Gaussian_Naive_Bias
The Gaussian Naive Bayes model was employed to predict the values in the "Healthy" column of a dataset consisting of four categorical columns ('Food preference', 'Smoker?', 'Living in?', 'Any hereditary condition?') and eleven numerical columns ('Specific ailments', 'Age', 'BMI', 'Follow Diet', 'Physical activity', 'Regular sleeping hours', 'Alcohol consumption', 'Social interaction', 'Taking supplements', 'Mental health management', 'Illness count last year'). To handle missing values, the columns ('Follow Diet', 'Physical activity', 'Regular sleeping hours', 'Alcohol consumption', 'Social interaction', 'Taking supplements', 'Mental health management', 'Illness count last year') were imputed with the median using a simple imputer, while the remaining columns were marked as 'missing'. Gaussian Naive Bayes is a probabilistic model that assumes features are conditionally independent given the class label and follows a Gaussian (normal) distribution. It estimates the class probabilities by calculating the likelihood of each feature value given the class, and then combines them using Bayes' theorem. After training the Gaussian Naive Bayes model on the dataset, the model's performance was evaluated using appropriate metrics such as accuracy, precision, recall, or F1 score. These metrics provide insights into the classifier's ability to accurately predict the "Healthy" values. The predictions made by the Gaussian Naive Bayes model were saved in a CSV file named "submission.csv."
Tags:
#machine-learning
#classification