Update app.py

app.py

@@ -3,32 +3,38 @@ import pandas as pd
 import os
 import glob
 
-# Load the provider specialty dataset CSV
-@st.cache(allow_output_mutation=True)
+# Decorator to cache loading of the CSV file and processing of text files
+@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
 specialties = load_specialties()
 
 # User interface for specialty selection
-st.title('🔍 Provider Specialty Analyzer')
+st.title('Provider Specialty Analyzer 📊')
 
-# Markdown outline for the fields description
-st.markdown("""
-## Specialty Fields Description 📋
-- **Code**: Unique identifier for the specialty.
-- **Grouping**: General category the specialty belongs to.
-- **Classification**: More detailed classification within the grouping.
-- **Specialization**: Further specialization details if applicable.
-- **Definition**: Brief description of the specialty.
-- **Notes**: Any additional notes or historical information.
-- **Display Name**: The common name used to display the specialty.
-- **Section**: The section of healthcare the specialty falls under.
-""")
+# Markdown outline with emojis
+st.markdown('''
+## Specialty Fields Description 📝
+- **Code**: Unique identifier for the specialty 🆔
+- **Grouping**: General category of the specialty 🏷️
+- **Classification**: Specific type of practice within the grouping 🎯
+- **Specialization**: Further refinement of the classification if applicable 🔍
+- **Definition**: Brief description of the specialty 📖
+- **Notes**: Additional information or updates about the specialty 🗒️
+- **Display Name**: Common name of the specialty 🏷️
+- **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)
+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 🔍')
@@ -39,27 +45,34 @@ else:
 
 st.dataframe(filtered_specialties)
 
-# Function to find and process text files with two-letter names
-def process_state_files(specialty_code):
-    files = glob.glob('./*.txt')
-    state_files = [file for file in files if len(os.path.basename(file).split('.')[0]) == 2]
-    results = []
+# Default state selection to MN for testing
+default_state = 'MN'
+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)
+use_specific_state = st.checkbox('Filter by selected state only? ✅', value=True)
 
-    for file in state_files:
-        state_df = pd.read_csv(file, names=['Code', 'Grouping', 'Classification', 'Specialization', 'Definition', 'Notes', 'Display Name', 'Section'])
-        filtered_df = state_df[state_df['Code'] == specialty_code]
+# Adjusted function to match specialty code with 48th column in state files
+def process_files(specialty_code, specific_state=default_state):
+    results = []
+    files_to_process = [f for f in state_files if f.split('/')[-1].startswith(specific_state + '.csv')]
+    
+    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).split('.')[0], filtered_df))
+            results.append((os.path.basename(file), filtered_df))
     
     return results
 
 # Show DataFrame UI for files matching the specialty code in the selected state
-if st.button('Analyze Text Files for Selected Specialty 📊'):
+if st.button('Analyze Text Files for Selected Specialty 🔍'):
     specialty_code = specialties[specialties['Display Name'] == selected_specialty].iloc[0]['Code']
-    state_data = process_state_files(specialty_code)
+    state_data = process_files(specialty_code, selected_state if use_specific_state else default_state)
     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.replace('.csv', '')} with Specialty '{selected_specialty}':")
             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 specialty.")