Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def parse_data(filename):
- """
- This function parses the data for the decision tree algorithm
- """
- header = filename.readline()
- header = ([[str(y) for y in header.strip().split(" ")][1:]])
- data = filename.readlines()
- data = ([[int(y) for y in x.strip().split(" ")][1:] for x in data])
- data = np.transpose(data)
- labels = np.transpose((data[-1,:]))
- data = np.transpose((data[:-1,:]))
- n = np.zeros(2)
- total = 0
- for x in labels:
- if(x == 0):
- n[0] = int(n[0]+1)
- total = total+1
- else:
- n[1] = int(n[1]+1)
- total = total+1
- return(data,header,labels,n,total)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement