def summary_performance(dataReduced, dataReconstructed):
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
val_l2 = rprec_a_l2(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
report=False)
if args.post_cn:
val_ip = val_l2
else:
val_ip = rprec_a_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
report=False)
if not args.skip_loss:
loss_q = sklearn.metrics.mean_squared_error(
data["queries"], dataReconstructed["queries"])
# loss of only the first 10k documents because it has to get copied
loss_d = sklearn.metrics.mean_squared_error(
data["docs"][:10000], dataReconstructed["docs"][:10000])
return val_ip, val_l2, loss_q.item(), loss_d.item()
else:
return val_ip, val_l2, None, None
def summary_performance(dataReduced):
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
val_l2 = rprec_a_l2(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
if args.post_cn:
val_ip = val_l2
else:
val_ip = rprec_a_ip(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
return val_ip, val_l2
def summary_performance(prefix, data_reduced, data, post_cn):
if post_cn:
data_reduced = center_data(data_reduced)
data_reduced = norm_data(data_reduced)
val_l2 = rprec_a_l2(
data_reduced["queries"],
data_reduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True, report=False
)
if post_cn:
val_ip = val_l2
else:
val_ip = rprec_a_ip(
data_reduced["queries"],
data_reduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
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_a_ip(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True)
val_l2 = rprec_a_l2(dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True)
name = name.replace("float", "f")
print(f"{name:<21} {val_ip:>5.3f} {val_l2:>5.3f}")
return val_ip, val_l2
def random_projection_performance(dim):
model = DropRandomProjection()
dataReduced = {
"queries": model.transform(data["queries"], dim, IMPR_L2),
"docs": model.transform(data["docs"], dim, IMPR_L2)
}
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
# copy to make it C-continuous
val_l2 = rprec_a_l2(
dataReduced["queries"].copy(),
dataReduced["docs"].copy(),
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
if not args.post_cn:
val_ip = rprec_a_ip(
dataReduced["queries"].copy(),
dataReduced["docs"].copy(),
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
else:
val_ip = val_l2
data_log.append({"del_dim": dim, "val_ip": val_ip, "val_l2": val_l2})
# continuously override the file
with open(args.logfile, "w") as f:
f.write(str(data_log))
print(f"Delete {dim} dims: {val_l2:<8.5f}")
def summary_performance(dataReduced, dataReconstructed):
# reconstructed data is not in the original form when scaling
# note the reverse order
if args.norm:
dataReconstructed = norm_model.inverse_transform(dataReconstructed)
if args.center:
dataReconstructed = center_model.inverse_transform(dataReconstructed)
if args.post_cn:
dataReduced = CenterScaler().transform(dataReduced)
dataReduced = NormScaler().transform(dataReduced)
val_l2 = rprec_a_l2(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
if args.post_cn:
val_ip = val_l2
else:
val_ip = rprec_a_ip(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=True,
)
loss_q = sklearn.metrics.mean_squared_error(data_orig["queries"],
dataReconstructed["queries"])
# loss of only the first 10k documents because it has to get copied
loss_d = sklearn.metrics.mean_squared_error(
data_orig["docs"][:10000], dataReconstructed["docs"][:10000])
return val_ip, val_l2, loss_q, loss_d
print("Fitting model")
# dataNew = model.fit_transform(similarities)
dataNew = model.fit_transform(dataNew)
dataNew = {
"docs": dataNew[:len(data["docs"])].copy(),
"queries": dataNew[len(data["docs"]):].copy(),
}
print(len(dataNew["docs"]))
print(len(dataNew["queries"]))
val_ip_pca = rprec_a_ip(dataNew["queries"],
dataNew["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=False)
val_l2_pca = rprec_a_l2(dataNew["queries"],
dataNew["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
fast=False)
print(f"ip: {val_ip_pca:.4f}, l2: {val_l2_pca:.4f} (MDS)")
val_ip_pca = rprec_a_ip(data["queries"],
data["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
def random_projection_performance(components, model_name, runs=3):
if model_name == "gauss":
Model = GaussianRandomProjection
elif model_name == "sparse":
Model = SparseRandomProjection
elif model_name == "crop":
Model = CropRandomProjection
else:
raise Exception("Unknown model")
random.seed(args.seed)
vals_ip = []
vals_l2 = []
for i in range(runs):
data = read_pickle(args.data)
# take only dev queries
data = sub_data(data, train=False, in_place=True)
# make sure the vectors are np arrays
data["queries"] = np.array(data["queries"])
data["docs"] = np.array(data["docs"])
model = Model(n_components=components,
random_state=random.randint(0, 2**8 - 1))
model.fit(data["docs"])
dataReduced = {
"queries": safe_transform(model, data["queries"]),
"docs": safe_transform(model, data["docs"])
}
del data["queries"]
del data["docs"]
if args.post_cn:
dataReduced = center_data(dataReduced)
dataReduced = norm_data(dataReduced)
# copy to make it C-continuous
# (skipped)
val_l2 = rprec_a_l2(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
report=False,
fast=True,
)
vals_l2.append(val_l2)
# skip IP computation because the vectors are normalized
if not args.post_cn:
val_ip = rprec_a_ip(
dataReduced["queries"],
dataReduced["docs"],
data["relevancy"],
data["relevancy_articles"],
data["docs_articles"],
report=False,
fast=True,
)
vals_ip.append(val_ip)
else:
vals_ip.append(val_l2)
logdata.append({
"dim": components,
"vals_ip": vals_ip,
"vals_l2": vals_l2,
"model": model_name
})
# continuously override the file
with open(args.logfile, "w") as f:
f.write(str(logdata))