Winning a Kaggle Competition in Python

Learn how to approach and win competitions on Kaggle.

Start Course for Free
4 Hours16 Videos52 Exercises10,334 Learners
4200 XP

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA. You confirm you are at least 16 years old (13 if you are an authorized Classrooms user).

Loved by learners at thousands of companies

Course Description

Kaggle is the most famous platform for Data Science competitions. Taking part in such competitions allows you to work with real-world datasets, explore various machine learning problems, compete with other participants and, finally, get invaluable hands-on experience. In this course, you will learn how to approach and structure any Data Science competition. You will be able to select the correct local validation scheme and to avoid overfitting. Moreover, you will master advanced feature engineering together with model ensembling approaches. All these techniques will be practiced on Kaggle competitions datasets.

  1. 1

    Kaggle competitions process

    Free

    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.

    Play Chapter Now
    Competitions overview
    50 xp
    Explore train data
    100 xp
    Explore test data
    100 xp
    Prepare your first submission
    50 xp
    Determine a problem type
    50 xp
    Train a simple model
    100 xp
    Prepare a submission
    100 xp
    Public vs Private leaderboard
    50 xp
    What model is overfitting?
    50 xp
    Train XGBoost models
    100 xp
    Explore overfitting XGBoost
    100 xp
  2. 2

    Dive into the Competition

    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.

    Play Chapter Now
    Understand the problem
    50 xp
    Understand the problem type
    50 xp
    Define a competition metric
    100 xp
    Initial EDA
    50 xp
    EDA statistics
    100 xp
    EDA plots I
    100 xp
    EDA plots II
    100 xp
    Local validation
    50 xp
    K-fold cross-validation
    100 xp
    Stratified K-fold
    100 xp
    Validation usage
    50 xp
    Time K-fold
    100 xp
    Overall validation score
    100 xp
  3. 3

    Feature Engineering

    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.

    Play Chapter Now
    Feature engineering
    50 xp
    Arithmetical features
    100 xp
    Date features
    100 xp
    Categorical features
    50 xp
    Label encoding
    100 xp
    One-Hot encoding
    100 xp
    Target encoding
    50 xp
    Mean target encoding
    100 xp
    K-fold cross-validation
    100 xp
    Beyond binary classification
    100 xp
    Missing data
    50 xp
    Find missing data
    100 xp
    Impute missing data
    100 xp
  4. 4

    Modeling

    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.

    Play Chapter Now
    Baseline model
    50 xp
    Replicate validation score
    100 xp
    Baseline based on the date
    100 xp
    Baseline based on the gradient boosting
    100 xp
    Hyperparameter tuning
    50 xp
    Grid search
    100 xp
    2D grid search
    100 xp
    Model ensembling
    50 xp
    Model blending
    100 xp
    Model stacking I
    100 xp
    Model stacking II
    100 xp
    Final tips
    50 xp
    Testing Kaggle forum ideas
    100 xp
    Select final submissions
    50 xp
    Final thoughts
    50 xp

In the following tracks

Machine Learning Scientist

Datasets

Demand forecasting (train)Demand forecasting (test)House prices (train)House prices (test)Taxi rides (train)Taxi rides (test)

Collaborators

Hadrien LacroixHillary Green-Lerman

Prerequisites

Supervised Learning with scikit-learnExtreme Gradient Boosting with XGBoostData Manipulation with pandas
Yauhen Babakhin Headshot

Yauhen Babakhin

Kaggle Grandmaster

Yauhen holds a Master’s Degree in Applied Data Analysis and has over 5 years of working experience in Data Science. He worked in Banking, Gaming and eCommerce domains. Yauhen is also the first Kaggle competitions Grandmaster in Belarus having gold medals in both classic Machine Learning and Deep Learning competitions.
See More

What do other learners have to say?

“I've used other sites—Coursera, Udacity, things like that—but DataCamp's been the one that I've stuck with.”

Devon Edwards Joseph
Lloyds Banking Group

“DataCamp is the top resource I recommend for learning data science.”

Louis Maiden
Harvard Business School

“DataCamp is by far my favorite website to learn from.”

Ronald Bowers
Decision Science Analytics, USAA