def calc_clv(clv_recs, end, months=12):
df = pandas.DataFrame(clv_recs)
df = df[['player_id', 'start_date', 'theo_win']]
df['theo_win'] = df['theo_win'].astype(float)
end_date = parse(end)
summary = summary_data_from_transaction_data(df,
'player_id',
'start_date',
monetary_value_col='theo_win',
observation_period_end=end_date)
bgf = BetaGeoFitter(penalizer_coef=0.0)
bgf.fit(summary['frequency'], summary['recency'], summary['T'])
ggf = GammaGammaFitter(penalizer_coef = 0)
ggf.fit(summary['frequency'], summary['monetary_value'])
ggf_clv = ggf.customer_lifetime_value(
bgf, #the model to use to predict the number of future transactions
summary['frequency'],
summary['recency'],
summary['T'],
summary['monetary_value'],
time=months,
discount_rate=0.0
)
clv_df = pandas.DataFrame(ggf_clv)
clv_df=clv_df.dropna()
clv_df[clv_df['clv']<0] = 0.0
summary=summary.merge(clv_df, left_index=True, right_index=True, how='inner')
return summary
def readGammaGammaFitterModel():
gammaGammaFitterModel = GammaGammaFitter()
gammaGammaFitterModel.load_model("GammaGammaFitterModel.pkl")
return gammaGammaFitterModel
def run_btyd(model_type, data_src, threshold_date, predict_end):
"""Run selected BTYD model on data files located in args.data_src.
Args:
model_type: model type (PARETO, BGNBD)
data_src: path to data
threshold_date: end date for training data 'YYYY-mm-dd'
predict_end: end date for predictions 'YYYY-mm-dd'
"""
train_end_date = datetime.strptime(threshold_date, '%Y-%m-%d')
predict_end_date = datetime.strptime(predict_end, '%Y-%m-%d')
# load training transaction data
summary, actual_df = load_data(data_src)
# train fitter for selected model
tf.logging.info('Fitting model...')
if model_type == PARETO:
fitter = paretonbd_model(summary)
elif model_type == BGNBD:
fitter = bgnbd_model(summary)
tf.logging.info('Done.')
#
# use trained fitter to compute actual vs predicted ltv for each user
#
# compute the number of days in the prediction period
time_days = (predict_end_date - train_end_date).days
time_months = int(math.ceil(time_days / 30.0))
# fit gamma-gamma model
tf.logging.info('Fitting GammaGamma model...')
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(summary['frequency'], summary['monetary_value'])
tf.logging.info('Done.')
ltv, rmse = predict_value(summary,
actual_df,
fitter,
ggf,
time_days,
time_months)
# output results to csv
output_file = os.path.join(data_src, OUTPUT_FILE)
ltv.to_csv(output_file, index=False)
# log results
tf.logging.info('BTYD RMSE error for %s model: %.2f', model_type, rmse)
print('RMSE prediction error: %.2f' % rmse)
def predictSpending(customerId):
# initialize the data dictionary that will be returned
data = {"success": False, "result": {"customerId": "", "y": 0.0}}
# ensure the customer ID was properly uploaded to our endpoint
if customerId:
print("* get data")
data = pandas.read_csv("sample_transactions.csv")
#data = pandas.read_json(baseURL + "/api/transactions")
#data = data.drop(columns="_id")
print("* prepare data")
# prepare and shaping the data
# columns -
# customerId
# frequency : number of repeat purchase transactions
# recency: time (in days) between first purchase and latest purchase
# T: time (in days) between first purchase and end of the period under study
# monetary_value: average transactions amount
today = pandas.to_datetime(datetime.date.today())
summaryData = summary_data_from_transaction_data(
data,
"customerId",
"transactionDate",
monetary_value_col="transactionAmount",
observation_period_end=today)
# filter the customer data that has no transaction
analysisData = summaryData[summaryData["frequency"] > 0]
# get the stat of the particular customer
customer = analysisData.loc[customerId]
# load model
ggf_loaded = GammaGammaFitter()
ggf_loaded.load_model('ggf.pkl')
# estimate the average transaction amount
predict = ggf_loaded.conditional_expected_average_profit(
customer["frequency"], customer['monetary_value'])
# add the input and predicted output to the return data
data = {
"success": True,
"result": {
"customerId": customerId,
"y": predict
}
}
# return the data dictionary as a JSON response
return flask.jsonify(data)
class transactionMonetary(object):
def summary_trans_create(self, df):
'''
Subset df on sales data, return trans summary with monetary spend
'''
sales = subset_data(df, 'OrderType', 1)
sales = sales[sales.OrderTotal>0]
transaction_data_monetary = sales[['OrderDate', 'CustomerNo', 'OrderTotal']]
self.summary_monetary = summary_data_from_transaction_data(transaction_data_monetary, 'CustomerNo', 'OrderDate', 'OrderTotal', observation_period_end='2017-02-08')
#keep customers with more than one spend
self.return_customers = self.summary_monetary[self.summary_monetary['frequency']>0]
return self.return_customers
def fit_ggf(self):
self.ggf = GammaGammaFitter(penalizer_coef = 0)
self.ggf.fit(self.return_customers['frequency'], self.return_customers['monetary_value'])
def summaryOutput(self, discount_rate=0.12, months=12):
'''
Fit beta geometric model to calculate CLV, and use GG model to calculate expected profit
Per customer
Write out CLV and profits to csv, print out averages to screen
'''
beta_model = BetaGeoFitter()
#calulate average transaction value
self.summary_monetary['avg_transaction_value'] = self.ggf.conditional_expected_average_profit(
self.summary_monetary['frequency'],
self.summary_monetary['monetary_value'])
#fit beta geo model
beta_model.fit(self.summary_monetary['frequency'], self.summary_monetary['recency'], self.summary_monetary['T'])
#calculate clv, with discount rate calulated over year (default)
disc_rate = discount_rate/months/30
self.summary_monetary['clv'] = self.ggf.customer_lifetime_value(
beta_model, #the model to use to predict the number of future transactions
self.summary_monetary['frequency'],
self.summary_monetary['recency'],
self.summary_monetary['T'],
self.summary_monetary['monetary_value'], time=months, # months
discount_rate=disc_rate # monthly discount rate ~ 12.7% annually
)
#print customer data with calculations
self.summary_monetary.to_csv("CLV_AVG_transactionValue_perCustomer.csv", index=False)
#print summary stats
