Scribd
Upload
17 views3 pages

Weka Ex

Uploaded by

Pallavi Singh CSE
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
17 views3 pages

Weka Ex

Uploaded by

Pallavi Singh CSE
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/ 3

Data Mining and Analytics

Part-1

Experiments using WEKA

1. Install WEKA, go through the whole software, and understand the functions supported by it.
2. Observe and study status bar and log button present at the bottom of the screen after starting
WEKA.
3. Select an appropriate data set and learn removing a data record, adding a new data record,
applying filter (converting attributes from one type to the other types, e. g. numeric to
nominal), etc.
4. Take dataset (from WEKA sample data) and perform data cleaning operations as suggested in
data mining text book.
5. Perform statistical study of attributes of an appropriate dataset and record them. Visualize and
interpret the behaviour of the attributes individually or in combination of two or more
depending on the dataset values.
6. Perform experiments as given in the following table using data mining algorithms supported by
the WEKA. Take appropriate datasets preferably of public interest like cancer disease,
earthquake prediction, weather forecast, road accidents, social networking, banking data, etc.;
otherwise students can take any datasets keeping in view its availability on web.

1
Topics SN Experiments
Preparing 1 Take example transactional dataset example as discussed in the
Datasets for chapter of association rules mining.
WEKA
Prepare arff format data file using Word/Notepad.
Prepare excel data file and convert it into arff format data file.

Association rule 2 Take appropriate dataset.


mining Generate association rules using Apriori algorithm with Bank.arff
dataset. Set minimum support range as 20% to 100% with
incremental decrease factor as 10% and confidence factor as
80%.
(a) Generate 5 rules
(b) Generate 4 rules
3 Take appropriate dataset.
Generate association rule for the credit card promotion dataset
using Apriori algorithm with the support range 40% to 100% with
incremental decrease factor as 5% and as 30% with incremental
decrease as 5%. Generate 6 rules.
4 Repeat 1 and 2 using FP-growth algorithm.

Classification and 1 Decision tree


regression
2 K-nearest neighbour classifier
3 Naive Bays
4 Linear

5 Logistic regression

6 SVM

Clustering Apply the under mentioned clustering algorithms on datasets; visualize


and analyze quality of clusters based on the criteria of no. of clusters
formed; and study the performance metrics.
1 K-mean
2 DBSCAN

3 Hierarchical

Dimensionality reduction

2
Dimensionality Principle component analysis
reduction
Singular value decomposition (SVD)

weather_nominal.arff

ionosphere.arff

ionosphere.arff

house.arff

ionosphere.arff

ionosphere.arff

bank.arff

bank.arff

glass.arff

weather_nomima.arff

You might also like