10/15/24, 8:57 PM Decision Tree - Jupyter Notebook

Decsion Tree Classifier

Using Loan Aproval Dataset

import Libraries
In [9]: # Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, classification_report

Create a Simple Dataset

In [13]: # Create the dataset
data = {
'Age': [25, 45, 35, 50, 23, 40, 30, 28, 55, 33],
'Income': ['Low', 'High', 'Medium', 'High', 'Low', 'Medium', 'High
'Credit_Score': [600, 700, 650, 720, 580, 660, 680, 590, 740, 620]
'Owns_House': ['No', 'Yes', 'No', 'Yes', 'No', 'Yes', 'Yes', 'No',
'Approved': ['No', 'Yes', 'Yes', 'Yes', 'No', 'Yes', 'Yes', 'No',
}

# Convert the dictionary to a pandas DataFrame

df = pd.DataFrame(data)

# Display the dataset

df

Out[13]: Age Income Credit_Score Owns_House Approved

0 25 Low 600 No No

1 45 High 700 Yes Yes

2 35 Medium 650 No Yes

3 50 High 720 Yes Yes

4 23 Low 580 No No

5 40 Medium 660 Yes Yes

6 30 High 680 Yes Yes

7 28 Low 590 No No

8 55 High 740 Yes Yes

9 33 Low 620 No No

localhost:8888/notebooks/Downloads/Decision Tree.ipynb 1/4

10/15/24, 8:57 PM Decision Tree - Jupyter Notebook

Step 3: Encode Categorical Features

convert the categorical variables like "Income" and "Owns_House" into numerical values for
the model. We'll use LabelEncoder for this.

In [17]: # Initialize LabelEncoder

le = LabelEncoder()

# Convert categorical columns to numerical ones

df['Income'] = le.fit_transform(df['Income']) # Low=1, Medium=2, High
df['Owns_House'] = le.fit_transform(df['Owns_House']) # No=0, Yes=1
df['Approved'] = le.fit_transform(df['Approved']) # No=0, Yes=1

# Display the dataset after encoding

df

Out[17]: Age Income Credit_Score Owns_House Approved

0 25 1 600 0 0

1 45 0 700 1 1

2 35 2 650 0 1

3 50 0 720 1 1

4 23 1 580 0 0

5 40 2 660 1 1

6 30 0 680 1 1

7 28 1 590 0 0

8 55 0 740 1 1

9 33 1 620 0 0

Split the Dataset into Features and Target

In [19]: # Define features (X) and target (y)
X = df.drop('Approved', axis=1)
y = df['Approved']

Split the Data into Training and Test Sets

localhost:8888/notebooks/Downloads/Decision Tree.ipynb 2/4

10/15/24, 8:57 PM Decision Tree - Jupyter Notebook

In [21]: # Split the dataset into training and testing sets (80% train, 20% tes
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.

# Print the shapes of training and testing sets

print(f"Training set size: {X_train.shape}")
print(f"Testing set size: {X_test.shape}")

Training set size: (8, 4)

Testing set size: (2, 4)

Train the Decision Tree Classifier

In [23]: # Initialize the Decision Tree Classifier
clf = DecisionTreeClassifier(random_state=42)

# Train the model using the training data

clf.fit(X_train, y_train)

Out[23]: DecisionTreeClassifier(random_state=42)
In a Jupyter environment, please rerun this cell to show the HTML representation or
trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page
with nbviewer.org.

Step 7: Make Predictions

In [31]: # Make predictions on the testing set
y_pred = clf.predict(X_test)

# Print the actual and predicted values side-by-side for comparison

print("Actual vs Predicted values:")
for actual, predicted in zip(y_test, y_pred):
print(f"Actual: {actual}, Predicted: {predicted}")

Actual vs Predicted values:

Actual: 1, Predicted: 1
Actual: 1, Predicted: 1

Step 8: Evaluate the Model

localhost:8888/notebooks/Downloads/Decision Tree.ipynb 3/4

10/15/24, 8:57 PM Decision Tree - Jupyter Notebook

In [27]: # Evaluate the model's performance

accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")

# Detailed classification report

print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Accuracy: 100.00%

Classification Report:
precision recall f1-score support

1 1.00 1.00 1.00 2

accuracy 1.00 2
macro avg 1.00 1.00 1.00 2
weighted avg 1.00 1.00 1.00 2

In [ ]:

localhost:8888/notebooks/Downloads/Decision Tree.ipynb 4/4