Initial commit (clean history)HEADmain

1 files changed, 52 insertions, 0 deletions

diff --git a/scripts/build_item_space.py b/scripts/build_item_space.py
new file mode 100644
index 0000000..c98238c
--- /dev/null
+++ b/scripts/build_item_space.py
@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""
+Script to build Item Space (PCA Projection) from Memory Embeddings.
+Inputs:
+- data/corpora/memory_embeddings.npy (M x 4096)
+Outputs:
+- data/corpora/item_projection.npz (P, mean, V)
+"""
+
+import sys
+import os
+import numpy as np
+
+# Add src to sys.path
+sys.path.append(os.path.join(os.path.dirname(__file__), "../src"))
+
+from personalization.user_model.features import ItemProjection
+
+def main():
+    emb_path = "data/corpora/memory_embeddings.npy"
+    out_path = "data/corpora/item_projection.npz"
+    
+    if not os.path.exists(emb_path):
+        print(f"Error: {emb_path} not found. Run migrate_preferences.py first.")
+        sys.exit(1)
+        
+    print(f"Loading embeddings from {emb_path}...")
+    E = np.load(emb_path)
+    print(f"Loaded shape: {E.shape}")
+    
+    # Target dimension k=256
+    k = 256
+    print(f"Fitting PCA with k={k}...")
+    
+    proj = ItemProjection.from_pca(E, k=k)
+    
+    print("Transforming all embeddings to item space...")
+    V = proj.transform_embeddings(E)
+    print(f"Item vectors shape: {V.shape}")
+    
+    print(f"Saving projection to {out_path}...")
+    np.savez(
+        out_path,
+        P=proj.P,
+        mean=proj.mean,
+        V=V
+    )
+    print("Done.")
+
+if __name__ == "__main__":
+    main()
+