switch tfidf search to use file list saved by joblib

src/do_pca_on_tfidf.py

@@ -30,7 +30,7 @@ vocab_norm = vocab_embeddings / np.linalg.norm(vocab_embeddings, axis=1, keepdim
 # get the document-term matrix and project it to 300 pseudo-topics.
 dtm_svd = load("outputs/dtm_svd.joblib")
 X_svd = np.load("outputs/X_svd.npy", allow_pickle=True)
-my_files = np.reshape(np.load("outputs/my_files.npy", allow_pickle=True), shape = -1)
+my_files = load("outputs/my_files.joblib")
 
 def query_worker(query, dtm_svd, dtm_svd_mat, vocab_norm, concentration = 10 ):
     # query embeddings: