g9_owa_dataset.py

#create hv segment
df_hv = pd.DataFrame()
df_hv['customer_id'] = np.array([count for count in range(30000)])
df_hv['segment'] = np.array(['high-value' for _ in range(30000)])
df_hv['group'] = 'A'
df_hv.loc[df_hv.index>=10000,'group'] = 'B' 
df_hv.loc[df_hv.index>=20000,'group'] = 'C' 

df_hv.loc[df_hv.group == 'A', 'purchase_count'] = np.random.poisson(0.4, 10000)
df_hv.loc[df_hv.group == 'B', 'purchase_count'] = np.random.poisson(0.6, 10000)
df_hv.loc[df_hv.group == 'C', 'purchase_count'] = np.random.poisson(0.2, 10000)

a_stats = df_hv[df_hv.group=='A'].purchase_count
b_stats = df_hv[df_hv.group=='B'].purchase_count
c_stats = df_hv[df_hv.group=='C'].purchase_count

hist_data = [a_stats, b_stats, c_stats]

group_labels = ['A', 'B','C']

# Create distplot with curve_type set to 'normal'
fig = ff.create_distplot(hist_data, group_labels, bin_size=.5,
                         curve_type='normal',show_rug=False)

fig.layout = go.Layout(
        title='Test vs Control Stats',
        plot_bgcolor  = 'rgb(243,243,243)',
        paper_bgcolor  = 'rgb(243,243,243)',
    )


# Plot!
pyoff.iplot(fig)