Upload 2 files

dashboard.py

@@ -0,0 +1,253 @@
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+
+# Load data and pre-process
+df = pd.read_csv("HR-Employee-Attrition.csv")
+df['Attrition'] = df['Attrition'].map({'Yes': 1, 'No': 0})
+df['Performance_Risk'] = (df['PerformanceRating'] < 3).astype(int)
+df['Retention_Risk'] = ((df['JobInvolvement'] < 2) & (df['JobSatisfaction'] < 2)).astype(int)
+
+# Create Retention Score using selected factors
+scaler = MinMaxScaler()
+retention_factors = df[['JobSatisfaction', 'EnvironmentSatisfaction', 'WorkLifeBalance', 'YearsAtCompany']]
+df['Retention_Score'] = scaler.fit_transform(retention_factors).mean(axis=1)
+
+# Configure the Streamlit page
+st.set_page_config(layout="wide")
+st.title("Employee Performance & Retention Analytics Dashboard")
+
+# Sidebar Filters
+st.sidebar.header("Filters")
+selected_dept = st.sidebar.selectbox("Department", df['Department'].unique())
+# Filter job roles by the selected department
+filtered_jobs = df[df['Department'] == selected_dept]['JobRole'].unique()
+selected_job = st.sidebar.selectbox("Job Role", filtered_jobs)
+attrition_filter = st.sidebar.radio("Attrition Status", ['All', 'Left', 'Current'])
+
+# Filter DataFrame based on sidebar filters
+filtered_df = df[(df['Department'] == selected_dept) & (df['JobRole'] == selected_job)]
+if attrition_filter == 'Left':
+    filtered_df = filtered_df[filtered_df['Attrition'] == 1]
+elif attrition_filter == 'Current':
+    filtered_df = filtered_df[filtered_df['Attrition'] == 0]
+
+# Display Key Metrics
+col1, col2, col3, col4 = st.columns(4)
+with col1:
+    st.metric("Attrition Rate", f"{filtered_df['Attrition'].mean()*100:.1f}%")
+with col2:
+    st.metric("Avg Performance Rating", f"{filtered_df['PerformanceRating'].mean():.1f}")
+with col3:
+    st.metric("High Retention Risk", f"{filtered_df['Retention_Risk'].mean()*100:.1f}%")
+with col4:
+    st.metric("Avg Tenure (Years)", f"{filtered_df['YearsAtCompany'].mean():.1f}")
+
+# Machine Learning Model for Attrition Prediction
+features = ['Age', 'MonthlyIncome', 'JobSatisfaction', 'EnvironmentSatisfaction', 'WorkLifeBalance', 'YearsAtCompany']
+X = df[features]
+y = df['Attrition']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+model = RandomForestClassifier(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+predictions = model.predict(X_test)
+accuracy = accuracy_score(y_test, predictions)
+st.sidebar.write(f"Model Accuracy: {accuracy*100:.2f}%")
+
+# Predict attrition for the filtered data
+if not filtered_df.empty:
+    filtered_df['Predicted Attrition'] = model.predict(filtered_df[features])
+    attrition_probability = filtered_df['Predicted Attrition'].mean() * 100
+else:
+    attrition_probability = 0
+
+# Create Tabs for Visualizations and Explanations
+tab1, tab2, tab3 = st.tabs(["Performance Analysis", "Retention Analysis", "Employee Evaluation"])
+
+# -------------------------------
+# Tab 1: Performance Analysis
+# -------------------------------
+with tab1:
+    st.header("Performance Analysis")
+    col_left, col_right = st.columns(2)
+    
+    with col_left:
+        st.subheader("Performance Rating vs Monthly Income")
+        fig1 = px.box(
+            filtered_df,
+            x='PerformanceRating',
+            y='MonthlyIncome',
+            color='Attrition',
+            title="Performance vs Income"
+        )
+        st.plotly_chart(fig1, use_container_width=True)
+        st.markdown(
+            """
+            **Explanation:**  
+            - **X-axis:** Performance Rating  
+            - **Y-axis:** Monthly Income  
+            - **Color:** Attrition status (Left/Stayed)  
+            This box plot shows the distribution of salaries across different performance ratings. It can highlight if high-performing employees are under-compensated, potentially driving attrition.
+            """
+        )
+    
+    with col_right:
+        st.subheader("Tenure vs Age Attrition Risk")
+        fig2 = px.density_heatmap(
+            filtered_df,
+            x='YearsAtCompany',
+            y='Age',
+            z='Attrition',
+            histfunc="avg",
+            title="Tenure vs Age Attrition Risk"
+        )
+        st.plotly_chart(fig2, use_container_width=True)
+        st.markdown(
+            """
+            **Explanation:**  
+            - **X-axis:** Years at Company  
+            - **Y-axis:** Age  
+            - **Color Intensity:** Attrition likelihood  
+            This heatmap correlates employees' age and tenure with their attrition risk. Darker areas suggest higher likelihoods of attrition, identifying groups that may need targeted retention efforts.
