当str数据不适合分析时
方法一:
def car1(s):
it = {b'vhigh': 1, b'high': 2, b'med': 3, b'low': 4}
return it[s]
path ='C:/Users/tjh/Desktop/car.data.txt' # 之前保存的文件路径
data = np.loadtxt(path, # 路径
dtype=float, # 数据类型
delimiter=',', # 数据以什么分割符号分割数据
converters={0:car1,1:car1})
# 对某列数据进行某种类型的转换
方法二:
path = 'C:/Users/tjh/Desktop/car.data.txt'
data = pd.read_csv(path)
data['buying']=data['vhigh'].replace(['vhigh','high','med','low'],['1','2','3','4']).astype('int')
data['maint']=data['vhigh.1'].replace(['vhigh','high','med','low'],['1','2','3','4']).astype('int')
删除列:data=data.drop('unacc',1)