Scribd
Upload
71 views5 pages

DM - Lab - 8 - Jupyter Notebook

The document discusses classification and regression trees using CART, ID3 algorithms. It loads tennis and salary datasets, encodes categorical variables, splits data into training and test sets. Decision trees are constructed to classify tennis play and predict salary. The trees are plotted to visualize the models. Regression tree is also built on salary data to learn the relationship between job level and salary.

Uploaded by

GATE Aspirant
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
71 views5 pages

DM - Lab - 8 - Jupyter Notebook

The document discusses classification and regression trees using CART, ID3 algorithms. It loads tennis and salary datasets, encodes categorical variables, splits data into training and test sets. Decision trees are constructed to classify tennis play and predict salary. The trees are plotted to visualize the models. Regression tree is also built on salary data to learn the relationship between job level and salary.

Uploaded by

GATE Aspirant
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

4/27/23, 8:17 PM DM_Lab_8 - Jupyter Notebook

Topic : CART - Classification & Regression Tree, ID3

In [22]:

1 import pandas as pd
2 import numpy as np
3
4 df1 = pd.read_csv('/home/c0nqu3r0r/Desktop/_Second sem/Data Mining/Dataset/Te
5 df1.drop('Day', axis = 1, inplace = True)# for classification
6
7 df2 = pd.read_csv('/home/c0nqu3r0r/Desktop/_Second sem/Data Mining/Dataset/ar

In [23]:

1 df1.head()

Out[23]:

Outlook Temperature Humidity Wind PlayTennis

0 Sunny Hot High Weak No

1 Sunny Hot High Strong No

2 Overcast Hot High Weak Yes

3 Rain Mild High Weak Yes

4 Rain Cool Normal Weak Yes

In [24]:

1 from sklearn.preprocessing import LabelEncoder


2 Le = LabelEncoder()
3
4 df1['Outlook'] = Le.fit_transform(df1['Outlook'])
5 df1['Temperature'] = Le.fit_transform(df1['Temperature'])
6 df1['Humidity'] = Le.fit_transform(df1['Humidity'])
7 df1['Wind'] = Le.fit_transform(df1['Wind'])
8 df1['PlayTennis'] = Le.fit_transform(df1['PlayTennis'])

In [25]:

1 y1 = df1['PlayTennis']
2 x1 = df1.drop(['PlayTennis'], axis = 1)

localhost:8888/notebooks/Desktop/_Second sem/Data Mining/Lab Work/DM_Lab_8.ipynb 1/5


4/27/23, 8:17 PM DM_Lab_8 - Jupyter Notebook

In [26]:

1 # CART classification Tree


2 from sklearn import tree
3 clf1 = tree.DecisionTreeClassifier(criterion = 'gini')
4 clf1 = clf1.fit(x1, y1)
5 tree.plot_tree(clf1)

Out[26]:

[Text(0.4444444444444444, 0.9, 'X[0] <= 0.5\ngini = 0.459\nsamples =


14\nvalue = [5, 9]'),
Text(0.3333333333333333, 0.7, 'gini = 0.0\nsamples = 4\nvalue = [0,
4]'),
Text(0.5555555555555556, 0.7, 'X[2] <= 0.5\ngini = 0.5\nsamples = 1
0\nvalue = [5, 5]'),
Text(0.3333333333333333, 0.5, 'X[0] <= 1.5\ngini = 0.32\nsamples =
5\nvalue = [4, 1]'),
Text(0.2222222222222222, 0.3, 'X[3] <= 0.5\ngini = 0.5\nsamples = 2
\nvalue = [1, 1]'),
Text(0.1111111111111111, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [1,
0]'),
Text(0.3333333333333333, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [0,
1]'),
Text(0.4444444444444444, 0.3, 'gini = 0.0\nsamples = 3\nvalue = [3,
0]'),
Text(0.7777777777777778, 0.5, 'X[3] <= 0.5\ngini = 0.32\nsamples =
5\nvalue = [1, 4]'),
Text(0.6666666666666666, 0.3, 'X[0] <= 1.5\ngini = 0.5\nsamples = 2
\nvalue = [1, 1]'),
Text(0.5555555555555556, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [1,
0]'),
Text(0.7777777777777778, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [0,
1]'),
Text(0.8888888888888888, 0.3, 'gini = 0.0\nsamples = 3\nvalue = [0,
3]')]

localhost:8888/notebooks/Desktop/_Second sem/Data Mining/Lab Work/DM_Lab_8.ipynb 2/5


4/27/23, 8:17 PM DM_Lab_8 - Jupyter Notebook

In [27]:

1 df2.head()

Out[27]:

Position Level Salary

0 Business Analyst 1 45000

1 Junior Consultant 2 50000

2 Senior Consultant 3 60000

3 Manager 4 80000

4 Country Manager 5 110000

In [28]:

1 x2 = df2.iloc[:, 1:2].values
2 y2 = df2.iloc[:, 2].values

localhost:8888/notebooks/Desktop/_Second sem/Data Mining/Lab Work/DM_Lab_8.ipynb 3/5


4/27/23, 8:17 PM DM_Lab_8 - Jupyter Notebook

In [29]:

1 # CART - Regression Tree


2 from sklearn import tree
3 clf2 = tree.DecisionTreeRegressor()
4 clf2 = clf2.fit(x2, y2)
5 tree.plot_tree(clf2)

Out[29]:

[Text(0.703125, 0.9285714285714286, 'X[0] <= 8.5\nsquared_error = 80


662250000.0\nsamples = 10\nvalue = 249500.0'),
Text(0.53125, 0.7857142857142857, 'X[0] <= 6.5\nsquared_error = 692
1484375.0\nsamples = 8\nvalue = 124375.0'),
Text(0.375, 0.6428571428571429, 'X[0] <= 4.5\nsquared_error = 13812
50000.0\nsamples = 6\nvalue = 82500.0'),
Text(0.25, 0.5, 'X[0] <= 3.5\nsquared_error = 179687500.0\nsamples
= 4\nvalue = 58750.0'),
Text(0.1875, 0.35714285714285715, 'X[0] <= 2.5\nsquared_error = 388
88888.889\nsamples = 3\nvalue = 51666.667'),
Text(0.125, 0.21428571428571427, 'X[0] <= 1.5\nsquared_error = 6250
000.0\nsamples = 2\nvalue = 47500.0'),
Text(0.0625, 0.07142857142857142, 'squared_error = 0.0\nsamples = 1
\nvalue = 45000.0'),
Text(0.1875, 0.07142857142857142, 'squared_error = 0.0\nsamples = 1
\nvalue = 50000.0'),
Text(0.25, 0.21428571428571427, 'squared_error = 0.0\nsamples = 1\n
value = 60000.0'),
Text(0.3125, 0.35714285714285715, 'squared_error = 0.0\nsamples = 1
\nvalue = 80000.0'),
Text(0.5, 0.5, 'X[0] <= 5.5\nsquared_error = 400000000.0\nsamples =
2\nvalue = 130000.0'),
Text(0.4375, 0.35714285714285715, 'squared_error = 0.0\nsamples = 1
\nvalue = 110000.0'),
Text(0.5625, 0.35714285714285715, 'squared_error = 0.0\nsamples = 1
\nvalue = 150000.0'),
Text(0.6875, 0.6428571428571429, 'X[0] <= 7.5\nsquared_error = 2500
000000.0\nsamples = 2\nvalue = 250000.0'),
Text(0.625, 0.5, 'squared_error = 0.0\nsamples = 1\nvalue = 200000.
0'),
Text(0.75, 0.5, 'squared_error = 0.0\nsamples = 1\nvalue = 300000.
0'),
Text(0.875, 0.7857142857142857, 'X[0] <= 9.5\nsquared_error = 62500
000000.0\nsamples = 2\nvalue = 750000.0'),
Text(0.8125, 0.6428571428571429, 'squared_error = 0.0\nsamples = 1
\nvalue = 500000.0'),
Text(0.9375, 0.6428571428571429, 'squared_error = 0.0\nsamples = 1
\nvalue = 1000000.0')]

localhost:8888/notebooks/Desktop/_Second sem/Data Mining/Lab Work/DM_Lab_8.ipynb 4/5


4/27/23, 8:17 PM DM_Lab_8 - Jupyter Notebook

In [30]:

1 # ID3
2 from sklearn import tree
3 clf3 = tree.DecisionTreeClassifier(criterion = 'entropy')
4 clf3 = clf3.fit(x1, y1)
5 tree.plot_tree(clf3)

Out[30]:

[Text(0.4444444444444444, 0.9, 'X[0] <= 0.5\nentropy = 0.94\nsamples


= 14\nvalue = [5, 9]'),
Text(0.3333333333333333, 0.7, 'entropy = 0.0\nsamples = 4\nvalue =
[0, 4]'),
Text(0.5555555555555556, 0.7, 'X[2] <= 0.5\nentropy = 1.0\nsamples
= 10\nvalue = [5, 5]'),
Text(0.3333333333333333, 0.5, 'X[0] <= 1.5\nentropy = 0.722\nsample
s = 5\nvalue = [4, 1]'),
Text(0.2222222222222222, 0.3, 'X[3] <= 0.5\nentropy = 1.0\nsamples
= 2\nvalue = [1, 1]'),
Text(0.1111111111111111, 0.1, 'entropy = 0.0\nsamples = 1\nvalue =
[1, 0]'),
Text(0.3333333333333333, 0.1, 'entropy = 0.0\nsamples = 1\nvalue =
[0, 1]'),
Text(0.4444444444444444, 0.3, 'entropy = 0.0\nsamples = 3\nvalue =
[3, 0]'),
Text(0.7777777777777778, 0.5, 'X[3] <= 0.5\nentropy = 0.722\nsample
s = 5\nvalue = [1, 4]'),
Text(0.6666666666666666, 0.3, 'X[0] <= 1.5\nentropy = 1.0\nsamples
= 2\nvalue = [1, 1]'),
Text(0.5555555555555556, 0.1, 'entropy = 0.0\nsamples = 1\nvalue =
[1, 0]'),
Text(0.7777777777777778, 0.1, 'entropy = 0.0\nsamples = 1\nvalue =
[0, 1]'),
Text(0.8888888888888888, 0.3, 'entropy = 0.0\nsamples = 3\nvalue =
[0, 3]')]

localhost:8888/notebooks/Desktop/_Second sem/Data Mining/Lab Work/DM_Lab_8.ipynb 5/5

You might also like