feat: add ncmapss (#49)

* chore: add h5py dependency

* feat: add N-C-MAPSS reader

* fix: linting issues

* fix: add missing feature selection

* docs: add documentation

README.md

@@ -7,11 +7,12 @@
 This library contains a collection of common benchmark datasets for **remaining useful lifetime (RUL)** estimation.
 They are provided as [LightningDataModules](https://pytorch-lightning.readthedocs.io/en/stable/api/pytorch_lightning.core.LightningDataModule.html#pytorch_lightning.core.LightningDataModule) to be readily used in [PyTorch Lightning](https://pytorch-lightning.readthedocs.io/en/latest/).
 
-Currently, four datasets are supported:
+Currently, five datasets are supported:
 
 * **C-MAPSS** Turbofan Degradation Dataset
 * **FEMTO** (PRONOSTIA) Bearing Dataset
 * **XJTU-SY** Bearing Dataset
+* **N-C-MAPSS** New Turbofan Degradation Dataset
 * **Dummy** A tiny, simple dataset for debugging
 
 All datasets share the same API, so they can be used as drop-in replacements for each other.

docs/index.md

@@ -3,11 +3,12 @@
 This library contains a collection of common benchmark datasets for **remaining useful lifetime (RUL)** estimation.
 They are provided as [LightningDataModules][lightning.pytorch.core.LightningDataModule] to be readily used in [PyTorch Lightning](https://pytorch-lightning.readthedocs.io/en/latest/).
 
-Currently, four datasets are supported:
+Currently, five datasets are supported:
 
 * **C-MAPSS** Turbofan Degradation Dataset
 * **FEMTO** (PRONOSTIA) Bearing Dataset
 * **XJTU-SY** Bearing Dataset
+* **N-C-MAPSS** New Turbofan Degradation Dataset
 * **Dummy** dataset for debugging
 
 All datasets share the same API, so they can be used as drop-in replacements for each other.

pyproject.toml

@@ -18,6 +18,7 @@ torch = "^1.9.0"
 pytorch-lightning = "^1.4.4"
 scikit-learn = "^1.0.0"
 tqdm = "^4.62.2"
+h5py = "^3.10.0"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["d"], version = "^22.8.0"}

rul_datasets/reader/__init__.py

@@ -3,13 +3,14 @@
 * **C-MAPSS** Turbofan Degradation Dataset
 * **FEMTO** (PRONOSTIA) Bearing Dataset
 * **XJTU-SY** Bearing Dataset
+* **N-C-MAPSS** New Turbofan Degradation Dataset
 
 Readers are the foundation of the RUL Datasets library. They provide access to the
 data on disk and convert them into a common format so that other parts of the library
 can interact with it. The common format is as follows:
 
 1. Each dataset consists of multiple sub-datasets. The indices of these sub-datasets
-are called `FD`, following CMAPSS convention.
+are called `FD`, following C-MAPSS convention.
 
 1. Each sub-dataset contains a development (`dev`), a validation (`val`) and test split
 (`test`).
@@ -18,7 +19,7 @@
 represent run-to-failure experiments.
 
 1. At each time step of a time series we have a window of features and a target RUL
-value. The target is the RUL value of the last time step of the window.
+value. The target is the RUL value of the window's last time step.
 
 A reader class, e.g. the [CmapssReader][rul_datasets.reader.cmapss.CmapssReader]
 represents a dataset and can manipulate it to your liking. A reader object has access
@@ -193,4 +194,5 @@
 from .cmapss import CmapssReader
 from .femto import FemtoReader, FemtoPreparator
 from .xjtu_sy import XjtuSyReader, XjtuSyPreparator
+from .ncmapss import NCmapssReader
 from .dummy import DummyReader

rul_datasets/reader/cmapss.py

@@ -1,4 +1,4 @@
-"""The NASA CMAPSS Turbofan Degradation dataset is a collection of simulated
+"""The NASA C-MAPSS Turbofan Degradation dataset is a collection of simulated
 degradation experiments on jet engines. It contains four sub-datasets named FD1, FD2,
 FD3 and FD4 which differ in operation conditions and possible failure types."""
 
@@ -97,7 +97,7 @@ def __init__(
         Ragab et al. This only affects FD002 and FD004 due to them having multiple
         operation conditions.
 
-        For more information about using readers refer to the [reader]
+        For more information about using readers, refer to the [reader]
         [rul_datasets.reader] module page.
 
         Args: