karamanbk

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


#order the cluster numbers
tx_user = order_cluster('RevenueCluster', 'Revenue',tx_user,True)

#show details of the dataframe

karamanbk

#calculate overall score and use mean() to see details
tx_user['OverallScore'] = tx_user['RecencyCluster'] + tx_user['FrequencyCluster'] + tx_user['RevenueCluster']
tx_user.groupby('OverallScore')['Recency','Frequency','Revenue'].mean()

karamanbk

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' 

karamanbk

#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,

karamanbk

karamanbk

#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

karamanbk

#calculate revenue and create a new dataframe for it
tx_6m['Revenue'] = tx_6m['UnitPrice'] * tx_6m['Quantity']
tx_user_6m = tx_6m.groupby('CustomerID')['Revenue'].sum().reset_index()
tx_user_6m.columns = ['CustomerID','m6_Revenue']


#plot LTV histogram
plot_data = [
    go.Histogram(
        x=tx_user_6m.query('m6_Revenue < 10000')['m6_Revenue']

karamanbk

tx_merge = pd.merge(tx_user, tx_user_6m, on='CustomerID', how='left')
tx_merge = tx_merge.fillna(0)

tx_graph = tx_merge.query("m6_Revenue < 30000")

plot_data = [
    go.Scatter(
        x=tx_graph.query("Segment == 'Low-Value'")['OverallScore'],
        y=tx_graph.query("Segment == 'Low-Value'")['m6_Revenue'],
        mode='markers',

karamanbk

#remove outliers
tx_merge = tx_merge[tx_merge['m6_Revenue']<tx_merge['m6_Revenue'].quantile(0.99)]


#creating 3 clusters
kmeans = KMeans(n_clusters=3)
kmeans.fit(tx_merge[['m6_Revenue']])
tx_merge['LTVCluster'] = kmeans.predict(tx_merge[['m6_Revenue']])

#order cluster number based on LTV

karamanbk

#convert categorical columns to numerical
tx_class = pd.get_dummies(tx_cluster)

#calculate and show correlations
corr_matrix = tx_class.corr()
corr_matrix['LTVCluster'].sort_values(ascending=False)

#create X and y, X will be feature set and y is the label - LTV
X = tx_class.drop(['LTVCluster','m6_Revenue'],axis=1)
y = tx_class['LTVCluster']