Scribd
Upload
11 views

Exp 4

Uploaded by

Om
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
11 views

Exp 4

Uploaded by

Om
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/ 2

Exp 4 –

import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

# Load the Iris dataset


data = load_iris()
X, y = data.data, data.target

# Split the data into a training and testing set


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Create a base classifier (e.g., Decision Tree)


base_classifier = DecisionTreeClassifier()

# Apply bagging by creating an ensemble of base classifiers


n_estimators = 10 # Number of base classifiers
bagging = BaggingClassifier(base_classifier, n_estimators=n_estimators, random_state=42)

# Fit the bagging model to the training data


bagging.fit(X_train, y_train)

# Make predictions using the bagging model


y_pred = bagging.predict(X_test)

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy of Bagging: {accuracy:.2f}")

# Compare the accuracy with the base classifier (without bagging)


base_classifier.fit(X_train, y_train)
y_base_pred = base_classifier.predict(X_test)
base_accuracy = accuracy_score(y_test, y_base_pred)
print(f"Accuracy of Base Classifier: {base_accuracy:.2f}")

# Analyze the impact on stability and generalization


# You can compare the variance of predictions using bagging vs. a single base classifier

bagging_predictions = []
base_classifier_predictions = []
n_iterations = 100

for _ in range(n_iterations):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=None)

# Bagging predictions
bagging.fit(X_train, y_train)
y_pred = bagging.predict(X_test)
bagging_predictions.append(y_pred)
# Base classifier predictions
base_classifier.fit(X_train, y_train)
y_base_pred = base_classifier.predict(X_test)
base_classifier_predictions.append(y_base_pred)

# Calculate the variance of predictions


bagging_variance = np.var(bagging_predictions)
base_classifier_variance = np.var(base_classifier_predictions)

print(f"Variance of Bagging Predictions: {bagging_variance:.2f}")


print(f"Variance of Base Classifier Predictions: {base_classifier_variance:.2f}")

You might also like