Update app.py

app.py

@@ -2,23 +2,8 @@ import streamlit as st
 import pandas as pd
 import os
 import glob
+import matplotlib.pyplot as plt
 
-
-# Set page configuration with a title and favicon
-st.set_page_config(
-    page_title="🩺🔍 Care Team Finder - Care Providers by Specialty and Location",
-    page_icon="🩺",
-    layout="wide",
-    initial_sidebar_state="expanded",
-    menu_items={
-        'Get Help': 'https://huggingface.co/awacke1',
-        'Report a bug': "https://huggingface.co/spaces/awacke1/WebDataDownload",
-        'About': "# 🩺🔍 Care Team Finder By Aaron Wacker - https://huggingface.co/awacke1"
-    }
-)
-
-
-# Define headers for dataframe
 headers = [
     "NPI", "EntityTypeCode", "ReplacementNPI", "EmployerIdentificationNumberEIN", 
     "ProviderOrganizationNameLegalBusinessName", "ProviderLastNameLegalName", 
@@ -43,6 +28,41 @@ headers = [
     "HealthcareProviderPrimaryTaxonomySwitch"
 ]
 
+def process_files_new(specialty_codes, specific_state='MN', use_specific_state=True):
+    results = []
+    city_counts = {}  # Dictionary to keep track of city counts
+    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:
+        # Now using the 'names' parameter to specify column names
+        state_df = pd.read_csv(file, header=None, names=headers)
+        for code in specialty_codes:
+            filtered_df = state_df[state_df['HealthcareProviderTaxonomyCode'].isin([code])]
+            if not filtered_df.empty:
+                # Update city counts
+                for city in filtered_df['ProviderBusinessPracticeLocationAddressCityName'].unique():
+                    city_counts[city] = city_counts.get(city, 0) + filtered_df[filtered_df['ProviderBusinessPracticeLocationAddressCityName'] == city].shape[0]
+                
+                # Prepare display information (assuming 'specialties' DataFrame exists)
+                display_info = specialties[specialties['Code'] == code][['Code', 'Grouping', 'Classification']].iloc[0].to_dict()
+                results.append((os.path.basename(file).replace('.csv', ''), display_info, filtered_df))
+    
+    # Plotting the city counts
+    cities = list(city_counts.keys())
+    counts = list(city_counts.values())
+    
+    #plt.figure(figsize=(10, 6))
+    #plt.bar(cities, counts, color='skyblue')
+    #plt.xlabel('City')
+    #plt.ylabel('Count')
+    #plt.xticks(rotation=45, ha='right')
+    #plt.title('Counts per City')
+    #plt.tight_layout()
+    #plt.show()
+    
+    return results
+
+
 # Cache the loading of specialties for efficiency
 @st.cache_resource
 def load_specialties(csv_file='Provider-Specialty.csv'):
@@ -53,13 +73,36 @@ 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]
 
-specialties = load_specialties()
-
-
+# Set page configuration with a title and favicon
+st.set_page_config(
+    page_title="🩺🔍 Care Team Finder - Care Providers by Specialty and Location",
+    page_icon="🩺",
+    layout="wide",
+    initial_sidebar_state="expanded",
+    menu_items={
+        'Get Help': 'https://huggingface.co/awacke1',
+        'Report a bug': "https://huggingface.co/spaces/awacke1/WebDataDownload",
+        'About': "# 🩺🔍 Care Team Finder By Aaron Wacker - https://huggingface.co/awacke1"
+    }
+)
 
+specialties = load_specialties()
 st.markdown("# 🩺🔍 Care Team Finder ")
 st.markdown("#### Search for Care Providers by Specialty and Location")
 
+if st.expander('🩺 Understand Provider Specialties 📝'):
+    st.markdown('''
+## Discover Care Providers by Specialty & Location: Quick Guide
+- **Code**: Unique ID identifies each specialty clearly. 🆔
+- **Grouping**: Broad category umbrella for general expertise area. 🏷️
+- **Classification**: Specifies type of practice within broader category. 🎯
+- **Specialization**: Details focus within classification for precise expertise. 🔍
+- **Definition**: Concise overview of the specialty's scope. 📖
+- **Notes**: Extra information or recent updates provided. 🗒️
+- **Display Name**: Commonly recognized name of the specialty. 🏷️
+- **Section**: Healthcare segment the specialty belongs to. 📚
+    ''')
+
 # Allows users to select or search for a specialty
 specialty_options = specialties['Display Name'].unique()
 selected_specialty = st.selectbox('Select a Specialty 🩺', options=specialty_options)
@@ -81,17 +124,19 @@ selected_state = st.selectbox('Select a State (optional) 🗺️', options=state
 # Checkbox to filter by selected state only
 use_specific_state = st.checkbox('Filter by selected state only? ✅', value=True)
 
+# Process files based on specialty codes and state selection
 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:
-        # Load data with headers
-        state_df = pd.read_csv(file, header=None, names=headers)
+        state_df = pd.read_csv(file, header=None)  # Assuming no header for simplicity
+        #state_df = pd.read_csv(file, header=0)  # Assuming no header for simplicity
         
         for code in specialty_codes:
-            filtered_df = state_df[state_df['HealthcareProviderTaxonomyCode'].isin([code])]
+            filtered_df = state_df[state_df[47].isin([code])]  # Match against 48th column, adjust as needed
             if not filtered_df.empty:
+                # Enhance the display to include 'Code', 'Grouping', and 'Classification' information
                 display_info = specialties[specialties['Code'] == code][['Code', 'Grouping', 'Classification']].iloc[0].to_dict()
                 results.append((os.path.basename(file).replace('.csv', ''), display_info, filtered_df))
     
@@ -101,6 +146,7 @@ def process_files(specialty_codes, specific_state='MN'):
 if st.button('Analyze Text Files for Selected Specialty 🔍'):
     specialty_codes = filtered_specialties['Code'].tolist()
     state_data = process_files(specialty_codes, selected_state if use_specific_state else None)
+    #state_data = process_files_new(specialty_codes, selected_state if use_specific_state else None)
     if state_data:
         for state, info, df in state_data:
             st.subheader(f"Providers in {state} with Specialties related to '{search_keyword or selected_specialty}':")
@@ -108,17 +154,3 @@ if st.button('Analyze Text Files for Selected Specialty 🔍'):
             st.dataframe(df)
     else:
         st.write("No matching records found in text files for the selected specialties.")
-
-# Moved Help Information to the bottom
-if st.expander('🩺 Understand Provider Specialties 📝'):
-    st.markdown('''
-## Discover Care Providers by Specialty & Location: Quick Guide
-- **Code**: Unique ID identifies each specialty clearly. 🆔
-- **Grouping**: Broad category umbrella for general expertise area. 🏷️
-- **Classification**: Specifies type of practice within broader category. 🎯
-- **Specialization**: Details focus within classification for precise expertise. 🔍
-- **Definition**: Concise overview of the specialty's scope. 📖
-- **Notes**: Extra information or recent updates provided. 🗒️
-- **Display Name**: Commonly recognized name of the specialty. 🏷️
-- **Section**: Healthcare segment the specialty belongs to. 📚
-    ''')