From 3465e9f1ddafb60d182fe0b9e18e5a9f03ba694d Mon Sep 17 00:00:00 2001 From: Eljas Roellin Date: Thu, 15 Aug 2024 13:53:50 +0200 Subject: [PATCH 1/3] tsdb.load_dataset to tsdb.load --- pypots/data/load_specific_datasets.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pypots/data/load_specific_datasets.py b/pypots/data/load_specific_datasets.py index 69e79615..50c6c297 100644 --- a/pypots/data/load_specific_datasets.py +++ b/pypots/data/load_specific_datasets.py @@ -35,7 +35,7 @@ def list_supported_datasets() -> list: def load_specific_dataset(dataset_name: str, use_cache: bool = True) -> dict: """Load specific datasets supported by PyPOTS. - Different from tsdb.load_dataset(), which only produces merely raw data, + Different from tsdb.load(), which only produces merely raw data, load_specific_dataset here does some preprocessing operations, like truncating time series to generate samples with the same length. @@ -45,7 +45,7 @@ def load_specific_dataset(dataset_name: str, use_cache: bool = True) -> dict: The name of the dataset to be loaded, which should be supported, i.e. in SUPPORTED_DATASETS. use_cache : - Whether to use cache. This is an argument of tsdb.load_dataset(). + Whether to use cache. This is an argument of tsdb.load(). Returns ------- From ec508a6700a3b7735e5f0678001b28066aa8ca49 Mon Sep 17 00:00:00 2001 From: Eljas Roellin <65244425+eroell@users.noreply.github.com> Date: Thu, 22 Aug 2024 08:07:48 +0200 Subject: [PATCH 2/3] Doc update Quickstart Example (#497) * update example snippet --- docs/examples.rst | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/docs/examples.rst b/docs/examples.rst index d7d6a1e2..5101eba8 100644 --- a/docs/examples.rst +++ b/docs/examples.rst @@ -29,15 +29,13 @@ You can also find a simple and quick-start tutorial notebook on Google Colab # Data preprocessing. Tedious, but PyPOTS can help. 🤓 data = load_specific_dataset('physionet_2012') # PyPOTS will automatically download and extract it. - X = data['X'] - num_samples = len(X['RecordID'].unique()) - X = X.drop(['RecordID', 'Time'], axis = 1) - X = StandardScaler().fit_transform(X.to_numpy()) - X = X.reshape(num_samples, 48, -1) + X = data['train_X'] + num_samples = len(X) + X = StandardScaler().fit_transform(X.reshape(-1, X.shape[-1])).reshape(X.shape) X_ori = X # keep X_ori for validation X = mcar(X, 0.1) # randomly hold out 10% observed values as ground truth dataset = {"X": X} # X for model input - print(X.shape) # (11988, 48, 37), 11988 samples, 48 time steps, 37 features + print(X.shape) # (7671, 48, 37), 7671 samples, 48 time steps, 37 features # initialize the model saits = SAITS( @@ -55,7 +53,7 @@ You can also find a simple and quick-start tutorial notebook on Google Colab model_saving_strategy="best", # only save the model with the best validation performance ) - # train the model. Here I use the whole dataset as the training set, because ground truth is not visible to the model. + # train the model. Here I consider the train dataset only, and evaluate on it, because ground truth is not visible to the model. saits.fit(dataset) # impute the originally-missing values and artificially-missing values imputation = saits.impute(dataset) @@ -64,6 +62,6 @@ You can also find a simple and quick-start tutorial notebook on Google Colab mae = calc_mae(imputation, np.nan_to_num(X_ori), indicating_mask) # calculate mean absolute error on the