Dataset Used: Nursery Data Set
Number of Instances: | 12960 |
---|---|
Number of Attributes: | 8 |
parents: usual, pretentious, great_pret
has_nurs: proper, less_proper, improper, critical, very_crit
form: complete, completed, incomplete, foster
children: 1, 2, 3, more
housing: convenient, less_conv, critical
finance: convenient, inconv
social: non-prob, slightly_prob, problematic
health: recommended, priority, not_recom
- Download the dataset
- Pre-process the dataset
- Create ten samples
- Split the samples in 70 : 30 for training and testing
- Optimise SVM using randomisation for every sample and report best accuracy and best parameters
- For the best sample plot the convergence graph
The best parameters of SVC for the given dataset are:
- Kernel : rbf
- C : 6.393915
- Gamma : 0.117114
The above parameter gave a maximum accuracy of 0.9915.
Name : Garima Chandna
Roll No : 102017070