The code for our models can be found in the following files:
- Data Processing:
data_process.py - Embedding Creation:
embedding_to_model.py,embedding_to_avg_max_model.py,word_embeddings.py - Linear Regression (manual features):
LR.py - Linear Regression (TF-IDF):
bow_tfidf.py,bow_visualizations.ipynb - Linear Regression (GloVe):
glove_max_avg.ipynb,glove_model.ipynb - Multi-class SVM:
SVM_base.py,SVM_more_features.py - XGBoosted Trees:
xgboosted_tree.py - Gaussian Mixture Models:
gmm_seniority.py
Additionally, there are various charts and raw output files in the /output folder