print("Expected conditional average profit: {}, Average profit: {}".format(
self.ggf.conditional_expected_average_profit(
self.summary_monetary['frequency'],
self.summary_monetary['monetary_value']).mean(),
self.summary_monetary[self.summary_monetary['frequency']>0]['monetary_value'].mean()))
def trainGammaGammaModel():
summaryDataFromTransactionDataForCLV = readsummaryDataFromTransactionDataForCLV(
)
#getting those customers who have done at least one transaction with the company
shortlistedCustomers = summaryDataFromTransactionDataForCLV[
summaryDataFromTransactionDataForCLV["frequency"] > 0]
gammaGammaFitterModel = GammaGammaFitter(penalizer_coef=0.0)
gammaGammaFitterModel.fit(shortlistedCustomers["frequency"],
shortlistedCustomers["monetary_value"])
saveGammaGammaFitterModel(gammaGammaFitterModel)
def fit(self,months=96):
"""
Computes CLV estimates for the next n months and stores results in self.results
INPUT
months (int) number of months to predict, default = 96 (8 years)
"""
### PREDICT NUMBER OF PURCHASES
self.bgf = BetaGeoFitter() # see lifetimes module documentation for details
self.bgf.fit(self.data['frequency'], self.data['recency'], self.data['T'])
# 8 years = 96 months
self.data['predicted_purchases'] = self.bgf.conditional_expected_number_of_purchases_up_to_time(
months,
self.data['frequency'],
self.data['recency'],
self.data['T'])
### PREDICT FUTURE PURCHASE AMOUNT
self.ggf = GammaGammaFitter(penalizer_coef = 0)
self.ggf.fit(self.data['frequency'], self.data['monetary_value'])
# predict next transaction
self.data['predicted_trans_profit'] = self.ggf.conditional_expected_average_profit(
frequency = self.data['frequency'],
monetary_value = self.data['monetary_value'])
### ESTIMATE CLV
self.data['clv_estimation'] = self.data['predicted_trans_profit'] * self.data['predicted_purchases']
self.data['prob_alive'] = self.bgf.conditional_probability_alive(
self.data['frequency'],
self.data['recency'],
self.data['T'])
self.results = self.data.sort_values(by='clv_estimation',ascending=False)
# store results
self.results.to_csv(self.outfile2,index=False)
def estimate_clv_model(summary, model_penalizer=None):
#set default values if they are not stated
if model_penalizer is None:
model_penalizer = 0
# Building the Model using BG/NBD
bgf = BetaGeoFitter(penalizer_coef=model_penalizer)
bgf.fit(summary['frequency'], summary['recency'], summary['T'])
# There cannot be non-positive values in the monetary_value or frequency vector
summary_with_value_and_returns = summary[(summary['monetary_value']>0) & (summary['frequency']>0)]
# Setting up Gamma Gamma model
ggf = GammaGammaFitter(penalizer_coef = 0)
ggf.fit(summary_with_value_and_returns['frequency'], summary_with_value_and_returns['monetary_value'])
# Refitting the BG/NBD model with the same data if frequency, recency or T are not zero length vectors
if not (len(x) == 0 for x in [summary_with_value_and_returns['recency'],summary_with_value_and_returns['frequency'],summary_with_value_and_returns['T']]):
bgf.fit(summary_with_value_and_returns['frequency'],summary_with_value_and_returns['recency'],summary_with_value_and_returns['T'])
return [bgf, ggf]
def create_cltv_pred(dataframe, w=4, m=1):
"""
Gamagama and BGNBD model and prediction
Parameters
----------
dataframe
w: int, week information for BGNBD model
m: int, month information for gamama model
Returns
Dataframe
-------
"""
# BGNBD
dataframe = dataframe[dataframe["monetary_avg"] > 0]
dataframe["frequency"] = dataframe["frequency"].astype(int)
bgf = BetaGeoFitter(penalizer_coef=0.001)
bgf.fit(dataframe['frequency'], dataframe['recency_weekly'],
dataframe['T_weekly'])
dataframe[f'exp_sales_{w}_week'] = bgf.predict(w, dataframe['frequency'],
dataframe['recency_weekly'],
dataframe['T_weekly'])
# Gamagama - expected_average_profit
ggf = GammaGammaFitter(penalizer_coef=0.001)
ggf.fit(dataframe['frequency'], dataframe['monetary_avg'])
dataframe[
"expected_average_profit"] = ggf.conditional_expected_average_profit(
dataframe['frequency'], dataframe['monetary_avg'])
# CLTV Prediction
cltv = ggf.customer_lifetime_value(bgf,
dataframe['frequency'],
dataframe['recency_weekly'],
dataframe['T_weekly'],
dataframe['monetary_avg'],
time=m,
freq="W",
discount_rate=0.01)
dataframe[f'cltv_p_{m}_month'] = cltv
scaler = MinMaxScaler(feature_range=(1, 100))
dataframe['cltv_p_score'] = scaler.fit_transform(
dataframe[[f'cltv_p_{m}_month']])
# cltv_p Segment
dataframe['cltv_p_segment'] = pd.qcut(dataframe['cltv_p_score'],
3,
labels=['C', 'B', 'A'])
new_col = dataframe.columns[~dataframe.columns.
isin(['recency', 'frequency', 'monetary'])]
dataframe = dataframe[new_col]
return dataframe
def clv(pareto, mbg, summary):
returning_customers_summary = summary[summary['frequency'] > 0]
ggf = GammaGammaFitter(penalizer_coef=0.0)
ggf.fit(frequency=returning_customers_summary['frequency'],
monetary_value=returning_customers_summary['monetary_value'])
pred_clv_pareto = ggf.customer_lifetime_value(
transaction_prediction_model=pareto,
frequency=summary['frequency'],
recency=summary['recency'],
T=summary['T'],
monetary_value=summary['monetary_value'],
time=12,
freq="D")
pred_clv_mbg = ggf.customer_lifetime_value(
transaction_prediction_model=mbg,
frequency=summary['frequency'],
recency=summary['recency'],
T=summary['T'],
monetary_value=summary['monetary_value'],
time=12,
freq="D")
return pred_clv_pareto, pred_clv_mbg
def gg_model(rfmmod, bgf, p, f):
# Build the Model
ret_cust = rfmmod[(rfmmod['frequency'] > 0)
& (rfmmod['monetary_value'] > 0)]
ggf = GammaGammaFitter(penalizer_coef=p)
ggf.fit(ret_cust['frequency'], ret_cust['monetary_value'])
pred_clt = ggf.customer_lifetime_value(
bgf,
ret_cust['frequency'],
ret_cust['recency'],
ret_cust['T'],
ret_cust['monetary_value'],
time=12, # months
freq=f,
discount_rate=0.01)
ret_cust['predicted_cltv'] = pred_clt
ret_cust['exp_profit'] = ggf.conditional_expected_average_profit(
ret_cust['frequency'], ret_cust['monetary_value'])
ret_cust = ret_cust.sort_values('predicted_cltv', ascending=False).round(3)
return ret_cust
def create_cltv_p(dataframe):
today_date = dt.datetime(2011, 12, 11)
