Upload folder using huggingface_hub

.gitattributes

@@ -38,3 +38,4 @@ examples/43522917.dat filter=lfs diff=lfs merge=lfs -text
 examples/45227415.dat filter=lfs diff=lfs merge=lfs -text
 examples/46642833.dat filter=lfs diff=lfs merge=lfs -text
 examples/49036311.dat filter=lfs diff=lfs merge=lfs -text
+machine_measurements.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -6,59 +6,76 @@ import numpy as np
 import matplotlib.pyplot as plt
 import os
 import glob
+from huggingface_hub import hf_hub_download 
 from labels_refined import get_refined_labels, CLASSES
 from model import ResNet1d
 from dataset import MIMICECGDataset
 
 # --- Configuration ---
-# HF Space configuration: Data is local
 DATA_DIR = "./examples" 
-MODEL_PATH = "resnet_advanced.pth" 
-DEVICE = torch.device("cpu") # Spaces usually CPU unless GPU requested
+CSV_PATH = "machine_measurements.csv" # Now local in Space
+DEVICE = torch.device("cpu") 
 
 # --- Load Resources ---
-print("Loading Model...")
+print("Downloading Model from Hub...")
+# Downloads to local cache and returns path
+model_path = hf_hub_download(repo_id="IFMedTech/ECG_Model", filename="resnet_advanced.pth")
+
+print(f"Loading Model from {model_path}...")
 model = ResNet1d(num_classes=5).to(DEVICE)
 try:
-    state_dict = torch.load(MODEL_PATH, map_location=DEVICE, weights_only=True)
+    state_dict = torch.load(model_path, map_location=DEVICE, weights_only=True)
 except:
-    state_dict = torch.load(MODEL_PATH, map_location=DEVICE)
+    state_dict = torch.load(model_path, map_location=DEVICE)
 model.load_state_dict(state_dict)
 model.eval()
 
-# --- Pre-defined Metadata for Examples ---
-# Hardcoded to avoid uploading the sensitive/huge patient CSV
-example_metadata = {
-    "40689238": {
-        "diagnosis": "Sinus Rhythm (Normal)", 
-        "text": "Sinus rhythm\nNormal ECG"
-    },
-    "46642833": {
-        "diagnosis": "Atrial Fibrillation", 
-        "text": "Atrial fibrillation\nRapid ventricular response"
-    },
-    "49036311": {
-        "diagnosis": "Sinus Tachycardia", 
-        "text": "Sinus tachycardia\nPossible Left Atrial Enlargement"
-    },
-    "43522917": {
-        "diagnosis": "Sinus Bradycardia", 
-        "text": "Sinus bradycardia\nOtherwise normal"
-    },
-    "45227415": {
-        "diagnosis": "Ventricular Tachycardia (Rare)", 
-        "text": "Ventricular tachycardia\nUrgent attention required"
-    }
-}
+print("Loading Dataset Index...")
+# Use CSV to dynamically find info for available examples
+try:
+    df = pd.read_csv(CSV_PATH, low_memory=False)
+    print(f"Loaded CSV with {len(df)} records.")
+except Exception as e:
+    print(f"Error loading CSV: {e}")
+    df = pd.DataFrame() # Fallback
+
+# Scan examples folder for .dat files
+example_files = glob.glob(os.path.join(DATA_DIR, "*.dat"))
+available_study_ids = [os.path.splitext(os.path.basename(f))[0] for f in example_files]
+print(f"Found examples: {available_study_ids}")
+
+# Build Metadata for Gradio
+example_metadata = {}
+for sid in available_study_ids:
+    if df.empty:
+        example_metadata[sid] = {"diagnosis": "Unknown (CSV Missing)", "text": "N/A"}
+        continue
+        
+    row = df[df['study_id'].astype(str) == str(sid)]
+    if not row.empty:
+        cols = [c for c in df.columns if 'report_' in c]
+        lines = [str(row.iloc[0][c]).strip() for c in cols if pd.notna(row.iloc[0][c]) and str(row.iloc[0][c]).strip() != '']
+        full_text = '\n'.join(lines)
+        
+        # Simple diagnosis estimation from labels for display title
+        labels_vec = get_refined_labels(' '.join(lines)) 
+        active_classes = [CLASSES[i] for i, val in enumerate(labels_vec) if val == 1.0]
+        diagnosis = ", ".join(active_classes) if active_classes else "Normal/Other"
+        
+        example_metadata[sid] = {
+            "diagnosis": diagnosis,
+            "text": full_text
+        }
+    else:
+        example_metadata[sid] = {"diagnosis": "Metadata Not Found", "text": "N/A"}
+
 
 def load_signal(path):
-    # Reusing logic from dataset.py
     if not os.path.exists(path):
         return None
     
     gain = 200.0
     with open(path, 'rb') as f:
-        # File is raw int16 binary
         raw_data = np.fromfile(f, dtype=np.int16)
         
     n_leads = 12
@@ -77,12 +94,9 @@ def load_signal(path):
     return signal
 
 def plot_ecg(signal, title="12-Lead ECG"):
-    """Generates a matplotlib figure for the 12-lead ECG"""
     leads = ['I', 'II', 'III', 'aVR', 'aVL', 'aVF', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6']
-    
     fig, axes = plt.subplots(12, 1, figsize=(10, 20), sharex=True)
     plt.subplots_adjust(hspace=0.2)
-    
     for i in range(12):
         axes[i].plot(signal[i], color='k', linewidth=0.8)
         axes[i].set_ylabel(leads[i], rotation=0, labelpad=20, fontsize=10, fontweight='bold')
@@ -91,44 +105,39 @@ def plot_ecg(signal, title="12-Lead ECG"):
         axes[i].spines['bottom'].set_visible(False if i < 11 else True)
         axes[i].spines['left'].set_visible(True)
         axes[i].grid(True, linestyle='--', alpha=0.5)
-        
     axes[11].set_xlabel("Samples (500Hz)", fontsize=12)
     fig.suptitle(title, fontsize=16, y=0.90)
-    
     return fig
 
 def predict_ecg(study_id):
-    # Path is local in examples/
     path = os.path.join(DATA_DIR, f"{study_id}.dat")
-    
     if not os.path.exists(path):
         return None, f"File not found for study {study_id}", {}
     
-    # Load Signal
     signal = load_signal(path)
     if signal is None:
         return None, "Error loading signal", {}
     
-    # Generate Plot
     fig = plot_ecg(signal, title=f"Study {study_id}")
     
-    # Inference
-    tensor_sig = torch.from_numpy(signal).float().unsqueeze(0).to(DEVICE) # (1, 12, 5000)
+    tensor_sig = torch.from_numpy(signal).float().unsqueeze(0).to(DEVICE)
     with torch.no_grad():
         logits = model(tensor_sig)
         probs = torch.sigmoid(logits).cpu().numpy()[0]
         
-    # Format Results
     results = {CLASSES[i]: float(probs[i]) for i in range(len(CLASSES))}
     
-    # Get True Text
     full_text = example_metadata.get(study_id, {}).get("text", "Unknown")
     
     return fig, results, full_text
 
 # --- Gradio UI ---
 examples = [[k, v["diagnosis"]] for k, v in example_metadata.items()]
-example_ids = [k for k in example_metadata.keys()]
+examples.sort(key=lambda x: x[0])
+example_ids = [k[0] for k in examples]
+
+if not example_ids:
+    example_ids = ["No Examples Found"]
 
 with gr.Blocks(title="ECG Arrhythmia Classifier") as demo:
     gr.Markdown("# 🫀 AI ECG Arrhythmia Classifier")
@@ -136,17 +145,12 @@ with gr.Blocks(title="ECG Arrhythmia Classifier") as demo:
     
     with gr.Row():
         with gr.Column(scale=1):
-            # Input
-            study_input = gr.Dropdown(choices=example_ids, label="Select Example Study ID", value=example_ids[0])
-            
-            # Info
+            study_input = gr.Dropdown(choices=example_ids, label="Select Example Study ID", value=example_ids[0] if example_ids else None)
             gr.Markdown("### Example Descriptions")
             gr.DataFrame(headers=["Study ID", "Diagnosis"], value=examples, interactive=False)
-            
             analyze_btn = gr.Button("Analyze ECG", variant="primary")
             
         with gr.Column(scale=2):
-            # Output
             plot_output = gr.Plot(label="12-Lead ECG Visualization")
             label_output = gr.Label(label="AI Predictions")
             text_output = gr.Textbox(label="Original Clinical Report (Ground Truth context)", lines=5)

machine_measurements.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f6b1413221bce95bd6f48b28ca1acf27ae0b073d6f2c1d12f3af7500eabbb6
+size 182674683

requirements.txt

@@ -4,3 +4,4 @@ numpy
 matplotlib
 gradio
 scipy
+huggingface_hub