fixes plot

README.md

@@ -1,5 +1,5 @@
 ---
-title: Example2
+title: CausalAI
 emoji: 🐨
 colorFrom: blue
 colorTo: yellow

app.py

@@ -281,6 +281,7 @@ def calculate_incremental_metrics(data, uplift_scores, treatment, threshold):
 
 
 def build_models_and_display(selected_features):
+
     """
     Build uplift models for all discount levels and display results.
     
@@ -293,6 +294,7 @@ def build_models_and_display(selected_features):
     Returns:
         tuple: Contains model information, feature importance plot, and uplift plot
     """
+    
     global rct_results, generated_data, uplift_models, last_used_features
     if rct_results is None or generated_data is None:
         return "Please generate customer data and run RCT simulation first.", None, None
@@ -316,9 +318,8 @@ def build_models_and_display(selected_features):
     all_feature_importance = []
     uplift_models = {}  # Store models for each treatment
     
-    # Create subplots for train and test
-    fig_uplift = make_subplots(rows=2, cols=1, subplot_titles=("Train Set Performance", "Test Set Performance"),
-                               vertical_spacing=0.1, row_heights=[0.5, 0.5])
+    # Create Matplotlib figure for uplift plots
+    fig_uplift, axs = plt.subplots(2, 1, figsize=(10, 12))
     
     for treatment, color in zip(treatments, colors):
         model, train_uplift_scores, feature_importance_df, X_train = build_uplift_model(train_df, selected_features, treatment, 'Control')
@@ -341,8 +342,18 @@ def build_models_and_display(selected_features):
             thresholds = np.linspace(np.min(uplift_scores), np.max(uplift_scores), 100)
             inc_purchases, inc_profits = zip(*[calculate_incremental_metrics(dataset, uplift_scores, treatment, threshold) for threshold in thresholds])
             
-            fig_uplift.add_trace(go.Scatter(x=inc_purchases, y=inc_profits, mode='lines', name=f'{treatment} Model', line=dict(color=color, width=2)), row=i+1, col=1)
-            fig_uplift.add_trace(go.Scatter(x=[0, inc_purchases[0]], y=[0, inc_profits[0]], mode='lines', name=f'{treatment} Random', line=dict(color=color, width=2, dash='dash')), row=i+1, col=1)
+            axs[i].plot(inc_purchases, inc_profits, label=f'{treatment} Model', color=color)
+            axs[i].plot([0, inc_purchases[0]], [0, inc_profits[0]], label=f'{treatment} Random', color=color, linestyle='--')
+    
+    # Customize uplift plots
+    for i, title in enumerate(["Train Set Performance", "Test Set Performance"]):
+        axs[i].set_title(title)
+        axs[i].set_xlabel("Incremental Purchases")
+        axs[i].set_ylabel("Incremental Profit")
+        axs[i].legend()
+        axs[i].grid(True)
+    
+    plt.tight_layout()
     
     # Create feature importance plot
     fig_importance, ax = plt.subplots(figsize=(12, 8))
@@ -358,19 +369,6 @@ def build_models_and_display(selected_features):
     ax.set_ylabel('Feature')
     plt.tight_layout()
     
-    # Improve uplift plot appearance
-    fig_uplift.update_layout(
-        height=1200, width=1000,
-        title={'text': 'Incremental Profit vs Incremental Purchases (All Treatments)', 'y':0.98, 'x':0.5, 'xanchor': 'center', 'yanchor': 'top'},
-        legend=dict(orientation='v', yanchor='bottom', y=0.02, xanchor='left', x=0.02, bgcolor='rgba(255, 255, 255, 0.5)')
-    )
-
-    for i in range(1, 3):
-        fig_uplift.update_xaxes(title_text="Incremental Purchases", row=i, col=1)
-        fig_uplift.update_yaxes(title_text="Incremental Profit", row=i, col=1)
-        fig_uplift.update_xaxes(showgrid=True, gridwidth=1, gridcolor='lightgray', row=i, col=1)
-        fig_uplift.update_yaxes(showgrid=True, gridwidth=1, gridcolor='lightgray', row=i, col=1)
-    
     last_used_features = selected_features  # Store the last used features
     
     info = f"Uplift models built using {len(selected_features)} features.\n"
@@ -379,7 +377,6 @@ def build_models_and_display(selected_features):
     info += f"Displaying results for both Train and Test sets"
     
     return info, fig_importance, fig_uplift
-    
 
 def run_targeting_policy(discount_level, target_percentage, experiment_duration):
     """
@@ -485,19 +482,18 @@ def run_targeted_simulation(df, experiment_duration, discount_level):
     return pd.DataFrame(transactions)
 
 def analyze_targeting_results(assignment_df, transactions_df):
+
     """
     Analyze the results of the targeting policy experiment.
-
     This function calculates various metrics for each variant, including conversion rates,
     average revenue and profit per customer, and incremental purchases and profits.
-
     Args:
         assignment_df (pandas.DataFrame): The DataFrame containing variant assignments
         transactions_df (pandas.DataFrame): The DataFrame containing transaction data
-
     Returns:
         tuple: Contains a DataFrame with variant metrics and a plotly Figure object
     """
+    
     # Calculate metrics for assigned customers
     assigned_customers = assignment_df.groupby('experiment_variant')['customer_id'].nunique().reset_index()
     assigned_customers.columns = ['variant', 'assigned_customers']
@@ -524,30 +520,27 @@ def analyze_targeting_results(assignment_df, transactions_df):
     variant_metrics['incremental_purchases'] = variant_metrics['purchasing_customers'] - control_metrics['purchasing_customers']
     variant_metrics['incremental_profit'] = variant_metrics['profit'] - control_metrics['profit']
     
-    # Create visualization
-    fig = go.Figure()
+    # Create visualization using Matplotlib
+    fig, ax = plt.subplots(figsize=(10, 6))
     
     colors = {'Control': 'blue', '5% discount': 'green', '10% discount': 'orange', 
               '15% discount': 'red', 'Targeted': 'purple'}
     
     for variant in variant_metrics['variant']:
         variant_data = variant_metrics[variant_metrics['variant'] == variant]
-        fig.add_trace(go.Scatter(
-            x=[variant_data['incremental_purchases'].values[0]],
-            y=[variant_data['incremental_profit'].values[0]],
-            mode='markers+text',
-            name=variant,
-            text=[variant],
-            textposition="top center",
-            marker=dict(size=12, color=colors.get(variant, 'gray'))
-        ))
-    
-    fig.update_layout(
-        title='Incremental Profit vs Incremental Purchases by Variant',
-        xaxis_title='Incremental Purchases',
-        yaxis_title='Incremental Profit',
-        showlegend=True
-    )
+        ax.scatter(variant_data['incremental_purchases'], variant_data['incremental_profit'],
+                   label=variant, color=colors.get(variant, 'gray'))
+        ax.annotate(variant, (variant_data['incremental_purchases'].values[0],
+                              variant_data['incremental_profit'].values[0]),
+                    xytext=(5, 5), textcoords='offset points')
+    
+    ax.set_title('Incremental Profit vs Incremental Purchases by Variant')
+    ax.set_xlabel('Incremental Purchases')
+    ax.set_ylabel('Incremental Profit')
+    ax.legend(loc='lower left')    
+    ax.grid(True)
+    
+    plt.tight_layout()
     
     return variant_metrics, fig
 
@@ -656,7 +649,6 @@ with gr.Blocks() as demo:
     with gr.Tab("Build Uplift Model"):
         gr.Markdown("## Build Uplift Models for All Discount Levels")
         
-        # Feature selection
         feature_checklist = gr.CheckboxGroup(
             choices=['age', 'gender', 'region', 'preferred_language', 'newsletter_subscription', 
                      'preferred_payment_method', 'loyalty_level', 'main_browsing_device',