# recency kullanıcıya özel dinamik.
rfm = dataframe.groupby('Customer ID').agg({
'InvoiceDate': [
lambda date: (date.max() - date.min()).days, lambda date:
(today_date - date.min()).days
],
'Invoice':
lambda num: num.nunique(),
'TotalPrice':
lambda TotalPrice: TotalPrice.sum()
})
rfm.columns = rfm.columns.droplevel(0)
# recency_cltv_p
rfm.columns = ['recency_cltv_p', 'T', 'frequency', 'monetary']
# basitleştirilmiş monetary_avg
rfm["monetary"] = rfm["monetary"] / rfm["frequency"]
rfm.rename(columns={"monetary": "monetary_avg"}, inplace=True)
# BGNBD için WEEKLY RECENCY VE WEEKLY T'nin HESAPLANMASI
# recency_weekly_cltv_p
rfm["recency_weekly_cltv_p"] = rfm["recency_cltv_p"] / 7
rfm["T_weekly"] = rfm["T"] / 7
# KONTROL
rfm = rfm[rfm["monetary_avg"] > 0]
# recency filtre (daha saglıklı cltvp hesabı için)
rfm = rfm[(rfm['frequency'] > 1)]
rfm["frequency"] = rfm["frequency"].astype(int)
# BGNBD
bgf = BetaGeoFitter(penalizer_coef=0.01)
bgf.fit(rfm['frequency'], rfm['recency_weekly_cltv_p'], rfm['T_weekly'])
# exp_sales_1_month
rfm["exp_sales_1_month"] = bgf.predict(4, rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'])
# exp_sales_3_month
rfm["exp_sales_3_month"] = bgf.predict(12, rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'])
# expected_average_profit
ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(rfm['frequency'], rfm['monetary_avg'])
rfm["expected_average_profit"] = ggf.conditional_expected_average_profit(
rfm['frequency'], rfm['monetary_avg'])
# 6 aylık cltv_p
cltv = ggf.customer_lifetime_value(bgf,
rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'],
rfm['monetary_avg'],
time=6,
freq="W",
discount_rate=0.01)
rfm["cltv_p"] = cltv
# minmaxscaler
scaler = MinMaxScaler(feature_range=(1, 100))
scaler.fit(rfm[["cltv_p"]])
rfm["cltv_p"] = scaler.transform(rfm[["cltv_p"]])
# rfm.fillna(0, inplace=True)
# cltv_p_segment
rfm["cltv_p_segment"] = pd.qcut(rfm["cltv_p"], 3, labels=["C", "B", "A"])
# recency_cltv_p, recency_weekly_cltv_p
rfm = rfm[[
"recency_cltv_p", "T", "monetary_avg", "recency_weekly_cltv_p",
"T_weekly", "exp_sales_1_month", "exp_sales_3_month",
"expected_average_profit", "cltv_p", "cltv_p_segment"
]]
return rfm
fig = plt.figure(figsize=(12,8)) # plot setting width and height
id = 14620 # id = 18074 id = 14606
days_since_birth = 365
sp_trans = df.loc[df['CustomerID'] == id]
plot_history_alive(bgf, days_since_birth, sp_trans, 'InvoiceDate')
# customers who had at least one repeat purchase with us
returning_customers_summary = modeldata[modeldata['frequency']>0]
print(len(returning_customers_summary))
returning_customers_summary.shape
from lifetimes import GammaGammaFitter
ggf = GammaGammaFitter(penalizer_coef = 0)
ggf.fit(returning_customers_summary['frequency'],
returning_customers_summary['monetary_value'])
print(ggf)
returning_customers_summary = returning_customers_summary[returning_customers_summary['monetary_value']>0]
returning_customers_summary['predicted_avg_sales']=ggf.conditional_expected_average_profit(returning_customers_summary['frequency'],returning_customers_summary['monetary_value'])
# checking the expevred average value and the actual average value in the data to make sure the values are good
print(f"Expected Average sales: {returning_customers_summary['predicted_avg_sales'].mean()}")
print(f"Actual Average sales: {returning_customers_summary['monetary_value'].mean()}")
# The values seem to be fine
customer_detail['p_alive'] = mbgnbd.conditional_probability_alive(
customer_detail['frequency'], customer_detail['recency'],
customer_detail['T'])
customer_detail.head()
# In[14]:
#The Gamma-Gamma model assumes that there is no relationship between the monetary value and the purchase frequency
customer_detail[['avg_order_value', 'frequency']].corr()
# In[15]:
#It is used to estimate the average monetary value of customer transactions
from lifetimes import GammaGammaFitter
gg = GammaGammaFitter(penalizer_coef=0.001)
gg.fit(customer_detail['frequency'],
customer_detail['avg_order_value'],
verbose=True)
print(
gg.conditional_expected_average_profit(
customer_detail['frequency'],
customer_detail['avg_order_value']).head(10))
# In[16]:
customer_detail['clv'] = gg.customer_lifetime_value(
mbgnbd,
customer_detail['frequency'],
customer_detail['recency'],
#plot_frequency_recency_matrix(bgf)
#pylab.show()
#plot_probability_alive_matrix(bgf)
#pylab.show()
index = 0
val = (sys.argv[1])
for row in summary:
if row[0] == val:
break
else:
index += 1
individual = summary.iloc[index]
#print(individual)
t = 7
#print("\n\n\nselected customer probability in next week")
#print(bgf.conditional_expected_number_of_purchases_up_to_time(t,individual['frequency'],individual['recency'],individual['T']))
#summary['predicted_purchases']=(bgf.conditional_expected_number_of_purchases_up_to_time(t, summary['frequency'], summary['recency'], summary['T']))
#print (summary.head())
summary2 = summary[summary['frequency'] > 0]
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(summary2['frequency'], summary2['monetary_value'])
#print (ggf)
#print("\n\n\nSelected customer clv")
print(
ggf.conditional_expected_average_profit(individual['frequency'],
individual['monetary_value']))
#summary['clv']=(ggf.conditional_expected_average_profit(summary2['frequency'],summary2['monetary_value']))
#print(summary.head())
def create_cltv_p(dataframe):
today_date = dt.datetime(2011, 12, 11)
rfm = dataframe.groupby('Customer ID').agg({'InvoiceDate': [lambda date: (today_date - date.max()).days,
lambda date: (today_date - date.min()).days],
'Invoice': lambda num: num.nunique(),
'TotalPrice': lambda TotalPrice: TotalPrice.sum()})
rfm.columns = rfm.columns.droplevel(0)
rfm.columns = ['recency', 'T', 'frequency', 'monetary']
# CALCULATION OF MONETARY AVG & ADDING RFM INTO DF
temp_df = dataframe.groupby(["Customer ID", "Invoice"]).agg({"TotalPrice": ["mean"]})
temp_df = temp_df.reset_index()
temp_df.columns = temp_df.columns.droplevel(0)
temp_df.columns = ["Customer ID", "Invoice", "total_price_mean"]
temp_df2 = temp_df.groupby(["Customer ID"], as_index=False).agg({"total_price_mean": ["mean"]})
temp_df2.columns = temp_df2.columns.droplevel(0)
temp_df2.columns = ["Customer ID", "monetary_avg"]
rfm = rfm.merge(temp_df2, how="left", on="Customer ID")
rfm.set_index("Customer ID", inplace=True)
rfm.index = rfm.index.astype(int)
# CALCULATION OF WEEKLY RECENCY AND WEEKLY T FOR BGNBD
rfm["recency_weekly"] = rfm["recency"] / 7
rfm["T_weekly"] = rfm["T"] / 7
# CONTROL
rfm = rfm[rfm["monetary_avg"] > 0]
rfm["frequency"] = rfm["frequency"].astype(int)
# BGNBD
bgf = BetaGeoFitter(penalizer_coef=0.001)
bgf.fit(rfm['frequency'],
rfm['recency_weekly'],
rfm['T_weekly'])
# exp_sales_1_month
rfm["exp_sales_1_month"] = bgf.predict(4,
rfm['frequency'],
rfm['recency_weekly'],
rfm['T_weekly'])
# exp_sales_3_month
rfm["exp_sales_3_month"] = bgf.predict(12,
rfm['frequency'],
rfm['recency_weekly'],
rfm['T_weekly'])
# expected_average_profit
ggf = GammaGammaFitter(penalizer_coef=0.001)
ggf.fit(rfm['frequency'], rfm['monetary_avg'])
rfm["expected_average_profit"] = ggf.conditional_expected_average_profit(rfm['frequency'],
rfm['monetary_avg'])
# 6 MONTHS cltv_p
cltv = ggf.customer_lifetime_value(bgf,
rfm['frequency'],
rfm['recency_weekly'],
rfm['T_weekly'],
rfm['monetary_avg'],
time=6,
freq="W",
discount_rate=0.01)
rfm["cltv_p"] = cltv
# minmaxscaler
scaler = MinMaxScaler(feature_range=(1, 100))
scaler.fit(rfm[["cltv_p"]])
rfm["cltv_p"] = scaler.transform(rfm[["cltv_p"]])
# cltv_p_segment
rfm["cltv_p_segment"] = pd.qcut(rfm["cltv_p"], 3, labels=["C", "B", "A"])
rfm = rfm[["monetary_avg", "T", "recency_weekly", "T_weekly",
"exp_sales_1_month", "exp_sales_3_month", "expected_average_profit",
"cltv_p", "cltv_p_segment"]]
return rfm
calibration_data.head()
from lifetimes.plotting import plot_calibration_purchases_vs_holdout_purchases
bgf.fit(calibration_data['frequency_cal'], calibration_data['recency_cal'],
calibration_data['T_cal'])
plot_calibration_purchases_vs_holdout_purchases(bgf, calibration_data)
with_frequency = data[data['frequency'] > 0]
with_frequency.head()
with_frequency[['monetary_value', 'frequency']].corr()
from lifetimes import GammaGammaFitter
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(with_frequency['frequency'], with_frequency['monetary_value'])
ggf
ggf.conditional_expected_average_profit(data['frequency'],
data['monetary_value']).head(20)
"Expected conditional average profit: %s, Average profit: %s" % (
ggf.conditional_expected_average_profit(data['frequency'],
data['monetary_value']).mean(),
data[data['frequency'] > 0]['monetary_value'].mean())
bgf.fit(data['frequency'], data['recency'], data['T'])
ggf.customer_lifetime_value(
# Ranking reps from best to worst
# ==========================================================================
t = 1
df["predicted_purchases"] = bgf.conditional_expected_number_of_purchases_up_to_time(
t, df["FREQUENCY"], df["RECENCY"], df["T"])
df.sort_values(by="predicted_purchases").tail(10)
# ==========================================================================
# Gamma Gamme Model
# Model assumes that there is no relationship between the monetary value and the purchase frequency
# ==========================================================================
df[["MONETARY_VALUE", "FREQUENCY"]].corr()
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(df["FREQUENCY"], df["MONETARY_VALUE"])
ggf.conditional_expected_average_profit(df["FREQUENCY"],
df["MONETARY_VALUE"]).head(10)
print("Expected conditional average profit: %s, Average profit: %s" %
(ggf.conditional_expected_average_profit(df["FREQUENCY"],
df["MONETARY_VALUE"]).mean(),
df[df["FREQUENCY"] > 0]["MONETARY_VALUE"].mean()))
bgf.fit(df["FREQUENCY"], df["RECENCY"], df["T"])
pred = ggf.customer_lifetime_value(
bgf, #the model to use to predict the number of future transactions
df["FREQUENCY"],
from lifetimes import BetaGeoFitter
bgf = BetaGeoFitter(penalizer_coef=0.0)
bgf.fit(data['frequency'], data['recency'], data['T'])
future_horizon = 10000
data['predicted_purchases'] = bgf.predict(future_horizon, data['frequency'],
data['recency'], data['T'])
data.head()
from lifetimes import GammaGammaFitter
returning_customers_summary = data[data['frequency'] > 0]
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(returning_customers_summary['frequency'],
returning_customers_summary['monetary_value'])
transaction_spend = ggf.conditional_expected_average_profit(
data['frequency'], data['monetary_value']).mean()
print(transaction_spend)
customers_pm = customers_ac.join(data['predicted_purchases'],
on='id',
how='left').drop(columns='clv')
customers_pm['clv'] = customers_pm \
.apply(
lambda x: x['predicted_purchases'] * transaction_spend,
axis = 1)
customers_pm.tail()
def fit_ggf(self):
self.ggf = GammaGammaFitter(penalizer_coef = 0)
self.ggf.fit(self.return_customers['frequency'], self.return_customers['monetary_value'])
def get_clv(oracle_conn_id, src_client_id, storage_bucket, ds, **context):
import matplotlib.pyplot
matplotlib.pyplot.ioff()
##
from lifetimes.utils import calibration_and_holdout_data
from lifetimes.plotting import plot_frequency_recency_matrix
from lifetimes.plotting import plot_probability_alive_matrix
from lifetimes.plotting import plot_calibration_purchases_vs_holdout_purchases
from lifetimes.plotting import plot_period_transactions
from lifetimes.plotting import plot_history_alive
from lifetimes.plotting import plot_cumulative_transactions
from lifetimes.utils import expected_cumulative_transactions
from lifetimes.utils import summary_data_from_transaction_data
from lifetimes import BetaGeoFitter
from lifetimes import GammaGammaFitter
import datetime
import pandas as pd
import datalab.storage as gcs
conn = OracleHook(oracle_conn_id=oracle_conn_id).get_conn()
print(src_client_id, context)
query = context['templates_dict']['query']
data = pd.read_sql(query, con=conn)
data.columns = data.columns.str.lower()
print(data.head())
# Calculate RFM values#
calibration_end_date = datetime.datetime(2018, 5, 24)
training_rfm = calibration_and_holdout_data(
transactions=data,
customer_id_col='src_user_id',
datetime_col='pickup_date',
calibration_period_end=calibration_end_date,
freq='D',
monetary_value_col='price_total')
bgf = BetaGeoFitter(penalizer_coef=0.0)
bgf.fit(training_rfm['frequency_cal'], training_rfm['recency_cal'],
training_rfm['T_cal'])
print(bgf)
# Matrix charts
plot_period_transactions_chart = context.get("ds_nodash") + str(
src_client_id) + '_plot_period_transactions_chart.svg'
plot_frequency_recency_chart = context.get("ds_nodash") + str(
src_client_id) + '_plot_frequency_recency_matrix.svg'
