Update app.py

app.py

@@ -14,58 +14,58 @@ warnings.filterwarnings('ignore')
 plt.style.use('default')
 sns.set_palette("husl")
 
-def generate_model_points(mp_count=10000, age_min=20, age_max=59, 
-                         sum_assured_min=10000, sum_assured_max=1000000,
-                         policy_terms=[10, 15, 20], include_sex=True, 
-                         policy_count_fixed=True, seed=12345):
+def generate_model_points(mp_count=10000, age_min=20, age_max=59,
+                          sum_assured_min=10000, sum_assured_max=1000000,
+                          policy_terms=[10, 15, 20], include_sex=True,
+                          policy_count_fixed=True, seed=12345):
     """
     Generate seriatim model points for actuarial analysis
     """
     # Set random seed for reproducibility
     rng = default_rng(seed)
-    
+
     # Issue Age (Integer): age_min - age_max year old
     age_at_entry = rng.integers(low=age_min, high=age_max+1, size=mp_count)
-    
+
     # Sex (Char) - optional
     if include_sex:
         Sex = ["M", "F"]
         sex = np.fromiter(map(lambda i: Sex[i], rng.integers(low=0, high=len(Sex), size=mp_count)), np.dtype('<U1'))
     else:
         sex = np.full(mp_count, "U")  # Unknown/Unspecified
-    
+
     # Policy Term (Integer): from policy_terms list
     policy_term_options = np.array(policy_terms)
     policy_term = rng.choice(policy_term_options, size=mp_count)
-    
+
     # Sum Assured (Float): sum_assured_min - sum_assured_max
     sum_assured = np.round((sum_assured_max - sum_assured_min) * rng.random(size=mp_count) + sum_assured_min, -3)
-    
+
     # Duration in month (Int): 1 <= Duration(mth) < Policy Term in month
     duration_mth = np.floor((policy_term * 12 - 1) * rng.random(size=mp_count)).astype(int) + 1
-    
+
     # Policy Count (Integer): 1 (fixed) or variable
     if policy_count_fixed:
         policy_count = np.ones(mp_count, dtype=int)
     else:
         policy_count = rng.integers(low=1, high=101, size=mp_count)
-    
+
     # Create DataFrame
     attrs = ["age_at_entry", "sex", "policy_term", "policy_count", "sum_assured", "duration_mth"]
     data = [age_at_entry, sex, policy_term, policy_count, sum_assured, duration_mth]
-    
+
     model_point_table = pd.DataFrame(dict(zip(attrs, data)), index=range(1, mp_count+1))
     model_point_table.index.name = "policy_id"
-    
+
     return model_point_table
 
 def create_summary_stats(df):
     """Generate summary statistics for the model points"""
     summary_stats = []
-    
+
     # Numeric columns
     numeric_cols = ['age_at_entry', 'policy_term', 'sum_assured', 'duration_mth', 'policy_count']
-    
+
     for col in numeric_cols:
         if col in df.columns:
             stats = {
@@ -78,7 +78,7 @@ def create_summary_stats(df):
                 'Median': f"{df[col].median():.2f}"
             }
             summary_stats.append(stats)
-    
+
     # Categorical columns
     if 'sex' in df.columns:
         sex_counts = df['sex'].value_counts()
@@ -93,49 +93,49 @@ def create_summary_stats(df):
                 'Median': '-'
             }
             summary_stats.append(stats)
-    
+
     return pd.DataFrame(summary_stats)
 
 def create_distribution_plots(df):
     """Create distribution plots for key variables"""
     fig = make_subplots(
         rows=2, cols=3,
-        subplot_titles=('Age at Entry', 'Policy Term', 'Sum Assured', 
-                       'Duration (Months)', 'Policy Count', 'Sex Distribution'),
+        subplot_titles=('Age at Entry', 'Policy Term', 'Sum Assured',
+                        'Duration (Months)', 'Policy Count', 'Sex Distribution'),
         specs=[[{'type': 'histogram'}, {'type': 'histogram'}, {'type': 'histogram'}],
                [{'type': 'histogram'}, {'type': 'histogram'}, {'type': 'bar'}]]
     )
-    
+
     # Age at Entry
     fig.add_trace(
         go.Histogram(x=df['age_at_entry'], name='Age at Entry', nbinsx=20),
         row=1, col=1
     )
-    
+
     # Policy Term
     fig.add_trace(
         go.Histogram(x=df['policy_term'], name='Policy Term', nbinsx=10),
         row=1, col=2
     )
-    
+
     # Sum Assured
     fig.add_trace(
         go.Histogram(x=df['sum_assured'], name='Sum Assured', nbinsx=30),
         row=1, col=3
     )
-    
+
     # Duration in Months
     fig.add_trace(
         go.Histogram(x=df['duration_mth'], name='Duration (Months)', nbinsx=25),
         row=2, col=1
     )
-    
+
     # Policy Count
     fig.add_trace(
         go.Histogram(x=df['policy_count'], name='Policy Count', nbinsx=20),
         row=2, col=2
     )
-    
+
     # Sex Distribution
     if 'sex' in df.columns:
         sex_counts = df['sex'].value_counts()
@@ -143,23 +143,23 @@ def create_distribution_plots(df):
             go.Bar(x=sex_counts.index, y=sex_counts.values, name='Sex Distribution'),
             row=2, col=3
         )
-    
+
     fig.update_layout(
         height=800,
         title_text="Model Points Distribution Analysis",
         showlegend=False
     )
-    
+
     return fig
 
