10/17/24, 4:07 PM Assignment6

In [1]: #Pranav Kulkarni(T512004)

import numpy as np
import pandas as pd

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
for filename in filenames:
print(os.path.join(dirname, filename))

In [3]: !pip install mlxtend

Defaulting to user installation because normal site-packages is not writeable

Requirement already satisfied: mlxtend in c:\users\student\appdata\roaming\python
\python312\site-packages (0.23.1)
Requirement already satisfied: scipy>=1.2.1 in c:\programdata\anaconda3\lib\site-
packages (from mlxtend) (1.13.1)
Requirement already satisfied: numpy>=1.16.2 in c:\programdata\anaconda3\lib\site
-packages (from mlxtend) (1.26.4)
Requirement already satisfied: pandas>=0.24.2 in c:\programdata\anaconda3\lib\sit
e-packages (from mlxtend) (2.2.2)
Requirement already satisfied: scikit-learn>=1.0.2 in c:\programdata\anaconda3\li
b\site-packages (from mlxtend) (1.4.2)
Requirement already satisfied: matplotlib>=3.0.0 in c:\programdata\anaconda3\lib
\site-packages (from mlxtend) (3.8.4)
Requirement already satisfied: joblib>=0.13.2 in c:\programdata\anaconda3\lib\sit
e-packages (from mlxtend) (1.4.2)
Requirement already satisfied: contourpy>=1.0.1 in c:\programdata\anaconda3\lib\s
ite-packages (from matplotlib>=3.0.0->mlxtend) (1.2.0)
Requirement already satisfied: cycler>=0.10 in c:\programdata\anaconda3\lib\site-
packages (from matplotlib>=3.0.0->mlxtend) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\programdata\anaconda3\lib
\site-packages (from matplotlib>=3.0.0->mlxtend) (4.51.0)
Requirement already satisfied: kiwisolver>=1.3.1 in c:\programdata\anaconda3\lib
\site-packages (from matplotlib>=3.0.0->mlxtend) (1.4.4)
Requirement already satisfied: packaging>=20.0 in c:\programdata\anaconda3\lib\si
te-packages (from matplotlib>=3.0.0->mlxtend) (23.2)
Requirement already satisfied: pillow>=8 in c:\programdata\anaconda3\lib\site-pac
kages (from matplotlib>=3.0.0->mlxtend) (10.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\programdata\anaconda3\lib\s
ite-packages (from matplotlib>=3.0.0->mlxtend) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in c:\programdata\anaconda3\l
ib\site-packages (from matplotlib>=3.0.0->mlxtend) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in c:\programdata\anaconda3\lib\site-
packages (from pandas>=0.24.2->mlxtend) (2024.1)
Requirement already satisfied: tzdata>=2022.7 in c:\programdata\anaconda3\lib\sit
e-packages (from pandas>=0.24.2->mlxtend) (2023.3)
Requirement already satisfied: threadpoolctl>=2.0.0 in c:\programdata\anaconda3\l
ib\site-packages (from scikit-learn>=1.0.2->mlxtend) (2.2.0)
Requirement already satisfied: six>=1.5 in c:\programdata\anaconda3\lib\site-pack
ages (from python-dateutil>=2.7->matplotlib>=3.0.0->mlxtend) (1.16.0)

In [5]: import csv

from mlxtend.preprocessing import TransactionEncoder
from mlxtend.frequent_patterns import apriori, association_rules

In [7]: data = []
with open('Market_Basket_Optimisation.csv') as file:
reader = csv.reader(file, delimiter=',')

file:///C:/Users/Student/Downloads/Assignment6 (3).html 1/7

10/17/24, 4:07 PM Assignment6

for row in reader:

data +=[row]

In [9]: data[1:10] #list of list

Out[9]: [['burgers', 'meatballs', 'eggs'],

['chutney'],
['turkey', 'avocado'],
['mineral water', 'milk', 'energy bar', 'whole wheat rice', 'green tea'],
['low fat yogurt'],
['whole wheat pasta', 'french fries'],
['soup', 'light cream', 'shallot'],
['frozen vegetables', 'spaghetti', 'green tea'],
['french fries']]

In [11]: len(data)

Out[11]: 7501

In [13]: te = TransactionEncoder()
x = te.fit_transform(data)

In [15]: x

Out[15]: array([[False, True, True, ..., True, False, False],

[False, False, False, ..., False, False, False],
[False, False, False, ..., False, False, False],
...,
[False, False, False, ..., False, False, False],
[False, False, False, ..., False, False, False],
[False, False, False, ..., False, True, False]])

