Update app.py

app.py

@@ -131,9 +131,9 @@ def generate_breast_cancer_data(num_patients):
 
     return pd.DataFrame(breast_cancer_data)
 
-# Function to generate synthetic Members
+# Function to generate Members from BreastCancer
 def generate_members_from_breast_cancer(breast_cancer_df):
-    members_data = {
+    return pd.DataFrame({
         "MEMBER_ID": breast_cancer_df["Patient ID"],
         "PRIMARY_PERSON_KEY": breast_cancer_df["Patient ID"],
         "MEM_GENDER": ["F"] * len(breast_cancer_df),
@@ -141,30 +141,37 @@ def generate_members_from_breast_cancer(breast_cancer_df):
         "MEM_RACE": np.random.choice(["White", "Black", "Asian", None], len(breast_cancer_df)),
         "MEM_STATE": np.random.choice(["MI", "HI", "CA"], len(breast_cancer_df)),
         "MEM_ZIP3": np.random.randint(100, 999, len(breast_cancer_df)),
-    }
-    return pd.DataFrame(members_data)
+    })
+
+# Function to generate Enrollments from BreastCancer
+def generate_enrollments_from_breast_cancer(breast_cancer_df):
+    return pd.DataFrame({
+        "PRIMARY_PERSON_KEY": breast_cancer_df["Patient ID"],
+        "MEM_STAT": np.random.choice(["ACTIVE", "INACTIVE"], len(breast_cancer_df)),
+        "PAYER_LOB": np.random.choice(["MEDICAID", "COMMERCIAL", "MEDICARE"], len(breast_cancer_df)),
+        "PAYER_TYPE": np.random.choice(["PPO", "HMO"], len(breast_cancer_df)),
+        "RELATION": np.random.choice(["SUBSCRIBER", "DEPENDENT"], len(breast_cancer_df)),
+    })
 
-# Function to generate synthetic Services
+# Function to generate Services from BreastCancer
 def generate_services(num_services, primary_keys):
-    services_data = {
+    return pd.DataFrame({
         "PRIMARY_PERSON_KEY": np.random.choice(primary_keys, num_services),
-        "Sum of AMT_ALLOWED": np.random.uniform(1000, 10000, num_services),
-        "Sum of AMT_BILLED": np.random.uniform(1000, 15000, num_services),
-        "Count of AMT_PAID": np.random.randint(1, 5, num_services),
         "SERVICE_SETTING": np.random.choice(["OUTPATIENT", "INPATIENT"], num_services),
-    }
-    return pd.DataFrame(services_data)
+        "AMOUNT_BILLED": np.random.uniform(500, 15000, num_services),
+    })
 
 # Main Streamlit App
 st.title("Synthetic Medical Data Generator")
 
-# Slider for breast cancer patients
+# 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)
 
 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["Patient ID"].tolist())
 
     # Display and download data
@@ -174,8 +181,12 @@ if st.button("Generate Data"):
 
     st.subheader("Members Data")
     st.dataframe(members_df.head())
-    st.download_button("Download Members", members_df.to_csv(index=False), "members.csv")
+    st.download_button("Download Members Data", members_df.to_csv(index=False), "members.csv")
+
+    st.subheader("Enrollments Data")
+    st.dataframe(enrollments_df.head())
+    st.download_button("Download Enrollments Data", enrollments_df.to_csv(index=False), "enrollments.csv")
 
     st.subheader("Services Data")
     st.dataframe(services_df.head())
-    st.download_button("Download Services", services_df.to_csv(index=False), "services.csv")
+    st.download_button("Download Services Data", services_df.to_csv(index=False), "services.csv")