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

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

#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

#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

#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

#preparing column names for the model
all_columns = []
for column in df_data.columns:
    column = column.replace(" ", "_").replace("(", "_").replace(")", "_").replace("-", "_")
    all_columns.append(column)

df_data.columns = all_columns

glm_columns = 'gender'

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

#create a dataframe with customer id and first purchase date in tx_next
tx_next_first_purchase = tx_next.groupby('CustomerID').InvoiceDate.min().reset_index()
tx_next_first_purchase.columns = ['CustomerID','MinPurchaseDate']

#create a dataframe with customer id and last purchase date in tx_6m
tx_last_purchase = tx_6m.groupby('CustomerID').InvoiceDate.max().reset_index()
tx_last_purchase.columns = ['CustomerID','MaxPurchaseDate']

#merge two dataframes
tx_purchase_dates = pd.merge(tx_last_purchase,tx_next_first_purchase,on='CustomerID',how='left')