%global _empty_manifest_terminate_build 0
Name: python-deephyper
Version: 0.5.0
Release: 1
Summary: Scalable asynchronous neural architecture and hyperparameter search for deep neural networks.
License: BSD 3-clause
URL: https://github.com/deephyper
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/f7/8f/56a7b380e46931396d0a0f314f29d5df9a96536924544ffae3528b2dd947/deephyper-0.5.0.tar.gz
BuildArch: noarch
Requires: python3-ConfigSpace
Requires: python3-dm-tree
Requires: python3-Jinja2
Requires: python3-numpy
Requires: python3-pandas
Requires: python3-packaging
Requires: python3-parse
Requires: python3-scikit-learn
Requires: python3-scipy
Requires: python3-tqdm
Requires: python3-pyyaml
Requires: python3-altair
Requires: python3-jupyter
Requires: python3-jupyter-contrib-nbextensions
Requires: python3-nbconvert
Requires: python3-streamlit
Requires: python3-streamlit-aggrid
Requires: python3-tinydb
Requires: python3-networkx
Requires: python3-pydot
Requires: python3-tensorflow
Requires: python3-tensorflow-probability
Requires: python3-ray[default]
Requires: python3-xgboost
Requires: python3-ConfigSpace
Requires: python3-dm-tree
Requires: python3-Jinja2
Requires: python3-numpy
Requires: python3-pandas
Requires: python3-packaging
Requires: python3-parse
Requires: python3-scikit-learn
Requires: python3-scipy
Requires: python3-tqdm
Requires: python3-pyyaml
Requires: python3-networkx
Requires: python3-pydot
Requires: python3-tensorflow
Requires: python3-tensorflow-probability
Requires: python3-ray[default]
Requires: python3-sdv
Requires: python3-jax[cpu]
Requires: python3-numpyro[cpu]
Requires: python3-codecov
Requires: python3-pytest
Requires: python3-pytest-cov
Requires: python3-twine
Requires: python3-black
Requires: python3-flake8
Requires: python3-pre-commit
Requires: python3-rstcheck
Requires: python3-GitPython
Requires: python3-ipython
Requires: python3-nbsphinx
Requires: python3-Sphinx
Requires: python3-sphinx-book-theme
Requires: python3-sphinx-copybutton
Requires: python3-sphinx-gallery
Requires: python3-sphinx-lfs-content
Requires: python3-sphinx-togglebutton
Requires: python3-sdv
Requires: python3-horovod
Requires: python3-mpi4py
Requires: python3-jax[cpu]
Requires: python3-numpyro[cpu]
Requires: python3-jax[cuda]
Requires: python3-numpyro[cuda]
Requires: python3-mpi4py
Requires: python3-networkx
Requires: python3-pydot
Requires: python3-tensorflow
Requires: python3-tensorflow-probability
Requires: python3-ray[default]
Requires: python3-redis[hiredis]
%description
[](https://zenodo.org/badge/latestdoi/156403341)
[](https://deephyper.readthedocs.io/en/latest/?badge=latest)
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
## What is DeepHyper?
DeepHyper is a powerful Python package for automating machine learning tasks, particularly focused on optimizing hyperparameters, searching for optimal neural architectures, and quantifying uncertainty through the use of deep ensembles. With DeepHyper, users can easily perform these tasks on a single machine or distributed across multiple machines, making it ideal for use in a variety of environments. Whether you're a beginner looking to optimize your machine learning models or an experienced data scientist looking to streamline your workflow, DeepHyper has something to offer. So why wait? Start using DeepHyper today and take your machine learning skills to the next level!
## Install instructions
From PyPI:
```bash
pip install deephyper
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e deephyper/
```
If you want to install deephyper with test and documentation packages:
From PyPI:
```bash
pip install 'deephyper[dev]'
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e 'deephyper/[dev]'
```
## Quickstart
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
The black-box function named `run` is defined by taking an input dictionnary named `config` which contains the different variables to optimize. Then the run-function is binded to an `Evaluator` in charge of distributing the computation of multiple evaluations. Finally, a Bayesian search named `CBO` is created and executed to find the values of config which maximize the return value of `run(config)`.
