svm算法python代码_SVM算法之代码实现

import csv

import numpy as np

import matplotlib.pyplot as plt

import copy

from time import sleep

import random

import types

def loadDataset(filename):

with open(filename, 'r') as f:

lines = csv.reader(f)

data_set = list(lines)

if filename != 'titanic.csv':

for i in range(len(data_set)):

del(data_set[i][0])

# 整理数据

for i in range(len(data_set)):

del(data_set[i][0])

del(data_set[i][2])

data_set[i][4] += data_set[i][5]

del(data_set[i][5])

del(data_set[i][5])

del(data_set[i][6])

del(data_set[i][-1])

category = data_set[0]

del (data_set[0])

# 转换数据格式

for data in data_set:

data[0] = int(data[0])

data[1] = int(data[1])

if data[3] != '':

data[3] = float(data[3])

else:

data[3] = None

data[4] = float(data[4])

data[5] = float(data[5])

# 补全缺失值 转换记录方式 分类

for data in data_set:

if data[3] is None:

data[3] = 28

# male : 1, female : 0

if data[2] == 'male':

data[2] = 1

else:

data[2] = 0

# 经过测试，如果不将数据进行以下处理，分布会过于密集，处理后，数据的分布变得稀疏了

# age <25 为0, 25<=age<31为1，age>=31为2