Update app.py

app.py

@@ -3,23 +3,22 @@ import pandas as pd
 import os
 import glob
 
-# Decorator to cache loading of the CSV file and processing of text files
+# Cache the loading of specialties and state files for efficiency
 @st.cache_resource
 def load_specialties(csv_file='Provider-Specialty.csv'):
     return pd.read_csv(csv_file)
 
 @st.cache_resource
 def find_state_files():
-    # Adjusted to include .csv files specifically for states
     return [file for file in glob.glob('./*.csv') if len(os.path.basename(file).split('.')[0]) == 2]
 
-# Load the provider specialty dataset CSV
+# Load the provider specialty dataset
 specialties = load_specialties()
 
 # User interface for specialty selection
 st.title('Provider Specialty Analyzer 📊')
 
-# Markdown outline with emojis
+# Markdown outline with emojis for specialty fields
 st.markdown('''
 ## Specialty Fields Description 📝
 - **Code**: Unique identifier for the specialty 🆔
@@ -45,34 +44,34 @@ else:
 
 st.dataframe(filtered_specialties)
 
-# Default state selection to MN for testing
-default_state = 'MN'
+# State selection UI with MN as the default option for testing
 state_files = find_state_files()
-state_options = [os.path.basename(file).split('.')[0] for file in state_files]
-state_options.insert(0, default_state)  # Default MN added to the start of the list for testing
-selected_state = st.selectbox('Select a State (optional) 🗺️', options=state_options, index=0)
+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)
 
-# Adjusted function to match specialty code with 48th column in state files
-def process_files(specialty_code, specific_state=default_state):
+# Function to process state files and match taxonomy codes
+def process_files(specialty_codes, specific_state='MN'):
     results = []
-    files_to_process = [f for f in state_files if f.split('/')[-1].startswith(specific_state + '.csv')]
+    file_to_process = f'./{specific_state}.csv' if use_specific_state else state_files
     
-    for file in files_to_process:
-        state_df = pd.read_csv(file, header=None)  # Assuming no header for state files
-        filtered_df = state_df[state_df[47] == specialty_code]  # Match with 48th column (index 47)
-        if not filtered_df.empty:
-            results.append((os.path.basename(file), filtered_df))
+    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
+        for code in specialty_codes:
+            # Filter rows where the 48th column matches the specialty code
+            filtered_df = state_df[state_df[47] == code]
+            if not filtered_df.empty:
+                results.append((os.path.basename(file).replace('.csv', ''), filtered_df))
     
     return results
 
-# Show DataFrame UI for files matching the specialty code in the selected state
+# Button to initiate analysis
 if st.button('Analyze Text Files for Selected Specialty 🔍'):
-    specialty_code = specialties[specialties['Display Name'] == selected_specialty].iloc[0]['Code']
-    state_data = process_files(specialty_code, selected_state if use_specific_state else default_state)
+    specialty_codes = filtered_specialties['Code'].unique()
+    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.replace('.csv', '')} with Specialty '{selected_specialty}':")
+            st.subheader(f"Providers in {state} with Specialty '{selected_specialty}':")
             st.dataframe(df)
     else:
         st.write("No matching records found in text files for the selected specialty.")