karamanbk

from sklearn.cluster import KMeans

sse={}
tx_recency = tx_user[['Recency']]
for k in range(1, 10):
    kmeans = KMeans(n_clusters=k, max_iter=1000).fit(tx_recency)
    tx_recency["clusters"] = kmeans.labels_
    sse[k] = kmeans.inertia_ 
plt.figure()
plt.plot(list(sse.keys()), list(sse.values()))

karamanbk

#create a generic user dataframe to keep CustomerID and new segmentation scores
tx_user = pd.DataFrame(tx_data['CustomerID'].unique())
tx_user.columns = ['CustomerID']

#get the max purchase date for each customer and create a dataframe with it
tx_max_purchase = tx_uk.groupby('CustomerID').InvoiceDate.max().reset_index()
tx_max_purchase.columns = ['CustomerID','MaxPurchaseDate']

#we take our observation point as the max invoice date in our dataset
tx_max_purchase['Recency'] = (tx_max_purchase['MaxPurchaseDate'].max() - tx_max_purchase['MaxPurchaseDate']).dt.days

karamanbk

# import libraries
from datetime import datetime, timedelta
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from __future__ import division

import plotly.plotly as py

karamanbk

karamanbk

karamanbk

#create our retention table again with crosstab() and add firs purchase year month view
tx_retention = pd.crosstab(tx_user_purchase['CustomerID'], tx_user_purchase['InvoiceYearMonth']).reset_index()
tx_retention = pd.merge(tx_retention,tx_min_purchase[['CustomerID','MinPurchaseYearMonth']],on='CustomerID')
new_column_names = [ 'm_' + str(column) for column in tx_retention.columns[:-1]]
new_column_names.append('MinPurchaseYearMonth')
tx_retention.columns = new_column_names

#create the array of Retained users for each cohort monthly
retention_array = []
for i in range(len(months)):

karamanbk

#identify which users are active by looking at their revenue per month
tx_user_purchase = tx_uk.groupby(['CustomerID','InvoiceYearMonth'])['Revenue'].sum().reset_index()

#create retention matrix with crosstab
tx_retention = pd.crosstab(tx_user_purchase['CustomerID'], tx_user_purchase['InvoiceYearMonth']).reset_index()

tx_retention.head()

#create an array of dictionary which keeps Retained & Total User count for each month
months = tx_retention.columns[2:]

karamanbk

#create a dataframe that shows new user ratio - we also need to drop NA values (first month new user ratio is 0)
tx_user_ratio = tx_uk.query("UserType == 'New'").groupby(['InvoiceYearMonth'])['CustomerID'].nunique()/tx_uk.query("UserType == 'Existing'").groupby(['InvoiceYearMonth'])['CustomerID'].nunique() 
tx_user_ratio = tx_user_ratio.reset_index()
tx_user_ratio = tx_user_ratio.dropna()

#print the dafaframe
tx_user_ratio

#plot the result

karamanbk

#create a dataframe contaning CustomerID and first purchase date
tx_min_purchase = tx_uk.groupby('CustomerID').InvoiceDate.min().reset_index()
tx_min_purchase.columns = ['CustomerID','MinPurchaseDate']
tx_min_purchase['MinPurchaseYearMonth'] = tx_min_purchase['MinPurchaseDate'].map(lambda date: 100*date.year + date.month)

#merge first purchase date column to our main dataframe (tx_uk)
tx_uk = pd.merge(tx_uk, tx_min_purchase, on='CustomerID')

tx_uk.head()

karamanbk

# create a new dataframe for average revenue by taking the mean of it
tx_monthly_order_avg = tx_uk.groupby('InvoiceYearMonth')['Revenue'].mean().reset_index()

#print the dataframe
tx_monthly_order_avg

#plot the bar chart
plot_data = [
    go.Bar(
        x=tx_monthly_order_avg['InvoiceYearMonth'],