Skip to content

Commit 8062e5c

Browse files
kehuoa10210532AnnnnnnnnnnnnnQGN123LinWencong
authored
Merge 0.2.0 into main (#143)
* data adapter supports paddle 2.3.1 * update module from models.dl.paddlepaddle.* to models.forecasting.dl.* * Add some new functions and fix some bugs * Add some new functions and fix some bugs * Modify the detail of callbacks * Add some new functions and fix some bugs (#114) * thirdparty model integration. * Backtest feature upgrade * Modify the details of models (lstnet, mlp, tcn, transformer) * thirdparty transform integration * Add informer model * backtest unitest upgrade * remove paddlepaddle version check in paddle data adapter. * Add TS2Vec representaion model * fix __init__.py * Dataset splitter and Cross validation (#121) * Dataset splitter and Cross validation * Dataset splitter and Cross validation * Update logger.py (#122) * probability forecasting & deepar * probability forecasting & deepar * Pipeline recursive predict optimize (#125) * change version to 0.2.0 * representation dl data adapter. * Add unitest of informer and ts2vec * representation dl data adapter. (#128) * Add some necessary files * Add some necessary files * add AutoTS(autots、optimize_runner、search_space_configer、searcher） (#130) * Update logger.py * add AutoTS(autots、optimize_runner、search_space_configer、searcher） * setup autots * Update test_search_space_configer.py * fix bug in nhits (#131) * Update logger.py * add AutoTS(autots、optimize_runner、search_space_configer、searcher） * setup autots * Update test_search_space_configer.py * fix bug in nhits * paddlets 0.2.0 docs. * paddlets.__version__ == 0.2.0 * add autots docs. * update docker image in run_on_gpu.rst * sklearn<=1.0.2 * update index, add autots api docs. * add proba forecast docs. * add proba forecast docs. * update FFT.png in get_started.rst * add req/autots.txt into .readthedocs.yaml * supplement tsdataset api zh docs * supplement tsdataset api zh docs (#135) * add representation docs * add representation docs (#136) * supplement tsdataset api zh docs * add representation docs * modify docs utils.utils (#138) * update ml model warpper unittest. (#137) * fix doc bug (#139) * Update logger.py * add AutoTS(autots、optimize_runner、search_space_configer、searcher） * setup autots * Update test_search_space_configer.py * fix bug in nhits * fix doc bug * modify requirements * fix zh docs bug in repr * deadlink in model doc (#142) Co-authored-by: a10210532 <kolakingcs@163.com> Co-authored-by: Annnnnnnnnnnnn <894577770@qq.com> Co-authored-by: QGN123 <1359914325@qq.com> Co-authored-by: QGN123 <38217558+QGN123@users.noreply.github.com> Co-authored-by: LinWencong <503848070@qq.com> Co-authored-by: bianchuanxin <bianchuanxin@163.com>
1 parent 514e6d6 commit 8062e5c

File tree

283 files changed

+25659
-5853
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

283 files changed

+25659
-5853
lines changed

‎.readthedocs.yaml

+1
Original file line numberDiff line numberDiff line change
@@ -24,5 +24,6 @@ python:
2424
- requirements: requirements/core.txt
2525
- requirements: requirements/docs.txt
2626
- requirements: requirements/paddle.txt
27+
- requirements: requirements/autots.txt
2728

2829
system_packages: true

‎README_cn.md

+18-12
Original file line numberDiff line numberDiff line change
@@ -23,27 +23,33 @@ PaddleTS 是一个易用的深度时序建模的Python库，它基于飞桨深
2323
* 内置业界领先的深度学习模型，如NBEATS、NHiTS、LSTNet、TCN、Transformer等
2424
* 内置多样化的数据转换算子，支持数据处理与转换，包括缺失值填充、异常值处理、归一化、时间相关的协变量提取等
2525
* 内置经典的数据分析算子，帮助开发者便捷实现数据探索，包括数据统计量信息及数据摘要等功能
26+
* 自动超参寻优
27+
* 第三方机器学习模型及数据转换模块自动集成
28+
* 支持在GPU设备上运行基于PaddlePaddle的时序模型
29+
* 新增DeepAR模型，支持时序概率预测
30+
* 新增TS2Vec模型，支持时序表征学习
2631

2732
未来，更多的高级特性会进一步发布，包括但不限于：
28-
* 自动超参寻优
29-
* 时序表征模型
30-
* 概率预测模型
33+
* 支持时序异常检测
34+
* 更多时序表征模型
35+
* 更多概率预测模型
3136
* 场景化Pipeline，支持端到端真实场景解决方案
3237

3338

3439
## 关于 PaddleTS
3540

3641
具体来说，PaddleTS 时序库包含以下子模块：
3742

38-
| 模块 | 简述 |
39-
|---------------------------------------------------------------------------------------------------------------|-------------------------------------------------|
40-
| [**paddlets.datasets**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/datasets/overview.html) | 时序数据模块，统一的时序数据结构和预定义的数据处理方法 |
41-
| [**paddlets.transform**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/transform/overview.html) | 数据转换模块，提供数据预处理和特征工程相关能力 |
42-
| [**paddlets.models**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/models/overview.html) | 时序模型模块，基于飞桨深度学习框架PaddlePaddle的时序模型 |
43-
| [**paddlets.pipeline**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/pipeline/overview.html) | 建模任务流模块，支持特征工程、模型训练、模型评估的任务流实现 |
44-
| [**paddlets.metrics**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/metrics/overview.html) | 效果评估模块，提供多维度模型评估能力 |
45-
| [**paddlets.analysis**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/analysis/overview.html) | 数据分析模块，提供高效的时序特色数据分析能力 |
46-
| [**paddlets.utils**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/backtest/overview.html) | 工具集模块，提供回测等基础功能 |
43+
| 模块 | 简述 |
44+
|---------------------------------------------------------------------------------------------------------------|------------------------------------|
45+
| [**paddlets.datasets**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/datasets/overview.html) | 时序数据模块，统一的时序数据结构和预定义的数据处理方法 |
46+
| [**paddlets.autots**](https://paddlets.readthedocs.io/en/latest/source/modules/autots/overview.html) | 自动超参寻优 |
47+
| [**paddlets.transform**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/transform/overview.html) | 数据转换模块，提供数据预处理和特征工程相关能力 |
48+
| [**paddlets.models**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/models/overview.html) | 时序模型模块，基于飞桨深度学习框架PaddlePaddle的时序模型 |
49+
| [**paddlets.pipeline**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/pipeline/overview.html) | 建模任务流模块，支持特征工程、模型训练、模型评估的任务流实现 |
50+
| [**paddlets.metrics**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/metrics/overview.html) | 效果评估模块，提供多维度模型评估能力 |
51+
| [**paddlets.analysis**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/analysis/overview.html) | 数据分析模块，提供高效的时序特色数据分析能力 |
52+
| [**paddlets.utils**](https://paddlets.readthedocs.io/zh_CN/latest/source/modules/backtest/overview.html) | 工具集模块，提供回测等基础功能 |
4753

4854

4955
## 安装

‎README_en.md

+9-3
Original file line numberDiff line numberDiff line change
@@ -35,12 +35,17 @@ PaddleTS is an easy to use Python library for deep time series modeling,
3535
* A set of transformation operators for data preprocessing (e.g. missing values/outliers handling,
3636
one-hot encoding, normalization, and automatic date/time-related covariate generation, etc.);
3737
* A set of analysis operators for quick data exploration (e.g. basic statistics and summary).
38+
* Automatic hyper-parameter tuning;
39+
* Third-party ML models & data transformations integration (e.g. scikit-learn).
40+
* Run models on GPU devices;
41+
* TS2Vec, a time series representation learning model;
42+
* DeepAR, a deep time series model for probabilistic forecasting.
3843

3944
In future, more advanced features will be coming, including:
4045

41-
* Automatic hyper-parameter tuning;
42-
* Time series representation learning models；
43-
* Add support for probabilistic forecasting;
46+
* Time series anomaly detection;
47+
* More time series representation learning models;
48+
* More probabilistic forecasting models;
4449
* Scenario-specific pipelines which aim to provide an end-to-end solution for solving real-world business problems;
4550
* And more.
4651

@@ -53,6 +58,7 @@ Specifically, PaddleTS consists of the following modules:
5358
| Module | Description |
5459
|------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------|
5560
| [**paddlets.datasets**](https://paddlets.readthedocs.io/en/latest/source/modules/datasets/overview.html) | Unified time series representation (TSDataset) and data repository with pre-built TSDatasets. |
61+
| [**paddlets.autots**](https://paddlets.readthedocs.io/en/latest/source/modules/autots/overview.html) | Automatic hyper-parameter tuning. |
5662
| [**paddlets.transform**](https://paddlets.readthedocs.io/en/latest/source/modules/transform/overview.html) | Data preprocessing and data transformations. |
5763
| [**paddlets.models**](https://paddlets.readthedocs.io/en/latest/source/modules/models/overview.html) | PaddlePaddle-based deep neural network models for time series modeling. |
5864
| [**paddlets.pipeline**](https://paddlets.readthedocs.io/en/latest/source/modules/pipeline/overview.html) | Pipeline for building time series analysis and modeling workflows. |

