In [1]:

    

from pml.api import *

data = load("../dataset_ext2.csv")


    

In [2]:

    

data.num_samples()


    

    
Out[2]:





80

In [3]:

    

data.feature_list()


    

    
Out[3]:





['ELEC199',
 'CHEM150',
 'PHYS125',
 'CSC115',
 'ENGR110',
 'CSC111',
 'MATH100',
 'MATH101',
 'ENGL135',
 'MATH110',
 'ENGR120',
 'PHYS122',
 'MECH141']

In [4]:

    

data.get_label_value_counts()


    

    
Out[4]:





f    30
s    29
p    21

In [5]:

    

data.combine_labels(["s", "p"], "s")
data.get_label_value_counts()


    

    
Out[5]:





s    50
f    30

In [6]:

    

training, testing = data.split(0.6, random=True)
training.num_samples()


    

    
Out[6]:





48

In [7]:

    

testing.num_samples()


    

    
Out[7]:





32

In [ ]: