ApplETS · antoinebou12 · Nov 6, 2024 · Nov 17, 2024 · Nov 17, 2024 · Nov 29, 2024
diff --git a/notebook/combined_embeddings.ipynb b/notebook/combined_embeddings.ipynb
diff --git a/notebook/course_embeddings.ipynb b/notebook/course_embeddings.ipynb
diff --git a/notebook/data/Course.csv b/notebook/data/Course.csv
diff --git a/notebook/data/Program.csv b/notebook/data/Program.csv
diff --git a/notebook/data/ProgramCourse.csv b/notebook/data/ProgramCourse.csv
diff --git a/notebook/data/ProgramType.csv b/notebook/data/ProgramType.csv
@@ -0,0 +1,11 @@
+"id","title"
+697435,Maîtrise avec projet
+738239,Microprogramme
+697451,Maîtrise avec mémoire
+915770,Concentration en technologies de la santé
+697388,Doctorat
+700093,Programme court
+700092,Certificat
+700095,DESS
+700094,Cheminement universitaire en technologie (CUT)
+699771,Baccalauréat
diff --git a/notebook/data_exploration.ipynb b/notebook/data_exploration.ipynb
diff --git a/notebook/data_science.ipynb b/notebook/data_science.ipynb
diff --git a/notebook/db/db.png b/notebook/db/db.png
diff --git a/notebook/db/prisma-erd.svg b/notebook/db/prisma-erd.svg
diff --git a/notebook/embedding.rar b/notebook/embedding.rar
diff --git a/notebook/embedding_evaluation_results.csv b/notebook/embedding_evaluation_results.csv
@@ -0,0 +1,39 @@
+Model Name,Silhouette Score,Number of Clusters,Inertia,Time Taken,dataframe
+MiniLM,0.06354355,5,2104.3017578125,62.3960816860199,course
+Multilingual MiniLM-L12,0.06972561,5,1927.947265625,88.9396481513977,course
+MiniLM-L6,0.06067439,5,6040.69970703125,48.64740014076233,course
+Multilingual MPNet,0.055970665,5,1884.258056640625,254.99050879478455,course
+DistilRoBERTa,0.049180128,5,13973.9873046875,159.84893226623535,course
+MiniLM-L12,0.04269758,5,3714.1708984375,98.60889649391174,course
+MiniLM-L3,0.038517494,5,2678.4150390625,23.103832721710205,course
+XLM-RoBERTa Base Multilingual,0.0772015,5,49950.2265625,277.00257778167725,course
+STSB XLM-R Multilingual,0.0772015,5,49950.2265625,330.6788206100464,course
+MS MARCO DistilBERT,0.0336069,5,5619.89453125,149.96267318725586,course
+MS MARCO BERT,0.044978958,5,16743.794921875,338.83691787719727,course
+T5 Small,0.14505102,5,204.54937744140625,77.6448757648468,course
+T5 Base,0.06801192,5,996.11279296875,396.1023998260498,course
+T5 Large,0.041167583,5,1061.4305419921875,1004.1282534599304,course
+FLAN-T5 Small,0.10541956,5,162.1136932373047,71.80396556854248,course
+FLAN-T5 Base,0.06095163,5,388.6905517578125,278.6274485588074,course
+FLAN-T5 Large,0.10817401,5,129.44412231445312,915.0140993595123,course
+RoBERTa Large v1,0.051263746,5,224872.84375,903.1814665794373,course
+MPNet Base v2,0.06346093,5,3160.8056640625,266.6551468372345,course
+MiniLM,0.06354355,5,2104.3017578125,35.63298296928406,combined
+Multilingual MiniLM-L12,0.06972561,5,1927.947265625,59.94369435310364,combined
+MiniLM-L6,0.06067439,5,6040.69921875,35.490906953811646,combined
+Multilingual MPNet,0.055970665,5,1884.258056640625,177.7440221309662,combined
+DistilRoBERTa,0.049180128,5,13973.9873046875,117.59407949447632,combined
+MiniLM-L12,0.04269758,5,3714.1708984375,68.83575224876404,combined
+MiniLM-L3,0.038517494,5,2678.4150390625,18.43731689453125,combined
+XLM-RoBERTa Base Multilingual,0.0772015,5,49950.2265625,177.5923249721527,combined
+STSB XLM-R Multilingual,0.0772015,5,49950.2265625,177.61623072624207,combined
+MS MARCO DistilBERT,0.0336069,5,5619.89453125,105.29467010498047,combined
+MS MARCO BERT,0.044978958,5,16743.794921875,209.93503665924072,combined
+T5 Small,0.14505102,5,204.54937744140625,59.6424446105957,combined
+T5 Base,0.06801192,5,996.11279296875,227.7394471168518,combined
+T5 Large,0.041167583,5,1061.4306640625,745.5525488853455,combined
+FLAN-T5 Small,0.10541956,5,162.1136932373047,67.67559218406677,combined
+FLAN-T5 Base,0.06095163,5,388.6905517578125,252.0490207672119,combined
+FLAN-T5 Large,0.10817401,5,129.44412231445312,818.083892583847,combined
+RoBERTa Large v1,0.051263746,5,224872.84375,748.9289219379425,combined
+MPNet Base v2,0.06346093,5,3160.8056640625,219.38725876808167,combined
diff --git a/notebook/gnn.ipynb b/notebook/gnn.ipynb
diff --git a/notebook/knn.ipynb b/notebook/knn.ipynb
diff --git a/notebook/program_embeddings.ipynb b/notebook/program_embeddings.ipynb