Update app.py

app.py

@@ -1,17 +1,18 @@
+
 import streamlit as st
 import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
+import plotly.express as px
 
-# Load the dataset
+# Load and clean the dataset
 @st.cache_data
 def load_data():
     df = pd.read_csv("hospital_readmissions.csv")
-    # Data Cleaning
+    # Clean missing values
     df['medical_specialty'] = df['medical_specialty'].replace('Missing', 'Unknown')
     df['diag_1'] = df['diag_1'].replace('Missing', 'Unknown_Diagnosis')
     df['diag_2'] = df['diag_2'].replace('Missing', 'Unknown_Diagnosis')
     df['diag_3'] = df['diag_3'].replace('Missing', 'Unknown_Diagnosis')
+    # Extract numerical age from range
     df['age'] = df['age'].str.extract(r'\[(\d+)-').astype(float)
     return df
 
@@ -23,71 +24,45 @@ page = st.sidebar.radio("Go to", ["Overview", "Factors Influencing Readmissions"
                                    "Hospital Stay and Procedures", "Patient Health Insights", 
                                    "Recommendations"])
 
+# Filters for interactivity
+st.sidebar.header("Filters")
+age_group = st.sidebar.multiselect("Select Age Group", options=sorted(df['age'].unique()), default=sorted(df['age'].unique()))
+diagnosis = st.sidebar.multiselect("Select Diagnosis", options=df['diag_1'].unique(), default=["Circulatory", "Diabetes"])
+
+# Filter the data based on user selection
+filtered_df = df[df['age'].isin(age_group) & df['diag_1'].isin(diagnosis)]
+
 # Page 1: Overview
 if page == "Overview":
     st.title("Hospital Readmissions Overview")
     
-    # Total Patients
-    total_patients = len(df)
-    readmission_rate = df['readmitted'].value_counts(normalize=True).get('yes', 0) * 100
-    avg_hospital_stay = df['time_in_hospital'].mean()
+    # Total Patients and Readmission Rate
+    total_patients = len(filtered_df)
+    readmission_rate = filtered_df['readmitted'].value_counts(normalize=True).get('yes', 0) * 100
     
-    st.metric("Total Patients", total_patients)
-    st.metric("Readmission Rate (%)", f"{readmission_rate:.2f}%")
-    st.metric("Average Hospital Stay (Days)", f"{avg_hospital_stay:.2f}")
+    col1, col2 = st.columns(2)
+    col1.metric("Total Patients", total_patients)
+    col2.metric("Readmission Rate (%)", f"{readmission_rate:.2f}%")
     
     # Age Distribution
-    st.subheader("Age Distribution")
-    fig, ax = plt.subplots()
-    sns.histplot(df['age'], bins=10, kde=False, ax=ax)
-    ax.set_title("Age Distribution")
-    ax.set_xlabel("Age Group")
-    ax.set_ylabel("Count")
-    st.pyplot(fig)
-    
-    # Medical Specialties
-    st.subheader("Top Medical Specialties")
-    specialty_counts = df['medical_specialty'].value_counts().head(5)
-    fig, ax = plt.subplots()
-    specialty_counts.plot(kind='pie', autopct='%1.1f%%', ax=ax)
-    ax.set_title("Top Medical Specialties")
-    ax.set_ylabel("")
-    st.pyplot(fig)
+    st.subheader("Age Distribution of Patients")
+    fig_age = px.histogram(filtered_df, x='age', nbins=10, title="Age Distribution",
+                           labels={'age': 'Age Group', 'count': 'Number of Patients'})
+    fig_age.update_layout(showlegend=False)
+    st.plotly_chart(fig_age, use_container_width=True)
 
 # Page 2: Factors Influencing Readmissions
 elif page == "Factors Influencing Readmissions":
     st.title("Factors Influencing Readmissions")
     
-    # Readmission by Age Group
-    st.subheader("Readmission by Age Group")
-    age_readmission = df.groupby(pd.cut(df['age'], bins=10))['readmitted'].value_counts(normalize=True).unstack().fillna(0)
-    fig, ax = plt.subplots()
-    age_readmission.plot(kind='bar', stacked=True, ax=ax)
-    ax.set_title("Readmission by Age Group")
-    ax.set_xlabel("Age Group")
-    ax.set_ylabel("Proportion")
-    st.pyplot(fig)
-    
     # Readmission by Medical Specialty
-    st.subheader("Readmission by Medical Specialty")
-    specialty_readmission = df.groupby('medical_specialty')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
+    st.subheader("Readmission Rates by Medical Specialty")
+    specialty_readmission = filtered_df.groupby('medical_specialty')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
     specialty_readmission = specialty_readmission.sort_values(by='yes', ascending=False).head(10)
-    fig, ax = plt.subplots()
-    specialty_readmission['yes'].plot(kind='barh', color='orange', ax=ax)
-    ax.set_title("Top Specialties with High Readmission Rates")
-    ax.set_xlabel("Readmission Rate")
-    st.pyplot(fig)
-    
-    # Readmission by Diagnosis
-    st.subheader("Readmission by Primary Diagnosis")
-    diag_readmission = df.groupby('diag_1')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
-    diag_readmission = diag_readmission.sort_values(by='yes', ascending=False).head(10)
-    fig, ax = plt.subplots()
-    diag_readmission['yes'].plot(kind='bar', color='green', ax=ax)
-    ax.set_title("Top Diagnoses with High Readmission Rates")
-    ax.set_xlabel("Diagnosis")
-    ax.set_ylabel("Readmission Rate")
-    st.pyplot(fig)
+    fig_specialty = px.bar(specialty_readmission, y='yes', title="Top Specialties with High Readmission Rates",
+                           labels={'index': 'Medical Specialty', 'yes': 'Readmission Rate (%)'})
+    fig_specialty.update_layout(yaxis_tickformat=".0%")
+    st.plotly_chart(fig_specialty, use_container_width=True)
 
