charts update

app.py

@@ -5,6 +5,9 @@ from models_utils.ml_models import ModelTraining
 from eval_utils.evaluation import ModelEvaluator
 
 import matplotlib.pyplot as plt
+import plotly.express as px
+import plotly.graph_objects as go
+
 import numpy as np
 import pandas as pd
 import streamlit as st
@@ -104,9 +107,12 @@ if tabs == "Exploratory analysis":
         st.write('We can also visualize the tradeoff between conversions and platform benefit by plotting the mean benefit per user on the y-axis and the mean conversion rate on the x-axis, for each treatment group.')
         mean_benefit_vs_conversion = eda.compute_mean_benefit_vs_conversion()
 
-        fig, ax = plt.subplots()
-        mean_benefit_vs_conversion.plot.scatter(x='conversion', y='benefit', c='DarkBlue', s=50, ax=ax)
-        st.pyplot(fig)
+        # fig, ax = plt.subplots()
+        # mean_benefit_vs_conversion.plot.scatter(x='conversion', y='benefit', c='DarkBlue', s=50, ax=ax)
+        # st.pyplot(fig)
+
+        fig = px.scatter(mean_benefit_vs_conversion, x='conversion', y='benefit', color_discrete_sequence=['LightBlue'], size_max=50)
+        st.plotly_chart(fig)
 
         st.write('''
                  We further compute the Average Treatment Effect (ATE) for both the mean conversion rate and the mean benefit per user:
@@ -116,9 +122,12 @@ if tabs == "Exploratory analysis":
                  ''')
         mean_conversions_ate = eda.compute_ate()
 
-        fig, ax = plt.subplots()
-        mean_conversions_ate.plot.scatter(x='conversion', y='benefit', c='DarkBlue', s=50, ax=ax)
-        st.pyplot(fig)
+        # fig, ax = plt.subplots()
+        # mean_conversions_ate.plot.scatter(x='conversion', y='benefit', c='DarkBlue', s=50, ax=ax)
+        # st.pyplot(fig)
+
+        fig = px.scatter(mean_conversions_ate, x='conversion', y='benefit', color_discrete_sequence=['LightBlue'], size_max=50)
+        st.plotly_chart(fig)
 
         st.subheader('Feature importance')
 
@@ -131,10 +140,13 @@ if tabs == "Exploratory analysis":
 
         feature_importance = FeatureImportance(uplift_sim.df, X_names, y_name = 'conversion', treatment_group = treatment_group)
         fi = feature_importance.compute_feature_importance()
-        fig, ax = plt.subplots()
+        # fig, ax = plt.subplots()
         di_df_sorted = fi.sort_values(by='score', ascending=False)
-        di_df_sorted[['feature', 'score']].plot.barh(x='feature', y='score', ax=ax)
-        st.pyplot(fig)
+        # di_df_sorted[['feature', 'score']].plot.barh(x='feature', y='score', ax=ax)
+        # st.pyplot(fig)
+        fig = px.bar(di_df_sorted, y='feature', x='score', orientation='h')
+        st.plotly_chart(fig)
+
 
         st.write("""
                     - AccountLifetimeIndex: Longer-standing accounts are key predictors of customer response to promotions \n
@@ -194,13 +206,26 @@ if tabs == "Model training":
             st.subheader('Feature Importances')
             fig, ax = plt.subplots()
 
+            # for k, v in feature_importances.items():
+            #     st.write(f"Feature importance for {k}")
+            #     v.plot(kind='barh', ax=ax)
+            #     ax.set_xlabel("Importance")
+            #     ax.set_ylabel("Feature")
+            #     ax.set_title(f"Feature Importance for {model_type}")
+            #     st.pyplot(fig)
+
             for k, v in feature_importances.items():
-                st.write(f"Feature importance for {k}")
-                v.plot(kind='barh', ax=ax)
-                ax.set_xlabel("Importance")
-                ax.set_ylabel("Feature")
-                ax.set_title(f"Feature Importance for {model_type}")
-                st.pyplot(fig)
+                # Reset index if 'v' is a Series or its index contains the feature names
+                if isinstance(v, pd.Series) or 'feature' not in v.columns:
+                    v = v.reset_index()
+                    v.columns = ['feature', 'score']  # Adjust column names accordingly
+
+                # Assuming 'v' now has columns ['feature', 'score']
+                fig = px.bar(v, y='feature', x='score', orientation='h', 
+                            title=f"Feature Importance for {model_type} ({k})", 
+                            labels={'score': 'Importance', 'feature': 'Feature'})
+                fig.update_layout(yaxis={'categoryorder':'total ascending'})  # Optional: This sorts the bars
+                st.plotly_chart(fig)
 
     else:
         st.error("Please generate and preprocess the dataset first.")
@@ -245,47 +270,184 @@ if tabs == "Economic effects":
         
         # Plotting CATE Conversion
         st.subheader("CATE Conversion vs Targeted Population")
-        fig, ax_conversion = plt.subplots()
-        for discount, color in zip(discounts, ['b', 'g', 'y']):
-            qini_conversions[discount].plot(ax=ax_conversion, x='index', y='S', color=color)
-            qini_conversions[discount].plot(ax=ax_conversion, x='index', y='Random', color='r', ls='--')
         
-        ax_conversion.legend([f'{d} model' for d in discounts] + [f'{d} random' for d in discounts], prop={'size': 10})
-        ax_conversion.set_xlabel('Fraction of Targeted Users')
-        ax_conversion.set_ylabel('CATE Conversion')
-        ax_conversion.set_title('CATE Conversion vs Targeted Population')
-        st.pyplot(fig)
+        # fig, ax_conversion = plt.subplots()
+        # for discount, color in zip(discounts, ['b', 'g', 'y']):
+        #     qini_conversions[discount].plot(ax=ax_conversion, x='index', y='S', color=color)
+        #     qini_conversions[discount].plot(ax=ax_conversion, x='index', y='Random', color='r', ls='--')
+        
+        # ax_conversion.legend([f'{d} model' for d in discounts] + [f'{d} random' for d in discounts], prop={'size': 10})
+        # ax_conversion.set_xlabel('Fraction of Targeted Users')
+        # ax_conversion.set_ylabel('CATE Conversion')
+        # ax_conversion.set_title('CATE Conversion vs Targeted Population')
+        # st.pyplot(fig)
+
+        # Initialize a figure object
+        fig = go.Figure()
+
+        # Define colors for each discount level and the random baseline
+        colors = ['blue', 'green', 'yellow']
+        random_line_dash = 'dash'
+
+        # Iterate over each discount to add its line to the plot
+        for i, discount in enumerate(discounts):
+            # Add the model line
+            fig.add_trace(go.Scatter(x=qini_conversions[discount]['index'], 
+                                    y=qini_conversions[discount]['S'], 
+                                    mode='lines', 
+                                    name=f'{discount} model',
+                                    line=dict(color=colors[i])))
+            
+            # Add the random baseline line
+            fig.add_trace(go.Scatter(x=qini_conversions[discount]['index'], 
+                                    y=qini_conversions[discount]['Random'], 
+                                    mode='lines', 
+                                    name=f'{discount} random',
+                                    line=dict(color='red', dash=random_line_dash)))
+
+        # Update the layout of the figure
+        fig.update_layout(
+            title='CATE Conversion vs Targeted Population',
+            xaxis_title='Fraction of Targeted Users',
+            yaxis_title='CATE Conversion',
+            legend_title='Legend',
+            legend=dict(
+                x=0,
+                y=1,
+                traceorder='normal',
+                font=dict(
+                    size=10,
+                )
+            )
+        )
+
+        # Display the figure in Streamlit
+        st.plotly_chart(fig)
 
         # Plotting CATE Benefit
         st.subheader("CATE Benefit vs Targeted Population")
-        fig, ax_benefit = plt.subplots()
-        for discount, color in zip(discounts, ['b', 'g', 'y']):
-            qini_benefits[discount].plot(ax=ax_benefit, x='index', y='S', color=color)
-            qini_benefits[discount].plot(ax=ax_benefit, x='index', y='Random', color='r', ls='--')
 
-        ax_benefit.legend([f'{d} model' for d in discounts] + [f'{d} random' for d in discounts], prop={'size': 10})
-        ax_benefit.set_xlabel('Fraction of Targeted Users')
-        ax_benefit.set_ylabel('CATE Benefit')
-        ax_benefit.set_title('CATE Benefit vs Targeted Population')
-        st.pyplot(fig)
+        # fig, ax_benefit = plt.subplots()
+        # for discount, color in zip(discounts, ['b', 'g', 'y']):
+        #     qini_benefits[discount].plot(ax=ax_benefit, x='index', y='S', color=color)
+        #     qini_benefits[discount].plot(ax=ax_benefit, x='index', y='Random', color='r', ls='--')
+
+        # ax_benefit.legend([f'{d} model' for d in discounts] + [f'{d} random' for d in discounts], prop={'size': 10})
+        # ax_benefit.set_xlabel('Fraction of Targeted Users')
+        # ax_benefit.set_ylabel('CATE Benefit')
+        # ax_benefit.set_title('CATE Benefit vs Targeted Population')
+        # st.pyplot(fig)
+
+
+        # Initialize a figure object
+        fig = go.Figure()
+
+        # Define colors for each discount level and the random baseline
+        colors = ['blue', 'green', 'yellow']
+        random_line_dash = 'dash'
+
+        # Iterate over each discount to add its line to the plot
+        for i, discount in enumerate(discounts):
+            # Add the model line
+            fig.add_trace(go.Scatter(x=qini_benefits[discount]['index'], 
+                                    y=qini_benefits[discount]['S'], 
+                                    mode='lines', 
+                                    name=f'{discount} model',
+                                    line=dict(color=colors[i])))
+            
+            # Add the random baseline line
+            fig.add_trace(go.Scatter(x=qini_benefits[discount]['index'], 
+                                    y=qini_benefits[discount]['Random'], 
+                                    mode='lines', 
+                                    name=f'{discount} random',
+                                    line=dict(color='red', dash=random_line_dash)))
+
+        # Update the layout of the figure
+        fig.update_layout(
+            title='CATE Benefit vs Targeted Population',
+            xaxis_title='Fraction of Targeted Users',
+            yaxis_title='CATE Benefit',
+            legend_title='Legend',
+            legend=dict(
+                x=0,
+                y=1,
+                traceorder='normal',
+                font=dict(
+                    size=10,
+                )
+            )
+        )
+
+        # Display the figure in Streamlit
+        st.plotly_chart(fig)
+
 
