Association Rule Mining-Hands - On

11/9/2018 ASM-hands_on
Welcome to the first Hands On association rule mining. In this exercise , you will try out ASM regression using
mlxtend library that you have learnt in the course. We have created this Python Notebook with all the necessary
things needed for completing this exercise. You have to write your code in between the are mentioned
Start Code ¶
Your Code here
End Code
To run the code in each cell click on the cell and press shift + enter
Run the below cell to load the data on which you will be performing ASM. The data has the records of items
purcahed where each element of 'Data' refers to a single transaction
In [1]:
Data = [['Power Bank', 'Screen Guard' , 'Travel Charger'],

['Screen Guard', 'Bluetooth Headset', 'Mobile Cover'],
['Screen Guard','Arm Band','Mobile Cover'],
['Power Bank','Screen Guard','Leather Pouch'],
['Bluetooth Headset', 'Power Bank' , 'Mobile Cover']]
Run the below cell to import necessary packages to perform AMS
In [2]:
import pandas as pd
from mlxtend.preprocessing import OnehotTransactions
from mlxtend.frequent_patterns import apriori
- initalize OnehotTransactions as oht

- fit and transform the transaction data('Data') to perform one hot encoding
- create a dataframe of one hot encoded data
- Find all frequent item sets with minimum support 0.1 using apriori function
**Follow the code snippet in the course on implementing the above steps**
https://2886795294-8888-host04-fresco.environments.katacoda.com/notebooks/ASM-hands_on.ipynb 1/4
In [13]:
###Start code here

oht = OnehotTransactions()
oht_ary = oht.fit(Data).transform(Data)
dataFrame = pd.DataFrame(oht_ary, columns=oht.columns_)
frequent_itemsets = apriori(dataFrame, min_support=0.1, use_colnames=True)
print(dataFrame)
###End code(approx 4 lines)
Arm Band Bluetooth Headset Leather Pouch Mobile Cover Power Bank \
0 False False False False True
1 False True False True False
2 True False False True False
3 False False True False True
4 False True False True True
Screen Guard Travel Charger

0 True True
1 True False
2 True False
3 True False
4 False False
/home/scrapbook/.local/lib/python3.5/site-packages/mlxtend/preprocessing/one
hot.py:66: DeprecationWarning: OnehotTransactions has been deprecated and wi
ll be removed in future. Please use TransactionEncoder instead.
warnings.warn(msg, DeprecationWarning)
generate association rule for all the itemsets(frequent_itemsets) with minimum confidence 0.7
In [14]:
from mlxtend.frequent_patterns import association_rules

###Start code here
association_rule = association_rules(frequent_itemsets, metric="confidence", min_threshold=
print(association_rule)
antecedents consequents \
0 (Mobile Cover, Power Bank) (Bluetooth Headset)
1 (Power Bank, Bluetooth Headset) (Mobile Cover)
2 (Mobile Cover, Arm Band) (Screen Guard)
3 (Screen Guard, Arm Band) (Mobile Cover)
4 (Arm Band) (Mobile Cover, Screen Guard)
5 (Travel Charger) (Screen Guard)
6 (Travel Charger) (Power Bank)
7 (Bluetooth Headset) (Mobile Cover)
8 (Leather Pouch) (Power Bank)
9 (Screen Guard, Travel Charger) (Power Bank)
10 (Power Bank, Travel Charger) (Screen Guard)
11 (Travel Charger) (Screen Guard, Power Bank)
12 (Leather Pouch, Power Bank) (Screen Guard)
13 (Leather Pouch, Screen Guard) (Power Bank)
14 (Leather Pouch) (Screen Guard, Power Bank)
15 (Arm Band) (Screen Guard)
16 (Leather Pouch) (Screen Guard)
17 (Arm Band) (Mobile Cover)
18 (Screen Guard, Bluetooth Headset) (Mobile Cover)
antecedent support consequent support support confidence lift \

0 0.2 0.4 0.2 1.0 2.500000
1 0.2 0.6 0.2 1.0 1.666667
2 0.2 0.8 0.2 1.0 1.250000
3 0.2 0.6 0.2 1.0 1.666667
4 0.2 0.4 0.2 1.0 2.500000
5 0.2 0.8 0.2 1.0 1.250000
6 0.2 0.6 0.2 1.0 1.666667
7 0.4 0.6 0.4 1.0 1.666667
8 0.2 0.6 0.2 1.0 1.666667
9 0.2 0.6 0.2 1.0 1.666667
10 0.2 0.8 0.2 1.0 1.250000
11 0.2 0.4 0.2 1.0 2.500000
12 0.2 0.8 0.2 1.0 1.250000
13 0.2 0.6 0.2 1.0 1.666667
14 0.2 0.4 0.2 1.0 2.500000
15 0.2 0.8 0.2 1.0 1.250000
16 0.2 0.8 0.2 1.0 1.250000
17 0.2 0.6 0.2 1.0 1.666667
18 0.2 0.6 0.2 1.0 1.666667
leverage conviction
0 0.12 inf
1 0.08 inf
2 0.04 inf
3 0.08 inf
4 0.12 inf
5 0.04 inf
6 0.08 inf
7 0.16 inf
8 0.08 inf
9 0.08 inf
10 0.04 inf
11 0.12 inf
12 0.04 inf
13 0.08 inf
14 0.12 inf
15 0.04 inf
16 0.04 inf
17 0.08 inf
18 0.08 inf
What is the consequent support value for Leather Pouch -> Screen Guard ?
What is the lift value for (Arm Band, Mobile Cover)->(Screen Guard) ?
In how many scenarios do you see 2 items (dualtons) in the antecedent set ?
assign the above abservations to respective variable in the cell below
In [15]:
###Start code here

support = 0.8
lift = 1.250000
dualtons = 9
with open("output.txt", "w") as text_file:
text_file.write("support= %f\n" % support)
text_file.write("lift= %f\n" % lift)
text_file.write("dualtons= %f\n" % dualtons)
In [ ]:

Association Rule Mining-Hands - On

Uploaded by

Copyright:

Available Formats

Association Rule Mining-Hands - On

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Association Rule Mining-Hands - On

Uploaded by

Copyright:

Available Formats

What is association rule mining used for?

What are some examples of items (antecedents and consequents) identified from the transactional data?

11/9/2018 ASM-hands_on

Data = [['Power Bank', 'Screen Guard' , 'Travel Charger'],

Run the below cell to import necessary packages to perform AMS

- initalize OnehotTransactions as oht

###Start code here

Screen Guard Travel Charger

from mlxtend.frequent_patterns import association_rules

antecedent support consequent support support confidence lift \

###Start code here

You might also like