Scribd
Upload
95 views41 pages

MBA in Python - 3

This document discusses market basket analysis and association rule mining using the Apriori algorithm in Python. It introduces the concept of market basket analysis and explores aggregating transaction data into item categories. It then covers how the Apriori algorithm works, including the Apriori principle of pruning subsets that are not frequent. The document shows an example of running Apriori on sample retail data and generating frequent itemsets. It also discusses how association rules can be computed from the frequent itemsets and the importance of pruning rules to reduce their number.

Uploaded by

Gusti Adli Anshari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
95 views41 pages

MBA in Python - 3

This document discusses market basket analysis and association rule mining using the Apriori algorithm in Python. It introduces the concept of market basket analysis and explores aggregating transaction data into item categories. It then covers how the Apriori algorithm works, including the Apriori principle of pruning subsets that are not frequent. The document shows an example of running Apriori on sample retail data and generating frequent itemsets. It also discusses how association rules can be computed from the frequent itemsets and the importance of pruning rules to reduce their number.

Uploaded by

Gusti Adli Anshari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 41

Aggregation

M A R K E T B A S K E T A N A LY S I S I N P Y T H O N

Isaiah Hull
Economist
Exploring the data
import pandas as pd

# Load novelty gift data.


gifts = pd.read_csv('datasets/novelty_gifts.csv')

# Preview data with head() method.


print(gifts.head())

InvoiceNo Description
0 562583 IVORY STRING CURTAIN WITH POLE
1 562583 PINK AND BLACK STRING CURTAIN
2 562583 PSYCHEDELIC TILE HOOK
3 562583 ENAMEL COLANDER CREAM
4 562583 SMALL FOLDING SCISSOR(POINTED EDGE)

MARKET BASKET ANALYSIS IN PYTHON


Exploring the data
# Print number of transactions.
print(len(gifts['InvoiceNo'].unique()))

9709

# Print number of items.


print(len(gifts['Description'].unique()))

3461

MARKET BASKET ANALYSIS IN PYTHON


Pruning and aggregation
Pruning Aggregation

MARKET BASKET ANALYSIS IN PYTHON


Aggregating the data
# Load one-hot encoded data
onehot = pd.read_csv('datasets/online_retail_onehot.csv')

# Print preview of DataFrame


print(onehot.head(2))

50'S CHRISTMAS GIFT BAG LARGE DOLLY GIRL BEAKER ... ZINC WILLIE WINKIE CANDLE STICK
0 False False False
1 False False True

MARKET BASKET ANALYSIS IN PYTHON


Aggregating the data
# Select the column names for bags and boxes
bag_headers = [i for i in onehot.columns if i.lower().find('bag')>=0]
box_headers = [i for i in onehot.columns if i.lower().find('box')>=0]

# Identify column headers


bags = onehot[bag_headers]
boxes = onehot[box_headers]
print(bags)

50'S CHRISTMAS GIFT BAG LARGE RED SPOT GIFT BAG LARGE
0 False False
1 False False
... ... ...

MARKET BASKET ANALYSIS IN PYTHON


Aggregating the data
# Sum over columns
bags = (bags.sum(axis=1) > 0.0).values
boxes = (boxes.sum(axis=1) > 0.0).values
print(bags)

[False True False ... False True False]

MARKET BASKET ANALYSIS IN PYTHON


Aggregating the data
# Add results to DataFrame
aggregated = pd.DataFrame(np.vstack([bags, boxes]).T, columns = ['bags', 'boxes'])

print(aggregated.head())

bags boxes
0 False False
1 True False
2 False False
3 False False
4 True False

MARKET BASKET ANALYSIS IN PYTHON


Market basket analysis with aggregates
Aggregation process:
Items -> Categories

Compute metrics

Identify rules

# Compute support
print(aggregated.mean())

bags 0.130075
boxes 0.071429

MARKET BASKET ANALYSIS IN PYTHON


Let's practice!
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N
The Apriori
algorithm
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N

Isaiah Hull
Economist
Counting itemsets
( )=
n n!
Item Count Itemset Size Combinations
k (n − k)!k!
3461 0 1

3461 1 3461

3461 2 5,987,530

3461 3 6,903,622,090

3461 4 5,968,181,296,805

MARKET BASKET ANALYSIS IN PYTHON


Counting itemsets
n
n = 3461 → 23461
∑ ( ) = 2n
n
k 23461 >> 1082
k=1

Number of atoms in universe: 1082 .

MARKET BASKET ANALYSIS IN PYTHON


Reducing the number of itemsets
Not possible to consider all itemsets.
Not even possible to enumerate them.

How do we remove an itemset without even evaluating it?


Could set maximum k value.

Apriori algorithm offers alternative.


Doesn't require enumeration of all itemsets.

Sensible rule for pruning.

MARKET BASKET ANALYSIS IN PYTHON


The Apriori principle
Apriori principle. Candles = Infrequent
Subsets of frequent sets are frequent. -> {Candles, Signs} = Infrequent

Retain sets known to be frequent. {Candles, Signs} = Infrequent


-> {Candles, Signs Boxes} = Infrequent
Prune sets not known to be frequent.
{Candles, Signs, Boxes} = Infrequent
-> {Candles, Signs, Boxes, Bags} =
Infrequent

MARKET BASKET ANALYSIS IN PYTHON


Apriori implementation
# Import Apriori algorithm
from mlxtend.frequent_patterns import apriori

# Load one-hot encoded novelty gifts data


onehot = pd.read_csv('datasets/online_retail_onehot.csv')

# Print header.
print(onehot.head())

50'S CHRISTMAS GIFT BAG LARGE ... ZINC WILLIE WINKIE CANDLE STICK \
0 False ... False
1 False ... False
2 False ... False
3 False ... False
4 False ... False

MARKET BASKET ANALYSIS IN PYTHON


Apriori implementation
# Compute frequent itemsets
frequent_itemsets = apriori(onehot, min_support = 0.0005,
max_len = 4, use_colnames = True)

# Print number of itemsets


print(len(frequent_itemsets))

3652

MARKET BASKET ANALYSIS IN PYTHON


Apriori implementation
# Print itemsets
print(frequent_itemsets.head())

support itemsets
0 0.000752 ( 50'S CHRISTMAS GIFT BAG LARGE)
1 0.001504 ( DOLLY GIRL BEAKER)
...
1500 0.000752 (PING MICROWAVE APRON, FOOD CONTAINER SET 3 LO...
1501 0.000752 (WOOD 2 DRAWER CABINET WHITE FINISH, FOOD CONT...
...

MARKET BASKET ANALYSIS IN PYTHON


Let's practice!
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N
Basic Apriori results
pruning
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N

Isaiah Hull
Economist
Apriori and association rules
Apriori prunes itemsets.
Applies minimum support threshold.

Modi ed version can prune by number of items.

Doesn't tell us about association rules.

Association rules.
Many more association rules than itemsets.

{Bags, Boxes}: Bags -> Boxes OR Boxes -> Bags.

MARKET BASKET ANALYSIS IN PYTHON


How to compute association rules
Computing rules from Apriori results. Reducing number of association rules.
Dif cult to enumerate for high n and k. mlxtend module offers means of pruning
association rules.
Could undo itemset pruning by Apriori.
association_rules() takes frequent
items, metric, and threshold.

MARKET BASKET ANALYSIS IN PYTHON


How to compute association rules
# Import Apriori algorithm
from mlxtend.frequent_patterns import apriori, association_rules

# Load one-hot encoded novelty gifts data


onehot = pd.read_csv('datasets/online_retail_onehot.csv')

# Apply Apriori algorithm


frequent_itemsets = apriori(onehot,
use_colnames=True,
min_support=0.0001)

# Compute association rules


rules = association_rules(frequent_itemsets,
metric = "support",
min_threshold = 0.0)

MARKET BASKET ANALYSIS IN PYTHON


The importance of pruning
# Print the rules.
print(rules)

antecedents ... conviction


0 (CARDHOLDER GINGHAM CHRISTMAS TREE) ... inf
...
79505 (SET OF 3 HEART COOKIE CUTTERS) ... 1.998496

# Print the frequent itemsets.


print(frequent_itemsets)

support itemsets
0 0.000752 ( 50'S CHRISTMAS GIFT BAG LARGE)
...
4707 0.000752 (PIZZA PLATE IN BOX, CHRISTMAS ...

MARKET BASKET ANALYSIS IN PYTHON


The importance of pruning
# Compute association rules
rules = association_rules(frequent_itemsets,
metric = "support",
min_threshold = 0.001)

# Print the rules.


print(rules)

antecedents conviction
0 (BIRTHDAY CARD, RETRO SPOT) ... 2.977444
1 (JUMBO BAG RED RETROSPOT) ... 1.247180

MARKET BASKET ANALYSIS IN PYTHON


Exploring the set of rules
print(rules.columns)

Index(['antecedents', 'consequents', 'antecedent support',


'consequent support', 'support', 'confidence', 'lift', 'leverage',
'conviction'],
dtype='object')

print(rules[['antecedents','consequents']])

antecedents consequents
0 (JUMBO BAG RED RETROSPOT) (BIRTHDAY CARD, RETRO SPOT)
1 (BIRTHDAY CARD, RETRO SPOT) (JUMBO BAG RED RETROSPOT)

