app.py

# ===================== IMPORTS =====================
import streamlit as st
import os
import json
import difflib
import pickle
import torch
import numpy as np
from PIL import Image
from tensorflow.keras.models import load_model  # ✅ FIXED
from tensorflow.keras.preprocessing.image import img_to_array, load_img  # ✅ FIXED
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint  # optional, if used
from transformers import CLIPProcessor, CLIPModel
from sentence_transformers import SentenceTransformer, CrossEncoder
from langdetect import detect

# ===================== PATHS =====================
Main_py = "Main_py"  
model_path = os.path.join(Main_py, "best_cnn_model_finetuned.keras")
label_path = os.path.join(Main_py, "label_encoder.pkl")
json_path = os.path.join(Main_py, "banana_disease_knowledge_base_updated_shuffled.json")

# ===================== LOAD MODELS & DATA =====================
@st.cache_resource
def load_cnn_clip_kb():
    model = load_model(model_path)  # ✅ FIXED
    with open(label_path, "rb") as f:
        le = pickle.load(f)
    with open(json_path, "r", encoding="utf-8") as f:
        kb_data = json.load(f)
    clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
    clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
    return model, le, kb_data, clip_model, clip_processor

@st.cache_resource
def load_nlp_models():
    embedder = SentenceTransformer("sentence-transformers/paraphrase-xlm-r-multilingual-v1")
    cross_encoder = CrossEncoder("cross-encoder/mmarco-mMiniLMv2-L12-H384-v1")
    return embedder, cross_encoder

model, le, kb_data, clip_model, clip_processor = load_cnn_clip_kb()
embedder, cross_encoder = load_nlp_models()

# ===================== CLIP FILTER =====================
def verify_image_with_clip(image_path):
    prompts = ["a photo of a banana leaf", "a photo of something that is not a banana leaf"]
    try:
        image = Image.open(image_path).convert("RGB")
    except Exception as e:
        return ('REJECTED', f'Invalid image file: {e}', 0.0)

    inputs = clip_processor(text=prompts, images=image, return_tensors="pt", padding=True)
    with torch.no_grad():
        outputs = clip_model(**inputs)
        probs = outputs.logits_per_image.softmax(dim=1).cpu().numpy()[0]

    banana_score, not_banana_score = probs[0], probs[1]
    rejection_factor = 3.0

    if banana_score >= not_banana_score * rejection_factor:
        return ('ACCEPTED', 'banana leaf', banana_score)
    else:
        return ('REJECTED', 'Not a banana leaf', not_banana_score)

# ===================== CNN PREDICTION =====================
def predict_disease(image_path, target_size=(224, 224)):
    image = load_img(image_path, target_size=target_size)
    img_array = img_to_array(image) / 255.0
    img_array = np.expand_dims(img_array, axis=0)
    preds = model.predict(img_array)[0]
    idx = np.argmax(preds)
    label = le.inverse_transform([idx])[0]
    confidence = preds[idx]
    return label, confidence, image

# ===================== FUZZY MARATHI OUTPUT =====================
def match_disease_name_fuzzy(predicted_name):
    disease_names = [entry["Disease"].strip().lower() for entry in kb_data]
    matches = difflib.get_close_matches(predicted_name.strip().lower(), disease_names, n=1, cutoff=0.5)
    if matches:
        for entry in kb_data:
            if entry["Disease"].strip().lower() == matches[0]:
                return entry
    return None

def get_marathi_recommendation_fuzzy(predicted_disease, confidence=None):
    entry = match_disease_name_fuzzy(predicted_disease)
    if entry:
        return {
            "पिक": entry.get("Crop", "केळी"),
            "रोग": entry.get("Local_Name", {}).get("mr", predicted_disease),
            "लक्षणे": entry.get("Symptoms_MR", ""),
            "कारण": entry.get("Cause_MR", ""),
            "किटकनाशके": entry.get("Pesticide_MR", ""),
            "किटकनाशक शिफारस": entry.get("Pesticide_Recommendation", {}).get("mr", ""),
            "नियंत्रण पद्धती": entry.get("Management_MR", ""),
            "रोगजन्य घटक": entry.get("Pathogen", ""),
            "विश्वासार्हता": f"{confidence:.2%}" if confidence else "N/A"
        }
    return None

# ===================== NLP PREDICTION =====================
def detect_language(query: str) -> str:
    try:
        lang = detect(query)
        return lang if lang in ["mr", "hi"] else "en"
    except:
        return "en"

def predict_disease_from_text(query: str):
    lang = detect_language(query)
    query_emb = embedder.encode([query], normalize_embeddings=True)

    symptom_key = f"Symptoms_{lang.upper()}" if lang != "en" else "Symptoms"
    pairs = [[query, entry.get(symptom_key, "")] for entry in kb_data]
    scores = cross_encoder.predict(pairs)
    best_idx = np.argmax(scores)

    if scores[best_idx] < 0.2:
        return {
            "message": {
                "mr": "हा रोग आमच्या डेटाबेसमध्ये नाही.",
                "hi": "यह रोग हमारे डेटाबेस में नहीं है।",
                "en": "This disease is not in our database."
            }[lang]
        }

    entry = kb_data[best_idx]
    return {
        "पिक": entry.get("Crop", "केळी"),
        "रोग": entry["Local_Name"].get(lang, entry["Disease"]),
        "लक्षणे": entry.get(symptom_key, ""),
        "कारण": entry.get(f"Cause_{lang.upper()}", entry.get("Cause", "")),
        "किटकनाशक शिफारस": entry.get("Pesticide_Recommendation", {}).get(lang, ""),
        "किटकनाशके": entry.get("Pesticide", ""),
        "रोगजन्य घटक": entry.get("Pathogen", ""),
        "नियंत्रण पद्धती": entry.get(f"Management_{lang.upper()}", entry.get("Management_Practices", "")),
    }

# ===================== STREAMLIT UI =====================
st.set_page_config(page_title="🍌\ Banana Disease Detection (CNN + NLP)", layout="centered")
st.title(" केळीच्या पानांवरील रोगांचे निदान")
st.markdown("प्रतिमा किंवा लक्षणे वापरून केळीवरील रोगांचे निदान करा (मराठी, हिंदी, इंग्रजी भाषांमध्ये).")

option = st.radio("इनपुट पद्धत निवडा:", ["Image Only", "Text Only", "Both"])

# ===================== IMAGE FLOW =====================
if option in ["Image Only", "Both"]:
    st.subheader(" प्रतिमा अपलोड करा")
    uploaded_img = st.file_uploader("JPG / PNG", type=["jpg", "jpeg", "png"])
    if uploaded_img:
        temp_path = "temp_uploaded.jpg"
        with open(temp_path, "wb") as f:
            f.write(uploaded_img.getbuffer())

        st.image(temp_path, caption="अपलोड केलेली प्रतिमा", use_column_width=True)
        st.info("CLIP मॉडेलद्वारे पडताळणी करत आहे...")

        status, reason, clip_conf = verify_image_with_clip(temp_path)
        if status == "REJECTED":
            st.error(f" CLIP नकार: {reason} [विश्वासार्हता: {clip_conf:.2f}]")
        else:
            st.success(f" CLIP मंजूरी: शक्यतो केळीचे पान [विश्वासार्हता: {clip_conf:.2f}]")
            pred_disease, cnn_conf, img = predict_disease(temp_path)
            st.markdown(f"**ओळखलेला रोग:** {pred_disease} (विश्वासार्हता: {cnn_conf:.2%})")

            marathi_info = get_marathi_recommendation_fuzzy(pred_disease, cnn_conf)
            if marathi_info:
                st.subheader(" मराठी शिफारस:")
                for k, v in marathi_info.items():
                    st.markdown(f"**{k}**: {v}")
            else:
                st.warning(" ज्ञानतळात रोगासाठी माहिती नाही.")
            st.image(img, caption=f"{pred_disease} ({cnn_conf:.2%})", use_column_width=True)

        os.remove(temp_path)

# ===================== TEXT FLOW =====================
if option in ["Text Only", "Both"]:
    st.subheader(" लक्षणे लिहा")
    symptoms = st.text_area("लक्षणे (मराठी / हिंदी / इंग्रजी):")
    if symptoms and st.button(" रोग ओळखा"):
        result = predict_disease_from_text(symptoms)
        if "message" in result:
            st.warning(result["message"])
        else:
            st.subheader(" शिफारस:")
            for k, v in result.items():
                st.markdown(f"**{k}**: {v}")