ground truth (artificially-missing values) # the best model has been already saved, but you can still manually save it with function save_model() as below - saits.save_model(saving_dir="examples/saits",file_name="manually_saved_saits_model") + saits.save(saving_path="examples/saits/manually_saved_saits_model") # you can load the saved model into a new initialized model - saits.load_model("examples/saits/manually_saved_saits_model") + saits.load("examples/saits/manually_saved_saits_model.pypots") From dd8c553b3ce0d27423854d60668c5bbb1026c7f3 Mon Sep 17 00:00:00 2001 From: Wenjie Du Date: Fri, 30 Aug 2024 01:08:42 +0800 Subject: [PATCH 3/3] Update docs (#498) * docs: update readme files; --- README.md | 83 ++++++++++++++++++++++++++-------------------------- README_zh.md | 83 ++++++++++++++++++++++++++-------------------------- 2 files changed, 84 insertions(+), 82 deletions(-) diff --git a/README.md b/README.md index fb77cedd..c11fe903 100644 --- a/README.md +++ b/README.md @@ -113,47 +113,47 @@ The task types are abbreviated as follows: **`ANOD`**: Anomaly Detection. The paper references and links are all listed at the bottom of this file. -| **Type** | **Algo** | **IMPU** | **FORE** | **CLAS** | **CLUS** | **ANOD** | **Year - Venue** | -|:--------------|:----------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:-------------------| -| LLM | Gungnir 🚀 [^36] | ✅ | ✅ | ✅ | ✅ | ✅ | `Later in 2024` | -| Neural Net | ImputeFormer🧑‍🔧[^34] | ✅ | | | | | `2024 - KDD` | -| Neural Net | iTransformer🧑‍🔧[^24] | ✅ | | | | | `2024 - ICLR` | -| Neural Net | SAITS[^1] | ✅ | | | | | `2023 - ESWA` | -| Neural Net | FreTS🧑‍🔧[^23] | ✅ | | | | | `2023 - NeurIPS` | -| Neural Net | Koopa🧑‍🔧[^29] | ✅ | | | | | `2023 - NeurIPS` | -| Neural Net | Crossformer🧑‍🔧[^16] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | TimesNet[^14] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | PatchTST🧑‍🔧[^18] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | ETSformer🧑‍🔧[^19] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | MICN🧑‍🔧[^27] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | DLinear🧑‍🔧[^17] | ✅ | | | | | `2023 - AAAI` | -| Neural Net | TiDE🧑‍🔧[^28] | ✅ | | | | | `2023 - TMLR` | -| Neural Net | SCINet🧑‍🔧[^30] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | Nonstationary Tr.🧑‍🔧[^25] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | FiLM🧑‍🔧[^22] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | RevIN_SCINet🧑‍🔧[^31] | ✅ | | | | | `2022 - ICLR` | -| Neural Net | Pyraformer🧑‍🔧[^26] | ✅ | | | | | `2022 - ICLR` | -| Neural Net | Raindrop[^5] | | | ✅ | | | `2022 - ICLR` | -| Neural Net | FEDformer🧑‍🔧[^20] | ✅ | | | | | `2022 - ICML` | -| Neural Net | Autoformer🧑‍🔧[^15] | ✅ | | | | | `2021 - NeurIPS` | -| Neural Net | CSDI[^12] | ✅ | ✅ | | | | `2021 - NeurIPS` | -| Neural Net | Informer🧑‍🔧[^21] | ✅ | | | | | `2021 - AAAI` | -| Neural Net | US-GAN[^10] | ✅ | | | | | `2021 - AAAI` | -| Neural Net | CRLI[^6] | | | | ✅ | | `2021 - AAAI` | -| Probabilistic | BTTF[^8] | | ✅ | | | | `2021 - TPAMI` | -| Neural Net | StemGNN🧑‍🔧[^33] | ✅ | | | | | `2020 - NeurIPS` | -| Neural Net | Reformer🧑‍🔧[^32] | ✅ | | | | | `2020 - ICLR` | -| Neural Net | GP-VAE[^11] | ✅ | | | | | `2020 - AISTATS` | -| Neural Net | VaDER[^7] | | | | ✅ | | `2019 - GigaSci.` | -| Neural Net | M-RNN[^9] | ✅ | | | | | `2019 - TBME` | -| Neural Net | BRITS[^3] | ✅ | | ✅ | | | `2018 - NeurIPS` | -| Neural Net | GRU-D[^4] | ✅ | | ✅ | | | `2018 - Sci. Rep.