import joblib
import pandas as pd
import numpy as np
import gradio as gr

# Load your trained model
model = joblib.load('trained_model.joblib')

# Define grade to numeric conversion (same as before)
def grade_to_numeric(grade):
    if pd.isna(grade) or grade == "":
        return np.nan
    grade_map = {
        "A1": 1, "B2": 2, "B3": 3, "C4": 4, "C5": 5, "C6": 6,
        "D7": 7, "E8": 8, "F9": 9
    }
    return grade_map.get(grade, np.nan)

# Define your preprocessing function
def preprocess_input(desired_career, aggregate, english, core_maths, science, 
                    social_studies, electives, elective_maths=None, 
                    business_management=None, government=None, chemistry=None,
                    physics=None, economics=None, visual_arts=None, geography=None,
                    e_ict=None, literature=None, biology=None):
    
    # Create a dictionary with all inputs
    input_data = {
        "Desired_Career": desired_career,
        "Aggregate": aggregate,
        "English": english,
        "Core Maths": core_maths,
        "Science": science,
        "Social Studies": social_studies,
        "Electives": electives,
        "Elective Maths": elective_maths,
        "Business Management": business_management,
        "Government": government,
        "Chemistry": chemistry,
        "Physics": physics,
        "Economics": economics,
        "Visual Arts": visual_arts,
        "Geography": geography,
        "E-ICT": e_ict,
        "Literature": literature,
        "Biology": biology
    }
    
    # Convert to DataFrame
    student_df = pd.DataFrame([input_data])
    
    # Convert grades to numerical
    grade_cols = ['English', 'Core Maths', 'Science', 'Social Studies',
                 'Elective Maths', 'Business Management', 'Government',
                 'Chemistry', 'Physics', 'Economics', 'Visual Arts',
                 'Geography', 'E-ICT', 'Literature', 'Biology']
    
    for col in grade_cols:
        if col in student_df.columns:
            student_df[col] = student_df[col].apply(grade_to_numeric)
    
    return student_df

def predict_career(desired_career, aggregate, english, core_maths, science, 
                  social_studies, electives, elective_maths=None, 
                  business_management=None, government=None, chemistry=None,
                  physics=None, economics=None, visual_arts=None, geography=None,
                  e_ict=None, literature=None, biology=None):
    
    # Preprocess input
    processed_input = preprocess_input(
        desired_career, aggregate, english, core_maths, science,
        social_studies, electives, elective_maths, business_management,
        government, chemistry, physics, economics, visual_arts, geography,
        e_ict, literature, biology
    )
    
    # Make prediction
    prediction = model.predict(processed_input)
    probabilities = model.predict_proba(processed_input)[0]
    
    # Get top 3 recommendations
    class_indices = np.argsort(probabilities)[::-1][:3]
    classes = model.classes_
    recommendations = [
        (classes[idx], float(probabilities[idx])) 
        for idx in class_indices
    ]
    
    # Format output
    output = "\n".join(
        [f"{course}: {prob*100:.1f}%" for course, prob in recommendations]
    )
    
    return output

# Create Gradio interface
inputs = [
    gr.Dropdown(["Medicine", "Pharmacy", "Law", "Computer Science", "Engineering", 
                "Business", "Nursing", "Agriculture", "Journalism", "Education"], 
               label="Desired Career"),
    gr.Number(label="Aggregate Score"),
    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="English"),
    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Core Maths"),
    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Science"),
    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Social Studies"),
    gr.Textbox(label="Electives (comma separated)"),
    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9", None], label="Elective Maths (optional)"),
    # Add other optional subjects similarly
]

outputs = gr.Textbox(label="Recommended Courses")

interface = gr.Interface(
    fn=predict_career,
    inputs=inputs,
    outputs=outputs,
    title="Career Path Recommender",
    description="Enter your academic information to get career recommendations"
)

interface.launch()