Create app.py

app.py

@@ -0,0 +1,103 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import plotly.express as px
+from datetime import datetime, timedelta
+
+# Set page config
+st.set_page_config(page_title="Healthcare Dashboard", layout="wide")
+
+# Load sample data (replace this with your actual data loading logic)
+@st.cache_data
+def load_data():
+    # Generate sample data
+    np.random.seed(42)
+    dates = pd.date_range(start="2022-01-01", end="2023-04-30", freq="D")
+    departments = ["Cardiology", "Neurology", "Oncology", "Pediatrics", "Emergency"]
+    diagnoses = ["Hypertension", "Stroke", "Cancer", "Diabetes", "Pneumonia", "Fracture", "Appendicitis", "Asthma", "Heart Disease", "Influenza"]
+    
+    data = {
+        "Date": np.random.choice(dates, 1000),
+        "Patient ID": np.arange(1, 1001),
+        "Age": np.random.randint(1, 100, 1000),
+        "Gender": np.random.choice(["Male", "Female"], 1000),
+        "Department": np.random.choice(departments, 1000),
+        "Diagnosis": np.random.choice(diagnoses, 1000),
+        "Length of Stay": np.random.randint(1, 30, 1000)
+    }
+    
+    return pd.DataFrame(data)
+
+df = load_data()
+
+# Title and introduction
+st.title("Healthcare Dashboard")
+st.write("Welcome to the healthcare dashboard. This interactive tool provides insights into patient data, hospital admissions, and key healthcare metrics.")
+
+# Sidebar
+st.sidebar.header("Filters")
+department = st.sidebar.multiselect("Select Department", options=df["Department"].unique(), default=df["Department"].unique())
+date_range = st.sidebar.date_input("Select Date Range", value=(df["Date"].min().date(), df["Date"].max().date()))
+
+# Convert date_range to datetime
+start_date = datetime.combine(date_range[0], datetime.min.time())
+end_date = datetime.combine(date_range[1], datetime.max.time())
+
+# Filter data based on user selection
+filtered_df = df[(df["Department"].isin(department)) & (df["Date"] >= start_date) & (df["Date"] <= end_date)]
+
+# Main content
+col1, col2 = st.columns(2)
+
+# Patient Demographics
+with col1:
+    st.subheader("Patient Demographics")
+    fig_gender = px.pie(filtered_df, names="Gender", title="Gender Distribution")
+    st.plotly_chart(fig_gender, use_container_width=True)
+
+# Hospital Admissions Over Time
+with col2:
+    st.subheader("Hospital Admissions Over Time")
+    admissions_over_time = filtered_df.groupby("Date").size().reset_index(name="Admissions")
+    fig_admissions = px.line(admissions_over_time, x="Date", y="Admissions", title="Daily Hospital Admissions")
+    st.plotly_chart(fig_admissions, use_container_width=True)
+
+# Top 10 Diagnoses
+st.subheader("Top 10 Diagnoses")
+top_diagnoses = filtered_df["Diagnosis"].value_counts().nlargest(10)
+fig_diagnoses = px.bar(top_diagnoses, x=top_diagnoses.index, y=top_diagnoses.values, title="Top 10 Diagnoses")
+st.plotly_chart(fig_diagnoses, use_container_width=True)
+
+# Average Length of Stay by Department
+st.subheader("Average Length of Stay by Department")
+avg_los = filtered_df.groupby("Department")["Length of Stay"].mean().sort_values(ascending=True)
+fig_los = px.bar(avg_los, x=avg_los.values, y=avg_los.index, orientation="h", title="Average Length of Stay (Days)")
+st.plotly_chart(fig_los, use_container_width=True)
+
+# Age Distribution
+st.subheader("Age Distribution")
+fig_age = px.histogram(filtered_df, x="Age", nbins=20, title="Age Distribution of Patients")
+st.plotly_chart(fig_age, use_container_width=True)
+
+# Interactive Data Table
+st.subheader("Patient Data")
+st.dataframe(filtered_df)
+
+# Add a download button for the filtered data
+csv = filtered_df.to_csv(index=False).encode('utf-8')
+st.download_button(
+    label="Download data as CSV",
+    data=csv,
+    file_name="healthcare_data.csv",
+    mime="text/csv",
+)
+
+# Key Metrics
+st.subheader("Key Metrics")
+col1, col2, col3, col4 = st.columns(4)
+col1.metric("Total Patients", len(filtered_df))
+col2.metric("Avg. Length of Stay", f"{filtered_df['Length of Stay'].mean():.2f} days")
+col3.metric("Most Common Diagnosis", filtered_df["Diagnosis"].mode()[0])
+col4.metric("Busiest Department", filtered_df["Department"].value_counts().index[0])