 def create_correlation_heatmap(df):
     """Create correlation heatmap for numeric variables"""
     numeric_cols = ['age_at_entry', 'policy_term', 'sum_assured', 'duration_mth', 'policy_count']
     available_cols = [col for col in numeric_cols if col in df.columns]
-    
+
     if len(available_cols) > 1:
         corr_matrix = df[available_cols].corr()
-        
+
         fig = go.Figure(data=go.Heatmap(
             z=corr_matrix.values,
             x=corr_matrix.columns,
@@ -171,48 +171,48 @@ def create_correlation_heatmap(df):
             textfont={"size": 12},
             hoverongaps=False
         ))
-        
+
         fig.update_layout(
             title='Correlation Matrix of Model Point Variables',
             width=600,
             height=500
         )
-        
+
         return fig
     else:
         return go.Figure().add_annotation(text="Not enough numeric variables for correlation analysis")
 
 def create_age_term_analysis(df):
     """Create age vs policy term analysis"""
-    fig = px.box(df, x='policy_term', y='age_at_entry', 
+    fig = px.box(df, x='policy_term', y='age_at_entry',
                  title='Age at Entry Distribution by Policy Term',
                  labels={'policy_term': 'Policy Term (Years)', 'age_at_entry': 'Age at Entry'})
-    
+
     fig.update_layout(height=400)
     return fig
 