         # Plotting CATE Benefit vs CATE Conversion
         st.subheader("CATE Benefit vs CATE Conversion")
-        fig, ax_comp = plt.subplots()
-        colors = ['b', 'g', 'y']
+
+        # fig, ax_comp = plt.subplots()
+        # colors = ['b', 'g', 'y']
+        # for i, discount in enumerate(discounts):
+        #     qini_conc_test = pd.concat([qini_conversions[discount][['S']], qini_benefits[discount][['S']]], axis=1)
+        #     qini_conc_test.columns = ['cate_conversion', 'cate_benefit']
+        #     qini_conc_test.plot(ax=ax_comp, x='cate_conversion', y='cate_benefit', color=colors[i], label=f'{discount} model')
+        
+        # st.write('To simplify the comparison, we can plot the CATE Benefit as a function of the CATE conversion.')
+        # st.write('In the last plot for example we can see that there is a region where offering 15% discount to a targeted group of users is more efficient than giving 10% to everyone. We can obtain the same impact in overall conversion uplift while reducing our benefit loss considerably.')
+
+        # ax_comp.legend(prop={'size': 10})
+        # ax_comp.set_xlabel('CATE Conversion')
+        # ax_comp.set_ylabel('CATE Benefit')
+        # ax_comp.set_title('CATE Benefit vs CATE Conversion')
+        # st.pyplot(fig)
+
+        # Initialize a figure object
+        fig = go.Figure()
+
+        # Define colors for each discount level
+        colors = ['blue', 'green', 'yellow']
+
+        # Iterate over each discount to add its scatter plot to the figure
         for i, discount in enumerate(discounts):
-            qini_conc_test = pd.concat([qini_conversions[discount][['S']], qini_benefits[discount][['S']]], axis=1)
+            qini_conc_test = pd.concat([qini_conversions[discount]['S'], qini_benefits[discount]['S']], axis=1)
             qini_conc_test.columns = ['cate_conversion', 'cate_benefit']
-            qini_conc_test.plot(ax=ax_comp, x='cate_conversion', y='cate_benefit', color=colors[i], label=f'{discount} model')
-        
+
+            # Add the scatter plot for each discount level
+            # Adjust marker size with `size` and line width with `line=dict(width=2)`
+            fig.add_trace(go.Scatter(x=qini_conc_test['cate_conversion'], 
+                                    y=qini_conc_test['cate_benefit'], 
+                                    mode='markers+lines', 
+                                    name=f'{discount} model',
+                                    marker=dict(color=colors[i], size=6),  # Adjust marker size here
+                                    line=dict(width=2)))  # Adjust line width here
+
+        # Update the layout of the figure to adjust aspect ratio and margins if needed
+        fig.update_layout(
+            title='CATE Benefit vs CATE Conversion',
+            xaxis_title='CATE Conversion',
+            yaxis_title='CATE Benefit',
+            legend_title='Legend',
+            legend=dict(
+                x=0,
+                y=1,
+                traceorder='normal',
+                font=dict(
+                    size=10,
+                )
+            ),
+            # Optionally adjust plot and margin size for a "thinner" appearance
+            margin=dict(l=20, r=20, t=50, b=20),  # Adjust margins to change plot boundary
+            height=400,  # Adjust height for overall "thinness"
+            width=600   # Adjust width as needed
+        )
+
+        # Display the figure in Streamlit
+        st.plotly_chart(fig)
+
+
         st.write('To simplify the comparison, we can plot the CATE Benefit as a function of the CATE conversion.')
-        st.write('In the last plot for example we can see that there is a region where offering 15% discount to a targeted group of users is more efficient than giving 10% to everyone. We can obtain the same impact in overall conversion uplift while reducing our benefit loss considerably.')
+        st.write('In the last plot for example, we can see that there is a region where offering a 15% discount to a targeted group of users is more efficient than giving 10% to everyone. We can obtain the same impact on overall conversion uplift while reducing our benefit loss considerably.')
 
-        ax_comp.legend(prop={'size': 10})
-        ax_comp.set_xlabel('CATE Conversion')
-        ax_comp.set_ylabel('CATE Benefit')
-        ax_comp.set_title('CATE Benefit vs CATE Conversion')
-        st.pyplot(fig)
 
     else:
-        st.error("Please ensure the model is trained and the dataset is prepared.")
+        st.error("Please ensure the model is trained and the dataset is prepared.")

requirements.txt

@@ -3,4 +3,4 @@ matplotlib==3.8.3
 numpy==1.23.5
 scikit_learn==1.4.1.post1
 streamlit==1.32.2
-xgboost==2.0.3
+xgboost==2.0.3