.gitignore

 data/
-./results/
+results/
+experiments_logs/*
\ No newline at end of file

cdbpr-env.yml

@@ -17,13 +17,17 @@ dependencies:
   - blas=1.0=mkl
   - bleach=4.1.0=pyhd3eb1b0_0
   - bottleneck=1.3.5=py311hbed6279_0
+  - brotli=1.0.9=h5eee18b_7
+  - brotli-bin=1.0.9=h5eee18b_7
   - bzip2=1.0.8=h7b6447c_0
   - ca-certificates=2023.12.12=h06a4308_0
   - certifi=2024.2.2=py311h06a4308_0
   - cffi=1.16.0=py311h5eee18b_0
   - charset-normalizer=2.0.4=pyhd3eb1b0_0
   - comm=0.1.2=py311h06a4308_0
+  - contourpy=1.2.0=py311hdb19cb5_0
   - cpuonly=2.0=0
+  - cycler=0.11.0=pyhd3eb1b0_0
   - cyrus-sasl=2.1.28=h52b45da_1
   - dbus=1.13.18=hb2f20db_0
   - debugpy=1.6.7=py311h6a678d5_0
@@ -34,6 +38,7 @@ dependencies:
   - ffmpeg=4.3=hf484d3e_0
   - filelock=3.13.1=py311h06a4308_0
   - fontconfig=2.14.1=h4c34cd2_2
+  - fonttools=4.25.0=pyhd3eb1b0_0
   - freetype=2.12.1=h4a9f257_0
   - glib=2.69.1=he621ea3_2
   - gmp=6.2.1=h295c915_3
@@ -66,11 +71,15 @@ dependencies:
   - jupyterlab_pygments=0.1.2=py_0
   - jupyterlab_server=2.25.1=py311h06a4308_0
   - jupyterlab_widgets=3.0.9=py311h06a4308_0
+  - kiwisolver=1.4.4=py311h6a678d5_0
   - krb5=1.20.1=h143b758_1
   - lame=3.100=h7b6447c_0
   - lcms2=2.12=h3be6417_0
   - ld_impl_linux-64=2.38=h1181459_1
   - lerc=3.0=h295c915_0
+  - libbrotlicommon=1.0.9=h5eee18b_7
+  - libbrotlidec=1.0.9=h5eee18b_7
+  - libbrotlienc=1.0.9=h5eee18b_7
   - libclang=14.0.6=default_hc6dbbc7_1
   - libclang13=14.0.6=default_he11475f_1
   - libcups=2.4.2=h2d74bed_1
@@ -100,6 +109,8 @@ dependencies:
   - llvm-openmp=14.0.6=h9e868ea_0
   - lz4-c=1.9.4=h6a678d5_0
   - markupsafe=2.1.3=py311h5eee18b_0
+  - matplotlib=3.8.0=py311h06a4308_0
+  - matplotlib-base=3.8.0=py311ha02d727_0
   - matplotlib-inline=0.1.6=py311h06a4308_0
   - mistune=2.0.4=py311h06a4308_0
   - mkl=2023.1.0=h213fc3f_46344
@@ -109,6 +120,7 @@ dependencies:
   - mpc=1.1.0=h10f8cd9_1
   - mpfr=4.0.2=hb69a4c5_1
   - mpmath=1.3.0=py311h06a4308_0
+  - munkres=1.1.4=py_0
   - mysql=5.7.24=h721c034_2
   - nbclient=0.8.0=py311h06a4308_0
   - nbconvert=7.10.0=py311h06a4308_0
@@ -135,6 +147,7 @@ dependencies:
   - pillow=10.2.0=py311h5eee18b_0
   - pip=23.3.1=py311h06a4308_0
   - platformdirs=3.10.0=py311h06a4308_0
+  - plotly=5.9.0=py311h06a4308_0
   - ply=3.11=py311h06a4308_0
   - prometheus_client=0.14.1=py311h06a4308_0
   - prompt-toolkit=3.0.43=py311h06a4308_0
@@ -144,6 +157,7 @@ dependencies:
   - pure_eval=0.2.2=pyhd3eb1b0_0
   - pycparser=2.21=pyhd3eb1b0_0
   - pygments=2.15.1=py311h06a4308_1
+  - pyparsing=3.0.9=py311h06a4308_0
   - pyqt=5.15.10=py311h6a678d5_0
   - pyqt5-sip=12.13.0=py311h5eee18b_0
   - python=3.11.7=h955ad1f_0
@@ -167,6 +181,7 @@ dependencies:
   - rpds-py=0.10.6=py311hb02cf49_0
   - scikit-learn=1.2.2=py311h6a678d5_1
   - scipy=1.11.4=py311h08b1b3b_0
+  - seaborn=0.12.2=py311h06a4308_0
   - send2trash=1.8.2=py311h06a4308_0
   - setuptools=68.2.2=py311h06a4308_0
   - sip=6.7.12=py311h6a678d5_0
@@ -177,6 +192,7 @@ dependencies:
   - stack_data=0.2.0=pyhd3eb1b0_0
   - sympy=1.12=py311h06a4308_0
   - tbb=2021.8.0=hdb19cb5_0
+  - tenacity=8.2.2=py311h06a4308_0
   - terminado=0.17.1=py311h06a4308_0
   - threadpoolctl=2.2.0=pyh0d69192_0
   - tinycss2=1.2.1=py311h06a4308_0

