This project involves building a regression model using PySpark's MLlib to predict the compressive strength of cement based on its ingredients. The dataset consists of 1030 instances of concrete samples, containing 9 attributes (8 continuous and 1 discrete), and 1 continuous quantitative output variable.

Our goal is to identify the features that are the strongest predictors of cement strength and provide recommendations for optimal values of cement ingredients. We will also create an application where users can input their own values for age and get a predicted value for cement strength.

Before running the code, you will need to have the following installed:

• PySpark: the Python API for Apache Spark
• Jupyter Notebook: an interactive development environment for Python

The dataset used in this project is the Concrete Compressive Strength Data Set from the UCI Machine Learning Repository. It contains 1030 instances of concrete samples, with 9 attributes (8 continuous and 1 discrete) and 1 continuous quantitative output variable (compressive strength).

To run the code, open the Cement_Strength_Prediction.ipynb file in Jupyter Notebook and execute the cells in order. The notebook contains detailed explanations of each step in the code and the results obtained.

To use the application for predicting cement strength based on user input, run the predict_cement_strength function in the notebook after it has been defined. This function takes a single argument age (in days) and returns the predicted cement strength (in MPa).