Merge pull request #6 from analysiscenter/release

New release 0.2.0

.gitignore

@@ -1,6 +1,5 @@
 *.pyc
-.cache/*
-__pycache__
-__pycache__/*
-*/__pycache__/*
-.ipynb_checkpoints
+docs/_build/
+.cache/
+__pycache__/
+.ipynb_checkpoints/

README.md

@@ -4,15 +4,16 @@
 
 Main features:
 
-* load and save signal in various formats (wfdb, blosc, etc)
+* load and save signal in various formats (wfdb, DICOM, EDF, etc)
 * resample, crop, flip and filter signals
 * detect PQ, QT, QRS segments
 * calculate heart rate and other ECG characteristics
-* apply complex transformations like fft and wavelets, as well as custom functions
+* perform complex processing like fourier and wavelet transformations
+* applpy custom functions to the data
 * recognize heart diseases (e.g. atrial fibrillation)
 * efficiently work with large datasets that do not even fit into memory
 * perform end-to-end ECG processing
-* build, train and test neural networks and other machine learning models.
+* build, train and test neural networks and other machine learning models
 
 For more details see [the documentation and tutorials](https://analysiscenter.github.io/cardio/).
 
@@ -22,45 +23,44 @@ For more details see [the documentation and tutorials](https://analysiscenter.gi
 > CardIO is based on [Dataset](https://github.com/analysiscenter/dataset). You might benefit from reading [its documentation](https://analysiscenter.github.io/dataset).
 However, it is not required, especially at the beginning.
 
-CardIO has three modules: [``batch``](https://analysiscenter.github.io/cardio/intro/batch.html),
-[``models``](https://analysiscenter.github.io/cardio/intro/models.html) and
-[``pipelines``](https://analysiscenter.github.io/cardio/intro/pipeline.html).
 
-``batch`` module contains ``EcgBatch`` class which defines how ECG are stored and includes actions for ECG processing.
-These actions might be used to build multi-staged workflows that can also involve machine learning models.
+CardIO has three modules: [``core``](https://analysiscenter.github.io/cardio/modules/core.html),
+[``models``](https://analysiscenter.github.io/cardio/modules/models.html) and
+[``pipelines``](https://analysiscenter.github.io/cardio/modules/pipelines.html).
+
+
+``core`` module contains ``EcgBatch`` and ``EcgDataset`` classes.
+``EcgBatch`` defines how ECGs are stored and includes actions for ECG processing. These actions might be used to build multi-staged workflows that can also involve machine learning models. ``EcgDataset`` is a class that stores indices of ECGs and generates batches of type ``EcgBatch``.
 
 ``models`` module provides several ready to use models for important problems in ECG analysis:
-* how to detect specific features of ECG like R-peaks, P-wave, T-wave, etc;
-* how to recognize heart diseases from ECG, for example, atrial fibrillation.
+
+* how to detect specific features of ECG like R-peaks, P-wave, T-wave, etc
+* how to recognize heart diseases from ECG, for example, atrial fibrillation
 
 ``pipelines`` module contains predefined workflows to
-* train a model to detect PQ, QT, QRS segments
-* calculate heart rate
-* train a model to find probabilities of heart diseases, in particular, atrial fibrillation.
 
-Under the hood these methods contain actions that load signals, filter it and do complex calculations.
+* train a model and perform an inference to detect PQ, QT, QRS segments and calculate heart rate
+* train a model and perform an inference to find probabilities of heart diseases, in particular, atrial fibrillation
 