plot_probability_chart = context.get("ds_nodash") + str(
src_client_id) + '_plot_probability_alive_matrix.svg'
plot_calibration_vs_holdout_chart = context.get("ds_nodash") + str(
src_client_id) + '_plot_calibration_vs_holdout_purchases.svg'
ax0 = plot_period_transactions(bgf, max_frequency=30)
ax0.figure.savefig(plot_period_transactions_chart, format='svg')
ax1 = plot_frequency_recency_matrix(bgf)
ax1.figure.savefig(plot_frequency_recency_chart, format='svg')
ax2 = plot_probability_alive_matrix(bgf)
ax2.figure.savefig(plot_probability_chart, format='svg')
ax3 = plot_calibration_purchases_vs_holdout_purchases(bgf,
training_rfm,
n=50)
ax3.figure.savefig(plot_calibration_vs_holdout_chart, format='svg')
full_rfm = summary_data_from_transaction_data(
data,
customer_id_col='src_user_id',
datetime_col='pickup_date',
monetary_value_col='price_total',
datetime_format=None,
observation_period_end=None,
freq='D')
returning_full_rfm = full_rfm[full_rfm['frequency'] > 0]
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(returning_full_rfm['frequency'],
returning_full_rfm['monetary_value'])
customer_lifetime = 30 # expected number of months lifetime of a customer
clv = ggf.customer_lifetime_value(
bgf, #the model to use to predict the number of future transactions
full_rfm['frequency'],
full_rfm['recency'],
full_rfm['T'],
full_rfm['monetary_value'],
time=customer_lifetime, # months
discount_rate=0.01 # monthly discount rate ~ 12.7% annually
).sort_values(ascending=False)
full_rfm_with_value = full_rfm.join(clv)
full_rfm_file = context.get("ds_nodash") + "-src_client_id-" + str(
src_client_id) + '-icabbi-test.csv'
full_rfm_with_value.to_csv(full_rfm_file)
GoogleCloudStorageHook(
google_cloud_storage_conn_id='google_conn_default').upload(
bucket=storage_bucket,
object=str(src_client_id) + "/" + context.get("ds_nodash") + "/" +
full_rfm_file,
filename=full_rfm_file)
GoogleCloudStorageHook(
google_cloud_storage_conn_id='google_conn_default').upload(
bucket=storage_bucket,
object=str(src_client_id) + "/" + context.get("ds_nodash") + "/" +
plot_period_transactions_chart,
filename=full_rfm_file)
GoogleCloudStorageHook(
google_cloud_storage_conn_id='google_conn_default').upload(
bucket=storage_bucket,
object=str(src_client_id) + "/" + context.get("ds_nodash") + "/" +
plot_frequency_recency_chart,
filename=full_rfm_file)
GoogleCloudStorageHook(
google_cloud_storage_conn_id='google_conn_default').upload(
bucket=storage_bucket,
object=str(src_client_id) + "/" + context.get("ds_nodash") + "/" +
plot_probability_chart,
filename=full_rfm_file)
GoogleCloudStorageHook(
google_cloud_storage_conn_id='google_conn_default').upload(
bucket=storage_bucket,
object=str(src_client_id) + "/" + context.get("ds_nodash") + "/" +
plot_calibration_vs_holdout_chart,
filename=full_rfm_file)
# Tahmin edilen frekans değeri combined_data'ya ekleme
combined_data["frequency_predict"] = predicted_freq
combined_data.head()
##############################################################
# GAMMA GAMMA MODEL
##############################################################
# Gamma Gamma'yı kullanabileceğimizden emin olmak için, frekans ve parasal değerlerin
# ilişkili olup olmadığını kontrol etmemiz gerekir. (?)
combined_data[['monetary_value_cal', 'frequency_cal']].corr()
# Korelasyon düşük, devam
#Model fit
ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(combined_data['frequency_cal'], combined_data['monetary_value_cal'])
#Prediction
monetary_pred = ggf.conditional_expected_average_profit(
combined_data['frequency_cal'], combined_data['monetary_value_cal'])
# Actual values ile predicted values gözlemlemek için yeni bir dataframe oluşturma
df_comp_m = pd.DataFrame()
df_comp_m["ActualMonetary"] = combined_data['monetary_value_holdout']
df_comp_m["Predicted"] = monetary_pred
df_comp_m.head(20)
print("Expected Average Sales: %s" % monetary_pred.mean())
print("Actual Average Sales: %s" %
combined_data["monetary_value_holdout"].mean())
lf_tx_data[['monetary_value', 'frequency']].corr()
# In[93]:
#Shortlist customers who had at least one repeat purchase with the company.
shortlisted_customers = lf_tx_data[lf_tx_data['frequency'] > 0]
print(shortlisted_customers.head().reset_index())
print("-----------------------------------------")
print("The Number of Returning Customers are: ", len(shortlisted_customers))
# In[94]:
#Train gamma-gamma model by taking into account the monetary_value.
from lifetimes import GammaGammaFitter
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(shortlisted_customers['frequency'],
shortlisted_customers['monetary_value'])
print(ggf)
# In[95]:
#After applying Gamma-Gamma model, now we can estimate average transaction value for each customer.
print(
ggf.conditional_expected_average_profit(
lf_tx_data['frequency'], lf_tx_data['monetary_value']).head(10))
# In[96]:
lf_tx_data['pred_txn_value'] = round(
ggf.conditional_expected_average_profit(lf_tx_data['frequency'],
from lifetimes.plotting import plot_history_alive
id = 14096
days_since_birth = 200
sp_trans = transaction_data.loc[transaction_data['CustomerID'] == id]
plot_history_alive(bgf, days_since_birth, sp_trans, 'InvoiceDate')
plt.savefig('history_alive.png', dpi=200)
plt.clf()
plt.cla()
plt.close()
returning_customers_summary = data.loc[data['frequency'] > 0]
from lifetimes import GammaGammaFitter
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(returning_customers_summary['frequency'],
returning_customers_summary['monetary_value'])
print(ggf)
bgf.fit(returning_customers_summary['frequency'],
returning_customers_summary['recency'], returning_customers_summary['T'])
clv = ggf.customer_lifetime_value(
bgf, # the model to use to predict the number of future transactions
returning_customers_summary['frequency'],
returning_customers_summary['recency'],
returning_customers_summary['T'],
returning_customers_summary['monetary_value'],
time=12, # months
discount_rate=0.01 # monthly discount rate ~ 12.7% annually
def generate_clv_table(data, clv_prediction_time=None, model_penalizer=None):
#set default values if they are not stated
if clv_prediction_time is None:
clv_prediction_time = 12
if model_penalizer is None:
model_penalizer = 0
# Reformat csv as a Pandas dataframe
#data = pd.read_csv(csv_file)
#Remove non search sessions
data = data[data['Searches'] > 0]
max_date = data['activity_date'].max()
