def search_tm(query_text, limit, lda_dictionary, lda_mdl, lda_index, lda_file_path_index):
ts_results = search_lda_model(query_text, lda_dictionary, lda_mdl, lda_index, lda_file_path_index, limit)
## ts_results are in this format [doc_id, doc_dir_path, doc_name, score]
if len(ts_results) == 0:
print 'No documents found.'
return
# Note: we need a float conversion because
# it's retrieving as string
results = [[row[2], ((float(row[3]) + 1.0) / 2.0)]
for row in ts_results]
return results
def search_tm(query_text, limit, mdl_cfg):
lda_dictionary, lda_mdl, lda_index, lda_file_path_index = load_tm(mdl_cfg)
ts_results = search_lda_model(query_text, lda_dictionary, lda_mdl, lda_index, lda_file_path_index, limit)
## ts_results are in this format [doc_id, doc_dir_path, doc_name, score]
# grabs the files details from the index
index_dir = mdl_cfg['LUCENE']['lucene_index_dir']
ts_results = get_indexed_file_details(ts_results, index_dir)
if len(ts_results) == 0:
print 'No documents found.'
return
# Normalize the similarity scores
results = [[row[0], ((float(row[10]) + 1.0) / 2.0)] for row in ts_results]
return results