#The process of reading the data set.
df_ = pd.read_excel(
r"C:\Users\LENOVO\PycharmProjects\DSMLBC4\datasets\online_retail_II.xlsx",
sheet_name="Year 2010-2011")
df = df_.copy()
df.info()
df.head()
from helpers.helpers import check_df
check_df(df)
from helpers.helpers import crm_data_prep
df = crm_data_prep(df)
check_df(df)
#Country selection -> [Germany]
df_ger = df[df['Country'] == "Germany"]
check_df(df_ger)
df_ger.groupby(['Invoice', 'StockCode']).agg({"Quantity": "sum"}).head(100)
df_ger.groupby(['Invoice', 'StockCode']).agg({
"Quantity": "sum"
}).unstack().iloc[0:6, 0:12]
# Control
df[(df["StockCode"] == 16016) & (df["Invoice"] == 536983)]
query = "select * from online_retail_2010_2011"
df_mysql = pd.read_sql_query(query, conn)
df.head()
df_mysql.head()
df.info()
df_mysql.info()
df_mysql["InvoiceDate"] = pd.to_datetime(df_mysql["InvoiceDate"])
df_mysql.rename(columns={"CustomerID": "Customer ID"}, inplace=True)
df.head()
from helpers.helpers import crm_data_prep
df_prep = crm_data_prep(df)
df_prep.head()
from helpers.helpers import check_df
check_df(df_prep)
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: