Bayesian Classifier

Erste Übungaufgabe aus dem Fach WT-2 Text- und Suchtechnologien bei Herrn Prof. Dr. Gefei Zhang

Sebastian Schmid -- S0543196



In [1]:

    
import numpy as np



In [2]:

    
def calculate_score(classname, _dat):
    C = data[data[:,len(_dat)] == classname] 
    attributes = [ C[C[:,i] == attr] for i, attr in enumerate(_dat) ]
    return (C.shape[0]/data.shape[0]) * np.prod( [(a.shape[0] / C.shape[0]) for a in attributes] )



In [1]:

    
classifier = lambda _dat, classes : classes[np.argmax(
    [calculate_score(classname, _dat) for classname in classes])]



In [4]:

    
data = np.genfromtxt('./weather.txt', delimiter=', ', dtype=str, skip_header=True)
classes = ['on time', 'late', 'very late']
classifier(['weekday', 'spring', 'normal', 'none'], classes)









    Out[4]:





'on time'



In [5]:

    
data = np.genfromtxt('./lens24.dat', delimiter=',', dtype=int, skip_header=True)
classes = [1,2,3]
classifier([1,1,1,1], classes)









    Out[5]:





3