g5_rfm.py

#get max purchase date for Recency and create a dataframe
tx_max_purchase = tx_6m.groupby('CustomerID').InvoiceDate.max().reset_index()
tx_max_purchase.columns = ['CustomerID','MaxPurchaseDate']

#find the recency in days and add it to tx_user
tx_max_purchase['Recency'] = (tx_max_purchase['MaxPurchaseDate'].max() - tx_max_purchase['MaxPurchaseDate']).dt.days
tx_user = pd.merge(tx_user, tx_max_purchase[['CustomerID','Recency']], on='CustomerID')

#plot recency
plot_data = [
    go.Histogram(
        x=tx_user['Recency']
    )
]

plot_layout = go.Layout(
        title='Recency'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

#clustering for Recency
kmeans = KMeans(n_clusters=4)
kmeans.fit(tx_user[['Recency']])
tx_user['RecencyCluster'] = kmeans.predict(tx_user[['Recency']])

#order cluster method
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


#order recency clusters
tx_user = order_cluster('RecencyCluster', 'Recency',tx_user,False)

#print cluster characteristics
tx_user.groupby('RecencyCluster')['Recency'].describe()


#get total purchases for frequency scores
tx_frequency = tx_6m.groupby('CustomerID').InvoiceDate.count().reset_index()
tx_frequency.columns = ['CustomerID','Frequency']

#add frequency column to tx_user
tx_user = pd.merge(tx_user, tx_frequency, on='CustomerID')

#plot frequency
plot_data = [
    go.Histogram(
        x=tx_user.query('Frequency < 1000')['Frequency']
    )
]

plot_layout = go.Layout(
        title='Frequency'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

#clustering for frequency
kmeans = KMeans(n_clusters=4)
kmeans.fit(tx_user[['Frequency']])
tx_user['FrequencyCluster'] = kmeans.predict(tx_user[['Frequency']])

#order frequency clusters and show the characteristics
tx_user = order_cluster('FrequencyCluster', 'Frequency',tx_user,True)
tx_user.groupby('FrequencyCluster')['Frequency'].describe()


#calculate monetary value, create a dataframe with it
tx_6m['Revenue'] = tx_6m['UnitPrice'] * tx_6m['Quantity']
tx_revenue = tx_6m.groupby('CustomerID').Revenue.sum().reset_index()

#add Revenue column to tx_user
tx_user = pd.merge(tx_user, tx_revenue, on='CustomerID')

#plot Revenue
plot_data = [
    go.Histogram(
        x=tx_user.query('Revenue < 10000')['Revenue']
    )
]

plot_layout = go.Layout(
        title='Monetary Value'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

#Revenue clusters 
kmeans = KMeans(n_clusters=4)
kmeans.fit(tx_user[['Revenue']])
tx_user['RevenueCluster'] = kmeans.predict(tx_user[['Revenue']])

#ordering clusters and who the characteristics
tx_user = order_cluster('RevenueCluster', 'Revenue',tx_user,True)
tx_user.groupby('RevenueCluster')['Revenue'].describe()


#building overall segmentation
tx_user['OverallScore'] = tx_user['RecencyCluster'] + tx_user['FrequencyCluster'] + tx_user['RevenueCluster']

#assign segment names
tx_user['Segment'] = 'Low-Value'
tx_user.loc[tx_user['OverallScore']>2,'Segment'] = 'Mid-Value' 
tx_user.loc[tx_user['OverallScore']>4,'Segment'] = 'High-Value' 

#plot revenue vs frequency
tx_graph = tx_user.query("Revenue < 50000 and Frequency < 2000")

plot_data = [
    go.Scatter(
        x=tx_graph.query("Segment == 'Low-Value'")['Frequency'],
        y=tx_graph.query("Segment == 'Low-Value'")['Revenue'],
        mode='markers',
        name='Low',
        marker= dict(size= 7,
            line= dict(width=1),
            color= 'blue',
            opacity= 0.8
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'Mid-Value'")['Frequency'],
        y=tx_graph.query("Segment == 'Mid-Value'")['Revenue'],
        mode='markers',
        name='Mid',
        marker= dict(size= 9,
            line= dict(width=1),
            color= 'green',
            opacity= 0.5
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'High-Value'")['Frequency'],
        y=tx_graph.query("Segment == 'High-Value'")['Revenue'],
        mode='markers',
        name='High',
        marker= dict(size= 11,
            line= dict(width=1),
            color= 'red',
            opacity= 0.9
           )
    ),
]

plot_layout = go.Layout(
        yaxis= {'title': "Revenue"},
        xaxis= {'title': "Frequency"},
        title='Segments'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

#plot revenue vs recency
tx_graph = tx_user.query("Revenue < 50000 and Frequency < 2000")

plot_data = [
    go.Scatter(
        x=tx_graph.query("Segment == 'Low-Value'")['Recency'],
        y=tx_graph.query("Segment == 'Low-Value'")['Revenue'],
        mode='markers',
        name='Low',
        marker= dict(size= 7,
            line= dict(width=1),
            color= 'blue',
            opacity= 0.8
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'Mid-Value'")['Recency'],
        y=tx_graph.query("Segment == 'Mid-Value'")['Revenue'],
        mode='markers',
        name='Mid',
        marker= dict(size= 9,
            line= dict(width=1),
            color= 'green',
            opacity= 0.5
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'High-Value'")['Recency'],
        y=tx_graph.query("Segment == 'High-Value'")['Revenue'],
        mode='markers',
        name='High',
        marker= dict(size= 11,
            line= dict(width=1),
            color= 'red',
            opacity= 0.9
           )
    ),
]

plot_layout = go.Layout(
        yaxis= {'title': "Revenue"},
        xaxis= {'title': "Recency"},
        title='Segments'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

#plot frequency vs recency
tx_graph = tx_user.query("Revenue < 50000 and Frequency < 2000")

plot_data = [
    go.Scatter(
        x=tx_graph.query("Segment == 'Low-Value'")['Recency'],
        y=tx_graph.query("Segment == 'Low-Value'")['Frequency'],
        mode='markers',
        name='Low',
        marker= dict(size= 7,
            line= dict(width=1),
            color= 'blue',
            opacity= 0.8
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'Mid-Value'")['Recency'],
        y=tx_graph.query("Segment == 'Mid-Value'")['Frequency'],
        mode='markers',
        name='Mid',
        marker= dict(size= 9,
            line= dict(width=1),
            color= 'green',
            opacity= 0.5
           )
    ),
        go.Scatter(
        x=tx_graph.query("Segment == 'High-Value'")['Recency'],
        y=tx_graph.query("Segment == 'High-Value'")['Frequency'],
        mode='markers',
        name='High',
        marker= dict(size= 11,
            line= dict(width=1),
            color= 'red',
            opacity= 0.9
           )
    ),
]

plot_layout = go.Layout(
        yaxis= {'title': "Frequency"},
        xaxis= {'title': "Recency"},
        title='Segments'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)