` | -| Neural Net | TCN🧑‍🔧[^35] | ✅ | | | | | `2018 - arXiv` | -| Neural Net | Transformer🧑‍🔧[^2] | ✅ | | | | | `2017 - NeurIPS` | -| Naive | Lerp | ✅ | | | | | | -| Naive | LOCF/NOCB | ✅ | | | | | | -| Naive | Mean | ✅ | | | | | | -| Naive | Median | ✅ | | | | | | +| **Type** | **Algo** | **IMPU** | **FORE** | **CLAS** | **CLUS** | **ANOD** | **Year - Venue** | +|:--------------|:---------------------------------------------------------------------------------------------------------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:-------------------| +| LLM | Time-Series.AI [^36] | ✅ | ✅ | ✅ | ✅ | ✅ | `Later in 2024` | +| Neural Net | ImputeFormer🧑‍🔧[^34] | ✅ | | | | | `2024 - KDD` | +| Neural Net | iTransformer🧑‍🔧[^24] | ✅ | | | | | `2024 - ICLR` | +| Neural Net | SAITS[^1] | ✅ | | | | | `2023 - ESWA` | +| Neural Net | FreTS🧑‍🔧[^23] | ✅ | | | | | `2023 - NeurIPS` | +| Neural Net | Koopa🧑‍🔧[^29] | ✅ | | | | | `2023 - NeurIPS` | +| Neural Net | Crossformer🧑‍🔧[^16] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | TimesNet[^14] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | PatchTST🧑‍🔧[^18] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | ETSformer🧑‍🔧[^19] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | MICN🧑‍🔧[^27] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | DLinear🧑‍🔧[^17] | ✅ | | | | | `2023 - AAAI` | +| Neural Net | TiDE🧑‍🔧[^28] | ✅ | | | | | `2023 - TMLR` | +| Neural Net | SCINet🧑‍🔧[^30] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | Nonstationary Tr.🧑‍🔧[^25] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | FiLM🧑‍🔧[^22] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | RevIN_SCINet🧑‍🔧[^31] | ✅ | | | | | `2022 - ICLR` | +| Neural Net | Pyraformer🧑‍🔧[^26] | ✅ | | | | | `2022 - ICLR` | +| Neural Net | Raindrop[^5] | | | ✅ | | | `2022 - ICLR` | +| Neural Net | FEDformer🧑‍🔧[^20] | ✅ | | | | | `2022 - ICML` | +| Neural Net | Autoformer🧑‍🔧[^15] | ✅ | | | | | `2021 - NeurIPS` | +| Neural Net | CSDI[^12] | ✅ | ✅ | | | | `2021 - NeurIPS` | +| Neural Net | Informer🧑‍🔧[^21] | ✅ | | | | | `2021 - AAAI` | +| Neural Net | US-GAN[^10] | ✅ | | | | | `2021 - AAAI` | +| Neural Net | CRLI[^6] | | | | ✅ | | `2021 - AAAI` | +| Probabilistic | BTTF[^8] | | ✅ | | | | `2021 - TPAMI` | +| Neural Net | StemGNN🧑‍🔧[^33] | ✅ | | | | | `2020 - NeurIPS` | +| Neural Net | Reformer🧑‍🔧[^32] | ✅ | | | | | `2020 - ICLR` | +| Neural Net | GP-VAE[^11] | ✅ | | | | | `2020 - AISTATS` | +| Neural Net | VaDER[^7] | | | | ✅ | | `2019 - GigaSci.` | +| Neural Net | M-RNN[^9] | ✅ | | | | | `2019 - TBME` | +| Neural Net | BRITS[^3] | ✅ | | ✅ | | | `2018 - NeurIPS` | +| Neural Net | GRU-D[^4] | ✅ | | ✅ | | | `2018 - Sci. Rep.` | +| Neural Net | TCN🧑‍🔧[^35] | ✅ | | | | | `2018 - arXiv` | +| Neural Net | Transformer🧑‍🔧[^2] | ✅ | | | | | `2017 - NeurIPS` | +| Naive | Lerp | ✅ | | | | | | +| Naive | LOCF/NOCB | ✅ | | | | | | +| Naive | Mean | ✅ | | | | | | +| Naive | Median | ✅ | | | | | | 💯 Contribute your model right now to increase your research impact! PyPOTS downloads are increasing rapidly (**[300K+ in total and 1K+ daily on PyPI so far](https://www.pepy.tech/projects/pypots)**), and your work will be widely used and cited by the community. @@ -394,3 +394,4 @@ PyPOTS community is open, transparent, and surely friendly. Let's work together [^35]: Bai, S., Kolter, J. Z., & Koltun, V. (2018). [An empirical evaluation of generic convolutional and recurrent networks for sequence modeling](https://arxiv.org/abs/1803.01271). *arXiv 2018*. [^36]: Project Gungnir, the world 1st LLM for time-series multitask modeling, will meet you soon. 