课程

Winning a Kaggle Competition in Python

高级技能水平

更新时间 2026年5月

Learn how to approach and win competitions on Kaggle.

免费开始课程

PythonMachine Learning4 小时16 视频52 练习4,200 经验值21,452成就声明

创建您的免费帐户

或

继续操作即表示您接受我们的《使用条款》和《隐私政策》，并同意您的数据存储在美国。

深受数千家公司学习者的喜爱

培训2人或更多？

试用DataCamp for Business

课程描述

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.

先决条件

Extreme Gradient Boosting with XGBoost

1

Kaggle competitions process

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

50 经验值

Explore train data

100 经验值

Explore test data

100 经验值

Prepare your first submission

50 经验值

Determine a problem type

50 经验值

Train a simple model

100 经验值

Prepare a submission

100 经验值

Public vs Private leaderboard

50 经验值

What model is overfitting?

50 经验值

Train XGBoost models

100 经验值

Explore overfitting XGBoost

100 经验值

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.

Understand the problem

50 经验值

Understand the problem type

50 经验值

Define a competition metric

100 经验值

Initial EDA

50 经验值

EDA statistics

100 经验值

EDA plots I

100 经验值

EDA plots II

100 经验值

Local validation

50 经验值

K-fold cross-validation

100 经验值

Stratified K-fold

100 经验值

Validation usage

50 经验值

Time K-fold

100 经验值

Overall validation score

100 经验值

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.

Feature engineering

50 经验值

Arithmetical features

100 经验值

Date features

100 经验值

Categorical features

50 经验值

Label encoding

100 经验值

One-Hot encoding

100 经验值

Target encoding

50 经验值

Mean target encoding

100 经验值

K-fold cross-validation

100 经验值

Beyond binary classification

100 经验值

Missing data

50 经验值

Find missing data

100 经验值

Impute missing data

100 经验值

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.

Baseline model

50 经验值

Replicate validation score

100 经验值

Baseline based on the date

100 经验值

Baseline based on the gradient boosting

100 经验值

Hyperparameter tuning

50 经验值

Grid search

100 经验值

2D grid search

100 经验值

Model ensembling

50 经验值

Model blending

100 经验值

Model stacking I

100 经验值

Model stacking II

100 经验值

50 经验值

Testing Kaggle forum ideas

100 经验值

Select final submissions

50 经验值

Final thoughts

50 经验值

Winning a Kaggle Competition in Python

课程完成

获得成就证明

将此证书添加到你的 LinkedIn 档案、简历或履历中
在社交媒体和绩效评估中分享立即注册

加入超过19百万学习者，今天就开始Winning a Kaggle Competition in Python！

创建您的免费帐户

或

继续操作即表示您接受我们的《使用条款》和《隐私政策》，并同意您的数据存储在美国。

通过 DataCamp for Mobile 提升您的数据技能

随时随地通过我们的移动课程和每日 5 分钟编程挑战提升技能。