src/processing_local.py

#this is the original processing.py file, but is being revised for Hugging Face. this works well locally with Streamlit and consider using if the other has issues.

import numpy as np
import os
import json
import tensorflow as tf
from src.preprocess import audio_to_spectrograms
from src.model import build_autoencoder
from src.storage import upload_file, download_file

TEMP_DIR = "temp_models"
if not os.path.exists(TEMP_DIR):
    os.makedirs(TEMP_DIR)

def train_mode_cloud(audio_path, mode_name, boat_id):
    # 1. Preprocess
    X_train = audio_to_spectrograms(audio_path)
    if X_train is None: return "❌ Audio too short (min 1 sec)."

    # 2. Train
    autoencoder = build_autoencoder(X_train.shape[1:])
    autoencoder.fit(X_train, X_train, epochs=40, batch_size=4, verbose=0)

    # 3. Calculate Threshold (THE FIX)
    reconstructions = autoencoder.predict(X_train)
    mse = np.mean(np.power(X_train - reconstructions, 2), axis=(1, 2, 3))
    
   
    threshold = float(np.mean(mse) + (2 * np.std(mse)))

    # 4. Save Locally
    model_filename = f"{mode_name}_model.h5"
    meta_filename = f"{mode_name}_meta.json"
    local_model_path = os.path.join(TEMP_DIR, model_filename)
    local_meta_path = os.path.join(TEMP_DIR, meta_filename)

    autoencoder.save(local_model_path, save_format='h5', include_optimizer=False)
    with open(local_meta_path, 'w') as f:
        json.dump({"threshold": threshold}, f)

    # 5. Upload
    u1 = upload_file(local_model_path, boat_id, model_filename)
    u2 = upload_file(local_meta_path, boat_id, meta_filename)

    if u1 and u2:
        return f"✅ Calibrated {mode_name.upper()} | Threshold: {threshold:.5f}"
    else:
        return "⚠️ Trained locally, but Cloud Upload Failed."

def predict_health_cloud(audio_path, mode_name, boat_id):
    model_filename = f"{mode_name}_model.h5"
    meta_filename = f"{mode_name}_meta.json"
    local_model_path = os.path.join(TEMP_DIR, model_filename)
    local_meta_path = os.path.join(TEMP_DIR, meta_filename)

    # 1. Download
    d1 = download_file(boat_id, model_filename, local_model_path)
    d2 = download_file(boat_id, meta_filename, local_meta_path)

    if not (d1 and d2):
        return f"⚠️ No trained model found in cloud for Boat: {boat_id} (Mode: {mode_name})"

    # 2. Load
    with open(local_meta_path, 'r') as f:
        threshold = json.load(f)["threshold"]
    
    model = tf.keras.models.load_model(local_model_path, compile=False)

    # 3. Predict
    X_test = audio_to_spectrograms(audio_path)
    if X_test is None: return "Error: Audio too short."
    
    reconstructions = model.predict(X_test)
    # Calculate error for each second of audio
    mse = np.mean(np.power(X_test - reconstructions, 2), axis=(1, 2, 3))
    
    # 4. Analysis
    anomalies = np.sum(mse > threshold)
    health_score = 100 * (1 - (anomalies / len(mse)))
    
    # 5. Debug Data (Shows you WHY it decided what it decided)
    avg_error = np.mean(mse)
    max_error = np.max(mse)
    
    status = "🟢 HEALTHY" if health_score > 85 else "🔴 ANOMALY DETECTED"
    
    # Return detailed report
    return f"""
    STATUS: {status}
    Confidence Score: {health_score:.1f}%
    
    --- TECHNICAL TELEMETRY ---
    Threshold Limit : {threshold:.5f}
    Your Avg Error  : {avg_error:.5f}
    Your Max Error  : {max_error:.5f}
    Anomalous Secs  : {anomalies} / {len(mse)}
    """