This project focuses on predicting the compressive strength of concrete, a critical property in construction, using a polynomial regression model. The dataset used in this project contains various features that influence the compressive strength of concrete, including the amounts of different materials and the age of the concrete.
The dataset is sourced from the UCI Machine Learning Repository and contains the following features:
Cement (kg in a cubic meter) Blast Furnace Slag (kg in a cubic meter) Fly Ash (kg in a cubic meter) Water (kg in a cubic meter) Superplasticizer (kg in a cubic meter) Coarse Aggregate (kg in a cubic meter) Fine Aggregate (kg in a cubic meter) Age (days) The target variable is:
The goal of this project is to build a predictive model that accurately estimates the compressive strength of concrete based on the given features. This involves:
Performing exploratory data analysis (EDA) to understand the relationships between the features and the target variable. Creating polynomial features to capture non-linear relationships. Building and training a polynomial regression model. Evaluating the model's performance using metrics such as RMSE and R². Visualizing the model's predictions compared to actual values. Testing the model with new, arbitrary input values to demonstrate its practical application. By completing this project, we aim to develop a robust predictive model that can assist in optimizing concrete mixtures for desired compressive strengths, ultimately contributing to more efficient and effective construction practices.
- Explored data relationships through exploratory analysis
- Developed and assessed a polynomial regression model
- Attained a solid fit with R² of 0.813 for training and 0.784 for testing
- Validated the model using new input values
you can find the Data Set in this link "https://archive.ics.uci.edu/ml/machine-learning-databases/concrete/compressive/Concrete_Data.xls"