Cancer is a complex and widespread disease characterized by the uncontrolled growth and spread of abnormal cells. There are nearly a hundred distinct forms of cancer that affect various areas of the body. Breast cancer is a condition caused by the overgrowth of cells. In women compared to men, it is more typical. This study aims to explore several types of machine learning models that are used by using Pyspark on a single-node cluster to explore their potential in tumor classification. Employing recursive feature elimination with the cross-validation method to select the best features through the training of a random forest classifier and applied five machine learning algorithms: Naïve Bayes, Logistic regression, Support vector machine, Decision tree, and XGBoost Classifier to distinguish between benign and malignant tumors. Compared to the other algorithms, the XGBoost Classifier improves classification and prediction accuracy by 99%. This research underscores the pivotal role of Pyspark-powered machine learning algorithms in enhancing medical diagnosis and prognosis, particularly in the critical domain of cancer classification. Healthcare providers may be able to increase patient outcomes and diagnostic accuracy by utilizing these cutting-edge computational tools, bringing in a new era of personalized cancer care.