Upload New File

NLP.py

+# Natural Language Processing for Predict IoT Network Anomaly
+
+# Importing the libraries
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sns
+import joblib
+import numpy as np
+
+# Importing the dataset
+dataset = pd.read_csv('DatasetRF.tsv', delimiter = '\t', quoting = 3)
+
+# Cleaning the texts
+import re
+import nltk
+nltk.download('stopwords')
+from nltk.corpus import stopwords
+from nltk.stem.porter import PorterStemmer
+corpus = []
+for i in range(0, 31):
+    log = re.sub('[^a-zA-Z0-9]', ' ', dataset['traffic'][i])
+    log = log.lower()
+    log = log.split()
+    ps = PorterStemmer()
+    log = [ps.stem(word) for word in log if not word in set(stopwords.words('english'))]
+    log = ' '.join(log)
+    corpus.append(log)
+
+# Creating the Bag of Words model
+from sklearn.feature_extraction.text import CountVectorizer
+cv = CountVectorizer(max_features = 140)
+X = cv.fit_transform(corpus).toarray()
+y = dataset.iloc[:, 1].values
+
+# Training the Random Forest Regression model on the whole dataset
+from sklearn.ensemble import RandomForestRegressor
+regressor = RandomForestRegressor(n_estimators = 10, random_state = 0)
+regressor.fit(X, y)
+
+# Saving the trained model
+joblib.dump(regressor, 'random_forest_model.joblib')
+joblib.dump(cv, 'count_vectorizer.joblib')
\ No newline at end of file