Saved viz's to HTML files, directly loading now

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.csv filter=lfs diff=lfs merge=lfs -text
+*.html filter=lfs diff=lfs merge=lfs -text

Visualizations/pca_visualization.html

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e654ab0d04dd190f2165a6c89a720606c80e2211f4bc5350022b5179574af41
+size 4290216

Visualizations/tsne_visualization.html

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ff7dda2c472758b59e110be2720024dcd3f38d5d8fdc4a1779ebcfd74f4632
+size 4266707

Visualizations/umap_visualization.html

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bdda27d0f4924077ee91d49ddf7855f313dc0a40bf9dd6f51fbef1accd92c0
+size 4251158

app.py

@@ -41,14 +41,14 @@ st.title("Movie Recommendation App")
 
 
 # --- VISUALIZATIONS ---
-#with open("umap_visualization.html", "r", encoding='utf-8') as f:
-#   umap_html = f.read()
+with open("./Visualizations/umap_visualization.html", "r", encoding='utf-8') as f:
+   umap_html = f.read()
 
-#with open("tsne_visualization.html", "r") as f:
-#    tsne_html = f.read()
+with open("./Visualizations/tsne_visualization.html", "r") as f:
+    tsne_html = f.read()
 
-#with open("pca_visualization.html", "r") as f:
-#    pca_html = f.read()
+with open("./Visualizations/pca_visualization.html", "r") as f:
+    pca_html = f.read()
 
 tab1, tab2 = st.tabs(["Visualizations", "Recommendations"])
                       
@@ -63,23 +63,23 @@ with tab1:
     umap_expander = st.expander("UMAP Visualization")
     with umap_expander:
         st.subheader('UMAP Visualization')
-        umap_fig = viz_utils.visualize_embeddings_umap(embedding_df)
-        st.plotly_chart(umap_fig)
-        #components.html(umap_html, width=800, height=800)
+        #umap_fig = viz_utils.visualize_embeddings_umap(embedding_df)
+        #st.plotly_chart(umap_fig)
+        components.html(umap_html, width=800, height=800)
 
     tsne_expander = st.expander("TSNE Visualization")
     with tsne_expander:
         st.subheader('TSNE Visualization')
-        tsne_fig = viz_utils.visualize_embeddings_tsne(embedding_df)
-        st.plotly_chart(tsne_fig)
-        #components.html(tsne_html, width=800, height=800)
+        #tsne_fig = viz_utils.visualize_embeddings_tsne(embedding_df)
+        #st.plotly_chart(tsne_fig)
+        components.html(tsne_html, width=800, height=800)
 
     pca_expander = st.expander("PCA Visualization")
     with pca_expander:
         st.subheader('PCA Visualization')
-        pca_fig = viz_utils.visualize_embeddings_pca(embedding_df)
-        st.plotly_chart(pca_fig)
-        #components.html(pca_html, width=800, height=800)
+        #pca_fig = viz_utils.visualize_embeddings_pca(embedding_df)
+        #st.plotly_chart(pca_fig)
+        components.html(pca_html, width=800, height=800)
 
 
 

visualizer.py

@@ -14,6 +14,8 @@ from torch_geometric.transforms import RandomLinkSplit, ToUndirected
 from sentence_transformers import SentenceTransformer
 from torch_geometric.data import HeteroData
 import yaml
+import os
+import model_def
 
 
 
@@ -24,48 +26,10 @@ data = torch.load("./PyGdata.pt", map_location=device)
 
 movies_df = pd.read_csv("./sampled_movie_dataset/movies_metadata.csv")
 
-class GNNEncoder(torch.nn.Module):
-    def __init__(self, hidden_channels, out_channels):
-        super().__init__()
-        # these convolutions have been replicated to match the number of edge types
-        self.conv1 = SAGEConv((-1, -1), hidden_channels)
-        self.conv2 = SAGEConv((-1, -1), out_channels)
-
-    def forward(self, x, edge_index):
-        x = self.conv1(x, edge_index).relu()
-        x = self.conv2(x, edge_index)
-        return x
-    
-class EdgeDecoder(torch.nn.Module):
-    def __init__(self, hidden_channels):
-        super().__init__()
-        self.lin1 = Linear(2 * hidden_channels, hidden_channels)
-        self.lin2 = Linear(hidden_channels, 1)
-
-    def forward(self, z_dict, edge_label_index):
-        row, col = edge_label_index
-        # concat user and movie embeddings
-        z = torch.cat([z_dict['user'][row], z_dict['movie'][col]], dim=-1)
-        # concatenated embeddings passed to linear layer
-        z = self.lin1(z).relu()
-        z = self.lin2(z)
-        return z.view(-1)
-    
-class Model(torch.nn.Module):
-    def __init__(self, hidden_channels):
-        super().__init__()
-        self.encoder = GNNEncoder(hidden_channels, hidden_channels)
-        self.encoder = to_hetero(self.encoder, data.metadata(), aggr='sum')
-        self.decoder = EdgeDecoder(hidden_channels)
-
-    def forward(self, x_dict, edge_index_dict, edge_label_index):
-        # z_dict contains dictionary of movie and user embeddings returned from GraphSage
-        z_dict = self.encoder(x_dict, edge_index_dict)
-        return self.decoder(z_dict, edge_label_index)
+
     
-model = Model(hidden_channels=32).to(device)
-model2 = Model(hidden_channels=32).to(device)
-model.load_state_dict(torch.load("PyGTrainedModelState.pt"), map_location=device)
+model = model_def.Model(hidden_channels=32).to(device)
+model.load_state_dict(torch.load("PyGTrainedModelState.pt", map_location=device)),
 model.eval()
 
 total_users = data['user'].num_nodes 
@@ -87,12 +51,16 @@ movie_index = 20
 title = movies_df.iloc[movie_index]['title']
 print(title) 
 
+os.makedirs("Visualizations", exist_ok=True)
 
 fig_umap = viz_utils.visualize_embeddings_umap(embedding_df) 
 viz_utils.save_visualization(fig_umap, "./Visualizations/umap_visualization")
+print("UMAP visualization saved")
 
 fig_tsne = viz_utils.visualize_embeddings_tsne(embedding_df) 
 viz_utils.save_visualization(fig_tsne, "./Visualizations/tsne_visualization")
+print("TSNE visualization saved")
 
 fig_pca = viz_utils.visualize_embeddings_pca(embedding_df) 
 viz_utils.save_visualization(fig_pca, "./Visualizations/pca_visualization")
+print("PCA visualization saved")