The project is converted into a python project with different scripts that map to the different stages
of the AI pipeline. The project is structured in a way that follows recommendations and looks clean
and well-organised. The library dependencies are specified and use an adequate package manager
that guarantees that the exact same dependencies and sub-dependencies are installed in different
machines. The dataset is stored outside the project and can be automatically downloaded as part
of the pipeline. The dataset is stored remotely and the feature encoding is a shared component.
Exploratory code appears only in Jupyter notebooks. Unnecessary code and artefacts are not part of
the project python source. There are clear instructions on how to run the pipeline. All decisions are
properly documented, supported by related work, and reveal a critical understanding of the theory.
The project is converted into a python project with different scripts that map to the different stages of the AI pipeline. The project is structured in a way that follows recommendations and looks clean and well-organised. The library dependencies are specified and use an adequate package manager that guarantees that the exact same dependencies and sub-dependencies are installed in different machines. The dataset is stored outside the project and can be automatically downloaded as part of the pipeline. The dataset is stored remotely and the feature encoding is a shared component. Exploratory code appears only in Jupyter notebooks. Unnecessary code and artefacts are not part of the project python source. There are clear instructions on how to run the pipeline. All decisions are properly documented, supported by related work, and reveal a critical understanding of the theory.