+            """
+        )
+
+# -------------------------------
+# Tab 2: Retention Analysis
+# -------------------------------
+with tab2:
+    st.header("Retention Analysis")
+    col_left, col_right = st.columns(2)
+    
+    with col_left:
+        st.subheader("Job Satisfaction vs Work-Life Balance")
+        fig3 = px.scatter(
+            filtered_df,
+            x='JobSatisfaction',
+            y='WorkLifeBalance',
+            color='Attrition',
+            size='YearsAtCompany',
+            title="Satisfaction vs Retention"
+        )
+        st.plotly_chart(fig3, use_container_width=True)
+        st.markdown(
+            """
+            **Explanation:**  
+            - **X-axis:** Job Satisfaction  
+            - **Y-axis:** Work-Life Balance  
+            - **Bubble Size:** Years at Company  
+            - **Color:** Attrition status  
+            This scatter plot helps visualize how job satisfaction and work-life balance correlate with attrition. Clusters in lower satisfaction and balance areas can indicate higher attrition risks.
+            """
+        )
+    
+    with col_right:
+        st.subheader("Promotion History Impact")
+        fig4 = go.Figure()
+        fig4.add_trace(
+            go.Histogram(
+                x=filtered_df[filtered_df['Attrition'] == 1]['YearsSinceLastPromotion'],
+                name='Left'
+            )
+        )
+        fig4.add_trace(
+            go.Histogram(
+                x=filtered_df[filtered_df['Attrition'] == 0]['YearsSinceLastPromotion'],
+                name='Stayed'
+            )
+        )
+        fig4.update_layout(title="Promotion History Impact", barmode='overlay')
+        st.plotly_chart(fig4, use_container_width=True)
+        st.markdown(
+            """
+            **Explanation:**  
+            - **X-axis:** Years Since Last Promotion  
+            - **Bars:** Comparison between employees who left and those who stayed  
+            This histogram examines whether long gaps since the last promotion correlate with higher attrition, suggesting that career stagnation might drive employees to leave.
+            """
+        )
+
+# -------------------------------
+# Tab 3: Employee Evaluation
+# -------------------------------
+with tab3:
+    st.header("Employee Evaluation")
+    if not filtered_df.empty:
+        selected_employee = st.selectbox("Select Employee", filtered_df['EmployeeNumber'])
+        emp_data = filtered_df[filtered_df['EmployeeNumber'] == selected_employee].iloc[0]
+        
+        col_left, col_right = st.columns(2)
+        
+        with col_left:
+            st.subheader("Employee Metrics")
+            metrics = {
+                'Performance Rating': emp_data['PerformanceRating'],
+                'Job Satisfaction': emp_data['JobSatisfaction'],
+                'Work-Life Balance': emp_data['WorkLifeBalance'],
+                'Retention Score': emp_data['Retention_Score']
+            }
+            fig5 = go.Figure(go.Bar(
+                x=list(metrics.values()),
+                y=list(metrics.keys()),
+                orientation='h'
+            ))
+            fig5.update_layout(title="Employee Profile")
+            st.plotly_chart(fig5, use_container_width=True)
+            st.markdown(
+                """
+                **Explanation:**  
+                This bar chart visualizes the key metrics for the selected employee, highlighting performance, satisfaction, work-life balance, and overall retention score.
+                """
+            )
+        
+        with col_right:
+            st.subheader("Retention Recommendation")
+            risk_factors = []
+            if emp_data['PerformanceRating'] < 3:
+                risk_factors.append("Low Performance")
+            if emp_data['YearsSinceLastPromotion'] > 3:
+                risk_factors.append("Stagnant Position")
+            if emp_data['WorkLifeBalance'] < 2:
+                risk_factors.append("Poor Work-Life Balance")
+            
+            retention_prob = emp_data['Retention_Score'] * 100
+            st.metric("Retention Probability", f"{retention_prob:.1f}%")
+            
+            if retention_prob > 70:
+                st.success("High Retention Potential - Recommend Retention Programs")
+            elif retention_prob > 40:
+                st.warning("Moderate Retention Risk - Monitor Closely")
+            else:
+                st.error("High Attrition Risk - Recommend Intervention")
+            
+            if risk_factors:
+                st.write("**Key Risk Factors:**")
+                for factor in risk_factors:
+                    st.write(f"- {factor}")
+                    
+            st.markdown(
+                """
+                **Explanation:**  
+                This section provides tailored retention recommendations based on the employee's metrics and key risk factors. The displayed retention probability guides whether further intervention is needed.
+                """
+            )
+    else:
+        st.write("No employee data available for the selected filters.")
+
+# -------------------------------
+# AI-Powered Insights Section
+# -------------------------------
+st.header("AI-Powered Insights")
+if st.button("Generate Department Insights"):
+    insights = f"""
+    **Department Insights for {selected_dept} - {selected_job}:**
+    - Overall Attrition Rate: {filtered_df['Attrition'].mean()*100:.1f}% compared to the company average: {df['Attrition'].mean()*100:.1f}%.
+    - Employees with lower job satisfaction and poor work-life balance tend to have higher attrition risk.
+    - Predicted attrition probability based on the ML model: {attrition_probability:.1f}%.
+    """
+    st.write(insights)