有关OneHotEncoding的问题 - Python

问题描述 投票:0回答:1

我正在开发一个将One Hot Encoding技术应用于.binetflow文件的分类列的项目。

码:

import pandas as pd
from sklearn.preprocessing import LabelEncoder,OneHotEncoder

mydataset = pd.read_csv('originalfiletest.binetflow')

le = LabelEncoder()
dfle = mydataset
dfle.State = le.fit_transform(dfle.State)
X = dfle[['State']].values
ohe = OneHotEncoder()
Onehot = ohe.fit_transform(X).toarray()

dfle['State'] = Onehot

mydataset.to_csv('newfiletest.binetflow', columns=['Dur','State','TotBytes','average_packet_size','average_bits_psecond'], index=False)

Original binetflow file

目前,我正在使用熊猫,我能够应用这项技术。问题是我需要在第二个文件中写入。

当我尝试写入时,我期望的输出是,例如:变量Onehot中的0001或0.0.0.1,但当我尝试将其传递给列dfle ['State'时,我得到的是0.0或1.0 。图像可以在下面找到。

variable Onehot

column dfle['State']

而且,应该只写的列,当我在编译器上打印时它正确显示但是当它在文件中写入时它会添加几个小数位。

Original and new binetflow file

python scikit-learn one-hot-encoding
1个回答
0
投票

Onehot是numpy数组,问题在于将数组赋值给dataframe列

import pandas as pd
from sklearn.preprocessing import LabelEncoder, OneHotEncoder

mydataset = pd.DataFrame(data={'State': ['a', 'a', 'b', 'c', 'a', 'd']})

le = LabelEncoder()

mydataset.State = le.fit_transform(mydataset.State)
X = mydataset[['State']].values
ohe = OneHotEncoder()
Onehot = ohe.fit_transform(X).toarray()

dx = pd.DataFrame(data=Onehot)

mydataset['State'] = (dx[dx.columns[0:]].apply(lambda x: ','.join(x.dropna().astype(int).astype(str)), axis=1))

mydataset.to_csv('newfiletest.binetflow',
                 columns=['Dur', 'State', 'TotBytes', 'average_packet_size', 'average_bits_psecond'], index=False)
© www.soinside.com 2019 - 2024. All rights reserved.