UI19CO44

ASSIGNMENT 10

AIM: To study and work with WEKA tool classification and clustering algorithms using training
dataset and test dataset.

DATASET USED: REUTER GRAIN (BOTH TEST AND TRAIN ) .arff

Weka is a collection of machine learning algorithms for data mining tasks. The
algorithms can either be applied directly to a dataset or called from your own Java
code. Weka contains tools for data pre-processing, classification, regression,
clustering, association rules, and visualization.

We use a sample dataset provided by Weka to perform the classification and

clustering by pre-existing algorithms available in Weka for both train and test sets
and study the results
UI19CO44

CLASSIFICATION OF TRAINING DATASET USING ZeroR CLASSIFIER :

ACCURACY : 93.3719 %
UI19CO44

CLASSIFICATION OF TESTING DATASET USING ZeroR CLASSIFIER :

ACCURACY : 90.5629 %
UI19CO44

CLUSTERING OF TRAINING DATASET USING HIERARCHIAL CLUSTER :

MODEL EVALUATION ACCURACY : 93 %

UI19CO44

CLUSTERING OF TESTING DATASET USING HIERARCHIAL CLUSTER :

MODEL EVALUATION ACCURACY : 91 %