diff --git a/code/binary_bpr/main.py b/code/binary_bpr/main.py
index b920d8d5f74191bd106b30f6ad3113375c54f665..479cedff19743bad9076af5eba80991c6e7ed2c3 100644
--- a/code/binary_bpr/main.py
+++ b/code/binary_bpr/main.py
@@ -289,6 +289,9 @@ if __name__ == '__main__':
acc_list = []
auc_list = []
rmse_list = []
+ precision_list = []
+ recall_list = []
+ f1_list = []
doa_train = []
#doa_test = []
if mode == 1 :
@@ -308,6 +311,7 @@ if __name__ == '__main__':
dico_kc, dico_users, dico_items = read_file(dataTrain, dataTest)
embedding_size = len(dico_kc)
dico_items, t_train, ty_train, item_users = parse_dataframe(dataTrain, dico_kc, dico_users, dico_items, True)
+
train, y_train = generate_quad(dico_items, t_train, ty_train, item_users, alpha)
dico_items, test, y_test = parse_dataframe(dataTest, dico_kc, dico_users, dico_items, False)
num_users = len(dico_users)
@@ -328,10 +332,13 @@ if __name__ == '__main__':
write_file_doa(FileNameTrain_temp, emb[0], train, dico_kc, dico_users, dico_items)
doa = compute_doa(FileNameTrain_temp)
# Test
- correctness, acc, users, auc, rmse = bpr_model.evaluate_model(test, len(dico_kc), y_test)
+ correctness, acc, users, auc, rmse, precision, recall, f1 = bpr_model.evaluate_model(test, len(dico_kc), y_test)
acc_list.append(acc)
auc_list.append(auc)
rmse_list.append(rmse)
+ precision_list.append(precision)
+ recall_list.append(recall)
+ f1_list.append(f1)
doa_train.append(doa)
print("Doa:", doa)
print("AUC and RMSE:", auc, rmse)
@@ -345,11 +352,17 @@ if __name__ == '__main__':
print(acc_list)
print(auc_list)
print(rmse_list)
+ print(precision_list)
+ print(recall_list)
+ print(f1_list)
print(doa_train)
#print(doa_test)
print("acc :",np.mean(acc_list),"+-",np.std(acc_list))
print("auc :", np.mean(auc_list), "+-", np.std(auc_list))
print("rmse :", np.mean(rmse_list), "+-", np.std(rmse_list))
+ print("precision :", np.mean(precision_list), "+-", np.std(precision_list))
+ print("recall :", np.mean(recall_list), "+-", np.std(recall_list))
+ print("f1 :", np.mean(f1_list), "+-", np.std(f1_list))
print("doa_train :", np.mean(doa_train), "+-", np.std(doa_train))
#print("doa_test :", np.mean(doa_test), "+-", np.std(doa_test))
#print("reo :",1- np.mean(doa_test)/np.mean(doa_train))
@@ -381,7 +394,7 @@ if __name__ == '__main__':
doa = compute_doa(trainFileName)
print("Doa:", doa)
# Test
- correctness, acc, users, auc, rmse = bpr_model.evaluate_model(test, len(dico_kc), y_test)
+ correctness, acc, users, auc, rmse, precision, recall, f1 = bpr_model.evaluate_model(test, len(dico_kc), y_test)
print(f'Accuracy: {acc}')
#new_embedding_value = bpr_model.user_embeddings.weight.clone().detach().cpu().numpy()
#write_file_doa_test(testFileName, new_embedding_value, test, y_test, dico_kc, dico_users, dico_items)
diff --git a/code/binary_bpr/script.py b/code/binary_bpr/script.py
index f87bf4fd7be4ec040413fd82b36db2eded9548c7..2a77babc503f6b4a78c730e2c35b3057c5617668 100644
--- a/code/binary_bpr/script.py
+++ b/code/binary_bpr/script.py
@@ -1,8 +1,8 @@
import os
-dPath = "../../data/"
+dPath = "../../data/cdbpr_format/"
embDirPath = "../../results/table_2/"
datasets = ['assist0910_tkde', 'assist17_tkde', 'algebra','math_1', 'math_2']
-epochs = [75 ,75, 95, 5, 90, 90]
+epochs = [70, 95, 75, 75, 90]
batchSize =[ 512, 512,512, 512,512]
learningRate = [0.01,0.01,0.01,0.01,0.01]
mode = [1,1,1,1,1]
diff --git a/code/binary_bpr_ablation/BPR_model.py b/code/binary_bpr_ablation/BPR_model.py
