ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

revise Chronos api doc (#4993)

Browse source
This commit is contained in:
Shane Huang 2022-07-01 18:19:46 +08:00 committed by GitHub
parent b53074af53
commit a6cab83afd
4 changed files with 143 additions and 112 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
docs/readthedocs/source/doc/PythonAPI/Chronos/automodels.rst
View file

@ -5,35 +5,52 @@ AutoTCN
------------------------------------------- -------------------------------------------
AutoTCN is a TCN forecasting model with Auto tuning. AutoTCN is a TCN forecasting model with Auto tuning.
Other API follows its base class(BaseAutomodel).
.. automodule:: bigdl.chronos.autots.model.auto_tcn
.. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.autots.model.auto_tcn
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
AutoLSTM AutoLSTM
---------------------------------------- ----------------------------------------
AutoLSTM is an LSTM forecasting model with Auto tuning. AutoLSTM is an LSTM forecasting model with Auto tuning.
Other API follows its base class(BaseAutomodel).
.. automodule:: bigdl.chronos.autots.model.auto_lstm
.. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.autots.model.auto_lstm
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
AutoSeq2Seq AutoSeq2Seq
---------------------------------------- ----------------------------------------
AutoSeq2Seq is an Seq2Seq forecasting model with Auto tuning. AutoSeq2Seq is an Seq2Seq forecasting model with Auto tuning.
Other API follows its base class(BaseAutomodel).
.. automodule:: bigdl.chronos.autots.model.auto_seq2seq
.. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.autots.model.auto_seq2seq
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
AutoARIMA AutoARIMA
---------------------------------------- ----------------------------------------
@ -44,6 +61,8 @@ AutoARIMA is an ARIMA forecasting model with Auto tuning.
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
AutoProphet AutoProphet
---------------------------------------- ----------------------------------------
@ -54,11 +73,4 @@ AutoProphet is a Prophet forecasting model with Auto tuning.
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
BaseAutomodel
------------------------------------------------------------
AutoLSTM, AutoSeq2Seq and AutoTCN all follow the same API as stated below.
.. autoclass:: bigdl.chronos.autots.model.base_automodel.BaseAutomodel
:members:
:show-inheritance:

13
docs/readthedocs/source/doc/PythonAPI/Chronos/autotsestimator.rst
View file

@ -7,7 +7,11 @@ AutoTSEstimator
Automated TimeSeries Estimator for time series forecasting task. Automated TimeSeries Estimator for time series forecasting task.
AutoTSEstimator will replace AutoTSTrainer in later version. AutoTSEstimator will replace AutoTSTrainer in later version.
.. automodule:: bigdl.chronos.autots.autotsestimator .. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.autots.autotsestimator
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
@ -19,7 +23,12 @@ TSPipeline
TSPipeline is an E2E solution for time series forecasting task. TSPipeline is an E2E solution for time series forecasting task.
AutoTSEstimator will replace original TSPipeline returned by AutoTSTrainer in later version. AutoTSEstimator will replace original TSPipeline returned by AutoTSTrainer in later version.
.. automodule:: bigdl.chronos.autots.tspipeline
.. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.autots.tspipeline
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:

