Update prediction_multilabel.py

prediction_multilabel.py

@@ -5,20 +5,22 @@ import pandas as pd
 import torch
 import torch.nn as nn
 from sentence_transformers import util
+import os
 
 # Set random seed for reproducibility
 torch.manual_seed(1)
 
+path = os.getcwd()
 # Load datasets
-df_inmemory = pd.read_csv('raw_data/labeled.csv') # labeled text extracted from 230 CSR GRI reports, 150 International companies, 2017-2021 period
-df_paragraph = pd.read_csv('raw_data/prediction_demo.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(path + '/raw_data/labeled.csv') # labeled text extracted from 230 CSR GRI reports, 150 International companies, 2017-2021 period
+df_paragraph = pd.read_csv(path + '/raw_data/prediction_demo.csv', encoding='latin1')
 
 # Load stored embeddings
-with open('embeddings/embeddings_prediction.pkl', "rb") as f:
+with open(path + '/embeddings/embeddings_prediction.pkl', "rb") as f:
     stored_data = pickle.load(f)
     pred_embeddings = stored_data['parg_embeddings']
 
-with open('embeddings/embeddings_labeled.pkl', "rb") as f:
+with open(path + '/embeddings/embeddings_labeled.pkl', "rb") as f:
     stored_data = pickle.load(f)
     embeddings = stored_data['sent_embeddings']