Add WatchSleepNet model with synthetic example and unit tests

docs/api/datasets/pyhealth.datasets.DREAMTDataset.rst

@@ -1,21 +1,24 @@
 pyhealth.datasets.DREAMTDataset
 ===================================
 
-The Dataset for Real-time sleep stage EstimAtion using Multisensor wearable Technology (DREAMT) includes wrist-based wearable and polysomnography (PSG) sleep data from 100 participants recruited from the Duke University Health System (DUHS) Sleep Disorder Lab. 
+The Dataset for Real-time sleep stage EstimAtion using Multisensor wearable
+Technology (DREAMT) includes wrist-based wearable and polysomnography (PSG)
+sleep data from 100 participants recruited from the Duke University Health
+System (DUHS) Sleep Disorder Lab.
 
-This includes wearable signals, PSG signals, sleep labels, and clinical data related to sleep health and disorders.
+This includes wearable signals, PSG signals, sleep labels, and clinical data
+related to sleep health and disorders.
 
-The DREAMTDataset class provides an interface for loading and working with the DREAMT dataset. It can process DREAMT data across versions into a well-structured dataset object providing support for modeling and analysis.
+``DREAMTDataset`` supports both official DREAMT release layouts and partial
+local subsets. It builds metadata linking each patient to locally available
+signal files and exposes data for both the simplified
+``SleepStagingDREAMT`` window-classification task and the more sequence-style
+``SleepStagingDREAMTSeq`` task.
 
-Refer to the `doc <https://physionet.org/content/dreamt/>`_ for more information about the dataset.
+Refer to the `doc <https://physionet.org/content/dreamt/>`_ for more
+information about the dataset.
 
 .. autoclass:: pyhealth.datasets.DREAMTDataset
     :members:
     :undoc-members:
     :show-inheritance:
-
-
-
-
-
-

docs/api/models.rst

@@ -190,6 +190,7 @@ API Reference
     models/pyhealth.models.SparcNet
     models/pyhealth.models.StageNet
     models/pyhealth.models.StageAttentionNet
+    models/pyhealth.models.WatchSleepNet
     models/pyhealth.models.AdaCare
     models/pyhealth.models.ConCare
     models/pyhealth.models.Agent

docs/api/models/pyhealth.models.WatchSleepNet.rst

@@ -0,0 +1,14 @@
+pyhealth.models.WatchSleepNet
+===================================
+
+Simplified WatchSleepNet-style architecture for wearable sleep staging.
+
+The implementation supports both:
+
+- pooled classification over fixed windows
+- sequence-output classification for epoch-level sleep staging
+
+.. autoclass:: pyhealth.models.WatchSleepNet
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/tasks/pyhealth.tasks.sleep_staging.rst

@@ -1,6 +1,19 @@
 pyhealth.tasks.sleep_staging
 =======================================
 
+``SleepStagingDREAMT`` provides a simplified window-classification task, while
+``SleepStagingDREAMTSeq`` provides a more paper-aligned sequence-style task.
+
+.. autoclass:: pyhealth.tasks.SleepStagingDREAMT
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.tasks.SleepStagingDREAMTSeq
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
 .. autofunction:: pyhealth.tasks.sleep_staging.sleep_staging_isruc_fn
 .. autofunction:: pyhealth.tasks.sleep_staging.sleep_staging_sleepedf_fn
-.. autofunction:: pyhealth.tasks.sleep_staging.sleep_staging_shhs_fn
+.. autofunction:: pyhealth.tasks.sleep_staging.sleep_staging_shhs_fn