```python
def run(config: dict):
return -config["x"]**2
# Necessary IF statement otherwise it will enter in a infinite loop
# when loading the 'run' function from a new process
if __name__ == "__main__":
from deephyper.problem import HpProblem
from deephyper.search.hps import CBO
from deephyper.evaluator import Evaluator
# define the variable you want to optimize
problem = HpProblem()
problem.add_hyperparameter((-10.0, 10.0), "x")
# define the evaluator to distribute the computation
evaluator = Evaluator.create(
run,
method="process",
method_kwargs={
"num_workers": 2,
},
)
# define your search and execute it
search = CBO(problem, evaluator)
results = search.search(max_evals=100)
print(results)
```
Which outputs the following where the best ``x`` found is clearly around ``0``.
```verbatim
p:x job_id objective timestamp_submit timestamp_gather
0 -7.744105 1 -5.997117e+01 0.011047 0.037649
1 -9.058254 2 -8.205196e+01 0.011054 0.056398
2 -1.959750 3 -3.840621e+00 0.049750 0.073166
3 -5.150553 4 -2.652819e+01 0.065681 0.089355
4 -6.697095 5 -4.485108e+01 0.082465 0.158050
.. ... ... ... ... ...
95 -0.034096 96 -1.162566e-03 26.479630 26.795639
96 -0.034204 97 -1.169901e-03 26.789255 27.155481
97 -0.037873 98 -1.434366e-03 27.148506 27.466934
98 -0.000073 99 -5.387088e-09 27.460253 27.774704
99 0.697162 100 -4.860350e-01 27.768153 28.142431
```
We also asked [ChatGPT](https://chat.openai.com) to explain this example and here is the reply:
"The code defines a function `run` that takes a dictionary `config` as input and returns the negative of `x` squared. The `if` block at the end of the code defines a black-box optimization process using the `CBO` (Centralized Bayesian Optimization) algorithm from the `deephyper` library.
The optimization process is defined as follows:
1. A hyperparameter optimization problem is created using the `HpProblem` class from `deephyper`. In this case, the problem has a single continuous hyperparameter `x` that ranges from -10.0 to 10.0.
2. An evaluator is created using the `Evaluator.create` method. The evaluator will be used to evaluate the function `run` with different configurations of the hyperparameters in the optimization problem. The evaluator uses the `process` method to distribute the evaluations across multiple worker processes, in this case 2 worker processes.
3. A search object is created using the `CBO` class and the problem and evaluator defined earlier. The `CBO` algorithm is a derivative-free optimization method that uses a Bayesian optimization approach to explore the hyperparameter space.
4. The optimization process is executed by calling the `search.search` method, which performs the evaluations of the `run` function with different configurations of the hyperparameters until a maximum number of evaluations (100 in this case) is reached.
5. The results of the optimization process, including the optimal configuration of the hyperparameters and the corresponding objective value, are printed to the console."
## How do I learn more?
* Documentation:
* GitHub repository:
* Blog:
## Contributions
Find all the list of contributors on the [DeepHyper Authors](https://deephyper.github.io/aboutus) page of the Documentation.
## Citing DeepHyper
Find all our publications on the [Research & Publication](https://deephyper.github.io/papers) page of the Documentation.
## How can I participate?
Questions, comments, feature requests, bug reports, etc. can be directed to:
* Issues on GitHub
Patches through pull requests are much appreciated on the software itself as well as documentation.
Optionally, please include in your first patch a credit for yourself in the list above.
The DeepHyper Team uses git-flow to organize the development: [Git-Flow cheatsheet](https://danielkummer.github.io/git-flow-cheatsheet/). For tests we are using: [Pytest](https://docs.pytest.org/en/latest/).
## Acknowledgements
* Scalable Data-Efficient Learning for Scientific Domains, U.S. Department of Energy 2018 Early Career Award funded by the Advanced Scientific Computing Research program within the DOE Office of Science (2018--Present)
* Argonne Leadership Computing Facility: This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357.
