Update visualization/segmentation_ranking.py

visualization/segmentation_ranking.py

@@ -0,0 +1,391 @@
+# visualizations/segment_ranking.py
+
+import plotly.graph_objects as go
+import plotly.express as px
+import pandas as pd
+from metrics.metric_registry import METRIC_FUNCTIONS
+from analytics.performance_analysis import generate_metric_view
+
+
+def calculate_segment_risk_score(
+    df,
+    metric_name,
+    category
+):
+    """
+    Calculate risk scores for each segment in a category.
+    
+    Args:
+        df: Master dataframe
+        metric_name: Metric name for risk calculation
+        category: Segmentation category
+    
+    Returns:
+        DataFrame with segment and risk score
+    """
+    
+    result = generate_metric_view(
+        df=df,
+        metric_name=metric_name,
+        group_col=category
+    )
+    
+    rate_col = [
+        col for col in result.columns
+        if "rate" in col.lower()
+    ][0]
+    
+    # Calculate average rate per segment
+    segment_risk = (
+        result.groupby(category)
+        .agg({
+            rate_col: "mean",
+            "total_accounts": "sum",
+            "total_balance": "sum"
+        })
+        .reset_index()
+    )
+    
+    segment_risk = segment_risk.rename(
+        columns={
+            category: "Segment",
+            rate_col: "Risk_Score"
+        }
+    )
+    
+    return segment_risk
+
+
+def generate_segment_risk_heatmap(
+    df,
+    metrics=None,
+    categories=None
+):
+    """
+    Generate heatmap showing risk scores across segments and metrics.
+    
+    Args:
+        df: Master dataframe
+        metrics: List of metrics to evaluate
+        categories: List of categories to analyze
+    
+    Returns:
+        Plotly figure with heatmap
+    """
+    
+    if metrics is None:
+        metrics = ["30+@3", "30+@6", "60+@6", "Yr1 NCL"]
+    
+    if categories is None:
+        categories = [
+            "fico_band",
+            "sourcing_channel",
+            "city_tier",
+            "occupation_type"
+        ]
+    
+    # Prepare data for heatmap
+    heatmap_data = {}
+    all_segments = {}
+    
+    for metric in metrics:
+        
+        metric_scores = {}
+        
+        for category in categories:
+            
+            try:
+                segment_risk = calculate_segment_risk_score(
+                    df=df,
+                    metric_name=metric,
+                    category=category
+                )
+                
+                for _, row in segment_risk.iterrows():
+                    segment_key = f"{category}_{row['Segment']}"
+                    metric_scores[segment_key] = row["Risk_Score"]
+                    all_segments[segment_key] = f"{category.replace('_', ' ').title()}: {row['Segment']}"
+            
+            except Exception as e:
+                print(f"Error processing {metric} x {category}: {e}")
+        
+        heatmap_data[metric] = metric_scores
+    
+    # Create DataFrame for heatmap
+    heatmap_df = pd.DataFrame(heatmap_data)
+    heatmap_df = heatmap_df.fillna(0)
+    
+    # Sort by average risk
+    heatmap_df["avg_risk"] = heatmap_df.mean(axis=1)
+    heatmap_df = heatmap_df.sort_values("avg_risk", ascending=False)
+    heatmap_df = heatmap_df.drop("avg_risk", axis=1)
+    
+    # Create heatmap
+    fig = go.Figure(
+        data=go.Heatmap(
+            z=heatmap_df.values,
+            x=heatmap_df.columns,
+            y=[all_segments.get(idx, idx) for idx in heatmap_df.index],
+            colorscale="RdYlGn_r",
+            hovertemplate=(
+                "<b>Segment: %{y}</b><br>" +
+                "<b>Metric: %{x}</b><br>" +
+                "Risk Score: %{z:.2f}%<br>" +
+                "<extra></extra>"
+            ),
+            text=[[f"{val:.2f}%" for val in row] for row in heatmap_df.values],
+            texttemplate="%{text}",
+            textfont={"size": 10},
+            colorbar=dict(
+                title="Risk Score<br>(%)"
+            )
+        )
+    )
+    
+    fig.update_layout(
+        title="Segment Risk Heatmap Across Delinquency Metrics",
+        xaxis_title="Delinquency Metrics",
+        yaxis_title="Segments",
+        height=max(400, len(heatmap_df) * 25),
+        template="plotly_white",
+        hovermode="closest"
+    )
+    
+    return fig
+
+
+def generate_segment_risk_ranking(
+    df,
+    metric_name,
+    category,
+    top_n=10
+):
+    """
+    Generate bar chart ranking segments by risk within a category.
