Update prediction_multilabel.py

prediction_multilabel.py

@@ -10,8 +10,8 @@ from sentence_transformers import util
 torch.manual_seed(1)
 
 # Load datasets
-df_inmemory = pd.read_csv('df_360k_41lables_05012023.csv') # labeled text extracted from 230 CSR GRI reports, 150 International companies, 2017-2021 period
-df_paragraph = pd.read_csv('german_plc_all_paragraphs_unnested_only.csv') # paragraphs to predict the label, extracted from 1.2k CSR reports, 150 German PLC companies, 2010-2021 period, 645k paragraphs)
+df_inmemory = pd.read_csv('labeled.csv') # labeled text extracted from 230 CSR GRI reports, 150 International companies, 2017-2021 period
+df_paragraph = pd.read_csv('prediction_demo.csv') # paragraphs to predict the label, extracted from 1.2k CSR reports, 150 German PLC companies, 2010-2021 period, 645k paragraphs)
 
 # Load stored embeddings
 with open('embeddings_prediction.pkl', "rb") as f: