Update app.py

app.py

@@ -166,18 +166,31 @@ def generate_services(num_services, primary_keys):
         "RELATION": np.random.choice(["SUBSCRIBER", "DEPENDENT"], num_services),
     })
 
+# Function to generate Providers
+def generate_providers(num_providers):
+    return pd.DataFrame({
+        "PROVIDER_ID": [f"PROV_{i+1:05d}" for i in range(num_providers)],
+        "PROV_NAME": np.random.choice(["Clinic A", "Clinic B", "Clinic C"], num_providers),
+        "PROV_STATE": np.random.choice(["MI", "HI", "CA"], num_providers),
+        "PROV_ZIP": np.random.randint(10000, 99999, num_providers),
+        "PROV_SPECIALTY": np.random.choice(["Oncology", "Radiology", "Surgery"], num_providers),
+        "PROV_TAXONOMY": np.random.choice(["208100000X", "207RE0101X"], num_providers),
+    })
+
 # Main Streamlit App
 st.title("Synthetic Medical Data Generator")
 
 # Sliders
 num_patients = st.slider("Number of Breast Cancer Patients to Generate", 10, 1000, 100)
 num_services = st.slider("Number of Services to Generate", 10, 2000, 500)
+num_providers = st.slider("Number of Providers to Generate", 10, 500, 100)
 
 if st.button("Generate Data"):
     breast_cancer_df = generate_breast_cancer_data(num_patients)
     members_df = generate_members_from_breast_cancer(breast_cancer_df)
     enrollments_df = generate_enrollments_from_breast_cancer(breast_cancer_df)
     services_df = generate_services(num_services, breast_cancer_df["PRIMARY_PERSON_KEY"].tolist())
+    providers_df = generate_providers(num_providers)
 
     # Display and download data
     st.subheader("Breast Cancer Data")
@@ -195,3 +208,7 @@ if st.button("Generate Data"):
     st.subheader("Services Data")
     st.dataframe(services_df.head())
     st.download_button("Download Services Data", services_df.to_csv(index=False), "services.csv")
+
+    st.subheader("Providers Data")
+    st.dataframe(providers_df.head())
+    st.download_button("Download Providers Data", providers_df.to_csv(index=False), "providers.csv")