g1_new_user.py

#create a dataframe contaning CustomerID and first purchase date
tx_min_purchase = tx_uk.groupby('CustomerID').InvoiceDate.min().reset_index()
tx_min_purchase.columns = ['CustomerID','MinPurchaseDate']
tx_min_purchase['MinPurchaseYearMonth'] = tx_min_purchase['MinPurchaseDate'].map(lambda date: 100*date.year + date.month)

#merge first purchase date column to our main dataframe (tx_uk)
tx_uk = pd.merge(tx_uk, tx_min_purchase, on='CustomerID')

tx_uk.head()

#create a column called User Type and assign Existing 
#if User's First Purchase Year Month before the selected Invoice Year Month
tx_uk['UserType'] = 'New'
tx_uk.loc[tx_uk['InvoiceYearMonth']>tx_uk['MinPurchaseYearMonth'],'UserType'] = 'Existing'

#calculate the Revenue per month for each user type
tx_user_type_revenue = tx_uk.groupby(['InvoiceYearMonth','UserType'])['Revenue'].sum().reset_index()

#filtering the dates and plot the result
tx_user_type_revenue = tx_user_type_revenue.query("InvoiceYearMonth != 201012 and InvoiceYearMonth != 201112")
plot_data = [
    go.Scatter(
        x=tx_user_type_revenue.query("UserType == 'Existing'")['InvoiceYearMonth'],
        y=tx_user_type_revenue.query("UserType == 'Existing'")['Revenue'],
        name = 'Existing'
    ),
    go.Scatter(
        x=tx_user_type_revenue.query("UserType == 'New'")['InvoiceYearMonth'],
        y=tx_user_type_revenue.query("UserType == 'New'")['Revenue'],
        name = 'New'
    )
]

plot_layout = go.Layout(
        xaxis={"type": "category"},
        title='New vs Existing'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)