labs/Module-4/4.Phishing_detection_Decision_trees.ipynb

In [ ]:

import pandas as pd
import numpy as np
from sklearn import *
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

In [ ]:

phishing_dataset = np.genfromtxt('datasets-2/phishing_dataset.csv', delimiter=',', dtype=np.int32)
samples = phishing_dataset[:,:-1]
targets = phishing_dataset[:, -1]

In [ ]:

from sklearn.model_selection import  train_test_split
training_samples, testing_samples, training_targets, testing_targets = train_test_split(samples, targets, test_size = 0.2, random_state= 0)

In [ ]:

from sklearn import tree
tree_classifier = tree.DecisionTreeClassifier()
tree_classifier.fit(training_samples, training_targets)
predictions = tree_classifier.predict(testing_samples)
accuracy = 100.0* accuracy_score(testing_targets, predictions)
print("Decision Tree accuracy: "+ str(accuracy))

In [ ]:

from sklearn.metrics import classification_report , confusion_matrix

print("Confusion Matrix:")
print(confusion_matrix(testing_targets, predictions))

print("\nClassification Report:")
print(classification_report(testing_targets, predictions))

In [ ]: