netsec-lab/competition/classifier.py
Günter Windsperger f87eb289e4 Update rf trainer +classifier
+ Change preprocessing method
+ Do sampling before data splitting
2021-06-14 19:11:22 +02:00

46 lines
1.4 KiB
Python

import pandas as pd
import pickle
from sklearn.preprocessing import LabelEncoder
# Source: https://stackoverflow.com/questions/24458645/label-encoding-across-multiple-columns-in-scikit-learn
class MultiColumnLabelEncoder:
def __init__(self, columns=None):
self.columns = columns # array of column names to encode
def fit(self, X, y=None):
return self # not relevant here
def transform(self, X):
'''
Transforms columns of X specified in self.columns using
LabelEncoder(). If no columns specified, transforms all
columns in X.
'''
output = X.copy()
if self.columns is not None:
for col in self.columns:
output[col] = LabelEncoder().fit_transform(output[col])
else:
for colname, col in output.iteritems():
output[colname] = LabelEncoder().fit_transform(col)
return output
def fit_transform(self, X, y=None):
return self.fit(X, y).transform(X)
# 1. Import data
data = pd.read_csv('input.csv')
data_end = pd.read_csv('input.csv')
data = MultiColumnLabelEncoder(columns=['sourceIPAddress', 'destinationIPAddress']).fit_transform(data)
x = data.to_numpy()
# 2. Loading a trained model and predict
model = pickle.load(open('network_traffic_classifier.sav', 'rb'))
y_pred = model.predict(x)
# 3. Add predictions and save output file
data_end['sublabel'] = y_pred
data_end.to_csv('output.csv', index=False)