 
 ## Basic usage
 
 Here is an example of pipeline that loads ECG signals, makes preprocessing and train a model over 50 epochs:
 ```python
 train_pipeline = (
-    dataset.train
-        .pipeline
-        .init_model("dynamic", DirichletModel, name="dirichlet",
-                    config=model_config)
-        .init_variable("loss_history", init=list)
-        .load(components=["signal", "meta"], fmt="wfdb")
-        .load(components="target", fmt="csv", src=LABELS_PATH)
-        .drop_labels(["~"])
-        .replace_labels({"N": "NO", "O": "NO"})
-        .flip_signals()
-        .random_resample_signals("normal", loc=300, scale=10)
-        .random_split_signals(2048, {"A": 9, "NO": 3})
-        .binarize_labels()
-        .train_model("dirichlet", make_data=make_data, fetches="loss", save_to=V("loss_history"), mode="a")
-        .run(batch_size=100, shuffle=True, drop_last=True, n_epochs=50)
+  ds.Pipeline()
+    .init_model("dynamic", DirichletModel, name="dirichlet", config=model_config)
+    .init_variable("loss_history", init_on_each_run=list)
+    .load(components=["signal", "meta"], fmt="wfdb")
+    .load(components="target", fmt="csv", src=LABELS_PATH)
+    .drop_labels(["~"])
+    .rename_labels({"N": "NO", "O": "NO"})
+    .flip_signals()
+    .random_resample_signals("normal", loc=300, scale=10)
+    .random_split_signals(2048, {"A": 9, "NO": 3})
+    .binarize_labels()
+    .train_model("dirichlet", make_data=concatenate_ecg_batch, fetches="loss", save_to=V("loss_history"), mode="a")
+    .run(batch_size=100, shuffle=True, drop_last=True, n_epochs=50)
 )
 ```
 
@@ -88,7 +88,7 @@ import cardio
 ```
 
 
-### Installation as a project repository:
+### Installation as a project repository
 
 When cloning repo from GitHub use flag ``--recursive`` to make sure that ``Dataset`` submodule is also cloned.
 

RELEASE.md

@@ -0,0 +1,50 @@
+# Release 0.2.0
+
+## Major Features and Improvements
+* `load` method now supports new signal formats:
+	* DICOM
+	* EDF
+	* wav
+* `meta` component structure has changed - now it always contains a number of predefined keys.
+* Added channels processing methods:
+	* `EcgBatch.keep_channels`
+	* `EcgBatch.drop_channels`
+	* `EcgBatch.rename_channels`
+* Added `apply_to_each_channel` method.
+* Added `standardize` method.
+* Added complex ECG transformations:
+	* Fourier-based transformations:
+		* `EcgBatch.fft`
+		* `EcgBatch.ifft`
+		* `EcgBatch.rfft`
+		* `EcgBatch.irfft`
+		* `EcgBatch.spectrogram`
+	* Wavelet-based transformations:
+		* `EcgBatch.dwt`
+		* `EcgBatch.idwt`
+		* `EcgBatch.wavedec`
+		* `EcgBatch.waverec`
+		* `EcgBatch.pdwt`
+		* `EcgBatch.cwt`
+
+## Breaking Changes to the API
+* Changed signature of the following methods:
+	* `EcgBatch.apply_transform`
+	* `EcgBatch.show_ecg`
+	* `EcgBatch.calc_ecg_parameters`
+* Changed signature of the following pipelines:
+	* `dirichlet_train_pipeline`
+	* `dirichlet_predict_pipeline`
+	* `hmm_preprocessing_pipeline`
+	* `hmm_train_pipeline`
+	* `hmm_predict_pipeline`
+* `wavelet_transform` method has been deleted.
+* `update` method has been deleted.
+* `replace_labels` method has been renamed to `rename_labels`.
+* `slice_signal` method has been renamed to `slice_signals`.
+* `ravel` method has been renamed to `unstack_signals`.
+
+
+# Release 0.1.0
+
+Initial release of CardIO.

cardio/__init__.py

@@ -1,8 +1,7 @@
-""" ECG package """
-import sys
+""" CardIO package """
 
-from .batch import *  # pylint: disable=wildcard-import
 from . import dataset  # pylint: disable=wildcard-import
+from .core import *  # pylint: disable=wildcard-import
 
 
-__version__ = '0.1.0'
+__version__ = '0.2.0'

cardio/core/__init__.py

@@ -0,0 +1,5 @@
+""" Core CardIO objects """
+
+from .ecg_batch import EcgBatch, add_actions
+from .ecg_dataset import EcgDataset
+from . import kernels