This repository contains Jupyter notebooks for learning the basics of Machine Learning. Each notebook has a run script that will start a docker container with the appropriate environment for the Jupyter server.
training dataset - the data you use for training your model
test dataset - the data you use to test your model
features - the attributes of your data that are used by the model as input
label(s) - the attribute(s) of your data that the model is trying to predict
- Analyse and improve the quality of your data
- Perform transformations on your data (example: change the type of some features or represent the differently)
- Understand your data
- Choose a model for training
- Train using part of your training dataset
- Test using the other part of your training dataset
- Measure accuracy of your model
- Go back to any of the steps above in order to improve the accuracy
- Test your model using the test dataset
- Celebrate! :)
Notebook: machine-learning/inspecting-data/inspecting-data.ipynb
Description: contains basic commands for inspecting the structure and quality of your data sets
Run: schipyrun.sh
Notebook: machine-learning/linear-regression/linear-regression.ipynb
Description: contains a simple example of training a model using Linear Regression
Run: schipyrun.sh
Notebook: tensor-flow/tf-simple-operations
Description: contains basic TensorFlow evaluations
Run: tfrun.sh
Author: Oana Cioara
Copyright: The content of this repository is public. You are allowed to access the "source-code" and use it as you wish, for study or change it for personal use.