‎docs/conf.py

+10-2
Original file line numberDiff line numberDiff line change
@@ -40,9 +40,9 @@
4040

4141
# Localization of Documentation.
4242
# https://docs.readthedocs.io/en/stable/localization.html
43-
locale_dirs = ['locale/']
43+
locale_dirs = ["locale/"]
4444
gettext_compact = False
45-
language = 'en'
45+
language = "en"
4646
add_module_names = False
4747
gettext_uuid = True
4848

@@ -56,5 +56,13 @@
5656
# -- Options for EPUB output
5757
# epub_show_urls = "footnote"
5858

59+
html_theme_options = {
60+
# "collapse_navigation": True,
61+
"display_version": True,
62+
# "navigation_depth": 5,
63+
# "navigation_with_keys": True,
64+
"body_max_width": "80%"
65+
}
66+
5967
# Html logo in drawer.
6068
html_logo = "static/images/logo/paddlets-rtd-logo.png"

‎docs/index.rst

+27-4
Original file line numberDiff line numberDiff line change
@@ -16,11 +16,21 @@ and excellent user experiences for practitioners and professionals. It’s featu
1616

1717
* A set of analysis operators for quick data exploration (e.g. basic statistics and summary).
1818

19+
* Automatic hyper-parameter tuning.
20+
21+
* Third-party ML models & data transformations integration (e.g., scikit-learn).
22+
23+
* Run models on GPU devices.
24+
25+
* TS2Vec, a time series representation learning model.
26+
27+
* DeepAR, a deep time series model for probabilistic forecasting.
28+
1929
In future, more advanced features will be coming, including:
2030

21-
* Automatic hyper-parameter tuning;
22-
* Time series representation learning models；
23-
* Add support for probabilistic forecasting;
31+
* Time series anomaly detection;
32+
* More time series representation learning models；
33+
* More probabilistic forecasting models;
2434
* Scenario-specific pipelines which aim to provide an end-to-end solution for solving real-world business problems;
2535
* And more.
2636

@@ -33,6 +43,7 @@ Project GitHub: https://github.com/PaddlePaddle/PaddleTS
3343
:caption: Get Started
3444

3545
Get Started <source/get_started/get_started.rst>
46+
Run On GPU <source/get_started/run_on_gpu.rst>
3647

3748
.. toctree::
3849
:maxdepth: 1
@@ -52,12 +63,16 @@ Project GitHub: https://github.com/PaddlePaddle/PaddleTS
5263
:caption: Transform
5364

5465
Transform <source/modules/transform/overview.md>
66+
Third-Party And User-Define Transform <source/modules/transform/thirdparty_userdefine.rst>
5567

5668
.. toctree::
5769
:maxdepth: 1
5870
:caption: Models
5971

60-
Models <source/modules/models/overview.md>
72+
Overview <source/modules/models/overview.rst>
73+
Third-party Model <source/modules/models/thirdparty.rst>
74+
Probability Forecasting <source/modules/models/probability_forecasting.rst>
75+
Representation <source/modules/models/representation.rst>
6176

6277

6378
.. toctree::
@@ -85,14 +100,22 @@ Project GitHub: https://github.com/PaddlePaddle/PaddleTS
85100

86101
Backtest <source/modules/backtest/overview.md>
87102

103+
.. toctree::
104+
:maxdepth: 1
105+
:caption: AutoTS
106+
107+
AutoTS <source/modules/autots/overview.rst>
108+
88109
.. toctree::
89110
:maxdepth: 1
90111
:caption: API
91112

92113
paddlets.analysis <source/api/paddlets.analysis.rst>
114+
paddlets.automl <source/api/paddlets.automl.rst>
93115
paddlets.datasets <source/api/paddlets.datasets.rst>
94116
paddlets.metrics <source/api/paddlets.metrics.rst>
95117
paddlets.models <source/api/paddlets.models.rst>
96118
paddlets.pipeline <source/api/paddlets.pipeline.rst>
97119
paddlets.transform <source/api/paddlets.transform.rst>
98120
paddlets.utils <source/api/paddlets.utils.rst>
121+

0 commit comments

Comments
 (0)