Alaska2

AlaskaEx1.csv

@@ -0,0 +1,3 @@
+file_path_raw_signals,file_path_preprocessed_signals,file_path_manual_state_annot_orig,file_path_manual_state_annotation,file_path_automated_state_annotation,file_path_refined_state_annotation,file_path_review_intervals,sampling_frequency_in_hz,ECG,BP,EEG,EOG,EMG,EMGamp,Resp,Tabd
+WorkPath\Bears11_Bear2\Bear20120112a-Bear2-HH.edf,WorkPath\Processed\Bear20120112a-Bear2-HH.npy,WorkPath\Scores\Bear20120112a-Bear2-HH_OT.edf,WorkPath\Scores\Bear20120112a-Bear2-HH_OT_adj.edf,WorkPath\Processed\Bear20120112a-Bear2-HH_annotation_predicted.edf,WorkPath\Processed\Bear20120112a-Bear2-HH_refined_annotation.csv,WorkPath\Processed\Bear20120112a-Bear2-HH_review_intervals.csv,500,ECG,BP,EEG,EOG,EMG,EMGamp,Resp,Tabd
+WorkPath\Bears11_Bear2\Bear20120203a-Bear2-HL.edf,WorkPath\Processed\Bear20120203a-Bear2-HL.npy,WorkPath\Scores\Bear20120203a-Bear2-HL_OT.edf,WorkPath\Scores\Bear20120203a-Bear2-HL_OT_adj.edf,WorkPath\Processed\Bear20120203a-Bear2-HL_annotation_predicted.edf,WorkPath\Processed\Bear20120203a-Bear2-HL_refined_annotation.csv,WorkPath\Processed\Bear20120203a-Bear2-HL_review_intervals.csv,500,ECG,BP,EEG,EOG,EMG,EMGamp,Resp,Tabd

example_pipeline/00_truncate_edf_annotations.py

@@ -15,6 +15,10 @@
 
 if __name__ == '__main__':
 
+    from configuration import (
+        time_resolution,
+    )
+
     # --------------------------------------------------------------------------------
     # parse and check inputs
 
@@ -34,10 +38,12 @@
     check_dataframe(datasets,
                     columns = [
                         'file_path_raw_signals',
+                        'file_path_manual_state_annot_orig',
                         'file_path_manual_state_annotation',
                     ],
                     column_to_dtype = {
                         'file_path_raw_signals' : str,
+                        'file_path_manual_state_annot_orig' : str,
                         'file_path_manual_state_annotation' : str,
                     }
     )
@@ -46,14 +52,19 @@
         datasets = datasets.loc[np.in1d(range(len(datasets)), args.only)]
 
     for ii, dataset in datasets.iterrows():
-        print("{} ({}/{})".format(dataset['file_path_manual_state_annotation'], ii+1, len(datasets)))
+        print("{} ({}/{})".format(dataset['file_path_manual_state_annot_orig'], ii+1, len(datasets)))
 
         file_path_raw_signals = dataset['file_path_raw_signals']
         with EdfReader(file_path_raw_signals) as f:
             total_time_in_seconds = f.file_duration
+        #truncate to whole number of epochs
+        total_time_in_seconds = time_resolution*(total_time_in_seconds // time_resolution) 
 
-        file_path_manual_state_annotation = dataset['file_path_manual_state_annotation']
-        states, intervals = _load_edf_hypnogram(file_path_manual_state_annotation)
+
+        file_path_manual_state_annot_orig = dataset['file_path_manual_state_annot_orig']
+
+
+        states, intervals = _load_edf_hypnogram(file_path_manual_state_annot_orig)
 
         start, stop = intervals[-1]
         while stop > total_time_in_seconds:
@@ -63,5 +74,9 @@
             elif (start < total_time_in_seconds) and (stop > total_time_in_seconds):
                 intervals[-1] = (start, total_time_in_seconds)
             start, stop = intervals[-1]
-
-        _export_edf_hypnogram(file_path_manual_state_annotation, states, intervals)
+
+        with EdfReader(file_path_manual_state_annot_orig) as f:
+            edf_header = f.getHeader()
+
+        file_path_manual_state_annotation = dataset['file_path_manual_state_annotation']       
+        _export_edf_hypnogram(file_path_manual_state_annotation, states, intervals, edf_header)

example_pipeline/02_test_state_annotation.py

@@ -152,15 +152,17 @@
 
             # LDA tranformed signals
             transformed_signals = annotator.transform(signal_arrays[ii])
-            plot_signals(transformed_signals, ax=axes[1])
+            plot_signals(transformed_signals, ax=axes[1], sampling_frequency=1/time_resolution)
             axes[1].set_ylabel("Transformed signals")
 
             predicted_state_vector = annotator.predict(signal_arrays[ii])
-            predicted_states, predicted_intervals = convert_state_vector_to_state_intervals(predicted_state_vector, mapping=int_to_state)
+            predicted_states, predicted_intervals = convert_state_vector_to_state_intervals(
+                predicted_state_vector, mapping=int_to_state, time_resolution=time_resolution)
             plot_states(predicted_states, predicted_intervals, ax=axes[2])
             axes[2].set_ylabel("Automated\nannotation")
 
-            states, intervals = convert_state_vector_to_state_intervals(state_vectors[ii], mapping=int_to_state)
+            states, intervals = convert_state_vector_to_state_intervals(
+                state_vectors[ii], mapping=int_to_state, time_resolution=time_resolution)
             plot_states(states, intervals, ax=axes[3])
             axes[3].set_ylabel("Manual\nannotation")
 

example_pipeline/04_run_state_annotation.py

@@ -11,6 +11,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
+from pyedflib import EdfReader, EdfWriter
 from somnotate._automated_state_annotation import StateAnnotator
 from somnotate._utils import (
     convert_state_vector_to_state_intervals,
@@ -89,11 +90,13 @@ def _get_score(vec):
     # check contents of spreadsheet
     check_dataframe(datasets,
                     columns = [
+                        'file_path_raw_signals',                   
                         'file_path_preprocessed_signals',
                         'file_path_automated_state_annotation',
                         'file_path_review_intervals',
                     ],
                     column_to_dtype = {
+                        'file_path_raw_signals' : str,             
                         'file_path_preprocessed_signals' : str,
                         'file_path_automated_state_annotation' : str,
                         'file_path_review_intervals' : str,
@@ -114,7 +117,11 @@ def _get_score(vec):
         predicted_state_vector = annotator.predict(signal_array)
         predicted_states, predicted_intervals = convert_state_vector_to_state_intervals(
             predicted_state_vector, mapping=int_to_state, time_resolution=time_resolution)
-        export_hypnogram(dataset['file_path_automated_state_annotation'], predicted_states, predicted_intervals)
+
+        with EdfReader(dataset['file_path_raw_signals']) as f:
+            edf_header = f.getHeader()
+
+        export_hypnogram(dataset['file_path_automated_state_annotation'], predicted_states, predicted_intervals, edf_header)
 
         # compute intervals for manual review
         state_probability = annotator.predict_proba(signal_array)

example_pipeline/configuration.py

@@ -153,7 +153,8 @@ def _chebychev_bandpass(lowcut, highcut, fs, rs, order=5):
     ('Sleep stage 1 (artefact)', -2),
     ('Sleep stage R'           ,  3),
     ('Sleep stage R (artefact)', -3),
-    ('undefined'               ,  0),
+    ('Sleep stage ?'           ,  0), # ? = Undefined/unscorable code in Polyman 
+    ('Movement Time'           ,  0), # Just included in case M code is accidentally added to avoid exception, cannot be deleted in Polyman
 ])
 
 # Construct the inverse mapping to convert back from state predictions to human readabe labels.
@@ -167,7 +168,7 @@ def _chebychev_bandpass(lowcut, highcut, fs, rs, order=5):
     'N' : 'Sleep stage 1 (artefact)',
     'r' : 'Sleep stage R'           ,
     'R' : 'Sleep stage R (artefact)',
-    'x' : 'undefined'               ,
+    'x' : 'Sleep stage ?'           ,  # ? = Undefined/unscorable code in Polyman
     'X' : 'undefined (artefact)'    ,
 }
 
@@ -179,7 +180,7 @@ def _chebychev_bandpass(lowcut, highcut, fs, rs, order=5):
     'Sleep stage 1 (artefact)' : 'cornflowerblue',
     'Sleep stage R'            : 'gold',
     'Sleep stage R (artefact)' : 'yellow',
-    'undefined'                : 'gray',
+    'Sleep stage ?'            : 'gray',       # ? = Undefined/unscorable code in Polyman
     'undefined (artefact)'     : 'lightgray',
 }
 
@@ -190,7 +191,7 @@ def _chebychev_bandpass(lowcut, highcut, fs, rs, order=5):
     'Sleep stage 1 (artefact)' ,
     'Sleep stage R'            ,
     'Sleep stage R (artefact)' ,
-    'undefined'                ,
+    'Sleep stage ?'            ,       # ? = Undefined/unscorable code in Polyman
     'undefined (artefact)'     ,
 ]
 
@@ -213,7 +214,7 @@ def _chebychev_bandpass(lowcut, highcut, fs, rs, order=5):
 # --------------------------------------------------------------------------------
 
 # desired time resolution of the automated annotation (in seconds)
-time_resolution = 1
+time_resolution = 10
 
 # default view length when manually annotating states
 default_view_length = 60.

example_pipeline/data_io.py

@@ -9,7 +9,12 @@
 import pandas
 
 from argparse import ArgumentParser
-from collections import Iterable
+try:
+    # Python <= 3.9
+    from collections import Iterable
+except ImportError:
+    # Python > 3.9
+    from collections.abc import Iterable
 from pyedflib import EdfReader, EdfWriter
 from six import ensure_str
 
@@ -338,7 +343,7 @@ def _load_edf_hypnogram(file_path):
     return states, intervals
 
 
-def _export_edf_hypnogram(file_path, states, intervals):
+def _export_edf_hypnogram(file_path, states, intervals, header=None):
     """Export hypnogram as "Time-stamped Annotations Lists (TALs)" in
     EDF annotations.
 
@@ -361,8 +366,10 @@ def _export_edf_hypnogram(file_path, states, intervals):
     with EdfWriter(file_path, 0) as writer:
         for (start, stop), state in zip(intervals, states):
             writer.writeAnnotation(start, stop-start, state)
+        if header:
+            writer.setHeader(header)  
         writer.close()
-
+        
 
 # --------------------------------------------------------------------------------
 # aliases