Create backup.04012024.app.py

backup.04012024.app.py

@@ -0,0 +1,110 @@
+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"
+    }
+)
+
+headers = [
+    "NPI", "EntityTypeCode", "ReplacementNPI", "EmployerIdentificationNumberEIN", 
+    "ProviderOrganizationNameLegalBusinessName", "ProviderLastNameLegalName", 
+    "ProviderFirstName", "ProviderMiddleName", "ProviderNamePrefixText", 
+    "ProviderNameSuffixText", "ProviderCredentialText", "ProviderOtherOrganizationName", 
+    "ProviderOtherOrganizationNameTypeCode", "ProviderOtherLastName", "ProviderOtherFirstName", 
+    "ProviderOtherMiddleName", "ProviderOtherNamePrefixText", "ProviderOtherNameSuffixText", 
+    "ProviderOtherCredentialText", "ProviderOtherLastNameTypeCode", 
+    "ProviderFirstLineBusinessMailingAddress", "ProviderSecondLineBusinessMailingAddress", 
+    "ProviderBusinessMailingAddressCityName", "ProviderBusinessMailingAddressStateName", 
+    "ProviderBusinessMailingAddressPostalCode", "ProviderBusinessMailingAddressCountryCodeIfoutsideUS", 
+    "ProviderBusinessMailingAddressTelephoneNumber", "ProviderBusinessMailingAddressFaxNumber", 
+    "ProviderFirstLineBusinessPracticeLocationAddress", "ProviderSecondLineBusinessPracticeLocationAddress", 
+    "ProviderBusinessPracticeLocationAddressCityName", "ProviderBusinessPracticeLocationAddressStateName", 
+    "ProviderBusinessPracticeLocationAddressPostalCode", "ProviderBusinessPracticeLocationAddressCountryCodeIfoutsideUS", 
+    "ProviderBusinessPracticeLocationAddressTelephoneNumber", "ProviderBusinessPracticeLocationAddressFaxNumber", 
+    "ProviderEnumerationDate", "LastUpdateDate", "NPIDeactivationReasonCode", 
+    "NPIDeactivationDate", "NPIReactivationDate", "ProviderGenderCode", 
+    "AuthorizedOfficialLastName", "AuthorizedOfficialFirstName", "AuthorizedOfficialMiddleName", 
+    "AuthorizedOfficialTitleorPosition", "AuthorizedOfficialTelephoneNumber", 
+    "HealthcareProviderTaxonomyCode", "ProviderLicenseNumber", "ProviderLicenseNumberStateCode", 
+    "HealthcareProviderPrimaryTaxonomySwitch"
+]
+
+# Cache the loading of specialties for efficiency
+@st.cache_resource
+def load_specialties(csv_file='Provider-Specialty.csv'):
+    return pd.read_csv(csv_file)
+
+# Cache the finding of state files to avoid repeated file system access
+@st.cache_resource
+def find_state_files():
+    return [file for file in glob.glob('./*.csv') if len(os.path.basename(file).split('.')[0]) == 2]
+
+specialties = load_specialties()
+st.markdown("# 🩺🔍 Care Team Finder ")
+st.markdown("#### Search for Care Providers by Specialty and Location")
+
+# 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)
+
+# Keyword search functionality
+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)]
+else:
+    filtered_specialties = specialties[specialties['Display Name'] == selected_specialty]
+
+st.dataframe(filtered_specialties[['Code', 'Grouping', 'Classification', 'Specialization', 'Definition']])
+
+# State selection UI with default selection 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)
+
+# 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:
+        #state_df = pd.read_csv(file, header=0)  # Assuming no header for simplicity
+        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[47].isin([code])]  # Match against 48th column, adjust as needed
+            #filtered_df = state_df[state_df['ProviderBusinessPracticeLocationAddressStateName'].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))
+    
+    return results
+
+# Button to initiate the analysis
+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}':")
+            st.markdown(f"**Code**: {info['Code']}, **Grouping**: {info['Grouping']}, **Classification**: {info['Classification']}")
+            st.dataframe(df)
+    else:
+        st.write("No matching records found in text files for the selected specialties.")