Update app.py

app.py

@@ -1,55 +1,13 @@
+#import libraries
 import streamlit as st
-import numpy as np
-from tensorflow.keras.preprocessing.image import img_to_array
-from tensorflow_hub.keras_layer import KerasLayer
-from tensorflow.keras.models import load_model
-from PIL import Image
-import tensorflow as tf
+import eda
+import prediction
 
-# Load model hanya sekali saat startup
-@st.cache_resource
-def load_skin_model():
-    return load_model('model_aug.keras', custom_objects={'KerasLayer': KerasLayer})
+#navigation
+navigation = st.sidebar.selectbox('Choose Page: ', ('Predictor', 'EDA'))
 
-model = load_skin_model()
-
-# Kelas target
-CLASS_NAMES = ['oily', 'dry', 'normal']
-
-def preprocess_image(uploaded_file):
-    """Preprocess the uploaded image for prediction."""
-    image = Image.open(uploaded_file).convert("RGB")  # Open image and ensure RGB format
-    img_array = img_to_array(image)  # Convert to NumPy array
-    img_resized = tf.image.resize(img_array, [220, 220])  # Resize to model input size
-    img_normalized = img_resized / 255.0  # Normalize pixel values
-    return tf.expand_dims(img_normalized, axis=0)  # Add batch dimension
-
-def predict_skin_type(image_data):
-    """Predict the skin type based on the input image."""
-    processed_image = preprocess_image(image_data)
-    predictions = model.predict(processed_image)
-    predicted_class = CLASS_NAMES[np.argmax(predictions)]
-    confidence = np.max(predictions) * 100
-    return predicted_class, confidence
-
-def run():
-    st.image('https://i.ytimg.com/vi/Y7nGCB3S5Ww/maxresdefault.jpg', use_container_width=True)
-    st.title("Skin Type Prediction Model")
-    st.write("Upload an image to know your skin type!")
-    
-    # Upload image
-    file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
-    
-    if file is not None:
-        # Display the uploaded image
-        st.image(file, caption="Uploaded Image", use_column_width=True)
-        
-        # Predict
-        predicted_class, confidence = predict_skin_type(file)
-        st.write(f"### Predicted Skin Type: {predicted_class}")
-        st.write(f"### Confidence: {confidence:.2f}%")
-    else:
-        st.write("Please upload an image to get predictions.")
-
-if __name__ == "__main__":
-    run()
+#pilih page
+if navigation == 'Predictor':
+    prediction.run()
+else:
+    eda.run()