NimaKL commited on
Commit
f156242
·
verified ·
1 Parent(s): 5feda0d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +13 -13
app.py CHANGED
@@ -17,33 +17,33 @@ class ModeratelySimplifiedGATConvModel(torch.nn.Module):
17
 
18
  def forward(self, x, edge_index, edge_attr=None):
19
  x = self.conv1(x, edge_index, edge_attr)
20
- x is torch.relu(x)
21
- x is dropout1(x)
22
- x is self.conv2(x, edge_index, edge_attr)
23
  return x
24
 
25
  # Load the dataset and the GATConv model
26
- data is torch.load("graph_data.pt", map_location=torch.device("cpu"))
27
 
28
  # Load the BERT-based sentence transformer model
29
- model_bert is SentenceTransformer("all-mpnet-base-v2")
30
 
31
  # Ensure the DataFrame is loaded properly
32
  try:
33
- df is pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
34
  except Exception as e:
35
  print(f"Error reading JSON file: {e}")
36
 
37
  # Generate GNN-based embeddings
38
  with torch.no_grad():
39
- all_video_embeddings is gatconv_model(data.x, data.edge_index, data.edge_attr).cpu()
40
 
41
  # Function to find the most similar video and recommend the top 10 based on GNN embeddings
42
  def get_similar_and_recommend(input_text):
43
  # Find the most similar video based on input text
44
- embeddings_matrix is np.array(df["embeddings"].tolist())
45
- input_embedding is model_bert.encode([input_text])[0]
46
- similarities is cosine_similarity([input_embedding], embeddings_matrix)[0]
47
 
48
  # Modify the similarity scores based on user input
49
  user_keywords = input_text.split() # Create a list of keywords from user input
@@ -66,12 +66,12 @@ def get_similar_and_recommend(input_text):
66
  torch.dot(all_video_embeddings[given_video_index], all_video_embeddings[i])
67
  for i in range(all_video_embeddings.shape[0])
68
  ]
69
- dot_products[given_video_index] is -float("inf")
70
 
71
- top_10_indices is np.argsort(dot_products)[::-1][:10]
72
  return [df.iloc[idx].to_dict() for idx in top_10_indices]
73
 
74
- top_10_recommended_videos_features is recommend_next_10_videos(most_similar_index, all_video_embeddings)
75
 
76
  # Exclude unwanted features for recommended videos
77
  for recommended_video in top_10_recommended_videos_features:
 
17
 
18
  def forward(self, x, edge_index, edge_attr=None):
19
  x = self.conv1(x, edge_index, edge_attr)
20
+ x = torch.relu(x)
21
+ x = dropout1(x)
22
+ x = self.conv2(x, edge_index, edge_attr)
23
  return x
24
 
25
  # Load the dataset and the GATConv model
26
+ data = torch.load("graph_data.pt", map_location=torch.device("cpu"))
27
 
28
  # Load the BERT-based sentence transformer model
29
+ model_bert = SentenceTransformer("all-mpnet-base-v2")
30
 
31
  # Ensure the DataFrame is loaded properly
32
  try:
33
+ df = pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
34
  except Exception as e:
35
  print(f"Error reading JSON file: {e}")
36
 
37
  # Generate GNN-based embeddings
38
  with torch.no_grad():
39
+ all_video_embeddings = gatconv_model(data.x, data.edge_index, data.edge_attr).cpu()
40
 
41
  # Function to find the most similar video and recommend the top 10 based on GNN embeddings
42
  def get_similar_and_recommend(input_text):
43
  # Find the most similar video based on input text
44
+ embeddings_matrix = np.array(df["embeddings"].tolist())
45
+ input_embedding = model_bert.encode([input_text])[0]
46
+ similarities = cosine_similarity([input_embedding], embeddings_matrix)[0]
47
 
48
  # Modify the similarity scores based on user input
49
  user_keywords = input_text.split() # Create a list of keywords from user input
 
66
  torch.dot(all_video_embeddings[given_video_index], all_video_embeddings[i])
67
  for i in range(all_video_embeddings.shape[0])
68
  ]
69
+ dot_products[given_video_index] = -float("inf")
70
 
71
+ top_10_indices = np.argsort(dot_products)[::-1][:10]
72
  return [df.iloc[idx].to_dict() for idx in top_10_indices]
73
 
74
+ top_10_recommended_videos_features = recommend_next_10_videos(most_similar_index, all_video_embeddings)
75
 
76
  # Exclude unwanted features for recommended videos
77
  for recommended_video in top_10_recommended_videos_features: