path: root/python-abdothebest.spec

%global _empty_manifest_terminate_build 0
Name:		python-abdoTheBest
Version:	1.0.0
Release:	1
Summary:	A small example package
License:	MIT
URL:		https://github.com/gituser/example-pkg
Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/55/f3/d948dfe7af193ea36a74b27f94c2c6d0490a6573a833982e13f3c207df03/abdoTheBest-1.0.0.tar.gz
BuildArch:	noarch


%description

# GeNN
[![GitHub license](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt)

GeNN (generative neural networks) is a high-level interface for text applications using PyTorch RNN's.


## Features

1.  Preprocessing: 
	- Parsing txt, json, and csv files.
	- NLTK, regex and spacy tokenization support.
	- GloVe and fastText pretrained embeddings, with the ability to fine-tune for your data.
2. Architectures and customization:
	- GPT2 with small, medium, and large variants.
	- LSTM and GRU, with variable size.
	- Variable number of layers and batches.
	- Dropout.
3. Text generation:
	- Random seed sampling from the n first tokens in all instances, or the most frequent token.
	- Top-K sampling for next token prediction with variable K.
	- Nucleus sampling for next token prediction with variable probability threshold.
4. Text Summarization:
	- All GPT2 variants can be trained to perform text summarization.

## Getting started

### How to install
```bash
pip install genn
```
### Prerequisites
* PyTorch 1.4.0
```bash
pip install torch==1.4.0
```
* Pytorch Transformers
```bash
pip install pytorch_transformers
```
* NumPy
```bash
pip install numpy
```
* fastText
```bash
pip install fasttext
```
Use the package manager [pip](https://pypi.org/project/genn) to install genn.

## Usage
### Text Generation:
##### RNNs (You can switch LSTMGenerator with GRUGenerator:
```python
from genn import Preprocessing, LSTMGenerator, GRUGenerator
#LSTM example
ds = Preprocessing("data.txt")
gen = LSTMGenerator(ds, nLayers = 2,
                        batchSize = 16,
                        embSize = 64,
                        lstmSize = 16,
                        epochs = 20)
			
#Train the model
gen.run()

# Generate 5 new documents
print(gen.generate_document(5))
```
##### GPT2 Generator:
```python
#GPT2 example
gen = GPT2("data.txt",
 	    taskToken = "Movie:",
	    epochs = 7,
	    variant = "medium")
#Train the model
gen.run()

#Generate 10 new documents
print(gen.generate_document(10))
```
### Text Summarization:
##### GPT2 Summarizer:
```python
#GPT2 Summarizer example
from genn import GPT2Summarizer
summ = GPT2Summarizer("data.txt",
					epochs=3,
					batch_size=8)

#Train the model
summ.run()

#Create 5 summaries of a source document
src_doc = "This is the source document to summarize"
print(summ.summarize_document(n=5, setSeed = src_doc))
```



#### For more examples on how to use Preprocessing, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/preprocessing_examples.md).
#### For more examples on how to use LSTMGenerator and GRUGenerator, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/generator_examples.md).
#### For more examples on how to use GPT2, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_examples.md).
#### For more examples on how to use GPT2Summarizer, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_summarizer_examples.md).
## Contributing
 Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
## License
Distributed under the MIT License. See [LICENSE](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt) for more information.




%package -n python3-abdoTheBest
Summary:	A small example package
Provides:	python-abdoTheBest
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-abdoTheBest

# GeNN
[![GitHub license](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt)

GeNN (generative neural networks) is a high-level interface for text applications using PyTorch RNN's.


## Features

1.  Preprocessing: 
	- Parsing txt, json, and csv files.
	- NLTK, regex and spacy tokenization support.
	- GloVe and fastText pretrained embeddings, with the ability to fine-tune for your data.
2. Architectures and customization:
	- GPT2 with small, medium, and large variants.
	- LSTM and GRU, with variable size.
	- Variable number of layers and batches.
	- Dropout.
3. Text generation:
	- Random seed sampling from the n first tokens in all instances, or the most frequent token.
	- Top-K sampling for next token prediction with variable K.
	- Nucleus sampling for next token prediction with variable probability threshold.
4. Text Summarization:
	- All GPT2 variants can be trained to perform text summarization.

## Getting started

### How to install
```bash
pip install genn
```
### Prerequisites
* PyTorch 1.4.0
```bash
pip install torch==1.4.0
```
* Pytorch Transformers
```bash
pip install pytorch_transformers
```
* NumPy
```bash
pip install numpy
```
* fastText
```bash
pip install fasttext
```
Use the package manager [pip](https://pypi.org/project/genn) to install genn.

## Usage
### Text Generation:
##### RNNs (You can switch LSTMGenerator with GRUGenerator:
```python
from genn import Preprocessing, LSTMGenerator, GRUGenerator
#LSTM example
ds = Preprocessing("data.txt")
gen = LSTMGenerator(ds, nLayers = 2,
                        batchSize = 16,
                        embSize = 64,
                        lstmSize = 16,
                        epochs = 20)
			
#Train the model
gen.run()

# Generate 5 new documents
print(gen.generate_document(5))
```
##### GPT2 Generator:
```python
#GPT2 example
gen = GPT2("data.txt",
 	    taskToken = "Movie:",
	    epochs = 7,
	    variant = "medium")
#Train the model
gen.run()

#Generate 10 new documents
print(gen.generate_document(10))
```
### Text Summarization:
##### GPT2 Summarizer:
```python
#GPT2 Summarizer example
from genn import GPT2Summarizer
summ = GPT2Summarizer("data.txt",
					epochs=3,
					batch_size=8)

#Train the model
summ.run()

#Create 5 summaries of a source document
src_doc = "This is the source document to summarize"
print(summ.summarize_document(n=5, setSeed = src_doc))
```



#### For more examples on how to use Preprocessing, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/preprocessing_examples.md).
#### For more examples on how to use LSTMGenerator and GRUGenerator, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/generator_examples.md).
#### For more examples on how to use GPT2, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_examples.md).
#### For more examples on how to use GPT2Summarizer, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_summarizer_examples.md).
## Contributing
 Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
## License
Distributed under the MIT License. See [LICENSE](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt) for more information.




%package help
Summary:	Development documents and examples for abdoTheBest
Provides:	python3-abdoTheBest-doc
%description help

# GeNN
[![GitHub license](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt)

GeNN (generative neural networks) is a high-level interface for text applications using PyTorch RNN's.


## Features

1.  Preprocessing: 
	- Parsing txt, json, and csv files.
	- NLTK, regex and spacy tokenization support.
	- GloVe and fastText pretrained embeddings, with the ability to fine-tune for your data.
2. Architectures and customization:
	- GPT2 with small, medium, and large variants.
	- LSTM and GRU, with variable size.
	- Variable number of layers and batches.
	- Dropout.
3. Text generation:
	- Random seed sampling from the n first tokens in all instances, or the most frequent token.
	- Top-K sampling for next token prediction with variable K.
	- Nucleus sampling for next token prediction with variable probability threshold.
4. Text Summarization:
	- All GPT2 variants can be trained to perform text summarization.

## Getting started

### How to install
```bash
pip install genn
```
### Prerequisites
* PyTorch 1.4.0
```bash
pip install torch==1.4.0
```
* Pytorch Transformers
```bash
pip install pytorch_transformers
```
* NumPy
```bash
pip install numpy
```
* fastText
```bash
pip install fasttext
```
Use the package manager [pip](https://pypi.org/project/genn) to install genn.

## Usage
### Text Generation:
##### RNNs (You can switch LSTMGenerator with GRUGenerator:
```python
from genn import Preprocessing, LSTMGenerator, GRUGenerator
#LSTM example
ds = Preprocessing("data.txt")
gen = LSTMGenerator(ds, nLayers = 2,
                        batchSize = 16,
                        embSize = 64,
                        lstmSize = 16,
                        epochs = 20)
			
#Train the model
gen.run()

# Generate 5 new documents
print(gen.generate_document(5))
```
##### GPT2 Generator:
```python
#GPT2 example
gen = GPT2("data.txt",
 	    taskToken = "Movie:",
	    epochs = 7,
	    variant = "medium")
#Train the model
gen.run()

#Generate 10 new documents
print(gen.generate_document(10))
```
### Text Summarization:
##### GPT2 Summarizer:
```python
#GPT2 Summarizer example
from genn import GPT2Summarizer
summ = GPT2Summarizer("data.txt",
					epochs=3,
					batch_size=8)

#Train the model
summ.run()

#Create 5 summaries of a source document
src_doc = "This is the source document to summarize"
print(summ.summarize_document(n=5, setSeed = src_doc))
```



#### For more examples on how to use Preprocessing, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/preprocessing_examples.md).
#### For more examples on how to use LSTMGenerator and GRUGenerator, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/generator_examples.md).
#### For more examples on how to use GPT2, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_examples.md).
#### For more examples on how to use GPT2Summarizer, please refer to [this file](https://github.com/FahedSabellioglu/genn/blob/master/gpt2_summarizer_examples.md).
## Contributing
 Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
## License
Distributed under the MIT License. See [LICENSE](https://github.com/FahedSabellioglu/genn/blob/master/LICENSE.txt) for more information.




%prep
%autosetup -n abdoTheBest-1.0.0

%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-abdoTheBest -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 1.0.0-1
- Package Spec generated