g3_3m_rfm.py

#import libraries
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 xgboost as xgb
from sklearn.model_selection import KFold, cross_val_score, train_test_split

import xgboost as xgb

#initate plotly
pyoff.init_notebook_mode()

#read data from csv and redo the data work we done before
tx_data = pd.read_csv('data.csv')
tx_data['InvoiceDate'] = pd.to_datetime(tx_data['InvoiceDate'])
tx_uk = tx_data.query("Country=='United Kingdom'").reset_index(drop=True)

#create 3m and 6m dataframes
tx_3m = tx_uk[(tx_uk.InvoiceDate < date(2011,6,1)) & (tx_uk.InvoiceDate >= date(2011,3,1))].reset_index(drop=True)
tx_6m = tx_uk[(tx_uk.InvoiceDate >= date(2011,6,1)) & (tx_uk.InvoiceDate < date(2011,12,1))].reset_index(drop=True)

#create tx_user for assigning clustering
tx_user = pd.DataFrame(tx_3m['CustomerID'].unique())
tx_user.columns = ['CustomerID']

#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


#calculate recency score
tx_max_purchase = tx_3m.groupby('CustomerID').InvoiceDate.max().reset_index()
tx_max_purchase.columns = ['CustomerID','MaxPurchaseDate']
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')

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

tx_user = order_cluster('RecencyCluster', 'Recency',tx_user,False)

#calcuate frequency score
tx_frequency = tx_3m.groupby('CustomerID').InvoiceDate.count().reset_index()
tx_frequency.columns = ['CustomerID','Frequency']
tx_user = pd.merge(tx_user, tx_frequency, on='CustomerID')

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

tx_user = order_cluster('FrequencyCluster', 'Frequency',tx_user,True)

#calcuate revenue score
tx_3m['Revenue'] = tx_3m['UnitPrice'] * tx_3m['Quantity']
tx_revenue = tx_3m.groupby('CustomerID').Revenue.sum().reset_index()
tx_user = pd.merge(tx_user, tx_revenue, on='CustomerID')

kmeans = KMeans(n_clusters=4)
kmeans.fit(tx_user[['Revenue']])
tx_user['RevenueCluster'] = kmeans.predict(tx_user[['Revenue']])
tx_user = order_cluster('RevenueCluster', 'Revenue',tx_user,True)


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

Thanks, it is very useful. But I am running the code there is an error popup

TypeError: can't compare datetime.datetime to datetime.date