Update app.py

app.py

@@ -5,142 +5,126 @@ import numpy as np
 # Seed for reproducibility
 np.random.seed(42)
 
-# Function to generate synthetic breast cancer data
-def generate_breast_cancer_data(num_patients=100):
-    patient_ids = [f"BC_{i+1:05d}" for i in range(num_patients)]
-    ages = []
-    menopausal_status = []
-    tumor_sizes = []
-    lymph_nodes = []
-    grades = []
-    stages = []
-    er_status = []
-    pr_status = []
-    her2_status = []
-    ki67_level = []
-    tnbc_status = []
-    brca_mutation = []
-    overall_health = []
-    genomic_score = []
-    treatment = []
+# Function to generate synthetic Enrollments
+def generate_enrollments(num_members):
+    primary_keys = [f"PPK_{i+1:05d}" for i in range(num_members)]
+    enrollments_data = {
+        "MEM_AGE": np.random.randint(18, 80, num_members),
+        "MEM_MSA_NAME": np.random.choice(["DETROIT", "HONOLULU", "LOS ANGELES"], num_members),
+        "MEM_STAT": np.random.choice(["ACTIVE", "INACTIVE"], num_members),
+        "MEMBER_ID": primary_keys,
+        "PRIMARY_PERSON_KEY": primary_keys,
+        "PAYER_LOB": np.random.choice(["MEDICAID", "COMMERCIAL", "MEDICARE"], num_members),
+        "PAYER_TYPE": np.random.choice(["PPO", "HMO"], num_members),
+        "PRIMARY_CHRONIC_CONDITION_ROLLUP_DESC": np.random.choice(["Cancer", "Diabetes", "Hypertension"], num_members),
+        "Count of PRIMARY_CHRONIC_CONDITION_ROLLUP_ID": np.random.randint(1, 5, num_members),
+        "PROD_TYPE": np.random.choice(["DENTAL", "VISION", "MEDICAL"], num_members),
+        "RELATION": np.random.choice(["SUBSCRIBER", "DEPENDENT"], num_members),
+        "YEARMO": np.random.randint(202201, 202412, num_members),
+    }
+    return pd.DataFrame(enrollments_data)
+
+# Function to generate synthetic Members
+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_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),
+        "MEM_ZIP3": np.random.randint(100, 999, num_members),
+        "MEMBER_ID": primary_keys,
+        "PRIMARY_PERSON_KEY": primary_keys,
+    }
+    return pd.DataFrame(members_data)
+
+# Function to generate synthetic Providers
+def generate_providers(num_providers):
+    providers_data = {
+        "PROV_CLINIC_STATE": np.random.choice(["MI", "HI", "CA"], num_providers),
+        "PROV_CLINIC_ZIP": np.random.randint(10000, 99999, num_providers),
+        "PROV_KEY": [f"PK_{i+1:05d}" for i in range(num_providers)],
+        "Sum of PROV_NPI_ORG": np.random.randint(1, 50, num_providers),
+        "PROV_TAXONOMY": np.random.choice(["208100000X", "207RE0101X"], num_providers),
+        "PROV_TYPE": np.random.choice(["Type1", "Type2"], num_providers),
+    }
+    return pd.DataFrame(providers_data)
+
+# Function to generate synthetic Services
+def generate_services(num_services, primary_keys):
+    services_data = {
+        "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),
+        "ATT_PROV_KEY": [f"PK_{i+1:05d}" for i in np.random.randint(1, len(primary_keys), num_services)],
+        "BILL_PROV_KEY": [f"PK_{i+1:05d}" for i in np.random.randint(1, len(primary_keys), num_services)],
+        "CLAIM_IN_NETWORK": np.random.choice(["Y", "N", None], num_services),
+        "RELATION": np.random.choice(["SUBSCRIBER", "DEPENDENT"], num_services),
+        "SERVICE_SETTING": np.random.choice(["OUTPATIENT", "INPATIENT"], num_services),
+        "Sum of SERVICE_LINE": np.random.randint(1, 10, num_services),
+        "Sum of SV_UNITS": np.random.randint(1, 100, num_services),
+        "YEARMO": np.random.randint(202201, 202412, num_services),
+    }
+    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)]
+    breast_cancer_data = {
+        "Patient ID": patient_ids,
+        "Age": np.random.randint(30, 80, num_patients),
+        "Menopausal Status": np.random.choice(["Post-menopausal", "Pre-menopausal"], num_patients),
+        "Tumor Size (cm)": np.round(np.random.lognormal(mean=0.7, sigma=0.5, size=num_patients), 2),
+        "Lymph Node Involvement": np.random.choice(["Positive", "Negative"], num_patients),
+        "Tumor Grade": np.random.choice([1, 2, 3], num_patients),
+        "Tumor Stage": np.random.choice(["I", "II", "III", "IV"], num_patients),
+        "ER Status": np.random.choice(["Positive", "Negative"], num_patients),
+        "PR Status": np.random.choice(["Positive", "Negative"], num_patients),
+        "HER2 Status": np.random.choice(["Positive", "Negative"], num_patients),
+        "Ki-67 Level": np.random.choice(["High", "Low"], num_patients),
+        "TNBC Status": np.random.choice(["Positive", "Negative"], num_patients),
+        "BRCA Mutation": np.random.choice(["Positive", "Negative"], num_patients),
+        "Overall Health": np.random.choice(["Good", "Poor"], num_patients),
+        "Genomic Recurrence Score": np.random.choice(["Low", "Intermediate", "High", "N/A"], num_patients),
+        "Treatment": np.random.choice(["Surgery", "Chemotherapy", "Radiation Therapy"], num_patients),
+    }
+    return pd.DataFrame(breast_cancer_data)
 
