Miuul - Birliktelik Kuralı Öğrenimi

pip install mlxtend

import pandas as pd
from mlxtend.frequent_patterns import apriori, association_rules

pd.set_option('display.max_columns', None)
pd.set_option('display.expand_frame_repr', False)

df_ = pd.read_excel('online_retail_II.xlsx', sheet_name="Year 2010-2011")
df = df_.copy()

df.head()

df.describe().T

df.isnull().sum()

df.shape

def outlier_thresholds(dataframe, variable):
    quartile1 = dataframe[variable].quantile(0.01)
    quartile3 = dataframe[variable].quantile(0.99)
    interquartile_range = quartile3 - quartile1
    up_limit = quartile3 + 1.5 * interquartile_range
    low_limit = quartile1 - 1.5 * interquartile_range
    return low_limit, up_limit

def replace_with_thresholds(dataframe, variable):
    low_limit, up_limit = outlier_thresholds(dataframe, variable)
    dataframe.loc[(dataframe[variable] < low_limit), variable] = low_limit
    dataframe.loc[(dataframe[variable] > up_limit), variable] = up_limit
    return

def retail_data_prep(dataframe):
    dataframe.dropna(inplace=True)
    dataframe = dataframe[~dataframe['Invoice'].str.contains("C",na=False)]
    dataframe = dataframe[dataframe['Quantity'] > 0]
    dataframe = dataframe[dataframe['Price'] > 0]
    replace_with_thresholds(dataframe, "Quantity")
    replace_with_thresholds(dataframe, "Price")
    return dataframe

df = retail_data_prep(df)

df.describe().T

df_fr = df[df["Country"] == "France"]
df_fr.head()