def regeression_sampler(self, test_id, batch, le):
pthway = Data()
pthway.test_id = test_id
pthway.operate_id = np.setdiff1d(batch, test_id)
pthway.pthway_NameList = self.data.pthway_NameList.iloc[pthway.operate_id,:]
if (self.data.pthway_NameList.iloc[pthway.test_id,:]['GenomeType'].values != 'protein'):
raise IndexError('The test element is not the protein type. \t')
if (np.all(pthway.pthway_NameList['GenomeType'].values == 'protein') is False):
raise IndexError('Some of Related Genome ar not protein type.\t')
# The pathway name list that exclude the target protein
pthway.Genome_NameList = pthway.pthway_NameList['GenomeName'].values
# Only the name of target protein
pthway.Test_NameList = self.data.pthway_NameList.iloc[pthway.test_id,:]['GenomeName'].values
# The overall trained dataset
activ_id = le.transform(pthway.Genome_NameList)
pthway.activ_free = self.data.activ_free[activ_id]
pthway.activ_cancer = self.data.activ_cancer[activ_id]
# the target value
activ_id_test = le.transform(pthway.Test_NameList)
pthway.activ_free_target = self.data.activ_free[activ_id_test]
pthway.activ_cancer_target = self.data.activ_cancer[activ_id_test]
return pthway
def sampler_generater(self, batch, le):
"""
This function passes batch index number to obtained trained object
"""
deep_pthway = Data()
newpthway_Namelist = self.data.pthway_NameList.iloc[batch,:].reset_index(drop=True)
deep_pthway.genome_Namelist = newpthway_Namelist[newpthway_Namelist['GenomeType'] == 'protein']['GenomeName'].values
activ_id = le.transform(deep_pthway.genome_Namelist)
deep_pthway.activ_free = self.data.activ_free[activ_id]
deep_pthway.activ_cancer = self.data.activ_cancer[activ_id]
deep_pthway.pth_Namelist = newpthway_Namelist
Edgelist = self.data.Edgelist
Namelist_l = list(newpthway_Namelist['GenomeName'].values)
Edgelist_l = list(Edgelist.iloc[:,0].values)
Edgelist_ll = list(Edgelist.iloc[:,1].values)
exclude_list = []
for idx, (elem, elem2) in enumerate(zip(Edgelist_l, Edgelist_ll)):
if ((elem not in Namelist_l) or (elem2 not in Namelist_l)):
exclude_list.append(idx)
newpthway_Edgelist = Edgelist.drop(exclude_list).reset_index(drop=True)
deep_pthway.Edgelist = newpthway_Edgelist
le2 = LabelEncoder()
le2.fit(deep_pthway.pth_Namelist['GenomeName'].values)
deep_pthway.edge_index = le2.transform(deep_pthway.Edgelist.iloc[:,:2].values.reshape(-1)).reshape(-1,2)
deep_pthway.all_elem_className = list(le2.classes_)
# Label edge_class
le2 = LabelEncoder()
le2.fit(deep_pthway.Edgelist['edgeType'])
deep_pthway.edge_class = le2.transform(deep_pthway.Edgelist['edgeType'])
deep_pthway.edge_className = list(le2.classes_)
# Label node class
le2 = LabelEncoder()
le2.fit(deep_pthway.pth_Namelist['GenomeType'])
deep_pthway.node_class = le2.transform(deep_pthway.pth_Namelist['GenomeType'])
deep_pthway.node_className = list(le2.classes_)
return deep_pthway
