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

65 lines
2.2 KiB
Python

import numpy as np
import pandas as pd
import pickle
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.model_selection import train_test_split
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)
df = pd.read_csv('training4tuplabeled.csv')
y = df['sublabel']
df = df.drop(columns=['sublabel'])
df = MultiColumnLabelEncoder(columns=['sourceIPAddress', 'destinationIPAddress']).fit_transform(df)
oversampler = SMOTE()
X, y = oversampler.fit_resample(df, y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=0)
model = RandomForestClassifier(max_depth=None, n_estimators=30, n_jobs=-1)
model.fit(X_train, y_train)
accuracy = model.score(X_test, y_test)
print('Accuracy: ', accuracy)
y_pred_train = model.predict(X_train)
y_pred_test = model.predict(X_test)
print("\n *************** TRAINING ****************")
# cm_train = confusion_matrix(y_train, y_pred_train)
# print(cm_train)
print(classification_report(y_train, y_pred_train))
print("\n ************** VALIDATION ***************")
# cm_test = confusion_matrix(y_test, y_pred_test)
# print(cm_test)
print(classification_report(y_test, y_pred_test))
pickle.dump(model, open('network_traffic_classifier.sav', 'wb'))