code/DOA.py

@@ -4,10 +4,8 @@ import numpy as np
 import argparse
 import numpy as np
 import sys
-sys.path.append('../')
-sys.path.insert(0, os.path.abspath('../portrait/'))
-sys.path.insert(0, os.path.abspath('../../portrait/'))
-from Utility import DatasetProcessor
+sys.path.append('/')
+from utility.DatasetProcessor import DatasetProcessor
 
 def compute_kc_user(name):
     fileName = name + "_responses.csv"
@@ -127,49 +125,27 @@ def fromDFtoArray(name, vector, type_value):
     return r
 
 if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-dt", "--datasetName", help="data file")
+    args = parser.parse_args()
+    dataset_name = args.datasetName
 
     xp_folder_name = "8-Preprocessing_pipeline"
-    rel_data_path = "01-Data"
-    rel_xp_path = "02-Resultats/04-Dataset_preparation_logs"
-    abs_xp_path = "../Experiments"
+    rel_data_path = "../data/raw_format"
+    rel_xp_path = "../experiments_logs"
+    abs_xp_path = "../experiments_logs"
+    embs_path = "../results/table_2/users/"
 
     exp = DatasetProcessor("3", data_path=rel_data_path, experiment_path=rel_xp_path)
 
-    dataset_name = "bridge"
-    dataset_file= 'preprocessed_bridge_to_algebra_2006_2007_30-01-2024.csv'
-    metadata_file = "metadata_bridge_to_algebra_2006_2007_30-01-2024.json"
+    dataset_file= dataset_name+'.csv'
+    metadata_file = "metadata_"+dataset_name+".json"
 
     exp.import_dataset(dataset_file_name=dataset_file, metadata_file_name="metadata/"+metadata_file,
                    dataset_name=dataset_name)
     exp.shuffle(dataset_name=dataset_name, attributes=["start_time"], group_attributes=["user_id"], rgn_seed=1)
 