-    for i in range(num_patients):
-        age = int(np.random.normal(60, 10))
-        age = max(30, min(age, 80))
-        ages.append(age)
-
-        menopausal = "Post-menopausal" if age >= 50 else "Pre-menopausal"
-        menopausal_status.append(menopausal)
-
-        tumor_size = round(np.random.lognormal(mean=0.7, sigma=0.5), 2)
-        tumor_sizes.append(tumor_size)
-
-        lymph_node = (
-            "Positive"
-            if (tumor_size > 2.0 and np.random.rand() < 0.6)
-            or (tumor_size <= 2.0 and np.random.rand() < 0.3)
-            else "Negative"
-        )
-        lymph_nodes.append(lymph_node)
-
-        grade = np.random.choice([1, 2, 3], p=[0.1, 0.4, 0.5] if tumor_size > 2.0 else [0.3, 0.5, 0.2])
-        grades.append(grade)
-
-        if tumor_size <= 2.0 and lymph_node == "Negative":
-            stage = "I"
-        elif (tumor_size > 2.0 and tumor_size <= 5.0) and lymph_node == "Negative":
-            stage = "II"
-        elif lymph_node == "Positive" or tumor_size > 5.0:
-            stage = "III"
-        else:
-            stage = "II"
-        if np.random.rand() < 0.05:
-            stage = "IV"
-        stages.append(stage)
-
-        er = np.random.choice(["Positive", "Negative"], p=[0.75, 0.25])
-        pr = "Positive" if er == "Positive" and np.random.rand() > 0.1 else "Negative"
-        er_status.append(er)
-        pr_status.append(pr)
-
-        her2 = np.random.choice(["Positive", "Negative"], p=[0.3, 0.7] if grade == 3 else [0.15, 0.85])
-        her2_status.append(her2)
-
-        ki67 = "High" if grade == 3 and np.random.rand() < 0.8 else "Low"
-        ki67_level.append(ki67)
-
-        tnbc = "Positive" if er == "Negative" and pr == "Negative" and her2 == "Negative" else "Negative"
-        tnbc_status.append(tnbc)
-
-        brca = "Positive" if (tnbc == "Positive" or age < 40) and np.random.rand() < 0.2 else "Negative"
-        brca_mutation.append(brca)
-
-        health = "Good" if age < 65 and np.random.rand() < 0.9 else "Poor"
-        overall_health.append(health)
-
-        recurrence_score = (
-            np.random.choice(["Low", "Intermediate", "High"], p=[0.6, 0.3, 0.1])
-            if er == "Positive" and her2 == "Negative"
-            else "N/A"
-        )
-        genomic_score.append(recurrence_score)
-
-        if stage in ["I", "II"]:
-            if tnbc == "Positive":
-                treat = "Surgery, Chemotherapy, and Radiation Therapy"
-            elif er == "Positive" and recurrence_score != "N/A":
-                if recurrence_score == "High":
-                    treat = "Surgery, Chemotherapy, Hormone Therapy, and Radiation Therapy"
-                elif recurrence_score == "Intermediate":
-                    treat = "Surgery, Consider Chemotherapy, Hormone Therapy, and Radiation Therapy"
-                else:
-                    treat = "Surgery, Hormone Therapy, and Radiation Therapy"
-            elif her2 == "Positive":
-                treat = "Surgery, HER2-Targeted Therapy, Chemotherapy, and Radiation Therapy"
-            else:
-                treat = "Surgery, Chemotherapy, and Radiation Therapy"
-        elif stage == "III":
-            treat = (
-                "Neoadjuvant Chemotherapy, Surgery, Radiation Therapy"
-                + (", HER2-Targeted Therapy" if her2 == "Positive" else "")
-                + (", Hormone Therapy" if er == "Positive" else "")
-            )
-        else:
-            treat = "Systemic Therapy (Palliative Care)"
-        treatment.append(treat)
-
-    return pd.DataFrame(
-        {
-            "Patient ID": patient_ids,
-            "Age": ages,
-            "Menopausal Status": menopausal_status,
-            "Tumor Size (cm)": tumor_sizes,
-            "Lymph Node Involvement": lymph_nodes,
-            "Tumor Grade": grades,
-            "Tumor Stage": stages,
-            "ER Status": er_status,
-            "PR Status": pr_status,
-            "HER2 Status": her2_status,
-            "Ki-67 Level": ki67_level,
-            "TNBC Status": tnbc_status,
-            "BRCA Mutation": brca_mutation,
-            "Overall Health": overall_health,
-            "Genomic Recurrence Score": genomic_score,
-            "Treatment": treatment,
-        }
-    )
+# Main Streamlit App
+st.title("Synthetic Medical Data Generator")
 