 def create_portfolio_metrics(df):
     """Calculate portfolio-level metrics"""
     metrics = {}
-    
+
     # Total exposure
     metrics['Total Policies'] = f"{len(df):,}"
     metrics['Total Sum Assured'] = f"${df['sum_assured'].sum():,.0f}"
     metrics['Average Sum Assured'] = f"${df['sum_assured'].mean():,.0f}"
-    
+
     # Age metrics
     metrics['Average Age at Entry'] = f"{df['age_at_entry'].mean():.1f} years"
     metrics['Age Range'] = f"{df['age_at_entry'].min()}-{df['age_at_entry'].max()} years"
-    
+
     # Policy term metrics
     metrics['Average Policy Term'] = f"{df['policy_term'].mean():.1f} years"
     term_dist = df['policy_term'].value_counts().sort_index()
     metrics['Policy Term Distribution'] = ', '.join([f"{term}Y: {count:,}" for term, count in term_dist.items()])
-    
+
     # Duration metrics
     metrics['Average Duration'] = f"{df['duration_mth'].mean():.1f} months"
     metrics['Duration Range'] = f"{df['duration_mth'].min()}-{df['duration_mth'].max()} months"
-    
+
     # Convert to DataFrame for display
     metrics_df = pd.DataFrame(list(metrics.items()), columns=['Metric', 'Value'])
     return metrics_df
@@ -225,26 +225,26 @@ def export_to_csv(df):
 with gr.Blocks(title="Actuarial Model Points Generator") as demo:
     gr.Markdown("""
     # 📊 Actuarial Model Points Generator
-    
+
     Generate synthetic seriatim policy data for actuarial modeling, cluster analysis, and portfolio testing.
     Perfect for creating realistic test datasets for insurance product development and risk analysis.
     """)
-    
+
     with gr.Row():
         with gr.Column(scale=1):
             gr.Markdown("### Generation Parameters")
-            
+
             # Basic parameters
             mp_count = gr.Slider(
                 minimum=100, maximum=50000, value=10000, step=100,
                 label="Number of Model Points"
             )
-            
+
             seed = gr.Number(
                 value=12345, precision=0,
                 label="Random Seed (for reproducibility)"
             )
-            
+
             # Age parameters
             gr.Markdown("#### Age Parameters")
             age_min = gr.Slider(
@@ -255,7 +255,7 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
                 minimum=45, maximum=80, value=59, step=1,
                 label="Maximum Age at Entry"
             )
-            
+
             # Sum Assured parameters
             gr.Markdown("#### Sum Assured Parameters")
             sum_assured_min = gr.Number(
@@ -266,7 +266,7 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
                 value=1000000,
                 label="Maximum Sum Assured ($)"
             )
-            
+
             # Policy options
             gr.Markdown("#### Policy Options")
             policy_terms = gr.CheckboxGroup(
@@ -274,63 +274,63 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
                 value=[10, 15, 20],
                 label="Available Policy Terms (Years)"
             )
-            
+
             include_sex = gr.Checkbox(
                 value=True,
                 label="Include Sex (M/F) in model points"
             )
-            
+
             policy_count_fixed = gr.Checkbox(
                 value=True,
                 label="Fixed Policy Count = 1 (uncheck for variable 1-100)"
             )
-            
+
             generate_btn = gr.Button("🎲 Generate Model Points", variant="primary")
-            
+
         with gr.Column(scale=2):
             with gr.Tabs():
                 with gr.TabItem("📋 Data Table"):
                     model_points_table = gr.Dataframe(
                         label="Generated Model Points",
-                        height=400,
+                        # height=400, <-- This line was removed/commented out
                         interactive=False
                     )
-                    
+
                     download_btn = gr.DownloadButton(
                         label="📥 Download CSV",
                         variant="secondary"
                     )
-                
+
                 with gr.TabItem("📊 Distributions"):
                     distribution_plot = gr.Plot(label="Variable Distributions")
-                
+
                 with gr.TabItem("📈 Analytics"):
                     with gr.Row():
                         correlation_plot = gr.Plot(label="Correlation Analysis")
                         age_term_plot = gr.Plot(label="Age vs Policy Term")
-                
+
                 with gr.TabItem("📋 Statistics"):
                     with gr.Row():
                         with gr.Column():
                             portfolio_metrics = gr.Dataframe(label="Portfolio Metrics")
                         with gr.Column():
                             summary_stats = gr.Dataframe(label="Summary Statistics")
-    
+
     gr.Markdown("""
     ### 🎯 Use Cases
-    
+
     **Actuarial Applications:**
     - **Cluster Analysis**: Group similar policies for pricing and reserving
     - **Portfolio Testing**: Stress test models with synthetic data
     - **Product Development**: Analyze policy mix and profitability
     - **Risk Management**: Understand exposure concentrations
-    
+
     **Key Features:**
     - **Realistic Distributions**: Age, term, and sum assured follow typical insurance patterns
     - **Existing Policies**: Duration > 0 represents in-force business
     - **Flexible Parameters**: Customize age ranges, policy terms, and sum assured limits
     - **Reproducible**: Fixed seed ensures consistent results
-    
+
     **Generated Variables:**
     - `policy_id`: Unique identifier for each policy
     - `age_at_entry`: Issue age (customizable range)
@@ -340,14 +340,14 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
     - `sum_assured`: Coverage amount (customizable range)
     - `duration_mth`: Months since issue (1 to term-1)
     """)
-    
+
     # Event handlers
-    def generate_and_analyze(mp_count, age_min, age_max, sum_assured_min, sum_assured_max, 
-                           policy_terms, include_sex, policy_count_fixed, seed):
+    def generate_and_analyze(mp_count, age_min, age_max, sum_assured_min, sum_assured_max,
+                             policy_terms, include_sex, policy_count_fixed, seed):
         """Generate model points and all analyses"""
         if not policy_terms:
             policy_terms = [10, 15, 20]  # Default if none selected
-            
+
         # Generate model points
         df = generate_model_points(
             mp_count=int(mp_count),
@@ -360,7 +360,7 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
             policy_count_fixed=policy_count_fixed,
             seed=int(seed)
         )
-        
+
         # Generate analyses
         dist_plot = create_distribution_plots(df)
         corr_plot = create_correlation_heatmap(df)
@@ -368,26 +368,26 @@ with gr.Blocks(title="Actuarial Model Points Generator") as demo:
         portfolio_metrics_df = create_portfolio_metrics(df)
         summary_stats_df = create_summary_stats(df)
         csv_data = export_to_csv(df)
-        
-        return (df, dist_plot, corr_plot, age_term_plot, 
+
+        return (df, dist_plot, corr_plot, age_term_plot,
                 portfolio_metrics_df, summary_stats_df, csv_data)
-    
+
     # Connect the generate button
     generate_btn.click(
         fn=generate_and_analyze,
         inputs=[mp_count, age_min, age_max, sum_assured_min, sum_assured_max,
                 policy_terms, include_sex, policy_count_fixed, seed],
-        outputs=[model_points_table, distribution_plot, correlation_plot, 
-                age_term_plot, portfolio_metrics, summary_stats, download_btn]
+        outputs=[model_points_table, distribution_plot, correlation_plot,
+                 age_term_plot, portfolio_metrics, summary_stats, download_btn]
     )
-    
+
     # Initialize with default values
     demo.load(
         fn=generate_and_analyze,
         inputs=[mp_count, age_min, age_max, sum_assured_min, sum_assured_max,
                 policy_terms, include_sex, policy_count_fixed, seed],
         outputs=[model_points_table, distribution_plot, correlation_plot,
-                age_term_plot, portfolio_metrics, summary_stats, download_btn]
+                 age_term_plot, portfolio_metrics, summary_stats, download_btn]
     )
 
 if __name__ == "__main__":