import gradio as gr
import pandas as pd
import joblib
import os
import google.generativeai as genai

# Load models
try:
    rf_ferti_name = joblib.load("rf_ferti_name.pkl")
    rf_ferti_value = joblib.load("rf_ferti_value.pkl")
except Exception as e:
    raise RuntimeError(f"Model loading failed: {e}")

# Encodings
soil_type_encodings = {
    'Black': 0, 'Clayey': 1, 'Loamy': 2, 'Red': 3, 'Sandy': 4
}
crop_type_encodings = {
    'Barley': 0, 'Cotton': 1, 'Ground Nuts': 2, 'Maize': 3, 'Millets': 4,
    'Oil seeds': 5, 'Other Variety': 6, 'Paddy': 7, 'Pulses': 8, 'Sugarcane': 9,
    'Tobacco': 10, 'Wheat': 11
}
fertilizer_name_encodings = {
    '10-26-26': 0, '14-35-14': 1, '15-15-15': 2, '17-17-17': 3, '20-20': 4,
    '20-20-20': 5, '28-28': 6, 'Ammonium sulfate': 7, 'Biofertilizer (e.g., Rhizobium)': 8,
    'Calcium nitrate': 9, 'DAP': 10, 'Ferrous sulfate': 11, 'Magnesium sulfate': 12,
    'Potassium chloride/Muriate of potash (MOP)': 13,
    'Potassium sulfate/Sulfate of potash (SOP)': 14, 'Rock phosphate (RP)': 15,
    'Single superphosphate (SSP)': 16, 'Triple superphosphate (TSP)': 17,
    'Urea': 18, 'Zinc sulfate': 19
}
inv_fert_name_encodings = {v: k for k, v in fertilizer_name_encodings.items()}

# Setup Gemini API
genai.configure(api_key=os.getenv("GEMINI_API"))
model = genai.GenerativeModel("gemini-1.5-flash")

def generate_ai_suggestions(fertilizer_name):
    prompt = (
        f"For {fertilizer_name} fertilizer, generate 3–4 short suggestions. "
        "Each on a new line. Text should be justified and not contain special characters."
    )
    try:
        response = model.generate_content(prompt)
        return response.text.strip()
    except Exception as e:
        return f"AI suggestion error: {str(e)}"

def predict_fertilizer(temp, humidity, moisture, soil_type, crop_type, nitrogen, potassium, phosphorous):
    # Encode input
    soil_encoded = soil_type_encodings.get(soil_type, -1)
    crop_encoded = crop_type_encodings.get(crop_type, -1)

    input_df = pd.DataFrame([{
        "Temperature": temp,
        "Humidity": humidity,
        "Moisture": moisture,
        "Nitrogen": nitrogen,
        "Potassium": potassium,
        "Phosphorous": phosphorous,
        "Soil Type": soil_encoded,
        "Crop Type": crop_encoded,
    }])

    try:
        # Predict
        pred_name_encoded = rf_ferti_name.predict(input_df)[0]
        fert_name = inv_fert_name_encodings[pred_name_encoded]
        fert_qty = rf_ferti_value.predict(input_df)[0]
    except Exception as e:
        return f"❌ Model prediction failed: {str(e)}"

    # Gemini suggestions
    ai_info = generate_ai_suggestions(fert_name)

    result = (
        f"🌾 **Recommended Fertilizer**: `{fert_name}`\n"
        f"📦 **Estimated Quantity**: `{fert_qty:.2f} units`\n\n"
        f"📘 **AI Suggestions**:\n{ai_info}"
    )
    return result

# Dropdown options
soil_list = list(soil_type_encodings.keys())
crop_list = list(crop_type_encodings.keys())

# Gradio Interface
interface = gr.Interface(
    fn=predict_fertilizer,
    inputs=[
        gr.Slider(0, 50, label="🌡️ Temperature (°C)"),
        gr.Slider(0, 100, label="💧 Humidity (%)"),
        gr.Slider(0, 100, label="🌱 Moisture (%)"),
        gr.Dropdown(soil_list, label="🧱 Soil Type"),
        gr.Dropdown(crop_list, label="🌾 Crop Type"),
        gr.Number(label="🧪 Nitrogen Level"),
        gr.Number(label="🧪 Potassium Level"),
        gr.Number(label="🧪 Phosphorous Level")
    ],
    outputs=gr.Markdown(label="🧾 Result"),
    title="🌿 Fertilizer Recommendation System",
    description="Enter environmental and soil parameters to get fertilizer suggestions powered by AI.",
    allow_flagging="never"
)

# Launch for Hugging Face
interface.launch()