* SLIK-D: Scalable Machine Learning Infrastructures for Knowledge Discovery, Argonne Computing, Environment and Life Sciences (CELS) Laboratory Directed Research and Development (LDRD) Program (2016--2018)
## Copyright and license
Copyright © 2019, UChicago Argonne, LLC
DeepHyper is distributed under the terms of BSD License. See [LICENSE](https://github.com/deephyper/deephyper/blob/master/LICENSE.md)
Argonne Patent & Intellectual Property File Number: SF-19-007
%package -n python3-deephyper
Summary: Scalable asynchronous neural architecture and hyperparameter search for deep neural networks.
Provides: python-deephyper
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-deephyper
[](https://zenodo.org/badge/latestdoi/156403341)
[](https://deephyper.readthedocs.io/en/latest/?badge=latest)
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
## What is DeepHyper?
DeepHyper is a powerful Python package for automating machine learning tasks, particularly focused on optimizing hyperparameters, searching for optimal neural architectures, and quantifying uncertainty through the use of deep ensembles. With DeepHyper, users can easily perform these tasks on a single machine or distributed across multiple machines, making it ideal for use in a variety of environments. Whether you're a beginner looking to optimize your machine learning models or an experienced data scientist looking to streamline your workflow, DeepHyper has something to offer. So why wait? Start using DeepHyper today and take your machine learning skills to the next level!
## Install instructions
From PyPI:
```bash
pip install deephyper
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e deephyper/
```
If you want to install deephyper with test and documentation packages:
From PyPI:
```bash
pip install 'deephyper[dev]'
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e 'deephyper/[dev]'
```
## Quickstart
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
The black-box function named `run` is defined by taking an input dictionnary named `config` which contains the different variables to optimize. Then the run-function is binded to an `Evaluator` in charge of distributing the computation of multiple evaluations. Finally, a Bayesian search named `CBO` is created and executed to find the values of config which maximize the return value of `run(config)`.
```python
def run(config: dict):
return -config["x"]**2
# Necessary IF statement otherwise it will enter in a infinite loop
# when loading the 'run' function from a new process
if __name__ == "__main__":
from deephyper.problem import HpProblem
from deephyper.search.hps import CBO
from deephyper.evaluator import Evaluator
# define the variable you want to optimize
problem = HpProblem()
problem.add_hyperparameter((-10.0, 10.0), "x")
# define the evaluator to distribute the computation
evaluator = Evaluator.create(
run,
method="process",
method_kwargs={
"num_workers": 2,
},
)
# define your search and execute it
search = CBO(problem, evaluator)
results = search.search(max_evals=100)
print(results)
```
Which outputs the following where the best ``x`` found is clearly around ``0``.
```verbatim
p:x job_id objective timestamp_submit timestamp_gather
0 -7.744105 1 -5.997117e+01 0.011047 0.037649
1 -9.058254 2 -8.205196e+01 0.011054 0.056398
2 -1.959750 3 -3.840621e+00 0.049750 0.073166
3 -5.150553 4 -2.652819e+01 0.065681 0.089355
4 -6.697095 5 -4.485108e+01 0.082465 0.158050
.. ... ... ... ... ...
95 -0.034096 96 -1.162566e-03 26.479630 26.795639
96 -0.034204 97 -1.169901e-03 26.789255 27.155481
97 -0.037873 98 -1.434366e-03 27.148506 27.466934
98 -0.000073 99 -5.387088e-09 27.460253 27.774704
99 0.697162 100 -4.860350e-01 27.768153 28.142431
```
We also asked [ChatGPT](https://chat.openai.com) to explain this example and here is the reply:
"The code defines a function `run` that takes a dictionary `config` as input and returns the negative of `x` squared. The `if` block at the end of the code defines a black-box optimization process using the `CBO` (Centralized Bayesian Optimization) algorithm from the `deephyper` library.
The optimization process is defined as follows:
1. A hyperparameter optimization problem is created using the `HpProblem` class from `deephyper`. In this case, the problem has a single continuous hyperparameter `x` that ranges from -10.0 to 10.0.
2. An evaluator is created using the `Evaluator.create` method. The evaluator will be used to evaluate the function `run` with different configurations of the hyperparameters in the optimization problem. The evaluator uses the `process` method to distribute the evaluations across multiple worker processes, in this case 2 worker processes.
