from flask import Flask, request, jsonify
from flask_cors import CORS
import os
from datetime import datetime
import numpy as np
from PIL import Image
from tensorflow.keras.models import load_model


# ==========================================
# FLASK CONFIG
# ==========================================

app = Flask(__name__)
CORS(app)


# ==========================================
# FOLDER & MODEL
# ==========================================

UPLOAD_FOLDER = os.path.join(
    os.path.dirname(__file__),
    'uploads'
)

os.makedirs(
    UPLOAD_FOLDER,
    exist_ok=True
)


MODEL_PATH = os.path.join(
    os.path.dirname(__file__),
    'model_padi.h5'
)



# ==========================================
# CLASS SESUAI TRAINING MODEL
# ==========================================

CLASS_NAMES = [

    'Healthy',
    'Blast',
    'Blight',
    'Non-Padi',
    'Tungro'

]



# ==========================================
# DESKRIPSI HASIL
# ==========================================

DESCRIPTIONS = {


    'Healthy': {

        'deskripsi':
        'Daun padi dalam kondisi sehat.',

        'solusi':
        'Pertahankan pemupukan, pengairan, dan perawatan tanaman secara rutin.'

    },


    'Blast': {

        'deskripsi':
        'Blast merupakan penyakit daun padi yang disebabkan oleh jamur Pyricularia oryzae.',

        'solusi':
        'Gunakan fungisida dan varietas padi yang tahan terhadap penyakit blast.'

    },


    'Blight': {

        'deskripsi':
        'Blight merupakan penyakit hawar daun yang disebabkan oleh bakteri.',

        'solusi':
        'Gunakan benih sehat dan lakukan sanitasi lahan.'

    },


    'Tungro': {

        'deskripsi':
        'Tungro merupakan penyakit virus yang ditularkan oleh wereng hijau.',

        'solusi':
        'Lakukan pengendalian wereng dan gunakan varietas tahan tungro.'

    },


    'Non-Padi': {

        'deskripsi':
        'Gambar yang diunggah bukan daun padi.',

        'solusi':
        'Silakan upload gambar daun padi yang jelas.'

    }


}



# ==========================================
# LOAD MODEL
# ==========================================

model = None


try:

    model = load_model(MODEL_PATH)

    print("Model berhasil dimuat")

    print(
        "Input Shape :",
        model.input_shape
    )

    print(
        "Output Shape:",
        model.output_shape
    )


except Exception as e:

    print(
        "Gagal load model:",
        e
    )




# ==========================================
# PREPROCESS IMAGE
# ==========================================


def preprocess_image(path):

    image = Image.open(path)

    image = image.convert('RGB')


    image = image.resize(
        (224,224)
    )


    image_array = np.array(image)


    image_array = (
        image_array.astype('float32')
        /
        255.0
    )


    image_array = np.expand_dims(
        image_array,
        axis=0
    )


    return image_array





# ==========================================
# TEST API
# ==========================================


@app.route('/')


def home():

    return jsonify({

        "status":
        "API Klasifikasi Penyakit Daun Padi Aktif"

    })





# ==========================================
# PREDIKSI
# ==========================================


@app.route(
    '/prediksi',
    methods=['POST']
)


def prediksi():


    if 'gambar' not in request.files:


        return jsonify({

            "error":
            "Tidak ada gambar dikirim"

        }),400




    file = request.files['gambar']



    if file.filename == '':


        return jsonify({

            "error":
            "File kosong"

        }),400





    filename = (

        datetime.now()
        .strftime('%Y%m%d%H%M%S_')

        +

        file.filename

    )



    filepath = os.path.join(

        UPLOAD_FOLDER,

        filename

    )



    file.save(filepath)



    print("\n====================")

    print(
        "Gambar diterima:",
        filename
    )





    if model is None:


        return jsonify({

            "error":
            "Model tidak tersedia"

        }),500





    try:



        # preprocessing

        image_array = preprocess_image(filepath)




        # prediksi

        predictions = model.predict(

            image_array,

            verbose=0

        )





        predicted_index = int(

            np.argmax(predictions[0])

        )




        confidence = float(

            np.max(predictions[0])

        )

        confidence_percent = confidence * 100




        label = CLASS_NAMES[

            predicted_index

        ]




        print("\nHASIL PREDIKSI")


        for i,nama in enumerate(CLASS_NAMES):


            print(

                nama,

                ":",

                round(

                    predictions[0][i]*100,

                    2

                ),

                "%"

            )




        print(

            "HASIL AKHIR:",

            label

        )



        print(

            "CONFIDENCE:",

            confidence_percent

        )





        # ==============================
        # FILTER GAMBAR TIDAK JELAS
        # ==============================


        if confidence_percent < 60:


            return jsonify({

                "error":

                "Gambar tidak dikenali. Pastikan gambar daun padi."

            }),400




        # ==============================
        # TOLAK NON PADI
        # ==============================


        if label == "Non-Padi":


            return jsonify({

                "error":

                "Gambar bukan daun padi. Silakan upload daun padi."

            }),400





        all_predictions = {}



        for i in range(len(CLASS_NAMES)):


            all_predictions[

                CLASS_NAMES[i]

            ] = round(

                float(

                    predictions[0][i]*100

                ),

                2

            )





        detail = DESCRIPTIONS[label]




        return jsonify({



            "penyakit":

            label,



            "confidence":

            f"{confidence_percent:.2f}%",




            "all_predictions":

            all_predictions,




            "deskripsi":

            detail['deskripsi'],




            "solusi":

            detail['solusi']


        })





    except Exception as e:


        print(

            "ERROR:",

            e

        )


        return jsonify({

            "error":

            str(e)

        }),500







# ==========================================
# RUN FLASK
# ==========================================


if __name__ == '__main__':


    print("="*50)

    print(
        "Klasifikasi Penyakit Daun Padi"
    )

    print("="*50)



    app.run(

        host='127.0.0.1',

        port=5000,

        debug=False

    )