Update app.py

app.py

@@ -29,7 +29,7 @@ def generate_members(num_members):
     primary_keys = [f"PPK_{i+1:05d}" for i in range(num_members)]
     members_data = {
         "MEM_ETHNICITY": np.random.choice(["Hispanic", "Non-Hispanic", None], num_members),
-        "MEM_GENDER": ["F"] * num_members,
+        "MEM_GENDER": ["F"] * num_members,  # All members are female
         "MEM_MSA_NAME": np.random.choice(["DETROIT", "HONOLULU", "LOS ANGELES"], num_members),
         "MEM_RACE": np.random.choice(["White", "Black", "Asian", None], num_members),
         "MEM_STATE": np.random.choice(["MI", "HI", "CA"], num_members),
@@ -70,8 +70,10 @@ def generate_services(num_services, primary_keys):
     return pd.DataFrame(services_data)
 
 # Function to generate synthetic BreastCancer data
-def generate_breast_cancer_data(num_patients):
-    patient_ids = [f"PPK_{i+1:05d}" for i in range(num_patients)]
+def generate_breast_cancer_data(members_df, num_patients):
+    # Randomly sample from PRIMARY_PERSON_KEY in Members
+    patient_ids = np.random.choice(members_df["PRIMARY_PERSON_KEY"], num_patients, replace=False)
+    
     breast_cancer_data = {
         "Patient ID": patient_ids,
         "Age": np.random.randint(30, 80, num_patients),
@@ -102,13 +104,14 @@ num_services = st.slider("Number of Services to Generate", 10, 2000, 500)
 num_patients = st.slider("Number of Breast Cancer Patients to Generate", 10, 500, 100)
 
 if st.button("Generate Data"):
+    # Generate data
     enrollments_df = generate_enrollments(num_members)
     members_df = generate_members(num_members)
     providers_df = generate_providers(num_providers)
     services_df = generate_services(num_services, enrollments_df["PRIMARY_PERSON_KEY"].tolist())
-    breast_cancer_df = generate_breast_cancer_data(num_patients)
+    breast_cancer_df = generate_breast_cancer_data(members_df, num_patients)
 
-    # Display data
+    # Display and download data
     st.subheader("Enrollments Data")
     st.dataframe(enrollments_df.head())
     st.download_button("Download Enrollments", enrollments_df.to_csv(index=False), "enrollments.csv")