Professional Documents
Culture Documents
20MIS1025 - DecisionTree - Ipynb - Colaboratory
20MIS1025 - DecisionTree - Ipynb - Colaboratory
ipynb - Colaboratory
from IPython.display import Image
%matplotlib inline
import os
from pathlib import Path
import pandas as pd
df = pd.read_csv("KDD_Train.csv")
df.replace(('normal','anomaly'), (0,1), inplace=True)
import warnings
warnings.filterwarnings('ignore')
import numpy as np
X = df.iloc[:,[4,9]].values
y=df.iloc[:, -1].values
print('Class labels:',np.unique(y))
Class labels: [0 1]
df.isnull().sum().sort_values(ascending=False).head()
duration 0
dst_host_count 0
srv_count 0
serror_rate 0
srv_serror_rate 0
dtype: int64
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 1, stratify = y)
print('Labels count in y', np.bincount(y))
print('Labels count in y_train', np.bincount(y_train))
print('Labels count in y_test', np.bincount(y_test))
from sklearn.preprocessing import StandardScaler #normalisation - converting values in the range 0
#all values are normalised
sc = StandardScaler() #mean and standard deviation
sc.fit(X_train) #fit against standard scalar con
X_train_std = sc.transform(X_train) #transformation of both training and test data is
X_test_std = sc.transform(X_test)
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
https://colab.research.google.com/drive/1FB1tRB0tXqyCLvBpmguU9gQbm0Ki-Plo#scrollTo=paC5OhBLFmoJ&printMode=true 1/4
8/23/23, 11:40 PM 20MIS1025_DecisionTree.ipynb - Colaboratory
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0],
y=X[y == cl, 1],
alpha=0.8,
c=colors[idx],
marker=markers[idx],
label=cl,
edgecolor='black')
# highlight test examples
if test_idx:
# plot all examples
X_test, y_test = X[test_idx, :], y[test_idx]
plt.scatter(X_test[:, 0],
X_test[:, 1],
c='',
edgecolor='black',
alpha=1.0,
linewidth=1,
marker='o',
s=100,
label='test set')
from sklearn.tree import DecisionTreeClassifier
tree_model = DecisionTreeClassifier(criterion='gini',max_depth=2,random_state=1)
tree_model.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
#plot_decision_regions(X_combined, y_combined,classifier=tree_model,test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
#plt.savefig('images/03_20.png', dpi=300)
plt.show()
https://colab.research.google.com/drive/1FB1tRB0tXqyCLvBpmguU9gQbm0Ki-Plo#scrollTo=paC5OhBLFmoJ&printMode=true 2/4
8/23/23, 11:40 PM 20MIS1025_DecisionTree.ipynb - Colaboratory
from sklearn import tree
tree.plot_tree(tree_model)
#plt.savefig('images/03_21_1.pdf')
plt.show()
!pip3 install pydotplus
!conda install python-graphviz
!pip install graphviz
!pip3 install pydotplus
from pydotplus import graph_from_dot_data
from sklearn.tree import export_graphviz
dot_data = export_graphviz(tree_model,
filled=True,
rounded=True,
class_names=['Setosa',
'Versicolor',
'Virginica'],
feature_names=['petal length',
'petal width'],
out_file=None)
graph = graph_from_dot_data(dot_data)
graph.write_png('tree.png')
True
https://colab.research.google.com/drive/1FB1tRB0tXqyCLvBpmguU9gQbm0Ki-Plo#scrollTo=paC5OhBLFmoJ&printMode=true 3/4
8/23/23, 11:40 PM 20MIS1025_DecisionTree.ipynb - Colaboratory
https://colab.research.google.com/drive/1FB1tRB0tXqyCLvBpmguU9gQbm0Ki-Plo#scrollTo=paC5OhBLFmoJ&printMode=true 4/4