X.fillna(0, inplace=True)
X["PairId"] = X["PairId"].apply(lambda x: int(x)-1)
#print X
edges = dataset.getAdjList_clique()
#edges = dataset.getAdjList_lineGraph()
#edges = dataset.getAdjList_tags()
#edges = dataset.getAdjList_allTags()
print "Length of edges returned", len(edges)
Adj, rowsum = get_GCN_inputs(edges, len(X))
print "Adjacency Graph", Adj
#print X
X_Tags_Feature = Variable(getPostContexts(X, dataset), requires_grad=False)
print len(X_Tags_Feature[0])
Pairs_train, Pairs_test, Y_train, Y_test = train_test_split(X.loc[:,'PairId'], X.loc[:,'Credible'], test_size=0.2, random_state=1234)
trainset = torch.utils.data.TensorDataset(torch.LongTensor(Pairs_train.values), torch.torch.LongTensor(Y_train.values))
testset = torch.utils.data.TensorDataset(torch.LongTensor(Pairs_test.values), torch.torch.LongTensor(Y_test.values))
# Data loader (input pipeline)
train_loader = torch.utils.data.DataLoader(dataset=trainset,
batch_size=args.batch_size)
test_loader = torch.utils.data.DataLoader(dataset=testset,
batch_size=len(Pairs_test),
for Pairs_train, Pairs_test in kf.split(Dataset):
count += 1
if count == 4:
print result_list
print sum(result_list) / len(result_list)
torch.save(
gcn_model.state_dict(),
'/home/junting/Downloads/GCN/UserCredibility/Accuracy-Stackexchange/WWW/gcnmodel_'
+ args.root.split('/')[-1] + '_www' + '.pt')
exit()
edges4 = dataset.getAdjList_Similarity3(Pairs_train.tolist())
Adj4, rowsum = get_GCN_inputs3(edges4, len(X))
Adj4 = Adj4.to(device)
X["Rating"] = dataset.Rating["Rating"]
data, X_Tags_Feature2 = getPostContexts(X, dataset)
X_Tags_Feature = Variable(data, requires_grad=False).cuda()
# setting of GCN
nComm = 1
nHid1 = 50
nHid2 = 10
nHid3 = 10
nHid4 = 5
nFeat = X_Tags_Feature.shape[1]
gcn_model = GCN_WWW(nFeat, nHid1, nHid2, nHid3, nHid4,
nComm).to(device)
criterion = nn.MSELoss()
gcn_optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad,
gcn_model.parameters()),
lr=args.learning_rate,
#NegClass_Sample = pd.DataFrame(NegClass_List, columns=PosClass.columns)
if len(PosClass) > len(NegClass):
NegClass_Sample = NegClass
else:
NegClass_Sample = NegClass.sample(n=len(PosClass))
X = pd.concat([PosClass, NegClass_Sample])
## PreProcess the dataset
cols = X.columns.drop('QTags')
X[cols] = X[cols].apply(pd.to_numeric, errors='coerce')
X.fillna(0, inplace=True)
X["PairId"] = X["PairId"].apply(lambda x: int(x) - 1)
X_Features_scaled = getPostContexts(X, dataset)
X.iloc[:, 6:] = X_Features_scaled
print X
exit()
#Text_Features_df = dataset.getTextFeatures(X)
#X_Text = X.merge(Text_Features_df, on='PairId')
#dtype = dict(PairId=int)
# #print X.dtypes
# Posters = X.AskerId.unique()
# Commenters = X.CommenterId.unique()
# Users = set(Posters).union(set(Commenters))
#
# #Create UserIndex
# UserIndex = dict()