3. A search object is created using the `CBO` class and the problem and evaluator defined earlier. The `CBO` algorithm is a derivative-free optimization method that uses a Bayesian optimization approach to explore the hyperparameter space.
4. The optimization process is executed by calling the `search.search` method, which performs the evaluations of the `run` function with different configurations of the hyperparameters until a maximum number of evaluations (100 in this case) is reached.
5. The results of the optimization process, including the optimal configuration of the hyperparameters and the corresponding objective value, are printed to the console."
## How do I learn more?
* Documentation:
* GitHub repository:
* Blog:
## Contributions
Find all the list of contributors on the [DeepHyper Authors](https://deephyper.github.io/aboutus) page of the Documentation.
## Citing DeepHyper
Find all our publications on the [Research & Publication](https://deephyper.github.io/papers) page of the Documentation.
## How can I participate?
Questions, comments, feature requests, bug reports, etc. can be directed to:
* Issues on GitHub
Patches through pull requests are much appreciated on the software itself as well as documentation.
Optionally, please include in your first patch a credit for yourself in the list above.
The DeepHyper Team uses git-flow to organize the development: [Git-Flow cheatsheet](https://danielkummer.github.io/git-flow-cheatsheet/). For tests we are using: [Pytest](https://docs.pytest.org/en/latest/).
## Acknowledgements
* Scalable Data-Efficient Learning for Scientific Domains, U.S. Department of Energy 2018 Early Career Award funded by the Advanced Scientific Computing Research program within the DOE Office of Science (2018--Present)
* Argonne Leadership Computing Facility: This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357.
* SLIK-D: Scalable Machine Learning Infrastructures for Knowledge Discovery, Argonne Computing, Environment and Life Sciences (CELS) Laboratory Directed Research and Development (LDRD) Program (2016--2018)
## Copyright and license
Copyright © 2019, UChicago Argonne, LLC
DeepHyper is distributed under the terms of BSD License. See [LICENSE](https://github.com/deephyper/deephyper/blob/master/LICENSE.md)
Argonne Patent & Intellectual Property File Number: SF-19-007
%package help
Summary: Development documents and examples for deephyper
Provides: python3-deephyper-doc
%description help
[](https://zenodo.org/badge/latestdoi/156403341)
[](https://deephyper.readthedocs.io/en/latest/?badge=latest)
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
## What is DeepHyper?
DeepHyper is a powerful Python package for automating machine learning tasks, particularly focused on optimizing hyperparameters, searching for optimal neural architectures, and quantifying uncertainty through the use of deep ensembles. With DeepHyper, users can easily perform these tasks on a single machine or distributed across multiple machines, making it ideal for use in a variety of environments. Whether you're a beginner looking to optimize your machine learning models or an experienced data scientist looking to streamline your workflow, DeepHyper has something to offer. So why wait? Start using DeepHyper today and take your machine learning skills to the next level!
## Install instructions
From PyPI:
```bash
pip install deephyper
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e deephyper/
```
If you want to install deephyper with test and documentation packages:
From PyPI:
```bash
pip install 'deephyper[dev]'
```
From Github:
```bash
git clone https://github.com/deephyper/deephyper.git
pip install -e 'deephyper/[dev]'
```
## Quickstart
[](https://colab.research.google.com/github/deephyper/tutorials/blob/main/tutorials/colab/DeepHyper_101.ipynb)
The black-box function named `run` is defined by taking an input dictionnary named `config` which contains the different variables to optimize. Then the run-function is binded to an `Evaluator` in charge of distributing the computation of multiple evaluations. Finally, a Bayesian search named `CBO` is created and executed to find the values of config which maximize the return value of `run(config)`.
```python
def run(config: dict):
return -config["x"]**2
# Necessary IF statement otherwise it will enter in a infinite loop
# when loading the 'run' function from a new process
if __name__ == "__main__":
from deephyper.problem import HpProblem
from deephyper.search.hps import CBO
from deephyper.evaluator import Evaluator
# define the variable you want to optimize
problem = HpProblem()
problem.add_hyperparameter((-10.0, 10.0), "x")
# define the evaluator to distribute the computation
evaluator = Evaluator.create(
run,
method="process",
method_kwargs={
"num_workers": 2,
},
)
# define your search and execute it
search = CBO(problem, evaluator)
results = search.search(max_evals=100)
print(results)
```
Which outputs the following where the best ``x`` found is clearly around ``0``.
