Scribd
Upload
19 views4 pages

APRIORI Algorithms

Uploaded by

Debangshu Goswami
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
19 views4 pages

APRIORI Algorithms

Uploaded by

Debangshu Goswami
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
Download as pdf or txt
You are on page 1/ 4

APRIORI Algorithm

import numpy as np

import pandas as pd

from mlxtend.frequent_patterns import apriori, association_rules

# Changing the working location to the location of the file

cd C:\Users\Dev\Desktop\Kaggle\Apriori Algorithm

# Loading the Data

data = pd.read_excel('Online_Retail.xlsx')

data.head()

# Exploring the columns of the data

data.columns

# Stripping extra spaces in the description

data['Description'] = data['Description'].str.strip()

# Dropping the rows without any invoice number

data.dropna(axis = 0, subset =['InvoiceNo'], inplace = True)

data['InvoiceNo'] = data['InvoiceNo'].astype('str')

# Dropping all transactions which were done on credit

data = data[~data['InvoiceNo'].str.contains('C')]

# Transactions done in France

basket_France = (data[data['Country'] =="France"]

.groupby(['InvoiceNo', 'Description'])['Quantity']
.sum().unstack().reset_index().fillna(0)

.set_index('InvoiceNo'))

# Transactions done in the United Kingdom

basket_UK = (data[data['Country'] =="United Kingdom"]

.groupby(['InvoiceNo', 'Description'])['Quantity']

.sum().unstack().reset_index().fillna(0)

.set_index('InvoiceNo'))

# Transactions done in Portugal

basket_Por = (data[data['Country'] =="Portugal"]

.groupby(['InvoiceNo', 'Description'])['Quantity']

.sum().unstack().reset_index().fillna(0)

.set_index('InvoiceNo'))

basket_Sweden = (data[data['Country'] =="Sweden"]

.groupby(['InvoiceNo', 'Description'])['Quantity']

.sum().unstack().reset_index().fillna(0)

.set_index('InvoiceNo'))

# Defining the hot encoding function to make the data suitable

# for the concerned libraries

def hot_encode(x):

if(x<= 0):

return 0

if(x>= 1):

return 1

# Encoding the datasets


basket_encoded = basket_France.applymap(hot_encode)

basket_France = basket_encoded

basket_encoded = basket_UK.applymap(hot_encode)

basket_UK = basket_encoded

basket_encoded = basket_Por.applymap(hot_encode)

basket_Por = basket_encoded

basket_encoded = basket_Sweden.applymap(hot_encode)

basket_Sweden = basket_encoded

# Building the model

frq_items = apriori(basket_France, min_support = 0.05, use_colnames = True)

# Collecting the inferred rules in a dataframe

rules = association_rules(frq_items, metric ="lift", min_threshold = 1)

rules = rules.sort_values(['confidence', 'lift'], ascending =[False, False])

print(rules.head())

frq_items = apriori(basket_UK, min_support = 0.01, use_colnames = True)

rules = association_rules(frq_items, metric ="lift", min_threshold = 1)

rules = rules.sort_values(['confidence', 'lift'], ascending =[False, False])

print(rules.head())

frq_items = apriori(basket_Por, min_support = 0.05, use_colnames = True)

rules = association_rules(frq_items, metric ="lift", min_threshold = 1)

rules = rules.sort_values(['confidence', 'lift'], ascending =[False, False])


print(rules.head())

frq_items = apriori(basket_Sweden, min_support = 0.05, use_colnames = True)

rules = association_rules(frq_items, metric ="lift", min_threshold = 1)

rules = rules.sort_values(['confidence', 'lift'], ascending =[False, False])

print(rules.head())

You might also like