hkbuttar · skylarliu1 · Aug 28, 2026 · Aug 28, 2026 · Aug 28, 2026
diff --git a/.DS_Store b/.DS_Store
diff --git a/.gitattributes b/.gitattributes
@@ -2,4 +2,3 @@
 Data/Raw/modcloth_final_data.json filter=lfs diff=lfs merge=lfs -text
 Data/Raw/renttherunway_final_data.json filter=lfs diff=lfs merge=lfs -text
 *.csv filter=lfs diff=lfs merge=lfs -text
-Models/bagging_simple_classifier.joblib filter=lfs diff=lfs merge=lfs -text
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,19 @@
+# Virtual environment (already committed historically; kept out of new commits)
+venvfit/
+
+# macOS
+.DS_Store
+**/.DS_Store
+
+# Python
+__pycache__/
+*.pyc
+*.pyo
+.ipynb_checkpoints/
+
+# Data — regenerable via src/download_data.py + src/data_cleaning.py + the notebooks
+Data/Raw/
+Data/Processed/
+
+# Trained model artifacts — regenerable by running the Phase 2 notebooks
+Models/
diff --git a/Data/Processed/Supervised_Outputs/bagging_feature_names.csv b/Data/Processed/Supervised_Outputs/bagging_feature_names.csv
diff --git a/Data/Processed/Supervised_Outputs/bagging_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/bagging_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/bagging_simple_predictions.csv b/Data/Processed/Supervised_Outputs/bagging_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/cart_feature_importances.csv b/Data/Processed/Supervised_Outputs/cart_feature_importances.csv
diff --git a/Data/Processed/Supervised_Outputs/cart_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/cart_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/cart_simple_predictions.csv b/Data/Processed/Supervised_Outputs/cart_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/comparison_rtr_vs_simple.csv b/Data/Processed/Supervised_Outputs/comparison_rtr_vs_simple.csv
diff --git a/Data/Processed/Supervised_Outputs/kernel_svm_feature_names.csv b/Data/Processed/Supervised_Outputs/kernel_svm_feature_names.csv
diff --git a/Data/Processed/Supervised_Outputs/kernel_svm_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/kernel_svm_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/kernel_svm_simple_predictions.csv b/Data/Processed/Supervised_Outputs/kernel_svm_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/knn_feature_names.csv b/Data/Processed/Supervised_Outputs/knn_feature_names.csv
diff --git a/Data/Processed/Supervised_Outputs/knn_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/knn_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/knn_simple_predictions.csv b/Data/Processed/Supervised_Outputs/knn_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/linear_svm_feature_names.csv b/Data/Processed/Supervised_Outputs/linear_svm_feature_names.csv
diff --git a/Data/Processed/Supervised_Outputs/linear_svm_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/linear_svm_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/linear_svm_simple_predictions.csv b/Data/Processed/Supervised_Outputs/linear_svm_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/naive_bayes_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/naive_bayes_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/naive_bayes_simple_predictions.csv b/Data/Processed/Supervised_Outputs/naive_bayes_simple_predictions.csv
diff --git a/Data/Processed/Supervised_Outputs/random_forest_feature_importances.csv b/Data/Processed/Supervised_Outputs/random_forest_feature_importances.csv
diff --git a/Data/Processed/Supervised_Outputs/random_forest_fit_probabilities.csv b/Data/Processed/Supervised_Outputs/random_forest_fit_probabilities.csv
diff --git a/Data/Processed/Supervised_Outputs/random_forest_simple_predictions.csv b/Data/Processed/Supervised_Outputs/random_forest_simple_predictions.csv
