Create app.py

app.py

@@ -0,0 +1,50 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+# Load the largest hospitals data
+data = [
+    {"Hospital": "Texas Health Presbyterian Hospital Dallas", "City": "Dallas", "State": "TX", "Beds": 898},
+    {"Hospital": "Cedars-Sinai Medical Center", "City": "Los Angeles", "State": "CA", "Beds": 886},
+    {"Hospital": "Jackson Memorial Hospital", "City": "Miami", "State": "FL", "Beds": 1618},
+    {"Hospital": "New York-Presbyterian Hospital", "City": "New York", "State": "NY", "Beds": 2528},
+    {"Hospital": "Barnes-Jewish Hospital", "City": "St. Louis", "State": "MO", "Beds": 1252},
+]
+
+# Create a Pandas DataFrame from the data
+df = pd.DataFrame(data)
+
+# Define the generative AI function
+def generate_data(df, num_rows=1):
+    # Calculate the mean and standard deviation of the Beds column
+    bed_mean = df["Beds"].mean()
+    bed_std = df["Beds"].std()
+    
+    # Generate new data using a normal distribution
+    new_data = {
+        "Hospital": [f"Generated Hospital {i}" for i in range(num_rows)],
+        "City": np.random.choice(df["City"], num_rows),
+        "State": np.random.choice(df["State"], num_rows),
+        "Beds": np.random.normal(bed_mean, bed_std, num_rows).astype(int)
+    }
+    
+    # Create a new DataFrame from the generated data and return it
+    return pd.DataFrame(new_data)
+
+# Define the Streamlit app
+def app():
+    st.title("Generative AI Demo")
+    
+    # Display the original data
+    st.subheader("Original Data")
+    st.write(df)
+    
+    # Generate new data and display it
+    st.subheader("Generated Data")
+    num_rows = st.slider("Number of rows to generate", min_value=1, max_value=100, value=1)
+    new_data = generate_data(df, num_rows=num_rows)
+    st.write(new_data)
+
+# Run the Streamlit app
+if __name__ == "__main__":
+    app()