Вы находитесь на странице: 1из 40

Data Mining

Course Code:PSIT1P1

INDEX
Sr. No. Title Date Sign.

1 Prepare the Analysis services for Adventure


Works Cycles(any other database).Build the
Data Mining Model Structure and built the
Decision Tree with Proper Decision Nodes.And
infer at least five different types of reports.
2 Prepare the Analysis services for Adventure
Works Cycles(any other database). Build the
Data Mining Model Structure and
Implement the Clustering Algorithm.
3 Prepare the Analysis services for Adventure
Works Cycles(any other database). Build the
Data Mining Model Structure. Implement
the Naïve Bayes Algorithm.
4 Prepare the Analysis services for Adventure
Works Cycles(any other database). Build the
basic Time Series Model Structure and Create
the Predictions.
5 Prepare the Analysis services for Adventure
Works Cycles(any other database). Build the
Basic Data Mining Model and Implement
the Association Algorithm.
6 Using R Tools, Show the
Analysis of Social Networking Site.
7 Consider the suitable data for text mining and
implement the Text technique using Weka.
8 Consider the suitable data for Apriori Algorithm
and implement the Apriori Algorithm using
Weka.
Aim:-Prepare the Analysis services for Adventure Works Cycles(any other
database).Build the Data Mining Model Structure and built the Decision
Tree with Proper Decision Nodes.And infer at least five different types of
reports.
Building a Decision Tree using Weka. Start the Weka GUI (without console)

Click on Explorer. The following window opens:


Click on “Open file…” to choose a required data file. Got to the location where Weka is
installed. Here the location is “C:\Program Files\Weka-3-6\”.

In the Weka-3-6 open the folder “data” and select the file “iris.arff”.
Opening of this file gives the following window. Here click on the Classify tab.

Click on “Choose” button, where various classifiers are available.


Select the “trees” classifier.

Under “trees” select the “J48” option.


Now click on the Start button.

The Decision Tree classification starts…


Now to visualize the decision tree, right click on the “trees.J48” under the
Result list section and select the “Visualize tree” option.

It gives the following Decision Tree graph.


Aim: Prepare the Analysis services for Adventure Works Cycles(any other
database). Build the Data Mining Model Structure and Implement the
Naïve Bayes Algorithm.
Start the Weka GUI(without console)

Click on Explorer. The following window opens:


Click on “Open file…” to choose a required data file. Go to the location
where Weka is installed. Here the location is “C:\Program
Files\Weka-3-6\”.

In the Weka-3-6 open the folder “data” and select the file “iris.arff”.
Opening of this file gives the following window. Here click on the Classify tab.

Click on “Choose” button, where various classifiers are available.


Click on the “bayes” classifier.

Select the “NaïveBayes” option


Now click on the Start button.

The Naïve Bayes classification starts…


Aim:-Consider the suitable data for text mining and implement the Text
Mining technique using Weka.
Start the Weka GUI (without console)

Click on Explorer. The following window opens:


Click on “Open file…” to choose a required data file. Got to the
location where Weka is installed. Here the location is “C:\Program
Files\Weka-3-6\”.

In the Weka-3-6 open the folder “data” and select the file “ReutersCorn-train.arff”.
Opening of this file gives the following window.

Click on “Choose” button, where various classifiers are available.


Click on the “filters unsupervised attribute”.

Select the “StringToNominal” option.


It results in the following screen.

Now click on the StringToNominal -R last textbox besides the Choose button. In the
weka.gui.GenericObjectEditor window change the attributeRange to “first” as shown in
the following window. Then click on OK.
Now select the “Text” option in the left pane. Then click on the “Apply” button.

The resultant is,


Click on the Classify tab.

Click on “Choose” button, where various classifiers are available.


Click on the “bayes” classifier.

Select the “NaïveBayes” option


Select the “Use training set” option under the available Test options.

Now click on the “Start” button.


The Classification starts…

The output is as follows:


For the next Text Mining procedure follow the following steps.Here the
StringToWordVector and NumericToNominal techniques will be used.

Click on Explorer. The following window opens:


Click on “Open file…” to choose a required data file. Got to the
location where Weka is installed. Here the location is “C:\Program
Files\Weka-3-6\”.

In the Weka-3-6 open the folder “data” and select the file “ReutersCorn-train.arff”.
Opening of this file gives the following window.

Click on “Choose” button, where various classifiers are available.


Click on the “filters unsupervised attribute”.

Select “StringToWordVector” option.


It results in the following screen.

Now click on the StringToWordVector textbox besides the Choose button. In the
weka.gui.GenericObjectEditor window do the following changes. Then click on OK.
Then click on “Apply” button and then select the “class-att” option in the left pane.

It gives the following screen.


Aim: Consider the suitable data for Apriori Algorithmand Implement the
Apriori Algorithm using Weka.

Start the Weka GUI(without console)

Click on Explorer. The following window opens:


Click on “Open file…” to choose a required data file. Got to the
location where Weka is installed. Here the location is “C:\Program
Files\Weka-3-6\”.

In the Weka-3-6 open the folder “data” and select the file “supermarket.arff”.
Opening of this file gives the following window. Here click on the Classify tab.

Click on the Associate tab


Here click on the Start button

The Apriori algorithm is run and the output is displayed in the “Associator output” pane.
To get the weka.gui.GenericObjectEditor window click on “Apriori” in the Choose text
field.
Clicking on “More” button gives Information window

Click on the “Capabilities” button to get Capabilities Information.


Aim: Using R-Tool , show the analysis for social networking sites.
Download the “termDocMatrix.rdata”. Load this file in the program. Continue with the
coding.

Install “igraph” package.


The “plot(g, layout=layout1)” command gives the following graph:
The “plot(g, layout=layout.kamada.kawai)” command gives the following graph:
The “tkplot(g, layout=layout.kamada.kawai)” command gives the following graph:
The “plot(g, layout=layout1)” command gives the following graph:

Вам также может понравиться