normalize_interactions.py

print('users')
users = da.from_npy_stack('users', mmap_mode=None).compute().astype(np.int32)

print('items')
items = da.from_npy_stack('items', mmap_mode=None).compute().astype(np.int32)

print('getting unique')
unique_items,  item_inverse, item_count = np.unique(items, return_counts=True, return_inverse=True)
print('creating mask')
good_items = unique_items[np.where(item_count > 50)[0]]
mask = np.isin(items, good_items)
users = users[mask]
items = items[mask]
item_count = item_count[np.where(item_count>50)[0]]

# Normalize users and items to start at id:0
user_id_map_norm = {v:i for i,v in enumerate(set(users))}
item_id_map_norm = {v:i for i,v in enumerate(set(items))}

users = np.array([user_id_map_norm[x] for x in users])
items = np.array([item_id_map_norm[x] for x in items])
users = users.astype(np.int32)
items = items.astype(np.int32)
print(f'we now have {len(items)} interactions')