Optimization

app.py

@@ -9,7 +9,7 @@ import requests
 import base64
 import json
 import sys
-from fetchPlaylistTrackUris import *
+
 import re
 import asyncio
 # import streamlit.components.v1 as components
@@ -20,7 +20,6 @@ import numpy as np
 import pandas as pd
 import os
 from scipy.sparse import vstack
-from recommender import *
 import huggingface_hub
 from huggingface_hub import Repository
 
@@ -44,6 +43,9 @@ repo_mat = Repository(
     local_dir="data_mat", clone_from=DATASET_REPO_URL_MAT, use_auth_token=HF_TOKEN, repo_type="dataset"
 )
 
+from fetchPlaylistTrackUris import *
+from recommender import *
+
 def get_repo_train():
     repo_train = Repository(
         local_dir="data_train", clone_from=DATASET_REPO_URL_TRAIN, use_auth_token=HF_TOKEN, repo_type="dataset"

recommender.py

@@ -5,6 +5,15 @@ import numpy as np
 import pandas as pd
 from scipy.sparse import vstack
 
+
+df_ps_train_ori = pd.read_hdf('model/df_ps_train_new.hdf')
+df_ps_train_extra = pd.read_hdf('data_train/df_ps_train_extra.hdf')
+pickle_path = 'model/giantMatrix_new.pickle'
+with open(pickle_path, 'rb') as f:
+    ps_matrix_ori = pickle.load(f)
+
+
+
 def add_row_train(df, list_tid):
     new_pid_add = df.iloc[-1].name +1
     list_tid_add = list_tid
@@ -25,9 +34,9 @@ def inference_row(list_tid, ps_matrix):
 
 
 def get_best_tid(current_list, ps_matrix_row, K=50, MAX_tid=10):
-    df_ps_train = pd.read_hdf('model/df_ps_train_new.hdf')
-    df_ps_train_extra = pd.read_hdf('data_train/df_ps_train_extra.hdf')
-    df_ps_train = pd.concat([df_ps_train,df_ps_train_extra])
+
+
+    df_ps_train = pd.concat([df_ps_train_ori,df_ps_train_extra])
     
     sim_vector, sparse_row = inference_row(current_list, ps_matrix_row)
     sim_vector = sim_vector.toarray()[0].tolist()
@@ -76,16 +85,13 @@ def get_best_tid(current_list, ps_matrix_row, K=50, MAX_tid=10):
 
 
 def inference_from_tid(list_tid, K=50, MAX_tid=10):
-    pickle_path = 'model/giantMatrix_new.pickle'
-    # pickle_path = 'data/giantMatrix_truth_new.pickle'
 
-    with open(pickle_path, 'rb') as f:
-        ps_matrix = pickle.load(f)
+    # pickle_path = 'data/giantMatrix_truth_new.pickle'
         
     with open("data_mat/giantMatrix_extra.pickle",'rb') as f:
         ps_matrix_extra = pickle.load(f)
     
-    ps_matrix = vstack((ps_matrix,ps_matrix_extra))
+    ps_matrix = vstack((ps_matrix_ori,ps_matrix_extra))
 
     result, sparse_row = get_best_tid(list_tid, ps_matrix.tocsr(), K, MAX_tid)
     ps_matrix_extra = vstack((ps_matrix_extra,sparse_row.todok()))