karamanbk

karamanbk

from datetime import datetime, timedelta,date
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
from __future__ import division

import warnings
warnings.filterwarnings("ignore")

karamanbk

karamanbk

karamanbk

#train & test split
tx_class = tx_class.drop('NextPurchaseDay',axis=1)
X, y = tx_class.drop('NextPurchaseDayRange',axis=1), tx_class.NextPurchaseDayRange
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=44)

#create an array of models
models = []
models.append(("LR",LogisticRegression()))
models.append(("NB",GaussianNB()))
models.append(("RF",RandomForestClassifier()))

karamanbk

#get max purchase date for Recency and create a dataframe
tx_max_purchase = tx_6m.groupby('CustomerID').InvoiceDate.max().reset_index()
tx_max_purchase.columns = ['CustomerID','MaxPurchaseDate']

#find the recency in days and add it to tx_user
tx_max_purchase['Recency'] = (tx_max_purchase['MaxPurchaseDate'].max() - tx_max_purchase['MaxPurchaseDate']).dt.days
tx_user = pd.merge(tx_user, tx_max_purchase[['CustomerID','Recency']], on='CustomerID')

#plot recency
plot_data = [

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')

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

#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'