+# Input parameters
+num_members = st.slider("Number of Members to Generate", 10, 1000, 100)
+num_providers = st.slider("Number of Providers to Generate", 10, 500, 100)
+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)
 
-# Main Streamlit App
-st.title("Synthetic Data Generator")
-num_patients = st.slider("Number of Patients to Generate", 10, 1000, 100)
 if st.button("Generate Data"):
-    breast_cancer_data = generate_breast_cancer_data(num_patients)
-    st.write("Breast Cancer Data")
-    st.dataframe(breast_cancer_data)
-    st.download_button(
-        "Download Breast Cancer Data",
-        data=breast_cancer_data.to_csv(index=False),
-        file_name="breast_cancer_data.csv",
-        mime="text/csv",
-    )
+    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)
+
+    # Display data
+    st.subheader("Enrollments Data")
+    st.dataframe(enrollments_df.head())
+    st.download_button("Download Enrollments", enrollments_df.to_csv(index=False), "enrollments.csv")
+
+    st.subheader("Members Data")
+    st.dataframe(members_df.head())
+    st.download_button("Download Members", members_df.to_csv(index=False), "members.csv")
+
+    st.subheader("Providers Data")
+    st.dataframe(providers_df.head())
+    st.download_button("Download Providers", providers_df.to_csv(index=False), "providers.csv")
+
+    st.subheader("Services Data")
+    st.dataframe(services_df.head())
+    st.download_button("Download Services", services_df.to_csv(index=False), "services.csv")
+
+    st.subheader("Breast Cancer Data")
+    st.dataframe(breast_cancer_df.head())
+    st.download_button("Download Breast Cancer Data", breast_cancer_df.to_csv(index=False), "breast_cancer.csv")