🚀 Missing values and variable lengths in your datasets? Hard to perform multitask learning with your time series? Not problems no longer. We'll open application for public beta test recently ;-) Follow us, and stay tuned! + Time-Series.AI diff --git a/README_zh.md b/README_zh.md index b04dd28d..e0c6eb08 100644 --- a/README_zh.md +++ b/README_zh.md @@ -99,47 +99,47 @@ PyPOTS当前支持多变量POTS数据的插补，预测，分类，聚类以及 所以这些模型的输入中不能带有缺失值，无法接受POTS数据作为输入，更加不是插补算法。 **为了使上述模型能够适用于POTS数据，我们采用了与[SAITS论文](https://arxiv.org/pdf/2202.08516)[^1]中相同的embedding策略和训练方法（ORT+MIT）对它们进行改进**。 -| **类型** | **算法** | **插补** | **预测** | **分类** | **聚类** | **异常检测** | **年份 - 刊物** | -|:--------------|:----------------------------|:------:|:------:|:------:|:------:|:--------:|:-------------------| -| LLM | Gungnir 🚀 [^36] | ✅ | ✅ | ✅ | ✅ | ✅ | `Later in 2024` | -| Neural Net | ImputeFormer🧑‍🔧[^34] | ✅ | | | | | `2024 - KDD` | -| Neural Net | iTransformer🧑‍🔧[^24] | ✅ | | | | | `2024 - ICLR` | -| Neural Net | SAITS[^1] | ✅ | | | | | `2023 - ESWA` | -| Neural Net | FreTS🧑‍🔧[^23] | ✅ | | | | | `2023 - NeurIPS` | -| Neural Net | Koopa🧑‍🔧[^29] | ✅ | | | | | `2023 - NeurIPS` | -| Neural Net | Crossformer🧑‍🔧[^16] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | TimesNet[^14] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | PatchTST🧑‍🔧[^18] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | ETSformer🧑‍🔧[^19] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | MICN🧑‍🔧[^27] | ✅ | | | | | `2023 - ICLR` | -| Neural Net | DLinear🧑‍🔧[^17] | ✅ | | | | | `2023 - AAAI` | -| Neural Net | TiDE🧑‍🔧[^28] | ✅ | | | | | `2023 - TMLR` | -| Neural Net | SCINet🧑‍🔧[^30] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | Nonstationary Tr.🧑‍🔧[^25] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | FiLM🧑‍🔧[^22] | ✅ | | | | | `2022 - NeurIPS` | -| Neural Net | RevIN_SCINet🧑‍🔧[^31] | ✅ | | | | | `2022 - ICLR` | -| Neural Net | Pyraformer🧑‍🔧[^26] | ✅ | | | | | `2022 - ICLR` | -| Neural Net | Raindrop[^5] | | | ✅ | | | `2022 - ICLR` | -| Neural Net | FEDformer🧑‍🔧[^20] | ✅ | | | | | `2022 - ICML` | -| Neural Net | Autoformer🧑‍🔧[^15] | ✅ | | | | | `2021 - NeurIPS` | -| Neural Net | CSDI[^12] | ✅ | ✅ | | | | `2021 - NeurIPS` | -| Neural Net | Informer🧑‍🔧[^21] | ✅ | | | | | `2021 - AAAI` | -| Neural Net | US-GAN[^10] | ✅ | | | | | `2021 - AAAI` | -| Neural Net | CRLI[^6] | | | | ✅ | | `2021 - AAAI` | -| Probabilistic | BTTF[^8] | | ✅ | | | | `2021 - TPAMI` | -| Neural Net | StemGNN🧑‍🔧[^33] | ✅ | | | | | `2020 - NeurIPS` | -| Neural Net | Reformer🧑‍🔧[^32] | ✅ | | | | | `2020 - ICLR` | -| Neural Net | GP-VAE[^11] | ✅ | | | | | `2020 - AISTATS` | -| Neural Net | VaDER[^7] | | | | ✅ | | `2019 - GigaSci.` | -| Neural Net | M-RNN[^9] | ✅ | | | | | `2019 - TBME` | -| Neural Net | BRITS[^3] | ✅ | | ✅ | | | `2018 - NeurIPS` | -| Neural Net | GRU-D[^4] | ✅ | | ✅ | | | `2018 - Sci. Rep.