Hakan Okay h-okay

## compare.csv

          
            CustomerID
            RFM Segment
            Recency
            T
            Frequency
            Monetary
            1M CLV
             1M Scaled CLV
             12M CLV
             12M Scaled CLV

            
              16000
              potential_loyalists
              0.0
              0.428571
              3
              2055.786667
              3843.408761
              0.258216
              39233.195047
              0.239831

            
              15061
              champions
              52.57143
              53.28571
              48
              1108.30781
              3670.30953
              0.24659
              40347.77563
              0.24664

## cltv.py
final["cltv_segment"] = pd.qcut(final["6m_scaled_clv"], 4, labels=["D", "C", "B", "A"])

## cltv.py
final = rfm[['rfm_segment']].merge(cltv_final, on='Customer ID') # Merging RFM
final.rename(columns={'scaled_clv': '6m_scaled_clv', 'clv': '6m_clv'},
             inplace=True)
final = add_clv(final, cltv_df, 1)
final = add_clv(final, cltv_df, 12)

## cltv.py
rfm = create_rfm(df)  # Creating RFM
rfm.rename(columns={'segment': 'rfm_segment'}, inplace=True)
rfm.index = rfm.index.astype('int64')

## cltv.py
# Models
bgf = BetaGeoFitter(penalizer_coef=0.001)
bgf.fit(cltv_df['frequency'],
        cltv_df['recency'],
        cltv_df['T'])

ggf = GammaGammaFitter(penalizer_coef=0.01)
ggf.fit(cltv_df['frequency'], cltv_df['monetary'])

cltv = ggf.customer_lifetime_value(bgf,

## cltv.py
replace_with_thresholds(df, 'Price')
replace_with_thresholds(df, 'Quantity')

df["TotalPrice"] = df["Quantity"] * df["Price"]

today_date = dt.datetime(2011, 12, 11) # Data we use is old. We need a proper analysis date.

cltv_df = df.groupby('Customer ID').agg(
    {'InvoiceDate': [lambda date: (date.max() - date.min()).days,
                     lambda date: (today_date - date.min()).days],

## level_based_eda.py
# Unique Sources and Frequencies
df.SOURCE.value_counts()

# Unique Prices and Frequencies
df.PRICE.value_counts()

# Unique Countries and Frequencies
df.COUNTRY.value_counts()

# Total Income Accumulated by Countries
CustomerID	RFM Segment	Recency	T	Frequency	Monetary	1M CLV	1M Scaled CLV	12M CLV	12M Scaled CLV
16000	potential_loyalists	0.0	0.428571	3	2055.786667	3843.408761	0.258216	39233.195047	0.239831
15061	champions	52.57143	53.28571	48	1108.30781	3670.30953	0.24659	40347.77563	0.24664
	final = rfm[['rfm_segment']].merge(cltv_final, on='Customer ID') # Merging RFM
	final.rename(columns={'scaled_clv': '6m_scaled_clv', 'clv': '6m_clv'},
	inplace=True)
	final = add_clv(final, cltv_df, 1)
	final = add_clv(final, cltv_df, 12)
	rfm = create_rfm(df) # Creating RFM
	rfm.rename(columns={'segment': 'rfm_segment'}, inplace=True)
	rfm.index = rfm.index.astype('int64')
	# Models
	bgf = BetaGeoFitter(penalizer_coef=0.001)
	bgf.fit(cltv_df['frequency'],
	cltv_df['recency'],
	cltv_df['T'])

	ggf = GammaGammaFitter(penalizer_coef=0.01)
	ggf.fit(cltv_df['frequency'], cltv_df['monetary'])

	cltv = ggf.customer_lifetime_value(bgf,
	replace_with_thresholds(df, 'Price')
	replace_with_thresholds(df, 'Quantity')

	df["TotalPrice"] = df["Quantity"] * df["Price"]

	today_date = dt.datetime(2011, 12, 11) # Data we use is old. We need a proper analysis date.

	cltv_df = df.groupby('Customer ID').agg(
	{'InvoiceDate': [lambda date: (date.max() - date.min()).days,
	lambda date: (today_date - date.min()).days],
	# Unique Sources and Frequencies
	df.SOURCE.value_counts()

	# Unique Prices and Frequencies
	df.PRICE.value_counts()

	# Unique Countries and Frequencies
	df.COUNTRY.value_counts()

	# Total Income Accumulated by Countries