diff --git a/Data/Processed/Unsupervised_Outputs/dbscan_cluster_profiles.csv b/Data/Processed/Unsupervised_Outputs/dbscan_cluster_profiles.csv
diff --git a/Data/Processed/Unsupervised_Outputs/dbscan_cluster_profiles_with_sizes.csv b/Data/Processed/Unsupervised_Outputs/dbscan_cluster_profiles_with_sizes.csv
diff --git a/Data/Processed/Unsupervised_Outputs/dbscan_df.csv b/Data/Processed/Unsupervised_Outputs/dbscan_df.csv
diff --git a/Data/Processed/Unsupervised_Outputs/dbscan_pca_results.csv b/Data/Processed/Unsupervised_Outputs/dbscan_pca_results.csv
diff --git a/Data/Processed/Unsupervised_Outputs/dbscan_tsne_results.csv b/Data/Processed/Unsupervised_Outputs/dbscan_tsne_results.csv
diff --git a/Data/Processed/Unsupervised_Outputs/gmm_cluster_profiles.csv b/Data/Processed/Unsupervised_Outputs/gmm_cluster_profiles.csv
diff --git a/Data/Processed/Unsupervised_Outputs/gmm_df.csv b/Data/Processed/Unsupervised_Outputs/gmm_df.csv
diff --git a/Data/Processed/Unsupervised_Outputs/gmm_pca_5d_body_features.csv b/Data/Processed/Unsupervised_Outputs/gmm_pca_5d_body_features.csv
diff --git a/Data/Processed/Unsupervised_Outputs/gmm_pca_tsne.csv b/Data/Processed/Unsupervised_Outputs/gmm_pca_tsne.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmeans_clusters.csv b/Data/Processed/Unsupervised_Outputs/kmeans_clusters.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmeans_pca_projection.csv b/Data/Processed/Unsupervised_Outputs/kmeans_pca_projection.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmeans_pca_tsne_projection.csv b/Data/Processed/Unsupervised_Outputs/kmeans_pca_tsne_projection.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmodes_clusters.csv b/Data/Processed/Unsupervised_Outputs/kmodes_clusters.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmodes_pca_projection.csv b/Data/Processed/Unsupervised_Outputs/kmodes_pca_projection.csv
diff --git a/Data/Processed/Unsupervised_Outputs/kmodes_pca_tsne_projection.csv b/Data/Processed/Unsupervised_Outputs/kmodes_pca_tsne_projection.csv
diff --git a/Data/Processed/Unsupervised_Outputs/renttherunway_lda_topics.csv b/Data/Processed/Unsupervised_Outputs/renttherunway_lda_topics.csv
diff --git a/Data/Processed/clothes_size_clean.csv b/Data/Processed/clothes_size_clean.csv
diff --git a/Data/Processed/modcloth_clean.csv b/Data/Processed/modcloth_clean.csv
diff --git a/Data/Processed/renttherunway_clean.csv b/Data/Processed/renttherunway_clean.csv
diff --git a/Data/Raw/final_test.csv b/Data/Raw/final_test.csv
diff --git a/Data/Raw/modcloth_final_data.json b/Data/Raw/modcloth_final_data.json
diff --git a/Data/Raw/renttherunway_final_data.json b/Data/Raw/renttherunway_final_data.json
diff --git a/Figures/Supervised_Outputs/Linear_svm_confusion_matrix.png b/Figures/Supervised_Outputs/Linear_svm_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/bagging_confusion_matrix.png b/Figures/Supervised_Outputs/bagging_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/cart_confusion_matrix.png b/Figures/Supervised_Outputs/cart_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/comparison_accuracy_f1_rtr_vs_simple.png b/Figures/Supervised_Outputs/comparison_accuracy_f1_rtr_vs_simple.png
diff --git a/Figures/Supervised_Outputs/comparison_macrof1_delta.png b/Figures/Supervised_Outputs/comparison_macrof1_delta.png
diff --git a/Figures/Supervised_Outputs/comparison_perclass_f1_rtr.png b/Figures/Supervised_Outputs/comparison_perclass_f1_rtr.png
diff --git a/Figures/Supervised_Outputs/kernel_svm_confusion_matrix.png b/Figures/Supervised_Outputs/kernel_svm_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/knn_confusion_matrix.png b/Figures/Supervised_Outputs/knn_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/naive_bayes_confusion_matrix.png b/Figures/Supervised_Outputs/naive_bayes_confusion_matrix.png
