:58,292   creating build/bdist.linux-armv7l
2021-07-05T14:45:58,293   creating build/bdist.linux-armv7l/wheel
2021-07-05T14:45:58,298   creating build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,300   copying build/lib/matrix_fact/greedy.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,305   copying build/lib/matrix_fact/cmde.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,309   copying build/lib/matrix_fact/sivm.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,314   copying build/lib/matrix_fact/cur.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,320   copying build/lib/matrix_fact/dist.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,326   copying build/lib/matrix_fact/__init__.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,331   copying build/lib/matrix_fact/greedycur.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,337   copying build/lib/matrix_fact/pmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,343   copying build/lib/matrix_fact/base.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,350   copying build/lib/matrix_fact/aa.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,356   copying build/lib/matrix_fact/awnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,362   copying build/lib/matrix_fact/snmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,367   copying build/lib/matrix_fact/nndsvd.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,373   copying build/lib/matrix_fact/abnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,379   copying build/lib/matrix_fact/kmeans.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,385   copying build/lib/matrix_fact/sivm_gsat.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,391   copying build/lib/matrix_fact/laesa.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,396   copying build/lib/matrix_fact/sivm_cur.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,402   copying build/lib/matrix_fact/wnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,407   copying build/lib/matrix_fact/cursl.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,413   copying build/lib/matrix_fact/svd.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,419   copying build/lib/matrix_fact/torch_snmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,425   copying build/lib/matrix_fact/bnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,431   copying build/lib/matrix_fact/cmeans.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,436   copying build/lib/matrix_fact/cnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,442   copying build/lib/matrix_fact/nmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,449   copying build/lib/matrix_fact/sivm_search.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,455   copying build/lib/matrix_fact/pca.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,463   copying build/lib/matrix_fact/chnmf.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,472   copying build/lib/matrix_fact/sivm_sgreedy.py -> build/bdist.linux-armv7l/wheel/matrix_fact
2021-07-05T14:45:58,477   running install_egg_info
2021-07-05T14:45:58,535   running egg_info
2021-07-05T14:45:58,538   writing top-level names to matrix_fact.egg-info/top_level.txt
2021-07-05T14:45:58,540   writing matrix_fact.egg-info/PKG-INFO
2021-07-05T14:45:58,545   writing dependency_links to matrix_fact.egg-info/dependency_links.txt
2021-07-05T14:45:58,547   writing requirements to matrix_fact.egg-info/requires.txt
2021-07-05T14:45:58,569   reading manifest file 'matrix_fact.egg-info/SOURCES.txt'
2021-07-05T14:45:58,586   writing manifest file 'matrix_fact.egg-info/SOURCES.txt'
2021-07-05T14:45:58,589   Copying matrix_fact.egg-info to build/bdist.linux-armv7l/wheel/matrix_fact-1.1.1-py3.5.egg-info
2021-07-05T14:45:58,613   running install_scripts
2021-07-05T14:45:58,809   creating build/bdist.linux-armv7l/wheel/matrix_fact-1.1.1.dist-info/WHEEL
2021-07-05T14:45:59,141   Building wheel for matrix-fact (setup.py): finished with status 'done'
2021-07-05T14:45:59,145   Created wheel for matrix-fact: filename=matrix_fact-1.1.1-py3-none-any.whl size=57502 sha256=9541cc639e832e63b92907d4e604c43af9e0dde8c1f8fd7f0e067a11ed72fb1c
2021-07-05T14:45:59,146   Stored in directory: /tmp/pip-ephem-wheel-cache-pq6792mh/wheels/f1/fc/a2/dcaac7bdeaf666ca0ef04d7cf14ac4da1b6c9f948a425581a4
2021-07-05T14:45:59,167 Successfully built matrix-fact
2021-07-05T14:45:59,182 Removed build tracker: '/tmp/pip-req-tracker-vnsiqyvf'