# Using "summary_data_from_transaction_data" function to agregate the activity stream into the appropriate metrics
# Model requires 'activity_date' column name. For our purpose this is synonymous with submission_date.
summary = summary_data_from_transaction_data(
data,
'client_id',
'activity_date',
'Revenue',
observation_period_end=max_date)
# Building the Model using BG/NBD
bgf = BetaGeoFitter(penalizer_coef=model_penalizer)
bgf.fit(summary['frequency'], summary['recency'], summary['T'])
# Conditional expected purchases
# These are the expected purchases expected from each individual given the time specified
# t = days in to future
t = 14
summary[
'predicted_searches'] = bgf.conditional_expected_number_of_purchases_up_to_time(
t, summary['frequency'], summary['recency'], summary['T'])
#Conditional Alive Probability
summary['alive_prob'] = summary.apply(
lambda row: calc_alive_prob(row, bgf), axis=1)
summary['alive_prob'] = summary['alive_prob'].astype(float)
#print summary['alive_prob']
# There cannot be non-positive values in the monetary_value or frequency vector
summary_with_value_and_returns = summary[(summary['monetary_value'] > 0)
& (summary['frequency'] > 0)]
# There cannot be zero length vectors in one of frequency, recency or T
#summary_with_value_and_returns =
#print summary_with_value_and_returns[
# (len(summary_with_value_and_returns['recency'])>0) &
# (len(summary_with_value_and_returns['frequency'])>0) &
# (len(summary_with_value_and_returns['T'])>0)
#]
if any(
len(x) == 0 for x in [
summary_with_value_and_returns['recency'],
summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['T']
]):
logger.debug(data['client_id'])
# Setting up Gamma Gamma model
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['monetary_value'])
# Output average profit per tranaction by client ID
ggf_output = ggf.conditional_expected_average_profit(
summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['monetary_value'])
# Refitting the BG/NBD model with the same data if frequency, recency or T are not zero length vectors
if not (len(x) == 0 for x in [
summary_with_value_and_returns['recency'],
summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['T']
]):
bgf.fit(summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['recency'],
summary_with_value_and_returns['T'])
# Getting Customer lifetime value using the Gamma Gamma output
# NOTE: the time can be adjusted, but is currently set to 12 months
customer_predicted_value = ggf.customer_lifetime_value(
bgf, #the model to use to predict the number of future transactions
summary_with_value_and_returns['frequency'],
summary_with_value_and_returns['recency'],
summary_with_value_and_returns['T'],
summary_with_value_and_returns['monetary_value'],
time=clv_prediction_time, # months
discount_rate=0.01 # monthly discount rate ~ 12.7% annually
)
# Converting to dataframe
df_cpv = pd.DataFrame({
'client_id': customer_predicted_value.index,
'pred_values': customer_predicted_value.values
})
# Setting client_id as index
df_cpv = df_cpv.set_index('client_id')
# Merge with original summary
df_merged = pd.merge(summary,
df_cpv,
left_index=True,
right_index=True,
how='outer')
# Historical CLV
data_hist = data.groupby(
['client_id'])['Searches',
'Revenue'].apply(lambda x: x.astype(float).sum())
# Merge with original summary
df_final = pd.merge(df_merged,
data_hist,
left_index=True,
right_index=True,
how='outer')
# Prevent NaN on the pred_clv column
df_final.pred_values[df_final.frequency == 0] = 0.0
# Create column that combines historical and predicted customer value
df_final['total_clv'] = df_final['pred_values'] + df_final['Revenue']
# Create column which calculates in days the number of days since they were last active
df_final['last_active'] = df_final['T'] - df_final['recency']
# Create a column which labels users inactive over 14 days as "Expired" ELSE "Active"
df_final['user_status'] = np.where(df_final['last_active'] > 14, 'Expired',
'Active')
# Add column with date of calculation
# Set calc_date to max submission date
df_final['calc_date'] = max_date.date() #pd.Timestamp('today').date()
# Rename columns as appropriate
df_final.columns = [
'frequency', 'recency', 'customer_age', 'avg_session_value',
'predicted_searches_14_days', 'alive_probability',
'predicted_clv_12_months', 'historical_searches', 'historical_clv',
'total_clv', 'days_since_last_active', 'user_status', 'calc_date'
]
#Prevent non returning customers from having 100% alive probability
df_final.alive_probability[df_final.frequency == 0] = 0.0
return df_final
class CLV(object):
"""
INPUT
pmg_num (int) the product market group number, default = 1
outfile1 (str) the filename indicating where to store the raw data before analysis, default = '../data/clvtrainingset01.csv'
outfile2 (str) the filename containing the results, default = '../data/clv01.csv'
date_range (list) the start date and end date of the years to analyze, default = ['2008-09-01','2016-09-01']
attributes other than those listed above
self.data (DataFrame) a pandas DataFrame object of the data to be used for analysis
self.bgf (from lifetimes) a statistical model object from the lifetimes package
self.ggf (from lifetimes) a statistical model object from the lifetimes package
self.results (DataFrame) a pandas DataFrame object of the results of analysis
"""
def __init__(self,pmg_num=1,outfile1='../data/clvtrainingset01.csv',outfile2='../data/clv01.csv',date_range=['2008-09-01','2016-09-01']):
self.pmg_num = pmg_num
# outfile1 stores a clean version of the raw data used for analysis; this is important for reproducibility
self.outfile1 = outfile1
# outfile2 stores the clv estimation results
self.outfile2 = outfile2
self.date_range = date_range
self.data = None
self.bgf = None
self.ggf = None
self.results = None
def get_data_from_server(self,cmd=None):
"""
Gets data from sales_db and stores the query results in self.data
INPUT
cmd (str) the default sql query is below
The default query has been replaced. The original query was an 8 line select command.
