updated csv handling + HRV plot

app.py

@@ -265,46 +265,28 @@ def get_visualizations(beattimes_table: str, cleanedaudio: gr.Audio):
     # 3. HRV (Heart Rate Variability)
     s1_durations = []
     s2_durations = []
+    
     for segment in segment_metrics:
-        if segment['s1_to_s2_duration']:  # Check if list is not empty
+        if segment['s1_to_s2_duration']:
             s1_durations.extend(segment['s1_to_s2_duration'])
-        if segment['s2_to_s1_duration']:  # Check if list is not empty
+        if segment['s2_to_s1_duration']:
             s2_durations.extend(segment['s2_to_s1_duration'])
-
-    t_interp, sdnn_interp, rmssd_interp, hr_interp = u.compute_and_plot_hrv(s1_durations, s2_durations, sr)
-
-    # Add each HRV metric as a separate trace
-    fig.add_trace(
-        go.Scatter(
-            x=t_interp, 
-            y=sdnn_interp, 
-            name='SDNN', 
-            line=dict(color='red', width=1)
-        ),
-        row=3, col=1
-    )
-
-    fig.add_trace(
-        go.Scatter(
-            x=t_interp, 
-            y=rmssd_interp, 
-            name='RMSSD', 
-            line=dict(color='blue', width=1)
-        ),
-        row=3, col=1
-    )
-
+    
+    # Compute HRV metrics
+    time, hrv_values, _ = u.compute_hrv(s1_durations, s2_durations, sr)
+       
+    # Add HRV trace to the third subplot
     fig.add_trace(
         go.Scatter(
-            x=t_interp, 
-            y=hr_interp, 
-            name='Heart Rate', 
-            line=dict(color='green', width=1),
-            yaxis='y2'  # Use secondary y-axis for heart rate
+            x=time,
+            y=hrv_values,
+            name='HRV (RMSSD)',
+            line=dict(color='blue', width=1.5),
+            hovertemplate='Time: %{x:.1f}s<br>HRV: %{y:.1f}ms<extra></extra>'
         ),
         row=3, col=1
     )
-
+    
 
     # 4. Average Heartbeat Waveform
     max_len = max(len(metric['segment']) for metric in segment_metrics)
@@ -356,7 +338,11 @@ def get_visualizations(beattimes_table: str, cleanedaudio: gr.Audio):
         plot_bgcolor='white',
         paper_bgcolor='white'
     )
-
+    # # Update layout for the HRV subplot
+    # fig.update_yaxes(title_text="Heart Rate (BPM)", 
+    #                  overlaying='y', 
+    #                  side='right',
+    #                  row=3, col=1)
 
     # Update y-axes for fixed scales where needed
     # fig.update_yaxes(range=[-0.05, 0.05], row=5, col=1)  # Fixed y-axis for overlaid segments
@@ -374,6 +360,33 @@ def get_visualizations(beattimes_table: str, cleanedaudio: gr.Audio):
     fig.update_xaxes(title_text="Time (s)", row=5, col=1, gridcolor='lightgray')
 
     return fig
+
+def download_all(beattimes_table:str, cleanedaudio:gr.Audio):
+
+    df = mdpd.from_md(beattimes_table)
+    df['Beattimes'] = df['Beattimes'].astype(float)
+    df['Label (S1=1/S2=0)'] = df['Label (S1=1/S2=0)'].astype(int)
+
+    sr, audiodata = cleanedaudio
+
+    segment_metrics = u.compute_segment_metrics(df, sr, audiodata)
+
+    downloaddf = pd.DataFrame(segment_metrics)
+
+    
+    # Convert numpy floats to regular floats
+    downloaddf['rms_energy'] = downloaddf['rms_energy'].astype(float)
+    downloaddf['mean_frequency'] = downloaddf['mean_frequency'].astype(float)
+
+    temp_dir = tempfile.gettempdir()
+    temp_path = os.path.join(temp_dir, "segment_metrics.csv")
+
+    downloaddf.to_csv(temp_path, index=False)
+
+    return temp_path
+
+
+
 #-----------------------------------------------
 #-----------------------------------------------
 # HELPER FUNCTIONS FOR SINGLE AUDIO ANALYSIS V2
@@ -423,6 +436,17 @@ def updateBeatsv2(audio:gr.Audio, uploadeddf:gr.File=None)-> go.Figure:
             sep=";",
             decimal=",",
             encoding="utf-8-sig")
+        
+        # Drop rows where all columns are NaN (empty)
+        beattimes_table = beattimes_table.dropna(how='all')
+    
+        # Reset the index after dropping rows
+        beattimes_table = beattimes_table.reset_index(drop=True)
+
+        # Check if the column "Label (S1=0/S2=1)" exists and rename it
+        if "Label (S1=0/S2=1)" in beattimes_table.columns:
+            beattimes_table = beattimes_table.rename(columns={"Label (S1=0/S2=1)": "Label (S1=1/S2=0)"})
+
     else:
         raise FileNotFoundError("No file uploaded")
 
