My Jupyter Notebooks and Google Colab notebooks consisting of the end to end workflow of picking, applying, evaluating and improving Machine Learning models:
- Dog Vision: a dog breed identifier that uses transfer learning to identify the breed of a dog from a picture (Kaggle)
- Bluebook for Bulldozers: learns from time series data to predict the price of bulldozers with regression (Kaggle)
- Predict Heart Disease: uses logistic regression to predict whether a patient has heart disease on the basis of symptoms (heart disease dataset from UCI)
Note: Before running the Dog Vision Deep Learning Google Colab notebook, keep in mind that the processes of training and testing the models (there are two cells that accomplish this) take 2 hours each. So do not blindly run all cells.
Built with: Pandas, Anaconda, NumPy, MatPlotLib, Seaborn, Scikit-Learn, TensorFlow 2, TensorFlow Hub, Keras