Update app.py

app.py

@@ -28,14 +28,14 @@ device = (
 )
 
 # 1. Product environment
-# INDEX_PATH = Path(__file__).parent.joinpath("data/index.bin")
-# CLUSTER_PATH = Path(__file__).parent.joinpath("data/repo_clusters.json")
+INDEX_PATH = Path(__file__).parent.joinpath("data/index.bin")
+CLUSTER_PATH = Path(__file__).parent.joinpath("data/repo_clusters.json")
 SCIBERT_MODEL_PATH = "allenai/scibert_scivocab_uncased"
 
 
 # 2. Developing environment
-INDEX_PATH = Path(__file__).parent.joinpath("data/index_test.bin")
-CLUSTER_PATH = Path(__file__).parent.joinpath("data/repo_clusters_test.json")
+# INDEX_PATH = Path(__file__).parent.joinpath("data/index_test.bin")
+# CLUSTER_PATH = Path(__file__).parent.joinpath("data/repo_clusters_test.json")
 # SCIBERT_MODEL_PATH = Path(__file__).parent.joinpath("data/scibert_scivocab_uncased")  # Download locally
 
 
@@ -377,66 +377,75 @@ if __name__ == "__main__":
         )
 
         display_columns = st.session_state.display_columns
-        code_sim_tab, doc_sim_tab, readme_sim_tab, requirement_sim_tab, repo_sim_tab, same_cluster_tab, diff_cluster_tab = st.tabs(
+        code_sim_tab, doc_sim_tab, readme_sim_tab, requirement_sim_tab, repo_sim_tab, cluster_tab, same_cluster_tab, = st.tabs(
             ["Code_sim", "Docstring_sim", "Readme_sim", "Requirement_sim",
-             "Repository_sim", "Same_cluster", "Different_cluster"])
-
-        if query_doc.code_embedding is not None:
-            code_sim_res = run_index_search(index, query_doc, "code_embedding", limit)
-            cluster_numbers = run_cluster_search(repo_clusters, code_sim_res["name"])
-            code_sim_res["cluster number"] = cluster_numbers
-            code_sim_tab.dataframe(code_sim_res[display_columns])
-        else:
-            code_sim_tab.error("No function code was extracted for this repository!")
-
-        if query_doc.doc_embedding is not None:
-            doc_sim_res = run_index_search(index, query_doc, "doc_embedding", limit)
-            cluster_numbers = run_cluster_search(repo_clusters, doc_sim_res["name"])
-            doc_sim_res["cluster number"] = cluster_numbers
-            doc_sim_tab.dataframe(doc_sim_res[display_columns])
-        else:
-            doc_sim_tab.error("No function docstring was extracted for this repository!")
-
-        if query_doc.readme_embedding is not None:
-            readme_sim_res = run_index_search(index, query_doc, "readme_embedding", limit)
-            cluster_numbers = run_cluster_search(repo_clusters, readme_sim_res["name"])
-            readme_sim_res["cluster number"] = cluster_numbers
-            readme_sim_tab.dataframe(readme_sim_res[display_columns])
-        else:
-            readme_sim_tab.error("No readme file was extracted for this repository!")
-
-        if query_doc.requirement_embedding is not None:
-            requirement_sim_res = run_index_search(index, query_doc, "requirement_embedding", limit)
-            cluster_numbers = run_cluster_search(repo_clusters, requirement_sim_res["name"])
-            requirement_sim_res["cluster number"] = cluster_numbers
-            requirement_sim_tab.dataframe(requirement_sim_res[display_columns])
-        else:
-            requirement_sim_tab.error("No requirement file was extracted for this repository!")
-
-        if query_doc.repository_embedding is not None:
-            repo_sim_res = run_index_search(index, query_doc, "repository_embedding", limit)
-            cluster_numbers = run_cluster_search(repo_clusters, repo_sim_res["name"])
-            repo_sim_res["cluster number"] = cluster_numbers
-            repo_sim_tab.dataframe(repo_sim_res[display_columns])
-        else:
-            repo_sim_tab.error("No such useful information was extracted for this repository!")
-
-        if cluster_number is not None and query_doc.repository_embedding is not None:
-            same_cluster_df = run_similaritycal_search(index, repo_clusters, sim_cal_model,
-                                                       query_doc, cluster_number, limit,
-                                                       same_cluster=True)
-            diff_cluster_df = run_similaritycal_search(index, repo_clusters, sim_cal_model,
-                                                       query_doc, cluster_number, limit,
-                                                       same_cluster=False)
-            same_cluster_numbers = run_cluster_search(repo_clusters, same_cluster_df["name"])
-            same_cluster_df["cluster number"] = same_cluster_numbers
-
-            diff_cluster_numbers = run_cluster_search(repo_clusters, diff_cluster_df["name"])
