g1_new_user_ratio.py

#create a dataframe that shows new user ratio - we also need to drop NA values (first month new user ratio is 0)
tx_user_ratio = tx_uk.query("UserType == 'New'").groupby(['InvoiceYearMonth'])['CustomerID'].nunique()/tx_uk.query("UserType == 'Existing'").groupby(['InvoiceYearMonth'])['CustomerID'].nunique() 
tx_user_ratio = tx_user_ratio.reset_index()
tx_user_ratio = tx_user_ratio.dropna()

#print the dafaframe
tx_user_ratio

#plot the result

plot_data = [
    go.Bar(
        x=tx_user_ratio.query("InvoiceYearMonth>201101 and InvoiceYearMonth<201112")['InvoiceYearMonth'],
        y=tx_user_ratio.query("InvoiceYearMonth>201101 and InvoiceYearMonth<201112")['CustomerID'],
    )
]

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