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

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

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

#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

#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 revenue for each customer
tx_uk['Revenue'] = tx_uk['UnitPrice'] * tx_uk['Quantity']
tx_revenue = tx_uk.groupby('CustomerID').Revenue.sum().reset_index()

#merge it with our main dataframe
tx_user = pd.merge(tx_user, tx_revenue, on='CustomerID')

#plot the histogram
plot_data = [
    go.Histogram(

karamanbk

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

#order the frequency cluster
tx_user = order_cluster('FrequencyCluster', 'Frequency',tx_user,True)

#see details of each cluster
tx_user.groupby('FrequencyCluster')['Frequency'].describe()

karamanbk

#get order counts for each user and create a dataframe with it
tx_frequency = tx_uk.groupby('CustomerID').InvoiceDate.count().reset_index()
tx_frequency.columns = ['CustomerID','Frequency']

#add this data to our main dataframe
tx_user = pd.merge(tx_user, tx_frequency, on='CustomerID')

#plot the histogram
plot_data = [
    go.Histogram(

karamanbk

#build 4 clusters for recency and add it to dataframe
kmeans = KMeans(n_clusters=4)
kmeans.fit(tx_user[['Recency']])
tx_user['RecencyCluster'] = kmeans.predict(tx_user[['Recency']])

#function for ordering cluster numbers
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)