Update app.py

app.py

@@ -12,13 +12,11 @@ def load_specialties(csv_file='Provider-Specialty.csv'):
 def find_state_files():
     return [file for file in glob.glob('./*.csv') if len(os.path.basename(file).split('.')[0]) == 2]
 
-# Load the provider specialty dataset
 specialties = load_specialties()
 
-# User interface for specialty selection
+# UI for specialty selection
 st.title('Provider Specialty Analyzer 📊')
 
-# Markdown outline with emojis for specialty fields
 st.markdown('''
 ## Specialty Fields Description 📝
 - **Code**: Unique identifier for the specialty 🆔
@@ -31,11 +29,9 @@ st.markdown('''
 - **Section**: Indicates the section of healthcare it belongs to 📚
 ''')
 
-# Dropdown for selecting a specialty
 specialty_options = specialties['Display Name'].unique()
 selected_specialty = st.selectbox('Select a Specialty 🩺', options=specialty_options)
 
-# Display specialties matching the selected option or search keyword
 search_keyword = st.text_input('Or search for a keyword in specialties 🔍')
 if search_keyword:
     filtered_specialties = specialties[specialties.apply(lambda row: row.astype(str).str.contains(search_keyword, case=False).any(), axis=1)]
@@ -44,34 +40,31 @@ else:
 
 st.dataframe(filtered_specialties)
 
-# State selection UI with MN as the default option for testing
+# State selection with MN as default for testing
 state_files = find_state_files()
 state_options = sorted([os.path.basename(file).split('.')[0] for file in state_files])
 selected_state = st.selectbox('Select a State (optional) 🗺️', options=state_options, index=state_options.index('MN') if 'MN' in state_options else 0)
 use_specific_state = st.checkbox('Filter by selected state only? ✅', value=True)
 
-# Function to process state files and match taxonomy codes
 def process_files(specialty_codes, specific_state='MN'):
     results = []
     file_to_process = f'./{specific_state}.csv' if use_specific_state else state_files
     
     for file in [file_to_process] if use_specific_state else state_files:
-        state_df = pd.read_csv(file, header=None)  # Assume no header for simplicity
+        state_df = pd.read_csv(file, header=None)  # Assuming no header for simplicity
         for code in specialty_codes:
-            # Filter rows where the 48th column matches the specialty code
-            filtered_df = state_df[state_df[47] == code]
+            filtered_df = state_df[state_df[47].isin(specialty_codes)]  # Match against 48th column
             if not filtered_df.empty:
                 results.append((os.path.basename(file).replace('.csv', ''), filtered_df))
     
     return results
 
-# Button to initiate analysis
 if st.button('Analyze Text Files for Selected Specialty 🔍'):
-    specialty_codes = filtered_specialties['Code'].unique()
+    specialty_codes = filtered_specialties['Code'].tolist()
     state_data = process_files(specialty_codes, selected_state if use_specific_state else 'MN')
     if state_data:
         for state, df in state_data:
-            st.subheader(f"Providers in {state} with Specialty '{selected_specialty}':")
+            st.subheader(f"Providers in {state} with Specialties related to '{search_keyword}':")
             st.dataframe(df)
     else:
-        st.write("No matching records found in text files for the selected specialty.")
+        st.write("No matching records found in text files for the selected specialties.")