-    files_dict = {
-        "DINA":[
-        "DINA_gs_DINA_bridge_to_algebra_2006_2007_1706638361__30-01-2024_18h05_55s_706709ms.csv",
-        "DINA_gs_DINA_bridge_to_algebra_2006_2007_1706638361__30-01-2024_18h11_36s_231506ms.csv",
-        "DINA_gs_DINA_bridge_to_algebra_2006_2007_1706638361__30-01-2024_18h17_17s_745290ms.csv",
-        "DINA_gs_DINA_bridge_to_algebra_2006_2007_1706638361__30-01-2024_18h23_07s_203039ms.csv",
-        "DINA_gs_DINA_bridge_to_algebra_2006_2007_1706638361__30-01-2024_18h28_59s_133353ms.csv"],
-        "MCD": [
-            "MCD_gs_MCD_bridge_to_algebra_2006_2007_1706630335__30-01-2024_15h42_34s_350457ms.csv",
-            "MCD_gs_MCD_bridge_to_algebra_2006_2007_1706630335__30-01-2024_15h44_20s_914592ms.csv",
-            "MCD_gs_MCD_bridge_to_algebra_2006_2007_1706630335__30-01-2024_15h46_09s_386992ms.csv",
-            "MCD_gs_MCD_bridge_to_algebra_2006_2007_1706630335__30-01-2024_15h47_58s_712822ms.csv",
-            "MCD_gs_MCD_bridge_to_algebra_2006_2007_1706630335__30-01-2024_15h49_48s_259017ms.csv"],
-        "NCDM": [
-            "NCDM_gs_NCDM_bridge_to_algebra_2006_2007_1706635966__30-01-2024_16h43_34s_649606ms.csv",
-            "NCDM_gs_NCDM_bridge_to_algebra_2006_2007_1706635966__30-01-2024_16h45_38s_895859ms.csv",
-            "NCDM_gs_NCDM_bridge_to_algebra_2006_2007_1706635966__30-01-2024_16h47_39s_318338ms.csv",
-            "NCDM_gs_NCDM_bridge_to_algebra_2006_2007_1706635966__30-01-2024_16h49_43s_359826ms.csv",
-            "NCDM_gs_NCDM_bridge_to_algebra_2006_2007_1706635966__30-01-2024_16h51_45s_189893ms.csv"],
-        "BPR" : [
-            "bpr_bridge_0_embed.csv",
-            "bpr_bridge_1_embed.csv",
-            "bpr_bridge_2_embed.csv",
-            "bpr_bridge_3_embed.csv",
-            "bpr_bridge_4_embed.csv"
-        ]
-    }
+
 
     print("dataset ",dataset_name)
 
@@ -179,7 +155,7 @@ if __name__ == '__main__':
 
     for i_fold in range(5):
         print("fold", i_fold)
-        for model in files_dict :
+        for model in dao_mean_train.keys() :
             print("model ", model)
 
             exp.train_test_split(dataset_name, test_proportion=0.2, valid_proportion=0.2, n_folds=5, i_fold=i_fold)
@@ -202,7 +178,7 @@ if __name__ == '__main__':
             data = pivot_df.sort_values('skill_id')
             data.to_csv('dataTest_responses.csv', header=False, index=False, na_rep='')
 
-            F = fromDFtoArray("./Embeddings/" + str(files_dict[model][i_fold]), False, 'f')
+            F = fromDFtoArray(embs_path + dataset_name +"_"+str(i_fold)+"_"+model+".csv", False, 'f')
             # print(F)
             kc_user, kc_user_val, dico_u, num_kc = compute_kc_user("dataTrain")
             print("num_kc", num_kc)
@@ -218,7 +194,7 @@ if __name__ == '__main__':
     print("dao train", dao_mean_train)
     print("dao test", dao_mean_test)
     print("reo", reo_mean)
-    for model in files_dict:
+    for model in dao_mean_train.keys():
         print("model",model)
         print("dao train", np.mean(np.array(dao_mean_train[model])),"+-",np.std(np.array(dao_mean_train[model])))
         print("dao test", np.mean(np.array(dao_mean_test[model])),"+-",np.std(np.array(dao_mean_test[model])))

code/binary_bpr/main.py

@@ -62,7 +62,7 @@ def read_file(dataTrain, dataTest):
     dico_items = { k:v for (k,v) in zip(items, range(num_items))} 
     return dico_kc, dico_users, dico_items
 
-def save_embeddings(xpName: str, modelName: str, embeddings,userEmbDir : str,itemEmbDir : str):
+def save_embeddings(xpName: str, modelName: str, embeddings,userEmbDir : str,itemEmbDir : str) :
     """
     Saves all the metrics measured after the training process.
 

code/binary_bpr/script.py

@@ -2,8 +2,8 @@ import os
 dPath = "../../data/"
 embDirPath = "../../results/table_2/"
 datasets = ['assist0910_tkde', 'assist17_tkde', 'algebra','math_1', 'math_2']
-epochs = [75 ,75, 95, 5, 90, 90]
-batchSize =[ 512, 512,512, 512,512,4000]
+epochs = [1, 75 ,75, 95, 5, 90, 90]
+batchSize =[4000, 512, 512,512, 512,512]
 learningRate = [0.01,0.01,0.01,0.01,0.01]
 mode = [1,1,1,1,1]
 for i in range(len(datasets)):

code/binary_bpr_ablation/script_ablation.py

@@ -5,5 +5,5 @@ 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/"+name[i]+"/train_0.csv --dataTest ../../data/"+name[i]+"/test_0.csv --ablation "+str(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)
         os.system(cmd)