codes and dataset used in the study "A feasibility study of machine learning-assisted alloy design using wrought aluminum alloys as an example" by Yasaman J. Soofi, Md Asad Rahman, Yijia Gu, Jinling Liu
The following are the python codes that were used to conduct this investigation:
- correlation_heatmap.ipynb Calculation of Spearman correlation coefficients and creation of a heatmap table are part of a statistical correlation research.
- feature_importance.ipynb Feature Importance study for both technological and mechanical properties, and figure preparation for top-10 important features for each property.
- 100seeds_mechanical.ipynb The implementation of regression models to predict mechanical properties for 100 different seeds.
- 100seeds_technological.ipynb The implementation of classification models to predict technological properties for 100 different seeds.
- LOOCV_scatterplt_mechanical Presents the LOOCV training and evaluation of the regression models and also the scatter plots for the mechanical properties.
- LOOCV_technological.ipynb present the LOOCV training and evaluation of the classification models for the technological properties.