index 6746938213182c83c589044107826db01f8a4caf..441416e0a6be1272d3cbb055097e89b872997eee 100644
--- a/code/binary_bpr_ablation/BPR_model.py
+++ b/code/binary_bpr_ablation/BPR_model.py
@@ -5,7 +5,7 @@ from torch.utils.data import DataLoader, TensorDataset
import numpy as np
import torch.nn.functional as F
import pandas as pd
-from sklearn.metrics import roc_auc_score
+from sklearn.metrics import roc_auc_score, recall_score, f1_score
from sklearn.metrics import mean_squared_error
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
@@ -151,12 +151,12 @@ class BPRModel(nn.Module):
all_decisions = np.concatenate((all_decisions, comp), axis=0)
mse1 = mean_squared_error(all_labels, all_predictions)
- print("RMSE", np.sqrt(mse1))
auc = roc_auc_score(all_labels, all_predictions)
- print("AUC:", auc)
acc = accuracy_score(all_labels, all_decisions)
- print("ACC:", acc)
precision = precision_score(all_labels, all_decisions)
- print(f'Prec: {precision}')
- return acc, precision
+ recall = recall_score(all_labels, all_decisions)
+ f1 = f1_score(all_labels, all_decisions)
+
+ print(f"acc, precision, recall, f1, auc, rmse : {acc},{precision},{recall},{f1},{auc},{np.sqrt(mse1)}")
+ return acc, precision, recall,f1, auc,np.sqrt(mse1)
diff --git a/code/binary_bpr_ablation/main.py b/code/binary_bpr_ablation/main.py
index 3fa28a5b549bb298bf38638bb1366086300e3ec0..0f8217a25a3c6d6a5df47629e822a2bd2c5bbf26 100644
--- a/code/binary_bpr_ablation/main.py
+++ b/code/binary_bpr_ablation/main.py
@@ -187,8 +187,7 @@ def write_file_doa(FileName, embed, train, dico_kc, dico_users, dico_items):
#############################
#############################
# HP
-epochs = 20
-batch_size = 1024
+batch_size = 512
ablation = 0
# 0 no ablation, 1 ablation L2, 2 ablation init, 3 both
if __name__ == '__main__':
@@ -196,9 +195,11 @@ if __name__ == '__main__':
parser.add_argument("-dtrain", "--dataTrain", help="data file")
parser.add_argument("-dtest", "--dataTest", help="data file")
parser.add_argument("-ab", "--ablation", help="int")
+ parser.add_argument("-e", "--epochs", help="int",type=int)
args = parser.parse_args()
dataTrain = args.dataTrain
dataTest = args.dataTest
+ epochs = args.epochs
if args.ablation:
ablation = int(args.ablation)
file = dataTrain[:-4]
@@ -223,4 +224,5 @@ if __name__ == '__main__':
doa = compute_doa(file)
print("DOA:", doa)
# Test
- acc, precision = bpr_model.evaluate_model(test, len(dico_kc), y_test)
+ acc, precision, recall,f1, auc, rmse = bpr_model.evaluate_model(test, len(dico_kc), y_test)
+
diff --git a/code/binary_bpr_ablation/script_ablation.py b/code/binary_bpr_ablation/script_ablation.py
index 7825c4b543b207d1ca0214d7e68a3eb72c2427cc..b7fb6e3deb0d3bb98f7f71c1d320deeebeaedb35 100644
--- a/code/binary_bpr_ablation/script_ablation.py
+++ b/code/binary_bpr_ablation/script_ablation.py
@@ -1,9 +1,10 @@
import os
+epochs = [70, 95, 75, 75, 90]
name = ["assist0910_tkde","assist17_tkde","algebra", "math_1","math_2"]
for i in range(4):
print("Ablation (0 no ablation, 1 ablation L2, 2 ablation init, 3 both) ",i)
for a in range(5):
print(name[i])
- cmd = "python main.py --dataTrain ../../data/cdbpr_format/"+name[i]+"/train_0.csv --dataTest ../../data/cdbpr_format/"+name[i]+"/test_0.csv --ablation "+str(i)
+ cmd = "python main.py --epochs "+str(epochs[i])+" --dataTrain ../../data/cdbpr_format/"+str(name[i])+"/train_valid_"+str(a)+".csv --dataTest ../../data/cdbpr_format/"+str(name[i])+"/test_"+str(a)+".csv --ablation "+str(i)
os.system(cmd)