KDD & Data Mining

Lab Experiment No 7 : FP Growth Algorithm

Name: - Gaurav Sonawane

PRN:- 20200802154

Aim : To perform FP Growth Algorithm on the given dataset (market-basket-optimisation.csv) using

1. By creating functions.
2. By using NumPy and FP Growth library.

And validating the results

By Creating Function

import numpy as np
In [ ]:
import pandas as pd
from futureimport division, print_function from mlxtend.preprocessing import TransactionEnc
from mlxtend.frequent_patterns import association_rules
import warnings
warnings.filterwarnings('ignore')

%pip install mlxtend --upgrade

In [ ]:

In [ ]: # Define the Node class for the FP-Tree

class Node:
def init (self, item, count, parent): self.item = item
self.count = count self.parent = parent self.children = {}

def increment(self, count): self.count += count

# Create the FP-Tree

def create_fp_tree(data, min_support):
# Count the frequency of each item in the dataset
item_counts = {}
for transaction in data:
for item in transaction:
if item in item_counts:
item_counts[item] += 1
else:
item_counts[item] = 1

# Remove infrequent items from the dataset

data = [[item for item in transaction if item_counts[item] >= min_support] for trans
Loading [MathJax]/extensions/Safe.js
 # Sort the items in each transaction by their frequency
data = [sorted(transaction, key=lambda item: item_counts[item], reverse=True) for tr

# Create the root node of the FP-Tree

root = Node(None, 0, None)

# Add each transaction to the FP-Tree

for transaction in data: current_node = root
for item in transaction:
if item in current_node.children:
child_node = current_node.children[item] child_node.increment(1)
else:
child_node = Node(item, 1, current_node) current_node.children[item] = child_node
current_node = child_node

return root, item_counts

In [ ]: # Define the FP-Growth algorithm

def fp_growth(data, min_support):
# Create the FP-Tree
root, item_counts = create_fp_tree(data, min_support)

# Mine the FP-Tree for frequent itemsets

itemset_list = []
mine_fp_tree(root, [], itemset_list, min_support)

# Return the frequent itemsets and their counts

return itemset_list

# Define the function to recursively mine the FP-Tree for frequent itemsets
def mine_fp_tree(node, prefix, itemset_list, min_support):
if node.count >= min_support:
itemset = prefix + [node.item]
itemset_list.append((itemset, node.count))
for child_node in node.children.values():
mine_fp_tree(child_node, prefix + [node.item], itemset_list, min_support)

In [ ]: df = pd.read_csv('/content/Market_Basket_Optimisation.csv', header=None)

transaction = []

for i in df.itertuples():
l = set(list(i))
transaction.append([i for i in l if (str(i)!="nan" and type(i)!=int)])

len(transaction)
7501
Out[ ]
:

In [ itemsets = fp_growth(transaction,150)
]: itemsets
Loading [MathJax]/extensions/Safe.js
Out[ ] [([None, 'mineral water'], 1788),
: ([None, 'mineral water', 'eggs'], 382),
([None, 'mineral water', 'spaghetti'],
341), ([None, 'mineral water',
'chocolate'], 174), ([None, 'eggs'], 966),
([None, 'eggs', 'french fries'], 184),
([None, 'eggs', 'spaghetti'], 167),
([None, 'french fries'], 714),
([None, 'spaghetti'], 691),
([None, 'cookies'], 305),
([None, 'chocolate'], 434),
([None, 'green tea'], 360),
([None, 'escalope'], 177),
([None, 'milk'], 215)]

Using Libraries in-built func

In [ df = pd.read_csv("/content/Market_Basket_Optimisation.csv", names=[i for i in

]: range(20)] df

Out[ ]: 0 1 2 3 4 5 6 7 8 9 10 11

whole low
vegetables green cottage energy tomato green
0 shrimp almonds avocado weat yams fat
mix grapes cheese drink juice tea
flour yogurt

