Blog Post

Apriori Algorithm

Apriori Algorithm

Data Mining

 

 

What is Data Mining?

 

  • Automatically searching large data to find patterns and trends that go beyond simple analysis.

  • Using sophisticated mathematical algorithms, artificial intelligence, statistical. analysis, and database systems to find patterns.

  • Predicts  likely outcomes.

***Algorithms are the core of Data Mining***

 

Data Mining Algorithms

 

  • Apriori***

  • Linear Regression

  • Logistic Regression

  • K-means

  • SVMs

  • Random Forests

  • Matrix Factorization

 

 

The APRIORI ALGORITHM keeps track of the frequency of item in a database. These frequent items are then used to determine patterns in the large data. These databases contain transactions data. The apriori uses breadth-first search and Hash tree structures to count the frequency data items.

 

Apriori algorithm for Data Mining – made simple

Great Explanation of How Apriori works and What it is used for

 

lhttp://nikhilvithlani.blogspot.com/2012/03/apriori-algorithm-for-data-mining-made.html

 

How to Run the Apriori Algorithm in Java Using Blue J

 

STEP 1

 

  • Download Blue J which is a free Java Development Environment designed for. beginners, used by millions worldwide.

  • Dowload Link http://www.bluej.org/

  • Make sure to get the correct version for your OS that includes JDK

  • Next run the executable and install Blue J.

 

.

 

 

 

STEP 2

  • Once You have Blue J installed open Blue J and under Project select new Project and name it Apriori Algorithm.

  • Add a new class and name  it Apriori.

 

STEP 3

 

  • Next open up the apriori class folder and select all the text and cut it.

 

 

STEP 4

 

  • Next we will get the source code from this link:

  • https://gist.github.com/monperrus/7157717

  • Copy and paste the Apriori.java code from the above link into your empty apriori class.

  • Make sure you copy all the code from line 1 to line 315.

 

 

STEP 5

 

 

  • Next download the chess.dat file and save it into your apriori algorithm folder that was created when we created the new project in BlueJ.

  • Next compile your code and run the program by right-clicking on your apriori class and clicking on the method void main(String[] args) and then click ok on the method call window pop up.

  • Your algorithm should get to work and compute hundreds of computations in a matter of seconds.

  • Scroll down to the writing in RED and it will give you information about your chess.dat file which contain rows with numbers. Each row represents a transaction

 

 

 

Data Mining in  the Real World

 

  • IBM offers businesses data mining of Twitter


 

http://www.skynews.com.au/business/business/world/2015/03/22/ibm-offers-businesses-data-mining-of-twitter.html

 

  • Data Mining Reveals When a Yellow Taxi Is Cheaper Than Uber

http://www.technologyreview.com/view/535886/data-mining-reveals-when-a-yellow-taxi-is-cheaper-than-uber/#comments

 

 

167

No comments