Update pages/type_text.py

pages/type_text.py

@@ -61,18 +61,11 @@ if len(combined_chapters_rows_indexes_list) == 1:
     st.warning("Please select at least one chapter")
 #st.write("COMBINED CHAPTERS ROWS INDEXES LIST: ", combined_chapters_rows_indexes_list)
 df_SBS = pd.read_csv("SBS_V2_0/Code_Sheet.csv", header=0, skip_blank_lines=False, skiprows = lambda x: x not in combined_chapters_rows_indexes_list)
-
-#df_SBS = pd.read_csv("SBS_V2_0/Code_Sheet.csv", index_col="SBS_Code", usecols=["Long_Description"]) # na_values=['NA']
-#df_SBS = pd.read_csv("SBS_V2_0/Code_Sheet.csv", usecols=["SBS_Code_Hyphenated","Long_Description"]) 
-#from_line = 850 # Imaging services chapter start, adjust as needed
-#to_line = 1250 # Imaging services chapter end, adjust as needed
-#nrows = to_line - from_line + 1
-#skiprows = list(range(1,from_line - 1))
-#df_SBS = pd.read_csv("SBS_V2_0/Code_Sheet.csv", header=0, skip_blank_lines=False, skiprows=skiprows, nrows=nrows)
-
 #st.write(df_SBS.head(5))
 SBScorpus = df_SBS['Long_Description'].values.tolist()
 
+dictA = {"Score": [], "SBS Code": [], "SBS Description V2.0": []}
+dfALL = pd.DataFrame.from_dict(dictA)
 
 
 def get_device_map() -> str:
@@ -101,8 +94,6 @@ placeholder, right_column = st.columns(2)
 right_column.button("Reset description", on_click=on_click)
 
 numMAPPINGS_input = 5
-#numMAPPINGS_input = st.text_input("Type number of mappings and hit Enter", key="user_input_numMAPPINGS")
-#st.button("Clear text", on_click=on_click)
 
 
 ## Define the Sentence Transformer models
@@ -158,25 +149,15 @@ def load_pipe():
 pipe = load_pipe()
 
 
-#mapSBS_button = st.button("Map to SBS codes", on_click=on_click, key="user_clickedSBS")
-
-INTdesc_embedding = model.encode(INTdesc_input)
-
 # Semantic search, Compute cosine similarity between INTdesc_embedding and SBS descriptions
-
+INTdesc_embedding = model.encode(INTdesc_input)
 SBScorpus_embeddings = model.encode(SBScorpus)
 
-dictA = {"Score": [], "SBS Code": [], "SBS Description V2.0": []}
-dfALL = pd.DataFrame.from_dict(dictA)
-
-
 if INTdesc_input is not None and st.button("Map to SBS codes"): 
-    #my_model_results = pipeline("ner", model= "checkpoint-92")
     HF_model_results = util.semantic_search(INTdesc_embedding, SBScorpus_embeddings)
     HF_model_results_sorted = sorted(HF_model_results, key=lambda x: x[1], reverse=True)
     HF_model_results_displayed = HF_model_results_sorted[0:numMAPPINGS_input]
-
-    #if INTdesc_input is not None and mapSBS_button == True: # earlier button version  
+    
     for i, result in enumerate(HF_model_results_displayed):
         dictA.update({"Score": "%.4f" % result[0]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[0]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[0]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)