def report(prefix, encoded, data, post_cn):
if post_cn:
encoded = center_data(encoded)
encoded = norm_data(encoded)
val_l2 = rprec_l2(
encoded["queries"], encoded["docs"],
data["relevancy"], fast=True, report=False)
if post_cn:
val_ip = val_l2
else:
val_ip = rprec_ip(
encoded["queries"], encoded["docs"],
data["relevancy"], fast=True, report=False)
print(f'{prefix} rprec_ip: {val_ip:.3f}, rprec_l2: {val_l2:.3f}')
return val_ip, val_l2
def summary_performance(name, dataReduced, dataReconstructed):
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
val_ip = rprec_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
val_l2 = rprec_l2(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
loss_q = torch.nn.MSELoss()(torch.Tensor(data["queries"]),
torch.Tensor(dataReconstructed["queries"]))
loss_d = torch.nn.MSELoss()(torch.Tensor(data["docs"]),
torch.Tensor(dataReconstructed["docs"]))
return val_ip, val_l2, loss_q.item(), loss_d.item()
def summary_performance(name, dataReduced, dataReconstructed):
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
val_ip = rprec_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
val_l2 = rprec_l2(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
loss_q = torch.nn.MSELoss()(torch.Tensor(data["queries"]),
torch.Tensor(dataReconstructed["queries"]))
loss_d = torch.nn.MSELoss()(torch.Tensor(data["docs"]),
torch.Tensor(dataReconstructed["docs"]))
name = name.replace("float", "f")
print(
f"{name:<21} {loss_d:>7.5f} {loss_q:>7.5f} {val_ip:>5.3f} {val_l2:>5.3f}"
)
return val_ip, val_l2, loss_q.item(), loss_d.item()
dataReduced = {
"queries": model.transform(data["queries"]),
"docs": model.transform(data["docs"])
}
print("\nReduced norms")
print(
f"Queries: {np.average(np.linalg.norm(dataReduced['queries'], axis=1)[:, np.newaxis]):.8f}"
)
print(
f"Docs: {np.average(np.linalg.norm(dataReduced['docs'], axis=1)[:, np.newaxis]):.8f}"
)
print("\nPerformance")
val_ip_pca = rprec_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
val_l2_pca = rprec_l2(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)
print(f"IP: {val_ip_pca}")
print(f"L2: {val_l2_pca}")
print("\nRenormalized performance")
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
val_ip_pca = rprec_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
fast=True)