diff --git a/Figures/Supervised_Outputs/random_forest_confusion_matrix.png b/Figures/Supervised_Outputs/random_forest_confusion_matrix.png
diff --git a/Figures/Unsupervised_Outputs/dbscan_k-distance_plot.png b/Figures/Unsupervised_Outputs/dbscan_k-distance_plot.png
diff --git a/Figures/Unsupervised_Outputs/dbscan_pca_clusters.png b/Figures/Unsupervised_Outputs/dbscan_pca_clusters.png
diff --git a/Figures/Unsupervised_Outputs/dbscan_tsne_clusters.png b/Figures/Unsupervised_Outputs/dbscan_tsne_clusters.png
diff --git a/Figures/Unsupervised_Outputs/dbscan_tsne_outliers.png b/Figures/Unsupervised_Outputs/dbscan_tsne_outliers.png
diff --git a/Figures/Unsupervised_Outputs/gmm_PCA_variance.png b/Figures/Unsupervised_Outputs/gmm_PCA_variance.png
diff --git a/Figures/Unsupervised_Outputs/gmm_bic_aic.png b/Figures/Unsupervised_Outputs/gmm_bic_aic.png
diff --git a/Figures/Unsupervised_Outputs/gmm_pca_2d_clusters.png b/Figures/Unsupervised_Outputs/gmm_pca_2d_clusters.png
diff --git a/Figures/Unsupervised_Outputs/gmm_tsne_clusters.png b/Figures/Unsupervised_Outputs/gmm_tsne_clusters.png
diff --git a/Figures/Unsupervised_Outputs/kmeans_elbow.png b/Figures/Unsupervised_Outputs/kmeans_elbow.png
diff --git a/Figures/Unsupervised_Outputs/kmeans_pca_projection.png b/Figures/Unsupervised_Outputs/kmeans_pca_projection.png
diff --git a/Figures/Unsupervised_Outputs/kmeans_pca_tsne.png b/Figures/Unsupervised_Outputs/kmeans_pca_tsne.png
diff --git a/Figures/Unsupervised_Outputs/lda_coherence.png b/Figures/Unsupervised_Outputs/lda_coherence.png
diff --git a/Figures/Unsupervised_Outputs/lda_fit_heatmap.png b/Figures/Unsupervised_Outputs/lda_fit_heatmap.png
diff --git a/Figures/Unsupervised_Outputs/lda_topic_by_bodytype.png b/Figures/Unsupervised_Outputs/lda_topic_by_bodytype.png
diff --git a/Figures/Unsupervised_Outputs/lda_topic_by_category.png b/Figures/Unsupervised_Outputs/lda_topic_by_category.png
diff --git a/Figures/Unsupervised_Outputs/lda_topic_by_fit.png b/Figures/Unsupervised_Outputs/lda_topic_by_fit.png
diff --git a/Figures/Unsupervised_Outputs/lda_topic_distribution.png b/Figures/Unsupervised_Outputs/lda_topic_distribution.png
diff --git a/Figures/Unsupervised_Outputs/lda_visualization.html b/Figures/Unsupervised_Outputs/lda_visualization.html
diff --git a/Models/bagging_fit_classifier.joblib b/Models/bagging_fit_classifier.joblib
diff --git a/Models/bagging_simple_classifier.joblib b/Models/bagging_simple_classifier.joblib
diff --git a/Models/cart_fit_classifier.joblib b/Models/cart_fit_classifier.joblib
diff --git a/Models/cart_simple_classifier.joblib b/Models/cart_simple_classifier.joblib
diff --git a/Models/kernel_svm_fit_classifier.joblib b/Models/kernel_svm_fit_classifier.joblib
diff --git a/Models/kernel_svm_simple_classifier.joblib b/Models/kernel_svm_simple_classifier.joblib
diff --git a/Models/knn_fit_classifier.joblib b/Models/knn_fit_classifier.joblib
diff --git a/Models/knn_simple_classifier.joblib b/Models/knn_simple_classifier.joblib
diff --git a/Models/linear_svm_fit_classifier.joblib b/Models/linear_svm_fit_classifier.joblib
diff --git a/Models/linear_svm_simple_classifier.joblib b/Models/linear_svm_simple_classifier.joblib
diff --git a/Models/naive_bayes_fit_classifier.joblib b/Models/naive_bayes_fit_classifier.joblib
diff --git a/Models/naive_bayes_simple_classifier.joblib b/Models/naive_bayes_simple_classifier.joblib
diff --git a/Models/random_forest_fit_classifier.joblib b/Models/random_forest_fit_classifier.joblib
diff --git a/Models/random_forest_simple_classifier.joblib b/Models/random_forest_simple_classifier.joblib