Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
import csv
import random
import math
def loadCsv(filename):
lines = csv.reader(open(filename, "r"))
dataset = list(lines)
for i in range(len(dataset)):
dataset[i] = [float(x) for x in dataset[i]]
return dataset
def split(dataset, ratio):
trainSize = int(len(dataset)*ratio)
trainSet = []
copy = list(dataset)
while len(trainSet)<trainSize:
index = random.randrange(len(copy))
trainSet.append(copy.pop(index))
return trainSet, copy
def separate(dataset):
separated = {}
for i in range(len(dataset)):
vector = dataset[i]
if vector[-1] not in separated:
separated[vector[-1]] = []
separated[vector[-1]].append(vector)
return separated
def mean(numbers):
return sum(numbers)/float(len(numbers))