"""
# server name
dsn = "THE SERVER NAME"
cnxn_name = "DSN=%s" % dsn
connection = odbc.connect(cnxn_name) # use to access the database
c = connection.cursor() # generate cursor object
# Grab transaction data from Postgres
if not cmd:
cmd = """SQL DEFAULT COMMAND GOES HERE""" % (self.pmg_num,self.date_range[0],self.date_range[1])
c.execute(cmd) # execute the sql command
# list to store the query data
transaction_data = []
# create a dictionary to convert customer ids to name
to_name = dict(np.genfromtxt('../data/names.csv',dtype=str,delimiter='\t'))
for row in c:
cust, rsv_date, sales = row # pull data from each row of the query data
cust_id = str(int(cust))
name = to_name[cust_id]
# check to see if customer is inactive
if use(name):
rsv_date1_readable = rsv_date.strftime('%Y-%m-%d') # date formatting
sales_float = float(sales) # convert to float; represents the transaction amount
transaction_data.append({"id":cust, "date":rsv_date, "sales":sales_float}) # add dictionary of data to list
# convert to dataframe
df = pd.DataFrame(transaction_data, columns=['id', 'date', 'sales'])
# store results
df.to_csv(self.outfile1,index=False)
# IMPORTANT: use correct observation_period_end date
self.data = summary_data_from_transaction_data(df, 'id', 'date', 'sales', observation_period_end=self.date_range[1], freq='M')
def get_data_from_file(self,filename,**kwargs):
df = pd.read_csv(filename,**kwargs)
self.data = summary_data_from_transaction_data(df, 'id', 'date', 'sales', observation_period_end=self.date_range[1], freq='M')
def fit(self,months=96):
"""
Computes CLV estimates for the next n months and stores results in self.results
INPUT
months (int) number of months to predict, default = 96 (8 years)
"""
### PREDICT NUMBER OF PURCHASES
self.bgf = BetaGeoFitter() # see lifetimes module documentation for details
self.bgf.fit(self.data['frequency'], self.data['recency'], self.data['T'])
# 8 years = 96 months
self.data['predicted_purchases'] = self.bgf.conditional_expected_number_of_purchases_up_to_time(
months,
self.data['frequency'],
self.data['recency'],
self.data['T'])
### PREDICT FUTURE PURCHASE AMOUNT
self.ggf = GammaGammaFitter(penalizer_coef = 0)
self.ggf.fit(self.data['frequency'], self.data['monetary_value'])
# predict next transaction
self.data['predicted_trans_profit'] = self.ggf.conditional_expected_average_profit(
frequency = self.data['frequency'],
monetary_value = self.data['monetary_value'])
### ESTIMATE CLV
self.data['clv_estimation'] = self.data['predicted_trans_profit'] * self.data['predicted_purchases']
self.data['prob_alive'] = self.bgf.conditional_probability_alive(
self.data['frequency'],
self.data['recency'],
self.data['T'])
self.results = self.data.sort_values(by='clv_estimation',ascending=False)
# store results
self.results.to_csv(self.outfile2,index=False)
def plot_matrices(self):
"""
plots three matrices:
probability alive matrix: displays the probability that a customer is active
frequency recency matrix: displays frequency and recency with color corresponding
to monetary value
period transactions: displays predicted and actual transaction values over time
(check documentation in lifetimes for more details)
"""
plot_probability_alive_matrix(self.bgf,cmap='viridis')
plot_frequency_recency_matrix(self.bgf,cmap='viridis')
plot_period_transactions(self.bgf)
cltv.sort_values (by="expected_number_of_purchases", ascending=False).head ()
# Expected sales for whole company for 1 week
bgf.conditional_expected_number_of_purchases_up_to_time (4,
cltv["frequency"],
cltv["recency_weekly"],
cltv["T_weekly"]).sort_values (ascending=False).sum ()
plot_period_transactions (bgf)
plt.show ()
######
# GAMMA-GAMMA
#####
ggf = GammaGammaFitter (penalizer_coef=0.01)
ggf.fit (cltv["frequency"], cltv["monetary_avg"])
cltv["expected_average_profit"] = ggf.conditional_expected_average_profit (cltv["frequency"], cltv["monetary_avg"])
cltv.sort_values (by="expected_average_profit", ascending=False).head ()
###########
# 4. CLTV calculation with BG-NBD and GG models
###########
cltv["cltv_six_months"] = ggf.customer_lifetime_value (bgf,
cltv["frequency"],
cltv["recency_weekly"],
cltv["T_weekly"],
cltv["monetary_avg"],
time=6,
recency = T - df.groupby("customer")[["step"]].min()
monetary = df.groupby(["customer", "step"])[["amount"]].mean() \
.reset_index() \
.groupby("customer")[["amount"]] \
.mean()
frequency = df.drop_duplicates(subset=["customer", "step"],
keep="first").groupby(["customer"]) \
.count() - 1
recency.rename(columns={"step": "recency"}, inplace=True)
frequency.rename(columns={"step": "frequency"}, inplace=True)
T.rename(columns={"step": "T"}, inplace=True)
monetary.rename(columns={"amount": "monetary_value"}, inplace=True)
df_rfm = pd.concat([recency, T, monetary, frequency], axis=1)
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(frequency=df_rfm["frequency"],
monetary_value=df_rfm["monetary_value"])
df_rfm["expected_monetary_value"] = df_rfm.apply(
lambda row: ggf.conditional_expected_average_profit(
row["frequency"], row["monetary_value"]),
axis=1)
bgf = BetaGeoFitter(penalizer_coef=1)
bgf.fit(frequency=df_rfm["frequency"],
recency=df_rfm["recency"],
T=df_rfm["T"])
df_rfm[
"pred_nb_purchases"] = bgf.conditional_expected_number_of_purchases_up_to_time(
def create_cltv_p(dataframe):
today_date = dt.datetime(2011, 12, 11)
rfm = dataframe.groupby('Customer ID').agg({
'InvoiceDate': [
lambda date: (date.max() - date.min()).days, lambda date:
(today_date - date.min()).days
],
'Invoice':
lambda num: num.nunique(),
'TotalPrice':
lambda price: price.sum()
})
rfm.columns = rfm.columns.droplevel(0)
rfm.columns = ['recency_cltv_p', 'T', 'frequency', 'monetary']
rfm['monetary'] = rfm['monetary'] / rfm['frequency']
rfm.rename(columns={'monetary': 'monetary_avg'}, inplace=True)
rfm["recency_weekly_cltv_p"] = rfm['recency_cltv_p'] / 7
rfm['T_weekly'] = rfm['T'] / 7
rfm = rfm[rfm['monetary_avg'] > 0]
rfm = rfm[(rfm['frequency'] > 1)]
rfm['frequency'] = rfm['frequency'].astype(int)
#BGNBD
bgf = BetaGeoFitter(penalizer_coef=0.01)
bgf.fit(rfm['frequency'], rfm['recency_weekly_cltv_p'], rfm['T_weekly'])
rfm["exp_sales_1_month"] = bgf.predict(4, rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'])
rfm["exp_sales_3_month"] = bgf.predict(12, rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'])
#Gamma Gamma
ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(rfm['frequency'], rfm['monetary_avg'])
rfm["expected_average_profit"] = ggf.conditional_expected_average_profit(
rfm['frequency'], rfm['monetary_avg'])
cltv = ggf.customer_lifetime_value(bgf,
rfm['frequency'],
rfm['recency_weekly_cltv_p'],
rfm['T_weekly'],
rfm['monetary_avg'],
time=6,
freq='W',
discount_rate=0.01)
rfm["cltv_p"] = cltv
scaler = MinMaxScaler(feature_range=(1, 100))
scaler.fit(rfm[["cltv_p"]])
rfm["cltv_p"] = scaler.transform(rfm[["cltv_p"]])
rfm["cltv_p_segment"] = pd.qcut(rfm["cltv_p"], 3, labels=["C", "B", "A"])
rfm = rfm[[
"recency_cltv_p", "T", "monetary_avg", "recency_weekly_cltv_p",
"T_weekly", "exp_sales_1_month", "exp_sales_3_month",
"expected_average_profit", "cltv_p", "cltv_p_segment"
]]
return rfm
bgf.fit(summary_cal_holdout['frequency_cal'],
summary_cal_holdout['recency_cal'], summary_cal_holdout['T_cal'])
plot_calibration_purchases_vs_holdout_purchases(bgf, summary_cal_holdout)
# Visualization
plot_frequency_recency_matrix(bgf)
plot_probability_alive_matrix(bgf)
plt.show()
### Gamma-Gamma model###
returning_customers_summary = data[data['frequency'] > 0]
returning_customers_summary[[
'monetary_value', 'frequency'
]].corr() # Correlation between monetary value and the purchase frequency.
