Data, Python, Machine learning
This competition was held on Kaggle from august to november 2017. Porto Seguro is a large brasilian insurance company that whishes to build a model that predicts the probability that a driver will initiate an auto insurance claim in the next year. The dataThe training data is a anonymized 113Mo .csv file with 59 features Read More …
After having completed the first three lectures in Andrew Ng’s excellent deep learning lecture on coursera, I decided to practice my new skills using kaggle competitions.For a first example, I’ll use the Titanic dataset again.The data has already been analysed and processed (log, binning, etc.) in a previous article, so I’ll skip this part. import Read More …
I have recently discovered MLBox, an automated machine learning python library.Its main author, Axel Aronio de Romblay, promises : Fast reading and distributed data preprocessing/cleaning/formatting. Highly robust feature selection and leak detection. Accurate hyper-parameter optimization in high-dimensional space. State-of-the art predictive models for classification and regression (Deep Learning, Stacking, LightGBM,…). Prediction with models interpretation. Quite Read More …
Suite à mon précédent post, j’ai passé quelques jours à travailler sur le problème de prédiction des prix de l’immobilier. J’ai pu améliorer mon score (~0.125) et gagner plus de 100 places dans le classement.Le code complet et largement commenté est fourni sous forme de notebook (voir plus bas), vous pouvez également le consulter sur Read More …
Cette compétition proposée sur kaggle, consiste à construire un modèle permettant de prédire les chances de survie lors du naufrage du Titanic.C’est un excellent premier exercice pour mettre en oeuvre ses talents de data scientist.Nous disposons d’une partie de la liste des passagers et de certaines informations : a-t-il péri dans le naufrage, nom, age, Read More …