+    
+    Args:
+        df: Master dataframe
+        metric_name: Metric name for risk calculation
+        category: Segmentation category
+        top_n: Number of top risk segments to display
+    
+    Returns:
+        Plotly bar chart figure
+    """
+    
+    segment_risk = calculate_segment_risk_score(
+        df=df,
+        metric_name=metric_name,
+        category=category
+    )
+    
+    # Sort by risk score descending
+    segment_risk = segment_risk.sort_values(
+        "Risk_Score",
+        ascending=True
+    ).tail(top_n)
+    
+    # Color code by risk level
+    colors = ["#d62728" if score > 10 else "#ff7f0e" if score > 5 else "#2ca02c"
+              for score in segment_risk["Risk_Score"]]
+    
+    fig = go.Figure(
+        data=go.Bar(
+            y=segment_risk["Segment"],
+            x=segment_risk["Risk_Score"],
+            orientation="h",
+            marker=dict(
+                color=colors,
+                line=dict(color="white", width=1)
+            ),
+            text=segment_risk["Risk_Score"],
+            texttemplate="%{text:.2f}%",
+            textposition="outside",
+            hovertemplate=(
+                "<b>Segment: %{y}</b><br>" +
+                "Risk Score: %{x:.2f}%<br>" +
+                "Accounts: %{customdata[0]}<br>" +
+                "Balance: %{customdata[1]:,.0f}<br>" +
+                "<extra></extra>"
+            ),
+            customdata=segment_risk[["total_accounts", "total_balance"]].values
+        )
+    )
+    
+    fig.update_layout(
+        title=f"Top {top_n} High-Risk Segments: {metric_name} by {category.replace('_', ' ').title()}",
+        xaxis_title="Risk Score (%)",
+        yaxis_title=category.replace('_', ' ').title(),
+        height=400 + (top_n * 15),
+        template="plotly_white",
+        hovermode="closest"
+    )
+    
+    fig.update_xaxes(
+        showgrid=True,
+        gridwidth=1,
+        gridcolor="lightgray"
+    )
+    
+    return fig
+
+
+def generate_multi_category_risk_comparison(
+    df,
+    metric_name
+):
+    """
+    Compare risk across all categories for a single metric.
+    
+    Args:
+        df: Master dataframe
+        metric_name: Metric name for risk calculation
+    
+    Returns:
+        Plotly figure with subplots (one per category)
+    """
+    
+    categories = [
+        "fico_band",
+        "sourcing_channel",
+        "city_tier",
+        "occupation_type"
+    ]
+    
+    # Create subplots
+    from plotly.subplots import make_subplots
+    
+    fig = make_subplots(
+        rows=2,
+        cols=2,
+        subplot_titles=[cat.replace('_', ' ').title() for cat in categories],
+        specs=[
+            [{"type": "bar"}, {"type": "bar"}],
+            [{"type": "bar"}, {"type": "bar"}]
+        ]
+    )
+    
+    positions = [
+        (1, 1),
+        (1, 2),
+        (2, 1),
+        (2, 2)
+    ]
+    
+    max_segments = 0
+    
+    for category, (row, col) in zip(categories, positions):
+        
+        try:
+            segment_risk = calculate_segment_risk_score(
+                df=df,
+                metric_name=metric_name,
+                category=category
+            )
+            
+            # Sort and take top 5
+            segment_risk = segment_risk.sort_values(
+                "Risk_Score",
+                ascending=True
+            ).tail(5)
+            
+            max_segments = max(max_segments, len(segment_risk))
+            
+            fig.add_trace(
+                go.Bar(
+                    y=segment_risk["Segment"],
+                    x=segment_risk["Risk_Score"],
+                    orientation="h",
+                    name=category,
+                    showlegend=False,
+                    marker=dict(
+                        color=segment_risk["Risk_Score"],
+                        colorscale="Reds",
+                        showscale=False
+                    ),
+                    text=segment_risk["Risk_Score"],
+                    texttemplate="%{text:.2f}%",
+                    textposition="outside",
+                    hovertemplate=(
+                        "<b>%{y}</b><br>" +
+                        "Risk Score: %{x:.2f}%<br>" +
+                        "<extra></extra>"
+                    )
+                ),
+                row=row,
+                col=col
+            )
+            
+            fig.update_xaxes(
+                title_text="Risk Score (%)",
+                row=row,
+                col=col
+            )
+        
+        except Exception as e:
+            print(f"Error processing category {category}: {e}")
+    
+    fig.update_layout(
+        title_text=f"High-Risk Segments Across Categories: {metric_name}",
+        height=800,
+        template="plotly_white",
+        hovermode="closest"
+    )
+    
+    return fig
+
+
+def calculate_portfolio_risk_summary(
+    df,
+    metrics=None
+):
+    """
+    Calculate overall portfolio risk summary across metrics and categories.
+    
+    Args:
+        df: Master dataframe
+        metrics: List of metrics to evaluate
+    
+    Returns:
+        DataFrame with portfolio risk summary
+    """
+    
+    if metrics is None:
+        metrics = ["30+@3", "30+@6", "60+@6", "Yr1 NCL"]
+    
+    summary_data = []
+    
+    categories = [
+        "fico_band",
+        "sourcing_channel",
+        "city_tier",
+        "occupation_type"
+    ]
+    
+    for metric in metrics:
+        for category in categories:
+            try:
+                segment_risk = calculate_segment_risk_score(
+                    df=df,
+                    metric_name=metric,
+                    category=category
+                )
+                
+                avg_risk = segment_risk["Risk_Score"].mean()
+                max_risk = segment_risk["Risk_Score"].max()
+                high_risk_count = len(segment_risk[segment_risk["Risk_Score"] > 10])
+                
+                summary_data.append({
+                    "Metric": metric,
+                    "Category": category.replace('_', ' ').title(),
+                    "Avg_Risk": avg_risk,
+                    "Max_Risk": max_risk,
+                    "High_Risk_Segments": high_risk_count
+                })
+            
+            except Exception as e:
+                print(f"Error calculating summary for {metric} x {category}: {e}")
+    
+    summary_df = pd.DataFrame(summary_data)
+    
+    return summary_df