MARKET BASKET ANALYSIS IN PYTHON


Pruning with other metrics
# Compute association rules
rules = association_rules(frequent_itemsets,
metric = "antecedent support",
min_threshold = 0.002)

# Print the number of rules.


print(len(rules))

3899

MARKET BASKET ANALYSIS IN PYTHON


Let's practice!
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N
Advanced Apriori
results pruning
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N

Isaiah Hull
Economist
Applications
Cross-Promotion Aggregation

MARKET BASKET ANALYSIS IN PYTHON


The Apriori algorithm
List of Lists One-Hot Encoding

Apriori Algorithm

MARKET BASKET ANALYSIS IN PYTHON


The Apriori algorithm
import pandas as pd
import numpy as np
from mlxtend.preprocessing import TransactionEncoder
from mlxtend.frequent_patterns import apriori

itemsets = np.load('itemsets.npy')
print(itemsets)

[['EASTER CRAFT 4 CHICKS'],


['CERAMIC CAKE DESIGN SPOTTED MUG', 'CHARLOTTE BAG APPLES DESIGN'],
['SET 12 COLOUR PENCILS DOLLY GIRL'],
...
['JUMBO BAG RED RETROSPOT', ... 'LIPSTICK PEN FUSCHIA']]

MARKET BASKET ANALYSIS IN PYTHON


The Apriori algorithm
# One-hot encode data
encoder = TransactionEncoder()
onehot = encoder.fit(itemsets).transform(itemsets)
onehot = pd.DataFrame(onehot, columns = encoder.columns_)

# Apply Apriori algorithm and print


frequent_itemsets = apriori(onehot, use_colnames=True, min_support=0.001)
print(frequent_itemsets)

support itemsets
0 0.001504 ( DOLLY GIRL BEAKER)
1 0.002256 ( RED SPOT GIFT BAG LARGE)
...
428 0.001504 (BIRTHDAY CARD, RETRO SPOT, JUMBO BAG RED RETR...

MARKET BASKET ANALYSIS IN PYTHON


Apriori algorithm results
print(len(data.columns))

4201

print(len(frequent_itemsets))

2328

rules = association_rules(frequent_itemsets)

MARKET BASKET ANALYSIS IN PYTHON


Association rules
print(rules['consequents'])

0 (DOTCOM POSTAGE)
...
9 (HERB MARKER THYME)
...
234 (JUMBO BAG RED RETROSPOT)
235 (WOODLAND CHARLOTTE BAG)
236 (RED RETROSPOT CHARLOTTE BAG)
237 (STRAWBERRY CHARLOTTE BAG)
238 (CHARLOTTE BAG SUKI DESIGN)
Name: consequents, Length: 239, dtype: object

MARKET BASKET ANALYSIS IN PYTHON


Filtering with multiple metrics
targeted_rules = rules[rules['consequents'] == {'HERB MARKER THYME'}].copy()

filtered_rules = targeted_rules[(targeted_rules['antecedent support'] > 0.01) &


(targeted_rules['support'] > 0.009) &
(targeted_rules['confidence'] > 0.85) &
(targeted_rules['lift'] > 1.00)]

print(filtered_rules['antecedents'])

9 (HERB MARKER BASIL)


25 (HERB MARKER PARSLEY)
27 (HERB MARKER ROSEMARY)
Name: antecedents, dtype: object

MARKET BASKET ANALYSIS IN PYTHON


Grouping products

MARKET BASKET ANALYSIS IN PYTHON


Aggregation and dissociation
# Load aggregated data
aggregated = pd.read_csv('datasets/online_retail_aggregated.csv')

# Compute frequent itemsets


onehot = encoder.fit(aggregated).transform(aggregated)
data = pd.DataFrame(onehot, columns = encoder.columns_)
frequent_itemsets = apriori(data, use_colnames=True)

# Compute standard metrics


rules = association_rules(frequent_itemsets)

# Compute Zhang's rule


rules['zhang'] = zhangs_rule(rules)

MARKET BASKET ANALYSIS IN PYTHON


Zhang's rule
# Print rules that indicate dissociation
print(rules[rules['zhang'] < 0][['antecedents','consequents']])

antecedents consequents
2 (bag) (candle)
3 (candle) (bag)
4 (sign) (bag)
5 (bag) (sign)

MARKET BASKET ANALYSIS IN PYTHON


Selecting a oorplan

MARKET BASKET ANALYSIS IN PYTHON


Let's practice!
M A R K E T B A S K E T A N A LY S I S I N P Y T H O N

You might also like