```verbatim
p:x job_id objective timestamp_submit timestamp_gather
0 -7.744105 1 -5.997117e+01 0.011047 0.037649
1 -9.058254 2 -8.205196e+01 0.011054 0.056398
2 -1.959750 3 -3.840621e+00 0.049750 0.073166
3 -5.150553 4 -2.652819e+01 0.065681 0.089355
4 -6.697095 5 -4.485108e+01 0.082465 0.158050
.. ... ... ... ... ...
95 -0.034096 96 -1.162566e-03 26.479630 26.795639
96 -0.034204 97 -1.169901e-03 26.789255 27.155481
97 -0.037873 98 -1.434366e-03 27.148506 27.466934
98 -0.000073 99 -5.387088e-09 27.460253 27.774704
99 0.697162 100 -4.860350e-01 27.768153 28.142431
```
We also asked [ChatGPT](https://chat.openai.com) to explain this example and here is the reply:
"The code defines a function `run` that takes a dictionary `config` as input and returns the negative of `x` squared. The `if` block at the end of the code defines a black-box optimization process using the `CBO` (Centralized Bayesian Optimization) algorithm from the `deephyper` library.
The optimization process is defined as follows:
1. A hyperparameter optimization problem is created using the `HpProblem` class from `deephyper`. In this case, the problem has a single continuous hyperparameter `x` that ranges from -10.0 to 10.0.
2. An evaluator is created using the `Evaluator.create` method. The evaluator will be used to evaluate the function `run` with different configurations of the hyperparameters in the optimization problem. The evaluator uses the `process` method to distribute the evaluations across multiple worker processes, in this case 2 worker processes.
3. A search object is created using the `CBO` class and the problem and evaluator defined earlier. The `CBO` algorithm is a derivative-free optimization method that uses a Bayesian optimization approach to explore the hyperparameter space.
4. The optimization process is executed by calling the `search.search` method, which performs the evaluations of the `run` function with different configurations of the hyperparameters until a maximum number of evaluations (100 in this case) is reached.
5. The results of the optimization process, including the optimal configuration of the hyperparameters and the corresponding objective value, are printed to the console."
## How do I learn more?
* Documentation:
* GitHub repository:
* Blog:
## Contributions
Find all the list of contributors on the [DeepHyper Authors](https://deephyper.github.io/aboutus) page of the Documentation.
## Citing DeepHyper
Find all our publications on the [Research & Publication](https://deephyper.github.io/papers) page of the Documentation.
## How can I participate?
Questions, comments, feature requests, bug reports, etc. can be directed to:
* Issues on GitHub
Patches through pull requests are much appreciated on the software itself as well as documentation.
Optionally, please include in your first patch a credit for yourself in the list above.
The DeepHyper Team uses git-flow to organize the development: [Git-Flow cheatsheet](https://danielkummer.github.io/git-flow-cheatsheet/). For tests we are using: [Pytest](https://docs.pytest.org/en/latest/).
## Acknowledgements
* Scalable Data-Efficient Learning for Scientific Domains, U.S. Department of Energy 2018 Early Career Award funded by the Advanced Scientific Computing Research program within the DOE Office of Science (2018--Present)
* Argonne Leadership Computing Facility: This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357.
* SLIK-D: Scalable Machine Learning Infrastructures for Knowledge Discovery, Argonne Computing, Environment and Life Sciences (CELS) Laboratory Directed Research and Development (LDRD) Program (2016--2018)
## Copyright and license
Copyright © 2019, UChicago Argonne, LLC
DeepHyper is distributed under the terms of BSD License. See [LICENSE](https://github.com/deephyper/deephyper/blob/master/LICENSE.md)
Argonne Patent & Intellectual Property File Number: SF-19-007
%prep
%autosetup -n deephyper-0.5.0
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-deephyper -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed May 31 2023 Python_Bot - 0.5.0-1
- Package Spec generated