0% completed

All LessonsFree Lessons

Introduction

What is feature engineering?Why do we need feature engineering?Feature engineering vs. feature selection

Variable Types

What is a variable?Numerical variables Categorical variables Dates & times variables Mixed variables Quiz

Common Concerns in Datasets

Missing data Categorical variable — cardinality Categorical variable — rare labels Linear model assumptions Variable distribution Outliers Feature magnitude Quiz

Handling & Imputing Missing Values

Data imputation definition and techniques Mean or median imputation Arbitrary value imputation End of tail imputation Frequent category imputation Missing category imputation Complete case analysis Random sample imputation Missing indicator Quizz Coding challenge

Encoding Categorical Variables

Categorical encoding One-hot encoding Integer or label encoding Count or frequency encoding Ordered label encoding Mean or target encoding Weight of evidence encoding Probability ratio encoding Rare label encoding Binary encoding Quiz Coding challenge

Transforming Variables

Why do we need transformations?Logarithmic transformation Square root transformation Reciprocal transformation Exponential or power transformation Box-Cox transformation Yeo-Johnson transformation Quiz

Variable Discretization

Discretization approaches Equal-width discretization Equal-frequency discretization K-Means discretization Discretization with decision trees How to use it now?Custom discretization Quiz Coding Challenge

Handling Outliers

Detecting outliers Handling outliers Trimming Censoring Imputing Transformation Quiz Coding Challenge

Feature Scaling

Why feature scaling matters Mean normalization Standardization Robust scaling (scaling to median and IQR)Min-Max scaling Maximum absolute scaling Scaling to vector unit norm Quiz Coding challenge

Engineering Geospatial Data

Setup & visualisation Latitude & longitude Perform clustering Reverse geocoding Distance feature Extract coordinates Other derived features Quiz

Handling Date-Time and Mixed Variables

Engineering variables of date and time

Cyclical feature problem

Engineering mixed variables types

Coding challenge

Resampling Imbalanced Data

What is an imbalanced dataset?Setup & the metric problem Resampling Undersampling Oversampling Combining oversampling and undersampling Other techniques & resources Quiz Coding Challenge

Advanced Feature Engineering Techniques

Advanced categorical encoding Advanced missing value imputation Advanced outlier detection Automated feature engineering Coding challenge

Conclusion

...

/

Quiz

Quiz

As we learned earlier, mixed and date-time variables are prevalent in datasets, ...

Create a free account to access the full course.

By signing up, you agree to Educative's Terms of Service and Privacy Policy