lift-4.py

#Observations where y=1
total_converts = df['CONVERT_ACTUAL'].sum()
#Total Observations
total_leads = df.index.size
baseline_convert_prob = total_converts/float(total_leads)

#Calculate Index of Positive Outcome Rate in Each Decile to the Baseline Positive Rate
lift_df['LIFT_INDEX'] = (lift_df['lift']/baseline_convert_prob)*100

#Add Baseling Positive Rate to DataFrame
lift_df['BASELINE_CONVERT_PROB'] = baseline_convert_prob

"""
Plotting
"""
#Configure Grid
fig = plt.figure(figsize=(12,6))
gs = gridspec.GridSpec(2,1)
ax1 = plt.subplot(gs[0,0])

#Calculate Percent of Total Leads Pursued for x-axis tick labels
lift_df['CUM_LEADS'] = lift_df['LEADS_COUNT'].cumsum()/lift_df['LEADS_COUNT'].sum()


ax1.plot(lift_plot_data['CUM_LEADS'], 
         lift_plot_data['LIFT_INDEX'],
         color='g', label='Classifier Performance')
ax1.axhline(100,linestyle='dashed',
            color='r',label="Baseline Performance")
ax1.fill_between(lift_plot_data['CUM_LEADS'],
                 lift_plot_data['LIFT_INDEX'],
                 100,where=lift_plot_data['LIFT_INDEX']>=100,
                 interpolate=True,color='g',alpha=0.25)

#Configure x-axis
ax1.set_xticks(np.linspace(0,1,6))
x1_vals = ax1.get_yticks()
ax1.set_xticklabels(['{:3.0f}%'.format(val*100) for val in x1_vals])

#Configure y-axis
ax1.set_ylim(top=1000)
y1_vals = ax1.get_yticks()
ax1.set_yticklabels(['{:,.0f}x'.format(val/100) for val in y1_vals])
ax1.set_ylabel("Upgrade Lift Index")

ax1.legend(loc='center right',frameon=True)
ax1.set_title("Lift Chart")
gs.tight_layout(fig)