In [17]: te.columns_

file:///C:/Users/Student/Downloads/Assignment6 (3).html 2/7

10/17/24, 4:07 PM Assignment6

Out[17]: [' asparagus',

'almonds',
'antioxydant juice',
'asparagus',
'avocado',
'babies food',
'bacon',
'barbecue sauce',
'black tea',
'blueberries',
'body spray',
'bramble',
'brownies',
'bug spray',
'burger sauce',
'burgers',
'butter',
'cake',
'candy bars',
'carrots',
'cauliflower',
'cereals',
'champagne',
'chicken',
'chili',
'chocolate',
'chocolate bread',
'chutney',
'cider',
'clothes accessories',
'cookies',
'cooking oil',
'corn',
'cottage cheese',
'cream',
'dessert wine',
'eggplant',
'eggs',
'energy bar',
'energy drink',
'escalope',
'extra dark chocolate',
'flax seed',
'french fries',
'french wine',
'fresh bread',
'fresh tuna',
'fromage blanc',
'frozen smoothie',
'frozen vegetables',
'gluten free bar',
'grated cheese',
'green beans',
'green grapes',
'green tea',
'ground beef',
'gums',
'ham',
'hand protein bar',
'herb & pepper',

file:///C:/Users/Student/Downloads/Assignment6 (3).html 3/7

10/17/24, 4:07 PM Assignment6

'honey',
'hot dogs',
'ketchup',
'light cream',
'light mayo',
'low fat yogurt',
'magazines',
'mashed potato',
'mayonnaise',
'meatballs',
'melons',
'milk',
'mineral water',
'mint',
'mint green tea',
'muffins',
'mushroom cream sauce',
'napkins',
'nonfat milk',
'oatmeal',
'oil',
'olive oil',
'pancakes',
'parmesan cheese',
'pasta',
'pepper',
'pet food',
'pickles',
'protein bar',
'red wine',
'rice',
'salad',
'salmon',
'salt',
'sandwich',
'shallot',
'shampoo',
'shrimp',
'soda',
'soup',
'spaghetti',
'sparkling water',
'spinach',
'strawberries',
'strong cheese',
'tea',
'tomato juice',
'tomato sauce',
'tomatoes',
'toothpaste',
'turkey',
'vegetables mix',
'water spray',
'white wine',
'whole weat flour',
'whole wheat pasta',
'whole wheat rice',
'yams',
'yogurt cake',
'zucchini']

file:///C:/Users/Student/Downloads/Assignment6 (3).html 4/7

10/17/24, 4:07 PM Assignment6

In [19]: df = pd.DataFrame(x, columns=te.columns_)

In [21]: df

Out[21]:
antioxydant babies barbecue
asparagus almonds asparagus avocado bacon
juice food sauce

0 False True True False True False False False

1 False False False False False False False False

2 False False False False False False False False

3 False False False False True False False False

4 False False False False False False False False

... ... ... ... ... ... ... ... ...

7496 False False False False False False False False

7497 False False False False False False False False

7498 False False False False False False False False

7499 False False False False False False False False

7500 False False False False False False False False

7501 rows × 120 columns

In [23]: freq_itemset = apriori(df, min_support=0.01, use_colnames=True)

In [25]: freq_itemset

file:///C:/Users/Student/Downloads/Assignment6 (3).html 5/7

10/17/24, 4:07 PM Assignment6

Out[25]: support itemsets

0 0.020397 (almonds)

1 0.033329 (avocado)

2 0.010799 (barbecue sauce)

3 0.014265 (black tea)

4 0.011465 (body spray)

... ... ...

252 0.011065 (ground beef, mineral water, milk)

253 0.017064 (ground beef, mineral water, spaghetti)

254 0.015731 (mineral water, spaghetti, milk)

255 0.010265 (olive oil, mineral water, spaghetti)

256 0.011465 (mineral water, pancakes, spaghetti)

257 rows × 2 columns

In [27]: rules = association_rules(freq_itemset, metric='confidence', min_threshold=0.10)

In [29]: rules = rules[['antecedents','consequents','support','confidence']]

rules

Out[29]: antecedents consequents support confidence

0 (avocado) (mineral water) 0.011598 0.348000

1 (burgers) (cake) 0.011465 0.131498

2 (cake) (burgers) 0.011465 0.141447

3 (chocolate) (burgers) 0.017064 0.104150

4 (burgers) (chocolate) 0.017064 0.195719

... ... ... ... ...

315 (olive oil) (mineral water, spaghetti) 0.010265 0.155870

316 (mineral water, pancakes) (spaghetti) 0.011465 0.339921

317 (mineral water, spaghetti) (pancakes) 0.011465 0.191964

318 (spaghetti, pancakes) (mineral water) 0.011465 0.455026

319 (pancakes) (mineral water, spaghetti) 0.011465 0.120617

320 rows × 4 columns

In [31]: rules[rules['antecedents'] == {'cake'}]['consequents']

file:///C:/Users/Student/Downloads/Assignment6 (3).html 6/7

10/17/24, 4:07 PM Assignment6

Out[31]: 2 (burgers)
25 (chocolate)
27 (eggs)
29 (french fries)
31 (frozen vegetables)
32 (green tea)
34 (milk)
37 (mineral water)
39 (pancakes)
41 (spaghetti)
Name: consequents, dtype: object

In [ ]:

file:///C:/Users/Student/Downloads/Assignment6 (3).html 7/7