This repository contains code that support the development of some Machine Learning projects I have developed during the course of my learning journey as a Data Scientist and NLP Engineer.
Here's a brief description of the projects I have pushed into this repo:
projects/creditcard_default_classifier.ipynb
: This file contains code for developing, training, and testing a classifier with the goal of predicting whether a credit card client will default or not. This is an end-to-end Machine Learning project covering all aspects along the model development cycle, from data splitting and pipeline development to feature engineering, feature selection, training of different models, hyperparameter optimization, best model evaluation, feature importance interpretation, and summary of final results.projects/ner_kaggle_competition.ipynb
: This file contains code for developing, training, and testing a Conditional Random Field (CRF) model to perform Named Entity Recognition (NER). The evaluation in the test set achieved a micro F1 Score of0.96819
reaching 1st place in the designated Kaggle Competition.