97
docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst
View file

@ -8,23 +8,27 @@ Long short-term memory(LSTM) is a special type of recurrent neural network(RNN).
For the detailed algorithm description, please refer to `here <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/Algorithm/LSTMAlgorithm.md>`__. For the detailed algorithm description, please refer to `here <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/Algorithm/LSTMAlgorithm.md>`__.
`version:pytorch`
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.lstm_forecaster .. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.forecaster.lstm_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
`version:tensorflow`
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`. .. tab:: Tensorflow
.. automodule:: bigdl.chronos.forecaster.tf.lstm_forecaster .. automodule:: bigdl.chronos.forecaster.tf.lstm_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
Seq2SeqForecaster Seq2SeqForecaster
@ -32,23 +36,23 @@ Seq2SeqForecaster
Seq2SeqForecaster wraps a sequence to sequence model based on LSTM, and is suitable for multivariant & multistep time series forecasting. Seq2SeqForecaster wraps a sequence to sequence model based on LSTM, and is suitable for multivariant & multistep time series forecasting.
`version:pytorch` .. tabs::
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`. .. tab:: PyTorch
.. automodule:: bigdl.chronos.forecaster.seq2seq_forecaster .. automodule:: bigdl.chronos.forecaster.seq2seq_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
`version:tensorflow` .. tab:: Tensorflow
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`. .. automodule:: bigdl.chronos.forecaster.tf.seq2seq_forecaster
.. automodule:: bigdl.chronos.forecaster.tf.seq2seq_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
TCNForecaster TCNForecaster
@ -56,49 +60,55 @@ TCNForecaster
Temporal Convolutional Networks (TCN) is a neural network that use convolutional architecture rather than recurrent networks. It supports multi-step and multi-variant cases. Causal Convolutions enables large scale parallel computing which makes TCN has less inference time than RNN based model such as LSTM. Temporal Convolutional Networks (TCN) is a neural network that use convolutional architecture rather than recurrent networks. It supports multi-step and multi-variant cases. Causal Convolutions enables large scale parallel computing which makes TCN has less inference time than RNN based model such as LSTM.
`version:pytorch` .. tabs::
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`. .. tab:: PyTorch
.. automodule:: bigdl.chronos.forecaster.tcn_forecaster .. automodule:: bigdl.chronos.forecaster.tcn_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
`version:tensorflow` .. tab:: Tensorflow
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`. .. automodule:: bigdl.chronos.forecaster.tf.tcn_forecaster
.. automodule:: bigdl.chronos.forecaster.tf.tcn_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
AutoformerForecaster AutoformerForecaster
---------------------------------------- ----------------------------------------
Autoformer is a neural network that use transformer architecture with autocorrelation. It supports multi-step and multi-variant cases. It shows significant accuracy improvement while longer training/inference time than TCN. Autoformer is a neural network that use transformer architecture with autocorrelation. It supports multi-step and multi-variant cases. It shows significant accuracy improvement while longer training/inference time than TCN.
`version:pytorch` .. tabs::
.. automodule:: bigdl.chronos.forecaster.autoformer_forecaster .. tab:: PyTorch
.. automodule:: bigdl.chronos.forecaster.autoformer_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
NBeatsForecaster NBeatsForecaster
---------------------------------------- ----------------------------------------
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
Neural basis expansion analysis for interpretable time series forecasting (`N-BEATS <https://arxiv.org/abs/1905.10437>`__) is a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. Nbeats can solve univariate time series point forecasting problems, being interpretable, and fast to train. .. tabs::
.. automodule:: bigdl.chronos.forecaster.nbeats_forecaster .. tab:: PyTorch
Neural basis expansion analysis for interpretable time series forecasting (`N-BEATS <https://arxiv.org/abs/1905.10437>`__) is a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. Nbeats can solve univariate time series point forecasting problems, being interpretable, and fast to train.
.. automodule:: bigdl.chronos.forecaster.nbeats_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
TCMFForecaster TCMFForecaster
@ -116,10 +126,16 @@ TCMFForecaster supports distributed training and inference. It is based on Orca
* You can refer to `TCMFForecaster installation <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/tutorials/TCMFForecaster.md#step-0-prepare-environment>`__ to install required packages. * You can refer to `TCMFForecaster installation <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/tutorials/TCMFForecaster.md#step-0-prepare-environment>`__ to install required packages.
* Your operating system (OS) is required to be one of the following 64-bit systems: **Ubuntu 16.04 or later** and **macOS 10.12.6 or later**. * Your operating system (OS) is required to be one of the following 64-bit systems: **Ubuntu 16.04 or later** and **macOS 10.12.6 or later**.
.. automodule:: bigdl.chronos.forecaster.tcmf_forecaster .. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.forecaster.tcmf_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
MTNetForecaster MTNetForecaster
---------------------------------------- ----------------------------------------
@ -130,10 +146,15 @@ MTNet is proposed by paper `A Memory-Network Based Solution for Multivariate Tim
For the detailed algorithm description, please refer to `here <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/Algorithm/MTNetAlgorithm.md>`__. For the detailed algorithm description, please refer to `here <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/Algorithm/MTNetAlgorithm.md>`__.
.. automodule:: bigdl.chronos.forecaster.tf.mtnet_forecaster .. tabs::
.. tab:: Tensorflow
.. automodule:: bigdl.chronos.forecaster.tf.mtnet_forecaster
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
ARIMAForecaster ARIMAForecaster
@ -145,7 +166,7 @@ AutoRegressive Integrated Moving Average (ARIMA) is a class of statistical model
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
ProphetForecaster ProphetForecaster
---------------------------------------- ----------------------------------------
@ -158,20 +179,4 @@ For the detailed algorithm description, please refer to `here <https://github.co
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance:
:inherited-members:
BasePytorchForecaster
----------------------------------------
.. autoclass:: bigdl.chronos.forecaster.base_forecaster.BasePytorchForecaster
:members:
:show-inheritance:
BaseTF2Forecaster
----------------------------------------
.. automodule:: bigdl.chronos.forecaster.tf.base_forecaster
:members:
:undoc-members:
:show-inheritance:

7
docs/readthedocs/source/doc/PythonAPI/Chronos/simulator.rst
View file

@ -4,7 +4,12 @@ Simulator
DPGANSimulator DPGANSimulator
------------------------------------ ------------------------------------
.. automodule:: bigdl.chronos.simulator.doppelganger_simulator
.. tabs::
.. tab:: PyTorch
.. automodule:: bigdl.chronos.simulator.doppelganger_simulator
:members: :members:
:undoc-members: :undoc-members:
:show-inheritance: :show-inheritance: