Notes

1. Write a program to implement the naïve Bayesian classifier for a sample training data set stored as a .CSV file. Compute the accuracy of the classifier, considering few test data sets.

sample_training_data.csv

feature1,feature2,feature3,target
1,2,3,A
4,5,6,B
7,8,9,A
10,11,12,B



import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

# Load the dataset from CSV
def load_dataset(filename):
return pd.read_csv(filename)

# Split dataset into train and test sets
def split_dataset(dataset, test_size=0.2):
X = dataset.drop('target', axis=1)
y = dataset['target']
return train_test_split(X, y, test_size=test_size, random_state=42)

# Train Naive Bayes classifier
def train_classifier(X_train, y_train):
classifier = GaussianNB()
classifier.fit(X_train, y_train)
return classifier

# Test classifier and compute accuracy
def test_classifier(classifier, X_test, y_test):
y_pred = classifier.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
return accuracy

# Main function
def main():
# Load dataset
dataset = load_dataset('sample_training_data.csv')

# Split dataset into train and test sets
X_train, X_test, y_train, y_test = split_dataset(dataset)

# Train Naive Bayes classifier
classifier = train_classifier(X_train, y_train)

# Test classifier
accuracy = test_classifier(classifier, X_test, y_test)
print("Accuracy:", accuracy)

if __name__ == "__main__":
main()