ECG Preprocessing is working correctly now... using neurokit2

docs/dev_requirements.txt

@@ -24,3 +24,4 @@ mne-icalabel
 scipy
 tensorflow
 tensorflow-addons
+neurokit2
\ No newline at end of file

src/hrvmeg/main.py

@@ -175,11 +175,11 @@ def preprocess_ecgs(
     for file in ecg_to_proc:
         fp = Path(file)
         output_folder = Path(config.INTERMEDIATE_DIR, fp.parent.name)
-        output_file = Path(output_folder, "clean_ecg.csv")
-        
+        clean_output_file = Path(output_folder, "clean_ecg.csv")
+
         Path(output_folder).mkdir(parents=True, exist_ok=True)
-        data_to_write= preprocess_ecg.preproc_ecg(fp, fs, args["downsample_freq"],output_folder)
-        np.savetxt(output_file, data_to_write, delimiter=',')
+        data_to_write = preprocess_ecg.preproc_ecg(fp, fs, args["downsample_freq"],output_folder)
+        np.savetxt(clean_output_file, data_to_write, delimiter=',')
 
 
 @app.command()

src/hrvmeg/plotter.py

 from pathlib import Path
-
+import neurokit2 as nk
 import matplotlib.pyplot as plt
 import mpld3
 
-def make_html(fig):
+def make_html(fig, output_file):
     # save figure as HTML file
     html_str = mpld3.fig_to_html(fig)
-    output_html = self._output_file.rename(self._output_file.with_suffix(".html"))
+    output_html = Path(output_file).rename(output_file.with_suffix(".html"))
     HTML_file = open(output_html, "w", encoding="utf8")
     HTML_file.write(html_str)
     HTML_file.close()
-
-
+    
 def plot_signals_comp(meg_values, ecg_values, output_file):
     fig, ax = plt.subplot(211)
     
@@ -21,9 +20,7 @@ def plot_signals_comp(meg_values, ecg_values, output_file):
     ax.ylabel("Cardiac Component")
     ax.title("Selected Cardiac Component")
     fig.savefig(Path(output_file), dpi=330)
-
-    # output_html = super().make_html(plt.gcf())
-    
+   
     fig.subplot(212)
     print('Plotting ECG...')
     fig.plot(ecg_values.iloc[:,0],ecg_values.iloc[:,1], linewidth=0.2)
@@ -33,18 +30,22 @@ def plot_signals_comp(meg_values, ecg_values, output_file):
     fig.savefig(str(output_file), dpi=330)
     print("outfile - ", Path(output_file))
 
-    make_html(fig)
+    #make_html(fig, output_file)
     plt.close()
     
 def plot_ecg(ecg_values, output_file):
-
+    plt.close()
     print('Plotting ECG...')
-    plt.plot(ecg_values.iloc[:,0],ecg_values.iloc[:,1], linewidth=0.2)
+    plt.plot(ecg_values[15000:25000], linewidth=1)
     plt.xlabel("Time (s)")
     plt.ylabel("ECG Signal")
-    plt.title("ECG Signal")
+    plt.legend(['Raw', 'Cleaned'])
+    plt.title("Cleaning ECG Signal")
     plt.savefig(str(output_file), dpi=330)
     print("outfile - ", Path(output_file))
 
-    make_html(plt.gcf())
-    plt.close()
\ No newline at end of file
+    #make_html(plt.gcf(), output_file)
+    plt.close()
+    
+def nk_plotter(signals, output_file):
+    nk.plot_ecgs(signals)
\ No newline at end of file

src/hrvmeg/preprocess_ecg.py

@@ -4,40 +4,32 @@ from pathlib import Path
 from sklearn.preprocessing import StandardScaler
 import pandas as pd
 import numpy as np
-from py_utils import baseline_wander_removal
+import neurokit2 as nk
 import plotter
 
+def nk_preproc(ecg_signal, fs):
+    # Do processing 
+    ecg_cleaned = nk.ecg_clean(ecg_signal, sampling_rate=fs, method="biosppy")
+
+    # Prepare output
+    signals = pd.DataFrame({"ECG_Raw": ecg_signal,
+                            "ECG_Clean": ecg_cleaned
+                            })
+    
+    
+    return signals
+
 def preproc_ecg(file_path, fs, downsample_freq, output_folder):   
     ecg_data = pd.read_csv(file_path)
-    #Determing the time domain of the raw signal from the length of data and sampling freq
-    time_s = np.arange(0, len(ecg_data)/fs, 1/fs)    
-    
+    signals = nk_preproc(ecg_data.iloc[:,0], fs)
+    for signal in signals:
+        downsamp_signals = nk.signal_resample(signals[signal],sampling_rate = fs, 
+                                          desired_sampling_rate=downsample_freq
+                                          )
     #spot checking
-    output_file = Path(output_folder, 'raw_data.png')
-    plotter.plot_ecg(ecg_data,output_file)
-    
-    #Basline Drift Removal
-    baseline, ecg_out = baseline_wander_removal.bwr(ecg_data)
-    #spot check 2
-    output_file = Path(output_folder, 'bwr_data.png')
-    plotter.plot_ecg(ecg_out,output_file)
-    #Perfrom a standard scaling of the data (x-mu/sigma)
-    scaler = StandardScaler()
-    scaled_ecg = scaler.fit_transform(ecg_out)
-    #spot check 3
-    output_file = Path(output_folder, 'scaled_data.png')
-    plotter.plot_ecg(ecg_data,scaled_ecg)
-    #Need to downsample to match the MEG data
-    secs = len(scaled_ecg)/fs
-    sampls = secs*downsample_freq
-    print('int - ', int(sampls)) 
-    scaled_down_ecg = signal.resample(scaled_ecg, int(sampls), t = time_s)
-    #spot check 4
-    output_file = Path(output_folder, 'scaled_downsampled_data.png')
-    plotter.plot_ecg(ecg_data,scaled_down_ecg)
-    #Combining time data with signal data
-    print(scaled_down_ecg[0])
-    scaled_down_ecg_wtime = np.insert(scaled_down_ecg[0], 0, scaled_down_ecg[1], axis=1)
+    output_file = Path(output_folder, 'ecg_cleaned_data_part_biosppy.png')
+    plotter.plot_ecg(signals,output_file) 
+    return downsamp_signals
 
-    return scaled_down_ecg_wtime
+  
     
\ No newline at end of file