USML3

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
rules = association_rules(frequent_itemsets, metric="confidence", min_threshold=0.1)
rules = rules[rules['antecedents'].apply(lambda x: len(x) >= 1) & rules['consequents'].apply(lambda x: len(x) >= 1)]
print("Association Rules:", rules.shape[0])
rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']].head(5)
-------------------------------------------------------------------------------
import matplotlib.pyplot as plt
top_items = df['itemDescription'].value_counts().head(10)
top_items.plot(kind='bar', title='Top 10 Most Purchased Items')
plt.xlabel("Item")
plt.ylabel("Count")
plt.show()