phash updates!

pr_from_store.py

@@ -0,0 +1,120 @@
+"""Recompute PR curves from an image_similarity .store file (messagepack).
+
+Replicates DescriptorStore::get_stats semantics:
+- micro-averaged over base-image queries
+- TP_m(t): mutant m of query found within Hamming distance t
+- FP: other base images count for every mutator; other images' mutants
+  count only for their own mutator
+"""
+import sys
+import msgpack
+import numpy as np
+
+TMAX = 33  # thresholds 0..32
+
+def load(path):
+    with open(path, "rb") as f:
+        m = msgpack.unpack(f, strict_map_key=False)
+    if isinstance(m, (list, tuple)):
+        # versioned format: [format, descriptor, descriptor_version, map]
+        print(f"{path}: {m[1]} v{m[2]} (store format {m[0]})")
+        return m[3]
+    return m  # legacy format: bare map
+
+def detect_mutators(buckets):
+    tags = set()
+    for bucket in buckets:
+        for name in bucket:
+            if name.startswith("mut."):
+                tags.add(name.split(".")[1])
+    return sorted(tags)
+
+def main(path, label):
+    m = load(path)
+    global MUTATORS
+    MUTATORS = detect_mutators(m.values())
+    print(f"mutators: {MUTATORS}")
+    keys = np.array(list(m.keys()), dtype=np.uint64)
+    buckets = list(m.values())
+    K = len(keys)
+
+    name2hash = {}
+    n_base = np.zeros(K, dtype=np.float64)
+    n_mut = {mut: np.zeros(K, dtype=np.float64) for mut in MUTATORS}
+    for ki, bucket in enumerate(buckets):
+        for name in bucket:
+            name2hash[name] = keys[ki]
+            if name.startswith("mut."):
+                for mut in MUTATORS:
+                    if name.startswith(f"mut.{mut}."):
+                        n_mut[mut][ki] += 1
+                        break
+            else:
+                n_base[ki] += 1
+
+    bases = [n for n in name2hash if not n.startswith("mut.")]
+    N = len(bases)
+    q = np.array([name2hash[b] for b in bases], dtype=np.uint64)
+
+    # TP_m(t): distance from each base to its own mutant, cumulative over t
+    tp = {}
+    for mut in MUTATORS:
+        d = np.array(
+            [bin(int(name2hash[b]) ^ int(name2hash[f"mut.{mut}.{b}"])).count("1")
+             for b in bases])
+        tp[mut] = np.cumsum(np.bincount(d, minlength=TMAX)[:TMAX])
+
+    # Histogram of (query, key) distances weighted by bucket composition
+    hist_base = np.zeros(TMAX)
+    hist_mut = {mut: np.zeros(TMAX) for mut in MUTATORS}
+    CHUNK = 512
+    for i in range(0, N, CHUNK):
+        d = np.bitwise_count(q[i:i + CHUNK, None] ^ keys[None, :]).astype(np.uint8)
+        flat = d.ravel()
+        sel = flat < TMAX
+        flat = flat[sel]
+        rows = d.shape[0]
+        hist_base += np.bincount(flat, weights=np.broadcast_to(n_base, (rows, K)).ravel()[sel], minlength=TMAX)[:TMAX]
+        for mut in MUTATORS:
+            hist_mut[mut] += np.bincount(flat, weights=np.broadcast_to(n_mut[mut], (rows, K)).ravel()[sel], minlength=TMAX)[:TMAX]
+
+    cum_base = np.cumsum(hist_base) - N          # exclude self (d=0 always)
+    print(f"\n=== {label} ===")
+    print(f"{'t':>2} | " + " | ".join(f"{mut:>22}" for mut in MUTATORS))
+    print(f"{'':>2} | " + " | ".join(f"{'recall':>10} {'precis':>11}" for _ in MUTATORS))
+    curves = {}
+    for mut in MUTATORS:
+        fp = (np.cumsum(hist_mut[mut]) - tp[mut]) + cum_base
+        rec = tp[mut] / N
+        prec = np.divide(tp[mut], tp[mut] + fp,
+                         out=np.zeros(TMAX), where=(tp[mut] + fp) > 0)
+        curves[mut] = (rec, prec)
+    for t in range(TMAX):
+        row = " | ".join(f"{curves[mut][0][t]:>10.4f} {curves[mut][1][t]:>11.6f}" for mut in MUTATORS)
+        print(f"{t:>2} | {row}")
+    return curves
+
+if __name__ == "__main__":
+    curves_by_store = {}
+    for path, label in [("dct.store", "DCT"), ("median.store", "Median")]:
+        full = f"/home/mark/workspace/repos/image-similarity/{path}"
+        curves_by_store[label] = main(full, label)
+
+    try:
+        import matplotlib
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+        fig, axes = plt.subplots(1, 2, figsize=(13, 5.5), sharey=True)
+        for ax, (label, curves) in zip(axes, curves_by_store.items()):
+            for mut, (rec, prec) in curves.items():
+                ax.plot(rec, prec, marker=".", label=mut)
+            ax.set_title(f"{label} hash — 24,988 Flickr images, thresholds 0–32")
+            ax.set_xlabel("Recall")
+            ax.set_ylabel("Precision")
+            ax.grid(alpha=.3)
+            ax.legend()
+        fig.tight_layout()
+        fig.savefig("/tmp/imgsim/pr-full.png", dpi=110)
+        print("\nplot: /tmp/imgsim/pr-full.png")
+    except ImportError:
+        print("\nmatplotlib not available; table output only")