app.py

from flask import Flask, request, render_template
import os
import json
import numpy as np
from Vit_concept import run_inference, model
from GP import genetic_programming

app = Flask(__name__)
UPLOAD_FOLDER = 'uploads'
os.makedirs(UPLOAD_FOLDER, exist_ok=True)

def tolist_safe(obj):
    if isinstance(obj, np.ndarray):
        return obj.tolist()
    return obj

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload', methods=['POST'])
def upload():
    if 'file' not in request.files:
        return "No file part"
    file = request.files['file']
    if file.filename == '':
        return "No selected file"

    filepath = os.path.join(UPLOAD_FOLDER, file.filename)
    file.save(filepath)

    with open(filepath, 'r') as f:
        data = json.load(f)

    input_output_pairs = []
    predicted_HLCs = []

    for sample in data.get("train", []):
        input_grid = sample["input"]
        output_grid = sample["output"]

        concept_label, _ = run_inference(model, input_grid, output_grid)
        predicted_HLCs.append(concept_label)
        input_output_pairs.append((input_grid, output_grid))

    predicted_HLCs = list(set(predicted_HLCs))

    best_program, generations = genetic_programming(
        input_output_pairs=input_output_pairs,
        population_size=300,
        generations=500,
        mutation_rate=0.2,
        crossover_rate=0.7,
        max_depth=3,
        predicted_HLCs=predicted_HLCs
    )

    # Convert train pairs to plain lists
    input_output_pairs = [(tolist_safe(i), tolist_safe(o)) for i, o in input_output_pairs]

    # Prepare test pairs as well
    test_pairs = [(tolist_safe(sample["input"]), tolist_safe(sample["output"])) for sample in data.get("test", [])]

    # Prepare final program evaluation display
    last_input = input_output_pairs[-1][0] if input_output_pairs else []
    last_ground_truth = input_output_pairs[-1][1] if input_output_pairs else []

    try:
        predicted_output = tolist_safe(best_program.evaluate(last_input))
    except Exception as e:
        print("Error during best_program evaluation:", e)
        predicted_output = [["ERROR"]]

    return render_template("results.html",
                           hlcs=predicted_HLCs,
                           input_output_pairs=input_output_pairs,
                           test_pairs=test_pairs,
                           best_program=str(best_program),
                           last_input=last_input,
                           last_ground_truth=last_ground_truth,
                           predicted_output=predicted_output)

if __name__ == '__main__':
    app.run(host="0.0.0.0", port=7860)