1burgersmeatballs eggs NaN NaNNaNNaN NaNNaNNaNNaNNaN

2 chutney NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

3 turkeyavocado NaN NaN NaNNaNNaN NaNNaNNaNNaNNaN

mineral energy whole

4 water milk green tea NaN NaN NaN NaN NaN NaN NaN
bar wheat rice

... ... ... ... ... ... ... ... ... ... ... ... ...
fresh
7496 butter light mayo
bread NaN NaN NaN NaN NaN NaN NaN NaN NaN

frozen vegetables french green

7497burgers eggs NaN NaNNaNNaNNaNNaN
fries magazines tea

7498 chicken NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

7499 escalopegreen tea NaN NaN NaNNaNNaN NaNNaNNaNNaNNaN

frozen
7500 eggs
smoothie yogurt low fat
cake yogurt NaN NaN NaN NaN NaN NaN NaN NaN

7501 rows × 20 columns

In [ ]: transaction = []

for i in
df.itertuples(): l =
set(list(i))
transaction.append([i for i in l if (str(i)!="nan" and type(i)!=int)])

7501
Out[ ]
:
 In [ ]: t = TransactionEncoder()
t_arr = t.fit_transform(transaction)

data = pd.DataFrame(t_arr, columns=t.columns_)

Loading [MathJax]/extensions/Safe.js
 Out[ ]:
antioxydant babie barbecue black
asparagus almonds bacon ...
asparagus avocado s food sauce blueberries
juice tea

0 False True True False True False False False False False ...

1 False False False False False False False False False False ...

2 False False False False False False False False False False ...

3 False False False False True False False False False False ...

4 False False False False False False False False False False ...

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

7496 False False False False False False False False False False ...

7497 False False False False False False False False False False ...

7498 False False False False False False False False False False ...

7499 False False False False False False False False False False ...

7500 False False False False False False False False False False ...

7501 rows × 120 columns

In [ ]: res = fpgrowth(data, min_support=0.05, use_colnames=True)

res

Loading [MathJax]/extensions/Safe.js
 Out[ ]: support itemsets

0 0.238368 (mineral water)

1 0.132116 (green tea)

2 0.076523 (low fat yogurt)

3 0.071457 (shrimp)

4 0.065858 (olive oil)

5 0.063325 (frozen smoothie)

6 0.179709 (eggs)

7 0.087188 (burgers)

8 0.062525 (turkey)

9 0.129583 (milk)

10 0.058526 (whole wheat rice)

11 0.170911 (french fries)

12 0.050527 (soup)

13 0.174110 (spaghetti)

14 0.095321 (frozen vegetables)

15 0.080389 (cookies)

16 0.051060 (cooking oil)

17 0.163845 (chocolate)

18 0.059992 (chicken)

19 0.068391 (tomatoes)

20 0.095054 (pancakes)

21 0.052393 (grated cheese)

22 0.098254 (ground beef)

23 0.079323 (escalope)

24 0.081056 (cake)

25 0.050927 (mineral water, eggs)

26 0.059725 (mineral water, spaghetti)

27 0.052660 (mineral water, chocolate)

In [ ]: res = association_rules(res,metric="confidence", min_threshold=0.06)

res

Loading [MathJax]/extensions/Safe.js
 Out[ ] antecedent
antecedents consequents consequent
: support confidence lift leverage conviction
support support

(mineral
0 water) (eggs) 0.238368 0.179709 0.050927 0.213647 1.188845 0.008090 1.043158

(mineral water)
1 (eggs) 0.179709 0.238368 0.0509270.283383 1.188845 0.0080901.062815

(mineral
2 water) (spaghetti) 0.238368 0.174110 0.059725 0.250559 1.439085 0.018223 1.102008

(mineral water)
3(spaghetti) 0.174110 0.238368 0.0597250.343032 1.439085 0.0182231.159314

(mineral
4 water) (chocolate) 0.238368 0.163845 0.052660 0.220917 1.348332 0.013604 1.073256

(mineral water)
5(chocolate) 0.163845 0.238368 0.0526600.321400 1.348332 0.0136041.122357

Loading [MathJax]/extensions/Safe.js