In this first chapter, you will get exposure to the Kaggle competition process. You will train a model and prepare a csv file ready for submission. You will learn the difference between Public and Private test splits, and how to prevent overfitting.

Competitions overview

Explore train data

Explore test data

Prepare your first submission

Determine a problem type

Train a simple model

Prepare a submission

Public vs Private leaderboard

What model is overfitting?

Train XGBoost models

Explore overfitting XGBoost

Kaggle competitions process

Now that you know the basics of Kaggle competitions, you will learn how to study the specific problem at hand. You will practice EDA and get to establish correct local validation strategies. You will also learn about data leakage.

Understand the problem

Understand the problem type

Define a competition metric

Initial EDA

EDA statistics

EDA plots I

EDA plots II

Local validation

K-fold cross-validation

Stratified K-fold

Validation usage

Time K-fold

Overall validation score

Dive into the Competition

You will now get exposure to different types of features. You will modify existing features and create new ones. Also, you will treat the missing data accordingly.

Feature engineering

Feature aritmetiche

Caratteristiche di data

Feature categoriche

Label encoding

One-Hot encoding

Target encoding

Mean target encoding

Oltre la classificazione binaria

Dati mancanti

Trova i dati mancanti

Imputa i dati mancanti

Feature Engineering

Time to bring everything together and build some models! In this last chapter, you will build a base model before tuning some hyperparameters and improving your results with ensembles. You will then get some final tips and tricks to help you compete more efficiently.

Baseline model

Replicate validation score

Baseline based on the date

Baseline based on the gradient boosting

Hyperparameter tuning

Grid search

2D grid search

Model ensembling

Model blending

Model stacking I

Model stacking II

Final tips

Testing Kaggle forum ideas

Select final submissions

Final thoughts

Modeling

Demand forecasting (train)

Demand forecasting (test)

House prices (train)

House prices (test)

Taxi rides (train)

Taxi rides (test)

Kaggle è la piattaforma più famosa per le competizioni di Data Science. Partecipare a queste competizioni ti permette di lavorare con insiemi di dati reali, esplorare vari problemi di Machine Learning, competere con altri partecipanti e, soprattutto, fare preziosa esperienza pratica. In questo corso imparerai ad affrontare e strutturare qualsiasi competizione di Data Science. Saprai scegliere il corretto schema di validazione locale ed evitare l'overfitting. Inoltre, padroneggerai tecniche avanzate di feature engineering e approcci di ensembling dei modelli. Tutte queste tecniche saranno messe in pratica su insiemi di dati delle competizioni Kaggle.

Extreme Gradient Boosting with XGBoost

Scopri come vincere le competizioni Kaggle: approccio giusto e schema di validazione adeguato.

Vincere una competizione Kaggle con Python

Scopri come partecipare e vincere le competizioni su Kaggle.

Scienziato specializzato in apprendimento automatico in Python

Trova i dati mancanti

Vincere una competizione Kaggle con Python

Esercizio pratico interattivo