added threshold slidebar

app.py

@@ -64,16 +64,18 @@ with st.sidebar:
     uploaded_excel = st.file_uploader("Upload the Master file (.xls or .csv)", type=["csv", "xls", "xlsx"])
     uploaded_text = st.file_uploader("Upload your Text file (.txt)", type=["txt"])
 
+    threshold = st.slider("Adjust Threshold", min_value=0, max_value=30, value=12)
+
 # Check if both files are uploaded
 if uploaded_excel and uploaded_text:
     master_data, df = process_files(uploaded_excel, uploaded_text)  # Process the files
 
-    res, fbdm, fben, fbbm25, nf = get_res_df(master_data, df)  # Generate the result DataFrame using the helper function
+    res, fbdm, fben, fbbm25, nf = get_res_df(master_data, df, threshold)  # Generate the result DataFrame using the helper function
     
     # Create a layout with four columns to display the metrics
     col1, col2, col3, col4 = st.columns(4)
     with col1:
-        st.metric("Direct Match", fbdm)
+        st.metric("Direct Search", fbdm)
     with col2:
         st.metric("Employer Number", fben)
     with col3:

helper.py

@@ -178,7 +178,7 @@ def generate_df(master_data, df, employer_names):
 
     return res_df
 
-def get_res_df(master_data, df):
+def get_res_df(master_data, df, thrshld):
     """
     Retrieves the result DataFrame by matching employer names using BM25 algorithm
     and employee numbers.
@@ -191,6 +191,7 @@ def get_res_df(master_data, df):
     DataFrame: A DataFrame containing matched employer data and transaction details.
     """
     # Preprocess master data
+    threshold = thrshld
     corpus = list(master_data['Employer Name'])
     lower_case_corpus = [clean_text(name) for name in corpus]
     corpus = corpus[1:]  # Exclude the first row if it's a header