Update app.py

app.py

@@ -1,8 +1,6 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
-import csv
-import io
 import random
 from datetime import datetime, timedelta
 
@@ -12,7 +10,6 @@ np.random.seed(42)
 # Function to generate synthetic BreastCancer data
 def generate_breast_cancer_data(num_patients):
     primary_keys = [f"PPK_{i+1:05d}" for i in range(num_patients)]
-    
     ages = []
     menopausal_status = []
     tumor_sizes = []
@@ -135,7 +132,7 @@ def generate_breast_cancer_data(num_patients):
 
     return pd.DataFrame(breast_cancer_data)
 
-# Function to generate Members from BreastCancer
+# Function to generate Members
 def generate_members_from_breast_cancer(breast_cancer_df):
     return pd.DataFrame({
         "MEMBER_ID": breast_cancer_df["PRIMARY_PERSON_KEY"],
@@ -147,7 +144,7 @@ def generate_members_from_breast_cancer(breast_cancer_df):
         "MEM_ZIP3": np.random.randint(100, 999, len(breast_cancer_df)),
     })
 
-# Function to generate Enrollments from BreastCancer
+# Function to generate Enrollments
 def generate_enrollments_from_breast_cancer(breast_cancer_df):
     return pd.DataFrame({
         "PRIMARY_PERSON_KEY": breast_cancer_df["PRIMARY_PERSON_KEY"],
@@ -181,7 +178,7 @@ def generate_providers(num_providers):
         "PROV_TAXONOMY": np.random.choice(["208100000X", "207RE0101X"], num_providers),
     })
 
-# Function to generate wearable data
+# Function to generate Wearable Data
 def generate_wearable_data(num_patients, num_measurements, start_datetime, time_interval, cancer_rate, chemo_brain_effect, primary_keys):
     num_cancer_patients = int((cancer_rate / 100) * num_patients)
     cancer_patients = set(random.sample(primary_keys, num_cancer_patients))
@@ -214,4 +211,58 @@ def generate_wearable_data(num_patients, num_measurements, start_datetime, time_
             heart_rate = max(heart_rate, 50)
             o2_sat = max(o2_sat, 90.0)
 
-            data_rows.append([pkey, ts.strftime("%Y-%m-%d %H:%M
+            data_rows.append([
+                pkey,
+                ts.strftime("%Y-%m-%d %H:%M:%S"),
+                activity,
+                heart_rate,
+                round(o2_sat, 1)
+            ])
+    
+    return pd.DataFrame(data_rows, columns=["PRIMARY_PERSON_KEY", "Measurement_Timestamp", "Activity_Level", "Heart_Rate", "O2_Saturation"])
+
+# Main Streamlit App
+st.title("Synthetic Medical Data Generator with Wearable Data")
+
+# Sliders
+num_patients = st.slider("Number of Breast Cancer Patients to Generate", 10, 1000, 100)
+num_measurements = st.slider("Measurements per Patient (Wearable Data)", 1, 100, 10)
+num_services = st.slider("Number of Services to Generate", 10, 2000, 500)
+num_providers = st.slider("Number of Providers to Generate", 10, 500, 100)
+
+start_date = st.date_input("Wearable Data Start Date", value=datetime(2024, 12, 1))
+start_time = st.time_input("Wearable Data Start Time", value=datetime(2024, 12, 1, 8, 0).time())
+cancer_rate = st.slider("Percentage of Patients with Cancer (Wearable Data)", 0, 100, 30)
+chemo_brain_effect = st.slider("Chemo Brain Impact on Activity Level (in % reduction)", 0, 50, 20)
+
+if st.button("Generate Data"):
+    primary_keys = [f"PPK_{i+1:05d}" for i in range(num_patients)]
+    wearable_start_datetime = datetime.combine(start_date, start_time)
+    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, primary_keys)
+    providers_df = generate_providers(num_providers)
+    wearable_data = generate_wearable_data(
+        num_patients, num_measurements, wearable_start_datetime, timedelta(hours=1), cancer_rate, chemo_brain_effect, primary_keys
+    )
+
+    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")
+
+    st.subheader("Members Data")
+    st.dataframe(members_df.head())
+    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 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