ggf = GammaGammaFitter(penalizer_coef=0)
ggf.fit(returning_customers_summary['frequency'],
returning_customers_summary['monetary_value'])
print(ggf)
# estimate the average transaction value
print(
ggf.conditional_expected_average_profit(data['frequency'],
data['monetary_value']).head(10))
# refit the BG model to the summary_with_money_value dataset
bgf.fit(data['frequency'], data['recency'], data['T'])
CLV_12M = ggf.customer_lifetime_value(
bgf, # the model to use to predict the number of future transactions
data['frequency'],
def create_cltv_p(dataframe):
today_date = dt.datetime(2011, 12, 11)
# recency user-specific
rfm = dataframe.groupby('Customer ID').agg({'InvoiceDate': [lambda date: (date.max() - date.min()).days, # "recency_cltv_p"
lambda date: (today_date - date.min()).days], # "T"
'Invoice': lambda num: num.nunique(), # "frequency"
'TotalPrice': lambda TotalPrice: TotalPrice.sum()}) # "monetary"
rfm.columns = rfm.columns.droplevel(0)
# recency_cltv_p
rfm.columns = ["recency_cltv_p", "T", "frequency", "monetary"]
# Simplified monetary_avg (since Gamma-Gamma model requires this way)
rfm["monetary"] = rfm["monetary"] / rfm["frequency"]
rfm.rename(columns={"monetary": "monetary_avg"}, inplace=True)
# Calculating WEEKLY RECENCY VE WEEKLY T for BG/NBD MODEL
# recency_weekly_cltv_p
rfm["recency_weekly_cltv_p"] = rfm["recency_cltv_p"] / 7
rfm["T_weekly"] = rfm["T"] / 7
# CHECK IT OUT! Monetary avg must be positive
rfm = rfm[rfm["monetary_avg"] > 0]
# recency filter
rfm = rfm[(rfm["frequency"] > 1)]
rfm["frequency"] = rfm["frequency"].astype(int) # converting it to integer just in case!
# Establishing the BGNBD Model
bgf = BetaGeoFitter(penalizer_coef=0.01)
bgf.fit(rfm["frequency"],
rfm["recency_weekly_cltv_p"],
rfm["T_weekly"])
# exp_sales_1_month
rfm["exp_sales_1_month"] = bgf.predict(4,
rfm["frequency"],
rfm["recency_weekly_cltv_p"],
rfm["T_weekly"])
# exp_sales_3_month
rfm["exp_sales_3_month"] = bgf.predict(12,
rfm["frequency"],
rfm["recency_weekly_cltv_p"],
rfm["T_weekly"])
# Establishing Gamma-Gamma Model calculates=> Expected Average Profit
ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(rfm["frequency"], rfm["monetary_avg"])
rfm["expected_average_profit"] = ggf.conditional_expected_average_profit(rfm["frequency"],
rfm["monetary_avg"])
# CLTV Pred for 6 months
cltv = ggf.customer_lifetime_value(bgf,
rfm["frequency"],
rfm["recency_weekly_cltv_p"],
rfm["T_weekly"],
rfm["monetary_avg"],
time=6,
freq="W",
discount_rate=0.01)
rfm["cltv_p"] = cltv
# Minmaxscaler
scaler = MinMaxScaler(feature_range=(1, 100))
scaler.fit(rfm[["cltv_p"]])
rfm["cltv_p"] = scaler.transform(rfm[["cltv_p"]])
# rfm.fillna(0, inplace=True)
# cltv_p_segment
rfm["cltv_p_segment"] = pd.qcut(rfm["cltv_p"], 3, labels=["C", "B", "A"])
# recency_cltv_p, recency_weekly_cltv_p
rfm = rfm[["recency_cltv_p", "T", "monetary_avg", "recency_weekly_cltv_p", "T_weekly",
"exp_sales_1_month", "exp_sales_3_month", "expected_average_profit",
"cltv_p", "cltv_p_segment"]]
return rfm
rfm_cltv["T_weekly"]).sum()
# 2082.05
# ==================================================================================
# Evaluating the Predictive Results?
# ==================================================================================
plot_period_transactions(bgf)
plt.show()
# ##################################
# Establishing the GAMMA-GAMMA MODEL ==> Expected Average Profit!
# ##################################
ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(rfm_cltv["Frequency"], rfm_cltv["monetary_avg"])
# <lifetimes.GammaGammaFitter: fitted with 4338 subjects, p: 3.54, q: 1.00, v: 3.25>
# =============================================
# ⭐ 10 most expected average profitable customers
# =============================================
ggf.conditional_expected_average_profit(rfm_cltv["Frequency"],
rfm_cltv["monetary_avg"]).sort_values(ascending=False).head(10)
# Customer ID
# 16000 1188.52359
# 16532 1123.69478
# 15749 970.89486
#plot_probability_alive_matrix(bgf)
#pylab.show()
index=0
val=(sys.argv[1])
for row in summary:
if row[0] == val:
break
else :
index+=1
individual=summary.iloc[index]
#print(individual)
t=7
#print("\n\n\nselected customer probability in next week")
print(bgf.conditional_expected_number_of_purchases_up_to_time(t,individual['frequency'],individual['recency'],individual['T']))
#summary['predicted_purchases']=(bgf.conditional_expected_number_of_purchases_up_to_time(t, summary['frequency'], summary['recency'], summary['T']))
#print (summary.head())
summary2 = summary[summary['frequency']>0]
ggf = GammaGammaFitter(penalizer_coef = 0)
ggf.fit(summary2['frequency'],
summary2['monetary_value'])
#print (ggf)
#print("\n\n\nSelected customer clv")
#print(ggf.conditional_expected_average_profit(individual['frequency'],individual['monetary_value']))
#summary['clv']=(ggf.conditional_expected_average_profit(summary2['frequency'],summary2['monetary_value']))
#print(summary.head())