karamanbk

#function to order 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)
    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

karamanbk

#plotting monthly charge
df_plot = df_data.copy()
df_plot['MonthlyCharges'] = df_plot['MonthlyCharges'].astype(int)
df_plot = df_plot.groupby('MonthlyCharges').Churn.mean().reset_index()


plot_data = [
    go.Scatter(
        x=df_plot['MonthlyCharges'],
        y=df_plot['Churn'],

karamanbk

#Partner
df_plot = df_data.groupby('Partner').Churn.mean().reset_index()
plot_data = [
    go.Bar(
        x=df_plot['Partner'],
        y=df_plot['Churn'],
        width = [0.5, 0.5],
        marker=dict(
        color=['green', 'blue'])
    )

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

karamanbk

karamanbk

#XGBoost Multiclassification Model
ltv_xgb_model = xgb.XGBClassifier(max_depth=5, learning_rate=0.1,objective= 'multi:softprob',n_jobs=-1).fit(X_train, y_train)

print('Accuracy of XGB classifier on training set: {:.2f}'
       .format(ltv_xgb_model.score(X_train, y_train)))
print('Accuracy of XGB classifier on test set: {:.2f}'
       .format(ltv_xgb_model.score(X_test[X_train.columns], y_test)))

y_pred = ltv_xgb_model.predict(X_test)
print(classification_report(y_test, y_pred))

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']

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

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

#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']