-            diff_cluster_df["cluster number"] = diff_cluster_numbers
-
-            same_cluster_tab.dataframe(same_cluster_df[display_columns])
-            diff_cluster_tab.dataframe(diff_cluster_df[display_columns])
-
-        else:
-            same_cluster_tab.error("No such useful information was extracted for this repository!")
-            diff_cluster_tab.error("No such useful information was extracted for this repository!")
+             "Repository_sim", "Cluster_sim", "Same_cluster_sim"])
+
+        with code_sim_tab:
+            if query_doc.code_embedding is not None:
+                code_sim_res = run_index_search(index, query_doc, "code_embedding", limit)
+                cluster_numbers = run_cluster_search(repo_clusters, code_sim_res["name"])
+                code_sim_res["cluster number"] = cluster_numbers
+                st.dataframe(code_sim_res[display_columns])
+            else:
+                st.error("No function code was extracted for this repository!")
+
+        with doc_sim_tab:
+            if query_doc.doc_embedding is not None:
+                doc_sim_res = run_index_search(index, query_doc, "doc_embedding", limit)
+                cluster_numbers = run_cluster_search(repo_clusters, doc_sim_res["name"])
+                doc_sim_res["cluster number"] = cluster_numbers
+                st.dataframe(doc_sim_res[display_columns])
+            else:
+                st.error("No function docstring was extracted for this repository!")
+
+        with readme_sim_tab:
+            if query_doc.readme_embedding is not None:
+                readme_sim_res = run_index_search(index, query_doc, "readme_embedding", limit)
+                cluster_numbers = run_cluster_search(repo_clusters, readme_sim_res["name"])
+                readme_sim_res["cluster number"] = cluster_numbers
+                st.dataframe(readme_sim_res[display_columns])
+            else:
+                st.error("No readme file was extracted for this repository!")
+
+        with requirement_sim_tab:
+            if query_doc.requirement_embedding is not None:
+                requirement_sim_res = run_index_search(index, query_doc, "requirement_embedding", limit)
+                cluster_numbers = run_cluster_search(repo_clusters, requirement_sim_res["name"])
+                requirement_sim_res["cluster number"] = cluster_numbers
+                st.dataframe(requirement_sim_res[display_columns])
+            else:
+                st.error("No requirement file was extracted for this repository!")
+
+        with repo_sim_tab:
+            if query_doc.repository_embedding is not None:
+                # Repo Sim tab
+                repo_sim_res = run_index_search(index, query_doc, "repository_embedding", limit)
+                cluster_numbers = run_cluster_search(repo_clusters, repo_sim_res["name"])
+                repo_sim_res["cluster number"] = cluster_numbers
+                st.dataframe(repo_sim_res[display_columns])
+            else:
+                st.error("No such useful information was extracted for this repository!")
+
+        with cluster_tab:
+            if query_doc.repository_embedding is not None:
+                cluster_df = run_similaritycal_search(index, repo_clusters, sim_cal_model,
+                                                      query_doc, cluster_number, limit,
+                                                      same_cluster=False)
+                cluster_numbers = run_cluster_search(repo_clusters, cluster_df["name"])
+                cluster_df["cluster number"] = cluster_numbers
+                st.dataframe(cluster_df[display_columns])
+            else:
+                st.error("No such useful information was extracted for this repository!")
+
+        with same_cluster_tab:
+            if query_doc.repository_embedding is not None:
+                # Cluster tab and same cluster tab
+                same_cluster_df = run_similaritycal_search(index, repo_clusters, sim_cal_model,
+                                                           query_doc, cluster_number, limit,
+                                                           same_cluster=True)
+                same_cluster_numbers = run_cluster_search(repo_clusters, same_cluster_df["name"])
+                same_cluster_df["cluster number"] = same_cluster_numbers
+                same_cluster_tab.dataframe(same_cluster_df[display_columns])
+            else:
+                same_cluster_tab.error("No such useful information was extracted for this repository!")