@@ -513,7 +537,10 @@ with gr.Blocks() as app:
 
         plot = gr.Plot()
 
+        download_btn = gr.DownloadButton()
+
         analyzebtn.click(get_visualizations, inputs=[beattimes_table, cleanedaudio], outputs=[plot])
+        download_btn.click(download_all, inputs=[beattimes_table, cleanedaudio], outputs=[download_btn])
 
 
 app.launch()

utils.py

@@ -575,29 +575,70 @@ def compute_segment_metrics(beattimes: pd.DataFrame, sr: int, audio: np.ndarray)
 
     return segment_metrics
 
-def compute_and_plot_hrv(s1_to_s2, s2_to_s1, sampling_rate=1000):
-    # Combine s1_to_s2 and s2_to_s1 to get RR intervals
-    rr_intervals = np.array(s1_to_s2) + np.array(s2_to_s1)
+def compute_hrv(s1_to_s2, s2_to_s1, sampling_rate=1000):
+    """
+    Compute Heart Rate Variability with debug statements
+    """
+    # Convert to numpy arrays if not already
+    s1_to_s2 = np.array(s1_to_s2)
+    s2_to_s1 = np.array(s2_to_s1)
+    
+    # Debug: Print input values
+    print("First few s1_to_s2 values:", s1_to_s2[:5])
+    print("First few s2_to_s1 values:", s2_to_s1[:5])
+    
+    # Calculate RR intervals (full cardiac cycle)
+    rr_intervals = s1_to_s2 + s2_to_s1
+    
+    # Debug: Print RR intervals
+    print("First few RR intervals (samples):", rr_intervals[:5])
+    
+    # Convert to seconds
+    rr_intervals = rr_intervals / sampling_rate
+    print("First few RR intervals (seconds):", rr_intervals[:5])
     
     # Calculate cumulative time for each heartbeat
-    time = np.cumsum(rr_intervals) / sampling_rate  # Convert to seconds
+    time = np.cumsum(rr_intervals)
     
     # Calculate instantaneous heart rate
-    hr = 60 / rr_intervals  # beats per minute
-    
-    # Compute rolling window HRV metrics
-    window_size = 30  # 30-second window
-    sdnn = np.array([np.std(rr_intervals[max(0, i-window_size):i+1]) 
-                     for i in range(len(rr_intervals))])
-    rmssd = np.array([np.sqrt(np.mean(np.diff(rr_intervals[max(0, i-window_size):i+1])**2)) 
-                      for i in range(len(rr_intervals))])
-    
-    # Create evenly spaced time array for plotting
-    t_interp = np.linspace(time.min(), time.max(), num=1000)
-    
-    # Interpolate HRV metrics for smooth plotting
-    sdnn_interp = interp1d(time, sdnn, kind='cubic')(t_interp)
-    rmssd_interp = interp1d(time, rmssd, kind='cubic')(t_interp)
-    hr_interp = interp1d(time, hr, kind='cubic')(t_interp)
-
-    return t_interp, sdnn_interp, rmssd_interp, hr_interp
+    heart_rate = 60 / rr_intervals  # beats per minute
+    print("First few heart rate values:", heart_rate[:5])
+    
+    # Compute RMSSD using a rolling window
+    window_size = int(30 / np.mean(rr_intervals))  # Approximate 30-second window
+    print("Window size:", window_size)
+    
+    hrv_values = []
+    
+    for i in range(len(rr_intervals)):
+        window_start = max(0, i - window_size)
+        window_data = rr_intervals[window_start:i+1]
+        if len(window_data) > 1:
+            # Debug: Print window data occasionally
+            if i % 100 == 0:
+                print(f"\nWindow {i}:")
+                print("Window data:", window_data)
+                print("Successive differences:", np.diff(window_data))
+            
+            successive_diffs = np.diff(window_data)
+            rmssd = np.sqrt(np.mean(successive_diffs ** 2)) * 1000  # Convert to ms
+            hrv_values.append(rmssd)
+        else:
+            hrv_values.append(np.nan)
+    
+    hrv_values = np.array(hrv_values)
+    
+    # Debug: Print HRV statistics
+    print("\nHRV Statistics:")
+    print("Min HRV:", np.nanmin(hrv_values))
+    print("Max HRV:", np.nanmax(hrv_values))
+    print("Mean HRV:", np.nanmean(hrv_values))
+    print("Number of valid HRV values:", np.sum(~np.isnan(hrv_values)))
+    
+    # Remove potential NaN values at the start
+    valid_idx = ~np.isnan(hrv_values)
+    time = time[valid_idx]
+    hrv_values = hrv_values[valid_idx]
+    heart_rate = heart_rate[valid_idx]
+    
+    return time, hrv_values, heart_rate