meraldo-aliz

import pandas as pd
from lifetimes.datasets import load_dataset

transactions = load_dataset(
    filename='CDNOW_sample.txt', 
    header=None, 
    delim_whitespace=True, 
    names=['customer_id', 'customer_index', 'date', 'quantity', 'amount'],
    converters={'date': lambda x: pd.to_datetime(x, format="%Y%m%d")}
)

meraldo-aliz

from lifetimes.utils import summary_data_from_transaction_data

rfm = summary_data_from_transaction_data(transactions=transactions,
                                         customer_id_col='customer_id',
                                         datetime_col='date',
                                         monetary_value_col = 'amount',
                                         observation_period_end=pd.to_datetime('1998-06-30'),
                                         freq='W')

rfm.head(3)

meraldo-aliz

from lifetimes.utils import calibration_and_holdout_data

rfm_cal_holdout = calibration_and_holdout_data(transactions=transactions,
                                               customer_id_col='customer_id', 
                                               datetime_col='date',
                                               monetary_value_col = 'amount',
                                               freq='W',
                                               calibration_period_end='1998-01-01',
                                               observation_period_end='1998-06-30' )

meraldo-aliz

from lifetimes.utils import summary_data_from_transaction_data

rfm = summary_data_from_transaction_data(transactions=transactions,
                                         customer_id_col='customer_id',
                                         datetime_col='date',
                                         monetary_value_col = 'amount',
                                         observation_period_end=pd.to_datetime('1998-06-30'),
                                         freq='W')

rfm.head(3)

meraldo-aliz

from lifetimes import BetaGeoFitter

# instantiation of BG-NBD model
bgf = BetaGeoFitter(penalizer_coef=0.0)

# fitting of BG-NBD model
bgf.fit(frequency=rfm_cal_holdout['frequency_cal'], 
        recency=rfm_cal_holdout['recency_cal'], 
        T=rfm_cal_holdout['T_cal'])

meraldo-aliz

bgf.summary

meraldo-aliz

from lifetimes.plotting import plot_period_transactions

_ = plot_period_transactions(bgf) 

meraldo-aliz

# First, we choose a sample customer. 
sample_customer = rfm_cal_holdout.iloc[20] 

# Let's inspect his frequency, recency and T both for the calibration and observation periods:
sample_customer

meraldo-aliz

# This function calculates the conditional expected number of transactions in the given time length
n_transactions_pred = bgf.predict(t=26, # we set it to 26 weeks (the length of the observation period)
                                  frequency=sample_customer['frequency_cal'], 
                                  recency=sample_customer['recency_cal'], 
                                  T=sample_customer['T_cal'])

n_transactions_pred # = 0.7647440846242359

meraldo-aliz

alive_prob = bgf.conditional_probability_alive(frequency=sample_customer['frequency_cal'], 
                                               recency=sample_customer['recency_cal'], 
                                               T=sample_customer['T_cal'])

alive_prob # = 0.57089896