{"entrez_gene_id": int})
candidate_sentence_df.head(2)
# In[10]:
total_candidates_df = (edge_level_df.merge(candidate_sentence_df,
on=["doid_id", "entrez_gene_id"]))
total_candidates_df.head(2)
# In[11]:
dev_candidates = (session.query(DiseaseGene).filter(
DiseaseGene.id.in_(
total_candidates_df.query("split==1").sample(
10000, random_state=100).candidate_id.tolist())).all())
dev_df = make_sentence_df(dev_candidates)
dev_df.head(2)
# In[12]:
test_candidates = (session.query(DiseaseGene).filter(
DiseaseGene.id.in_(
total_candidates_df.query("split==2").sample(
10000, random_state=120).candidate_id.tolist())).all())
test_df = make_sentence_df(test_candidates)
test_df.head(2)
# In[13]:
#write_candidates_to_excel(dev_df, "../data/sentences/sentence_labels_dev.xlsx")
#write_candidates_to_excel(test_df, "../data/sentences/sentence_labels_test.xlsx")
'dev': 'data/compound_disease/sentence_labels_dev.xlsx'
}
# In[ ]:
for sql, spreadsheet_name in zip(sql_statements, spreadsheet_names.values()):
target_cids = [x[0] for x in session.execute(sql)]
candidates = (
session
.query(CandidateClass)
.filter(CandidateClass.id.in_(target_cids))
.all()
)
candidate_df = make_sentence_df(candidates)
write_candidates_to_excel(candidate_df, spreadsheet_name)
# # Develop Label Functions
# ## Look at potential Candidates
# Use this to look at loaded candidates from a given set. The constants represent the index to retrieve the appropiate set. Ideally, here is where one can look at a subset of the candidate and develop label functions for candidate labeling.
# In[ ]:
train_df = pd.read_excel(spreadsheet_names['train'])
train_df.head(2)