Create classifier.py

competition/classifier.py

@@ -0,0 +1,24 @@
+# 1. Importing new CSV data in pandas dataframes
+import pandas as pd
+import pickle
+from sklearn import preprocessing
+
+data = pd.read_csv("input.csv")
+x = data.to_numpy()
+
+# Preprocessing data - encode ip addresses to numerical values
+le = preprocessing.LabelEncoder()
+le.fit(data['sourceIPAddress'])
+data['sourceIPAddress'] = le.transform(data['sourceIPAddress'])
+le.fit(data['destinationIPAddress'])
+data['destinationIPAddress'] = le.transform(data['destinationIPAddress'])
+
+# 3. Loading a trained model
+model = pickle.load(open('network_traffic_classifier.sav', 'rb'))
+y_pred = model.predict(x)
+
+print(data)
+
+data.append(y_pred)
+
+