#!/usr/bin/env python3
"""
classification.py — single-seed image-level vs patient-level comparison.

This script OWNS the shared classification-runs cache
(scripts/cache/classification_runs.json): a flat list of per-(model, seed,
split) run dicts. It reads any runs it needs from the cache and writes back any
it has to compute, so the cache is maintained here. figure4_6.py references the
same file to draw the 20-seed boxplots.

Usage:
    conda activate fundus_imaging
    python scripts/classification.py
"""

import os, sys, json
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(
    os.path.abspath(__file__)))))

from classes import PatientLeakageClassifier

SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
ROOT = os.path.dirname(SCRIPT_DIR)
MODELS = ["VGG16", "DenseNet121", "EfficientNetB1", "MobileNetV2", "ResNet50"]
SEED = 20
CACHE_PATH = os.path.join(SCRIPT_DIR, "cache", "classification_runs.json")

# Load the run cache: keep the raw list (to append to) and an index (to look up).
runs = []
if os.path.exists(CACHE_PATH):
    with open(CACHE_PATH) as f:
        runs = json.load(f)
index = {(r["model"], r["seed"], r["split_type"]): r for r in runs}

clf = None  # lazily created only if the cache is missing something


def get_run(name, split):
    """Return the cached run, else compute it and write it back to the cache."""
    global clf
    hit = index.get((name, SEED, split))
    if hit is not None:
        return hit
    if clf is None:
        clf = PatientLeakageClassifier(
            os.path.join(ROOT, "results", "simple_patient_manifest.csv"),
            os.path.join(ROOT, "features"), n_jobs=8)
    print(f"    (cache miss for {name}/{split} — computing)")
    r = clf.run(name, SEED, split)
    runs.append(r)
    index[(name, SEED, split)] = r
    os.makedirs(os.path.dirname(CACHE_PATH), exist_ok=True)
    with open(CACHE_PATH, "w") as f:
        json.dump(runs, f, indent=2)
    return r


print(f"{'='*60}")
print(f"IMAGE-LEVEL vs PATIENT-LEVEL (seed={SEED})")
print(f"{'='*60}")

results = []
for name in MODELS:
    print(f"\n  {name} ...")
    img = get_run(name, "image")
    pat = get_run(name, "patient")
    results.append({"model": name,
                    "image_cv": img["cv"], "image_test": img["test"],
                    "patient_cv": pat["cv"], "patient_test": pat["test"],
                    "drop": img["test"] - pat["test"]})
    print(f"    Image:   CV={img['cv']:.4f}  Test={img['test']:.4f}")
    print(f"    Patient: CV={pat['cv']:.4f}  Test={pat['test']:.4f}")
    print(f"    Drop:    {img['test'] - pat['test']:.4f}")

print(f"\n  {'Model':<18s} {'Img-CV':>8s} {'Img-Test':>9s} "
      f"{'Pat-CV':>8s} {'Pat-Test':>9s} {'Drop':>7s}")
print(f"  {'-'*54}")
for r in results:
    print(f"  {r['model']:<18s} {r['image_cv']:>8.4f} {r['image_test']:>9.4f} "
          f"{r['patient_cv']:>8.4f} {r['patient_test']:>9.4f} {r['drop']:>7.4f}")

with open(os.path.join(ROOT, "results", "classification_pca50.json"), "w") as f:
    json.dump(results, f, indent=2)
print(f"\nDONE")