 # Page 3: Hospital Stay and Procedures
 elif page == "Hospital Stay and Procedures":
@@ -95,64 +70,21 @@ elif page == "Hospital Stay and Procedures":
     
     # Hospital Stay Duration by Readmission Status
     st.subheader("Hospital Stay Duration by Readmission Status")
-    fig, ax = plt.subplots()
-    sns.boxplot(x='readmitted', y='time_in_hospital', data=df, ax=ax)
-    ax.set_title("Hospital Stay Duration by Readmission Status")
-    ax.set_xlabel("Readmitted")
-    ax.set_ylabel("Hospital Stay (Days)")
-    st.pyplot(fig)
-    
-    # Number of Lab Procedures
-    st.subheader("Number of Lab Procedures")
-    fig, ax = plt.subplots()
-    sns.histplot(df['n_lab_procedures'], bins=20, kde=False, ax=ax)
-    ax.set_title("Distribution of Lab Procedures")
-    ax.set_xlabel("Number of Lab Procedures")
-    ax.set_ylabel("Count")
-    st.pyplot(fig)
-    
-    # Medication Count by Readmission Status
-    st.subheader("Medication Count by Readmission Status")
-    fig, ax = plt.subplots()
-    sns.violinplot(x='readmitted', y='n_medications', data=df, ax=ax)
-    ax.set_title("Medication Count by Readmission Status")
-    ax.set_xlabel("Readmitted")
-    ax.set_ylabel("Number of Medications")
-    st.pyplot(fig)
+    fig_stay = px.box(filtered_df, x='readmitted', y='time_in_hospital', title="Hospital Stay Duration by Readmission Status",
+                      labels={'readmitted': 'Readmitted', 'time_in_hospital': 'Hospital Stay (Days)'})
+    st.plotly_chart(fig_stay, use_container_width=True)
 
 # Page 4: Patient Health Insights
 elif page == "Patient Health Insights":
     st.title("Patient Health Insights")
     
     # Diabetes and Readmissions
-    st.subheader("Diabetes and Readmissions")
-    diabetes_readmission = df.groupby('diabetes_med')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
-    fig, ax = plt.subplots()
-    diabetes_readmission.plot(kind='bar', ax=ax)
-    ax.set_title("Readmission Rates by Diabetes Medication")
-    ax.set_xlabel("Diabetes Medication")
-    ax.set_ylabel("Proportion")
-    st.pyplot(fig)
-    
-    # Glucose Test Results
-    st.subheader("Glucose Test Results and Readmissions")
-    glucose_readmission = df.groupby('glucose_test')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
-    fig, ax = plt.subplots()
-    glucose_readmission.plot(kind='bar', stacked=True, ax=ax)
-    ax.set_title("Glucose Test Results and Readmissions")
-    ax.set_xlabel("Glucose Test Result")
-    ax.set_ylabel("Proportion")
-    st.pyplot(fig)
-    
-    # Secondary Diagnoses
-    st.subheader("Common Secondary Diagnoses")
-    secondary_diagnoses = df['diag_2'].value_counts().head(10)
-    fig, ax = plt.subplots()
-    secondary_diagnoses.plot(kind='bar', color='purple', ax=ax)
-    ax.set_title("Top Secondary Diagnoses")
-    ax.set_xlabel("Diagnosis")
-    ax.set_ylabel("Count")
-    st.pyplot(fig)
+    st.subheader("Diabetes Medication and Readmissions")
+    diabetes_readmission = filtered_df.groupby('diabetes_med')['readmitted'].value_counts(normalize=True).unstack().fillna(0)
+    fig_diabetes = px.bar(diabetes_readmission, barmode='group', title="Readmission Rates by Diabetes Medication",
+                          labels={'index': 'Diabetes Medication', 'yes': 'Readmission Rate (%)'})
+    fig_diabetes.update_layout(yaxis_tickformat=".0%")
+    st.plotly_chart(fig_diabetes, use_container_width=True)
 
 # Page 5: Recommendations
 elif page == "Recommendations":
@@ -174,9 +106,9 @@ elif page == "Recommendations":
     
     # Interactive Widget
     st.subheader("Personalized Risk Factors")
-    age_group = st.selectbox("Select Age Group", sorted(df['age'].unique()))
-    diagnosis = st.selectbox("Select Diagnosis", df['diag_1'].unique())
+    selected_age = st.selectbox("Select Age Group", sorted(filtered_df['age'].unique()))
+    selected_diagnosis = st.selectbox("Select Diagnosis", filtered_df['diag_1'].unique())
     
-    filtered_df = df[(df['age'] == age_group) & (df['diag_1'] == diagnosis)]
-    readmission_rate = filtered_df['readmitted'].value_counts(normalize=True).get('yes', 0) * 100
-    st.metric("Readmission Rate for Selected Group", f"{readmission_rate:.2f}%")
+    personalized_df = filtered_df[(filtered_df['age'] == selected_age) & (filtered_df['diag_1'] == selected_diagnosis)]
+    readmission_rate_personalized = personalized_df['readmitted'].value_counts(normalize=True).get('yes', 0) * 100
+    st.metric("Readmission Rate for Selected Group", f"{readmission_rate_personalized:.2f}%")