MLTask

• In this project, several classification algorithms were implemented and evaluated. The best accuracy has been achieved using a Random Forest Classifier. The main scripts supporting this statement are 'randomforestclassifier.py' and 'randomforestclassifier.ipynb'. The datasets used in those files were processed using 'preprocess_data.py' and saved under '/data'
• Other classification algorithms were saved in 'RNN', 'CNN', and 'basic learnings.py'
• The implementation of several additional data-preprocessing techniques are saved under:
  • The "some_processed_data" folder contains the data prepared using some
  • The file 'preprocess_data_fft_maf.py' contains a FFT and moving average filter implementation on the input data
  • The "data_process.ipynb" file contains the code for preparing the dataset for the Machine Learning model.
  • The "visualization"folder contains the code and data for visualizations.
    • The "visualization.ipynb" file contains the code for visualizations.
    • The four .npy files are the data currently using, prepared for visualizations.