` | -| Neural Net | TCN🧑‍🔧[^35] | ✅ | | | | | `2018 - arXiv` | -| Neural Net | Transformer🧑‍🔧[^2] | ✅ | | | | | `2017 - NeurIPS` | -| Naive | Lerp | ✅ | | | | | | -| Naive | LOCF/NOCB | ✅ | | | | | | -| Naive | Mean | ✅ | | | | | | -| Naive | Median | ✅ | | | | | | +| **类型** | **算法** | **插补** | **预测** | **分类** | **聚类** | **异常检测** | **年份 - 刊物** | +|:--------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------|:------:|:------:|:------:|:------:|:--------:|:-------------------| +| LLM | Time-Series.AI [^36] | ✅ | ✅ | ✅ | ✅ | ✅ | `Later in 2024` | +| Neural Net | ImputeFormer🧑‍🔧[^34] | ✅ | | | | | `2024 - KDD` | +| Neural Net | iTransformer🧑‍🔧[^24] | ✅ | | | | | `2024 - ICLR` | +| Neural Net | SAITS[^1] | ✅ | | | | | `2023 - ESWA` | +| Neural Net | FreTS🧑‍🔧[^23] | ✅ | | | | | `2023 - NeurIPS` | +| Neural Net | Koopa🧑‍🔧[^29] | ✅ | | | | | `2023 - NeurIPS` | +| Neural Net | Crossformer🧑‍🔧[^16] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | TimesNet[^14] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | PatchTST🧑‍🔧[^18] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | ETSformer🧑‍🔧[^19] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | MICN🧑‍🔧[^27] | ✅ | | | | | `2023 - ICLR` | +| Neural Net | DLinear🧑‍🔧[^17] | ✅ | | | | | `2023 - AAAI` | +| Neural Net | TiDE🧑‍🔧[^28] | ✅ | | | | | `2023 - TMLR` | +| Neural Net | SCINet🧑‍🔧[^30] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | Nonstationary Tr.🧑‍🔧[^25] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | FiLM🧑‍🔧[^22] | ✅ | | | | | `2022 - NeurIPS` | +| Neural Net | RevIN_SCINet🧑‍🔧[^31] | ✅ | | | | | `2022 - ICLR` | +| Neural Net | Pyraformer🧑‍🔧[^26] | ✅ | | | | | `2022 - ICLR` | +| Neural Net | Raindrop[^5] | | | ✅ | | | `2022 - ICLR` | +| Neural Net | FEDformer🧑‍🔧[^20] | ✅ | | | | | `2022 - ICML` | +| Neural Net | Autoformer🧑‍🔧[^15] | ✅ | | | | | `2021 - NeurIPS` | +| Neural Net | CSDI[^12] | ✅ | ✅ | | | | `2021 - NeurIPS` | +| Neural Net | Informer🧑‍🔧[^21] | ✅ | | | | | `2021 - AAAI` | +| Neural Net | US-GAN[^10] | ✅ | | | | | `2021 - AAAI` | +| Neural Net | CRLI[^6] | | | | ✅ | | `2021 - AAAI` | +| Probabilistic | BTTF[^8] | | ✅ | | | | `2021 - TPAMI` | +| Neural Net | StemGNN🧑‍🔧[^33] | ✅ | | | | | `2020 - NeurIPS` | +| Neural Net | Reformer🧑‍🔧[^32] | ✅ | | | | | `2020 - ICLR` | +| Neural Net | GP-VAE[^11] | ✅ | | | | | `2020 - AISTATS` | +| Neural Net | VaDER[^7] | | | | ✅ | | `2019 - GigaSci.` | +| Neural Net | M-RNN[^9] | ✅ | | | | | `2019 - TBME` | +| Neural Net | BRITS[^3] | ✅ | | ✅ | | | `2018 - NeurIPS` | +| Neural Net | GRU-D[^4] | ✅ | | ✅ | | | `2018 - Sci. Rep.` | +| Neural Net | TCN🧑‍🔧[^35] | ✅ | | | | | `2018 - arXiv` | +| Neural Net | Transformer🧑‍🔧[^2] | ✅ | | | | | `2017 - NeurIPS` | +| Naive | Lerp | ✅ | | | | | | +| Naive | LOCF/NOCB | ✅ | | | | | | +| Naive | Mean | ✅ | | | | | | +| Naive | Median | ✅ | | | | | | 💯 现在贡献你的模型来增加你的研究影响力！PyPOTS的下载量正在迅速增长(**[目前PyPI上总共超过30万次且每日超1000的下载](https://www.pepy.tech/projects/pypots)**), 你的工作将被社区广泛使用和引用。请参阅[贡献指南](https://github.com/WenjieDu/PyPOTS/blob/main/README_zh.md#-%E8%B4%A1%E7%8C%AE%E5%A3%B0%E6%98%8E)，了解如何将模型包含在PyPOTS中。 @@ -363,3 +363,4 @@ PyPOTS社区是一个开放、透明、友好的社区，让我们共同努力 [^34]: Nie, T., Qin, G., Mei, Y., & Sun, J. (2024). [ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation](https://arxiv.org/abs/2312.01728). *KDD 2024*. [^35]: Bai, S., Kolter, J. Z., & Koltun, V. (2018). [An empirical evaluation of generic convolutional and recurrent networks for sequence modeling](https://arxiv.org/abs/1803.01271). *arXiv 2018*. [^36]: Gungnir项目，世界上第一个时间序列多任务大模型，将很快与大家见面。🚀 数据集存在缺少值且样本长短不一？多任务建模场景困难？都不再是问题，让我们的大模型来帮你解决。我们将在近期开放公测申请 ;-) 关注我们，敬请期待! + Time-Series.AI