[TBD]Data science programming

Useful tools

Anaconda in MacBook

Installation

Download Individual edition from here and then run bash <.sh file path> in terminal

Uninstallation

https://docs.anaconda.com/anaconda/install/uninstall/

Jupyter notebook in Mac

Installation

Refer https://jupyter.org/install

conda install -c conda-forge jupyterlab

pytorch library on MacBook

Refer https://pytorch.org/get-started/locally/

conda install pytorch -c pytorch

Try-out pytorch tutorial

https://www.analyticsvidhya.com/blog/2019/09/introduction-to-pytorch-from-scratch/

Transformers on MacBook

Installation

Refer https://anaconda.org/conda-forge/transformers

conda install -c conda-forge transformers

Adaptive learning rate optimization algorithm

The issue with learning rate schedules is that they all depend on hyperparameters that must be manually chosen for each given learning session and may vary greatly depending on the problem at hand or the model used. To combat this there are many different types of adaptive gradient descent algorithms such as Adagrad, Adadelta, RMSprop, Adam which are generally built into deep learning libraries such as Keras.

Refer: https://en.wikipedia.org/wiki/Learning_rate#Adaptive_learning_rate