join = MetaRule([body0, body1], [[[attr_name + "1"], [attr_name + "2"]]], alpha, False)
print("done join (" + str(time.time()-begtime) + "s)")
proj = Project(join, [attr_name + "0", attr_name + "3"])
print("done project (" + str(time.time()-begtime) + "s)")
metap = copy.deepcopy(body0)
metap.df.columns = [attr_name + "0", attr_name + "3"]
disj = DisjunctionRule([metap, proj], alpha, 0)
print("done disjunction (" + str(time.time()-begtime) + "s)")
meta = disj
df = labels_df_train
label = 'Label'
step = 1e-3
batch_size = 32
epochs = 1000
y = align_labels(meta, df, label)
#tmp_df = meta.df
#tmp_df["Label"] = y.numpy()
#links = tmp_df.loc[(tmp_df[label] == 1)]
#for index, row in links.iterrows():
# reverse = tmp_df.loc[(tmp_df[attr_name + "0"] == row[attr_name + "3"]) & (tmp_df[attr_name + "3"] == row[attr_name + "0"])]
# if reverse.shape[0] > 0:
# tmp_df.loc[(tmp_df[attr_name + "0"] == row[attr_name + "3"]) & (tmp_df[attr_name + "3"] == row[attr_name + "0"]), [label]] = 1
#y = torch.FloatTensor(tmp_df[[label]].values)
#tmp_df.drop([label], axis=1, inplace=True)
print("done label alignment (" + str(time.time()-begtime) + "s)")
data = TensorDataset(torch.arange(y.size()[0]), y)
all_loader = DataLoader(data, batch_size=batch_size, shuffle=True)
body1 = copy.deepcopy(body0)
body1.df.columns = [attr_name + "2", attr_name + "3"]
join = MetaRule([body0, body1], [[[attr_name + "1"], [attr_name + "2"]]],
alpha, False)
print("done join (" + str(time.time() - begtime) + "s)")
proj = Project(join, [attr_name + "0", attr_name + "3"])
print("done project (" + str(time.time() - begtime) + "s)")
#train(proj, labels_df_train, 'Label', 1e-3, 32, 400, True)
meta = proj
label = 'Label'
step = 1e-1
batch_size = 32
epochs = 1000
y = align_labels(meta, labels_df_train, label)
print("done label alignment (" + str(time.time() - begtime) + "s)")
pos_idx = np.nonzero(y.numpy())[0].tolist()
pos_loader = DataLoader(TensorDataset(torch.LongTensor(pos_idx)),
batch_size=batch_size,
shuffle=True)
optimizer = optim.Adam(meta.parameters(), lr=step)
loss_fn = nn.BCEWithLogitsLoss(reduction="sum")
#basemetapredicate alpha: is predicates, project: sum
iter = 0
for epoch in range(epochs):
pos_loss = 0.0
for idx in pos_loader:
yb = torch.ones(idx[0].size()[0], 1)