datatrigger

asymmetric_loss

Implement a custom asymmetric loss to train and drive a regression model towards underestimation or overestimation

nlp_hugging_face

Text classification with the transformers library from Hugging Face, by fine-tuning DistilBERT or using summarization + Zero-Shot classification.

aircraft_classifier

This repo is the source of the web app built on the cloud platoform Heroku at:

shiny_apps

Run the CLT Shiny app : https://datatrigger.shinyapps.io/CLT_Visualization/

interpretable_machine_learning

Getting explanations for predictions made by black box models.

kafka_stream_air_quality

Retrieving the air quality index of various cities through an HTTP API and generating a Kafka stream.

algorithms_data_structures

Algorithms & Data Structures in Python

stocks_backend

FastAPI backend to fetch stocks data

stocks_frontend

Frontend of stocks single-page application stocks.vlgdata.io

unlimited-translation_docker_swarm

A translation service (German to English) with no character limit.

unlimited-translation_kubernetes

Deploying our multi-container app unlimited-translation to a GKE cluster

unlimited_translation-backend

Source of the Docker image for the API backend of the unlimited-translation app

unlimited_translation-frontend-k8s

Source code of a translation app's Flask frontend microservice

annotated_research_papers

This repo contains annotated research papers that I found really good and useful

anomaly_detection_lof

Anomaly detection using Local Outlier Factor / Isolation Forest with Python / R

aws_data_engineering

AWS Certified Data Engineer - Associate

computer_vision

Computer vision projects with PyTorch and fast.ai.

datatrigger

My blog about data engineering and machine learning operations

light_gradient_boosted_machine

Experiment with with Microsoft's LightGBM to predict the critical temperature of superconductors.

pandas_spark_training

python-sample-vscode-flask-tutorial

Sample code for the Flask tutorial in the VS Code documentation

scaling

How to properly split and scale a dataset using Python, Spark & R modules.

school_projects

Here are some projects I did during my master of science in statistics and data science at ISUP, Paris.

snippets

Snippets of code frequently used

subtotals

Adding totals and subtotals rows with pandas / the tidyverse

sum_random_variables

Contour plots to answer this question: if the sum of two random variables is large, are they likely to be both large ?

unlimited_translation-frontend-swarm

Source code of the Docker image for the unlimited-translation app frontend

weighted_random_forest_spark_3

Experiment with sample weights support added to random forest and a few other classifiers in Spark 3