将分类网络流量特征转换为数值 - ISCX VPN2016 数据集

Question

我正在使用 ISCX VPN2016 数据集对加密的网络流量进行分类，我想实现一种深度神经网络技术进行分类。 数据集包括 14 个 pcap 文件，指示 14 类流量，我已将 pcap 文件导出为 csv，添加一列作为类并将它们合并为一个文件。但问题是特征的数据类型，我无法将它们转换为数值特征，我尝试在 Numpy、Pandas 和 Sklearn 中使用建议的常用方法，例如：OneHotEncoder、LabelEncoder、astype、get_dummies , ... 但他们都没有工作。

我的问题是我应该怎么做才能转换这些功能？如果根本需要转换？ 这是我的代码：

from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense
import numpy as np
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import make_column_transformer


seed = 9
np.random.seed(seed)
netTraffic = np.loadtxt('netTraffic_100each.csv', delimiter=',', skiprows=1)

# OneHotEncoder
make_column_transformer(
    (OneHotEncoder(), ['Source'], ['Destination'], ['Protocol'], ['Info']))

# LabelEncoder
le = preprocessing.LabelEncoder()
le.fit(['Class'])
list(le.classes_)
le.transform(['Class'])
print(netTraffic.Class.dtypes)

X = netTraffic[:, 0:6]
Y = netTraffic[:, 6]

(X_train, X_test, Y_train, Y_test) = train_test_split(X, Y, test_size=0.3, random_state=seed)

model = Sequential()
model.add(Dense(7, input_dim=6, init='uniform', activation='relu'))
model.add(Dense(6, init='uniform', activation='relu'))
model.add(Dense(14, init='uniform', activation='relu'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(X_train, Y_train, validation_data=(X_test, Y_test), nb_epoch=20, batch_size=5)

scores = model.evaluate(X_test, Y_test)
print("Accuracy: %.2f%%" % (scores[1] * 100))

这是错误：

Traceback (most recent call last):
  File "C:/Users/PycharmProjects/webmining/testNN/neuralNetusingtfSite.py", line 12, in <module>
    netTraffic = np.loadtxt('netTraffic_100each.csv', delimiter=',', skiprows=1)
  File "C:\Users\Anaconda3\envs\webmining\lib\site-packages\numpy\lib\npyio.py", line 1141, in loadtxt
    for x in read_data(_loadtxt_chunksize):
  File "C:\Users\Anaconda3\envs\webmining\lib\site-packages\numpy\lib\npyio.py", line 1068, in read_data
    items = [conv(val) for (conv, val) in zip(converters, vals)]
  File "C:\Users\Anaconda3\envs\webmining\lib\site-packages\numpy\lib\npyio.py", line 1068, in <listcomp>
    items = [conv(val) for (conv, val) in zip(converters, vals)]
  File "C:\Users\Anaconda3\envs\webmining\lib\site-packages\numpy\lib\npyio.py", line 775, in floatconv
    return float(x)
ValueError: could not convert string to float: 'Dell_b2:5b:a6'

前几行数据：

我还在这里更新了用于此代码的 csv 文件：https://gofile.io/?c=L8UNYb

Answer 1

看看pd.get_dummies:

import pandas as pd

df = pd.read_csv('netTraffic_100each.csv')
df_encoded = pd.get_dummies(df, drop_first=True)
..