Prediction of Mental Health Care Needs for an Employee using Pyspark
Project assignments of Big Data Course
📌 Created the best model that predicted which employees will need mental health care using the dataset Mental Health in Tech Survey from Kaggle
📌 Used Pyspark with 7 different algorithms namely Logistic Regression, K-Nearest Neighbor, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, and XGBoost then compares all of these algorithms to get the best accuracy in making predictions.
📌 Utilized preprocessing and visualization techniques for the analysis of variables in the dataset.