g_series_8_intro.py

from datetime import datetime, timedelta,date
import pandas as pd
%matplotlib inline
from sklearn.metrics import classification_report,confusion_matrix
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from __future__ import division
from sklearn.cluster import KMeans

import plotly.plotly as py
import plotly.offline as pyoff
import plotly.graph_objs as go

import sklearn
import xgboost as xgb
from sklearn.model_selection import KFold, cross_val_score, train_test_split
import warnings
warnings.filterwarnings("ignore")

#initiate plotly
pyoff.init_notebook_mode()

#function to order clusters
def order_cluster(cluster_field_name, target_field_name,df,ascending):
    new_cluster_field_name = 'new_' + cluster_field_name
    df_new = df.groupby(cluster_field_name)[target_field_name].mean().reset_index()
    df_new = df_new.sort_values(by=target_field_name,ascending=ascending).reset_index(drop=True)
    df_new['index'] = df_new.index
    df_final = pd.merge(df,df_new[[cluster_field_name,'index']], on=cluster_field_name)
    df_final = df_final.drop([cluster_field_name],axis=1)
    df_final = df_final.rename(columns={"index":cluster_field_name})
    return df_final

  
#function for calculating the uplift
def calc_uplift(df):
    avg_order_value = 25
    
    #calculate conversions for each offer type
    base_conv = df[df.offer == 'No Offer']['conversion'].mean()
    disc_conv = df[df.offer == 'Discount']['conversion'].mean()
    bogo_conv = df[df.offer == 'Buy One Get One']['conversion'].mean()
    
    #calculate conversion uplift for discount and bogo
    disc_conv_uplift = disc_conv - base_conv
    bogo_conv_uplift = bogo_conv - base_conv
    
    #calculate order uplift
    disc_order_uplift = disc_conv_uplift * len(df[df.offer == 'Discount']['conversion'])
    bogo_order_uplift = bogo_conv_uplift * len(df[df.offer == 'Buy One Get One']['conversion'])
    
    #calculate revenue uplift
    disc_rev_uplift = disc_order_uplift * avg_order_value
    bogo_rev_uplift = bogo_order_uplift * avg_order_value
    
    
    print('Discount Conversion Uplift: {0}%'.format(np.round(disc_conv_uplift*100,2)))
    print('Discount Order Uplift: {0}'.format(np.round(disc_order_uplift,2)))
    print('Discount Revenue Uplift: ${0}\n'.format(np.round(disc_rev_uplift,2)))
    
    if len(df[df.offer == 'Buy One Get One']['conversion']) > 0:
          
        print('-------------- \n')
        print('BOGO Conversion Uplift: {0}%'.format(np.round(bogo_conv_uplift*100,2)))
        print('BOGO Order Uplift: {0}'.format(np.round(bogo_order_uplift,2)))
        print('BOGO Revenue Uplift: ${0}'.format(np.round(bogo_rev_uplift,2)))     
        
 

i could excute uplift model from 41 line