USML4

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import os

df= pd.read_csv(r"C:/Users/chava/Downloads/Groceries_dataset.csv")

print(df.head())

basket = df.groupby(['Member_number', 'Date'])['itemDescription'].apply(list).reset_index()
transactions = basket['itemDescription'].tolist()
print(transactions)

from mlxtend.preprocessing import TransactionEncoder
te = TransactionEncoder()
te_array = te.fit(transactions).transform(transactions)
df_encoded = pd.DataFrame(te_array, columns=te.columns_)

from mlxtend.frequent_patterns import apriori
frequent_itemsets = apriori(df_encoded, min_support=0.01, use_colnames=True)
print("Total Frequent Itemsets:", frequent_itemsets.shape[0])

from mlxtend.frequent_patterns import association_rules
def generate_rules(frequent_itemsets, metric="confidence", min_threshold=0.1):

    rules = association_rules(frequent_itemsets, metric=metric, min_threshold=min_threshold)
    return rules

rules = generate_rules(frequent_itemsets.copy(), metric="confidence", min_threshold=0.1)
print("Total Rules Generated:", rules.shape[0])
print(rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']].head(10))