Update app.py

app.py

@@ -4,67 +4,110 @@ import joblib
 import numpy as np
 import zipfile
 import os
-from huggingface_hub import hf_hub_download
+import re
 
-# Hugging Face repository ID
-repo_id = "CaxtonEmeraldS/CholesterolConcentrationPredictor"  # Replace with your actual repo name
-
-# Unzip models only once
+# Step 1: Unzip models only once
 unzip_dir = "unzipped_models"
+zip_file = "Models.zip"  # Make sure this is the filename inside your Space repo
+
 if not os.path.exists(unzip_dir):
-    print("Downloading and extracting model zip file...")
-    zip_path = hf_hub_download(repo_id=os.path.join('spaces', repo_id), filename="Models.zip")  # Replace with your actual uploaded ZIP filename
-    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+    print("Extracting model zip file...")
+    with zipfile.ZipFile(zip_file, 'r') as zip_ref:
         zip_ref.extractall(unzip_dir)
     print("Extraction complete.")
 
-# Load linear models
+# Step 2: Parse folders to dynamically populate dropdowns
+activations = []
+seeds_dict = dict()  # activation -> list of seeds
+neurons_dict = dict()  # (activation, seed) -> list of neuron counts
+
+for act in os.listdir(unzip_dir):
+    act_path = os.path.join(unzip_dir, act)
+    if os.path.isdir(act_path) and not act.startswith("linear_models"):
+        activations.append(act)
+        seeds = []
+        for seed_folder in os.listdir(act_path):
+            seed_path = os.path.join(act_path, seed_folder)
+            if os.path.isdir(seed_path):
+                seeds.append(seed_folder)
+                neuron_list = []
+                for model_file in os.listdir(seed_path):
+                    match = re.match(r"model_(\d+)\.keras", model_file)
+                    if match:
+                        neuron_list.append(int(match.group(1)))
+                neurons_dict[(act, seed_folder)] = sorted(neuron_list)
+        seeds_dict[act] = sorted(seeds)
+
+activations = sorted(activations)
+
+# Step 3: Load linear models
 # linear_rgb_path = os.path.join(unzip_dir, "linear_models/linear_rgb.joblib")
 # linear_grey_path = os.path.join(unzip_dir, "linear_models/linear_grey.joblib")
 
 # linear_rgb = joblib.load(linear_rgb_path)
 # linear_grey = joblib.load(linear_grey_path)
 
+# Step 4: Prediction function
 def predict(r, g, b, activation, seed, neurons):
     try:
         X = np.array([[r, g, b]])
-        # grey = 0.2989 * r + 0.5870 * g + 0.1140 * b
-
-        # # Linear predictions
-        # lin_pred_rgb = linear_rgb.predict(X)[0]
-        # lin_pred_grey = linear_grey.predict([[grey]])[0]
+        
+        # Linear predictions
+        lin_pred_rgb = (1.9221 * r) - (1.3817 * g) + (1.4058 * b) - 0.1318
 
-        # Load corresponding ANN model
-        keras_path = os.path.join(unzip_dir, f"{activation}/seed_{seed}/model_{neurons}.keras")
+        # ANN prediction
+        keras_path = os.path.join(unzip_dir, activation, seed, f"model_{neurons}.keras")
         if not os.path.exists(keras_path):
             raise FileNotFoundError(f"Model not found: {keras_path}")
         
         model = tf.keras.models.load_model(keras_path)
         ann_pred = model.predict(X)[0][0]
 
-        return ann_pred, lin_pred_rgb, lin_pred_grey
-    
+        return ann_pred, lin_pred_rgb
+
     except Exception as e:
         return f"Error: {str(e)}", "", ""
 
-iface = gr.Interface(
-    fn=predict,
-    inputs=[
-        gr.Number(label="R"), 
-        gr.Number(label="G"), 
-        gr.Number(label="B"),
-        gr.Textbox(label="Activation (folder name)"),
-        gr.Number(label="Seed (folder name)"),
-        gr.Number(label="Neurons (model number)")
-    ],
-    outputs=[
-        gr.Text(label="ANN Model Prediction"),
-        gr.Text(label="Linear RGB Prediction"),
-        gr.Text(label="Linear Grey Prediction"),
-    ],
-    title="ANN vs Linear Model Predictor",
-    description="Dynamically load models from Hugging Face repo and predict."
-)
+# Dynamic components for UI
+
+def update_seeds(activation):
+    return gr.Dropdown.update(choices=seeds_dict[activation], value=seeds_dict[activation][0])
+
+def update_neurons(activation, seed):
+    neurons = neurons_dict[(activation, seed)]
+    return gr.Dropdown.update(choices=neurons, value=neurons[0])
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# ANN vs Linear Model Predictor")
+    gr.Markdown("Dynamically select models and predict cholesterol concentration.")
+    
+    with gr.Row():
+        r = gr.Number(label="R")
+        g = gr.Number(label="G")
+        b = gr.Number(label="B")
+
+    with gr.Row():
+        activation = gr.Dropdown(choices=activations, label="Activation Function")
+        seed = gr.Dropdown(label="Seed")
+        neurons = gr.Dropdown(label="Neurons")
+
+    activation.change(update_seeds, inputs=[activation], outputs=[seed])
+    seed.change(update_neurons, inputs=[activation, seed], outputs=[neurons])
+
+    with gr.Row():
+        btn = gr.Button("Predict")
+    
+    with gr.Row():
+        ann_output = gr.Text(label="ANN Model Prediction")
+        lin_rgb_output = gr.Text(label="Linear RGB Prediction")
+        # lin_grey_output = gr.Text(label="Linear Grey Prediction")
+
+    btn.click(
+        fn=predict, 
+        inputs=[r, g, b, activation, seed, neurons],
+        outputs=[ann_output, lin_rgb_output, lin_grey_output]
+    )
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()