User guide

Skrub facilitates preparing tables for machine learning. It is not a replacement for tools such as SQL or pandas, as these tools are much more versatile. Rather it gives higher-level operations for machine-learning, typically with scikit-learn with its pipelines.

Skrub highlights:

• facilitates separating the train and test operations, for model selection and to put models in production

• enables statistical and imperfect assembly, as machine-learning models can typically retrieve signals even in noisy data.

• Encoding: creating feature matrices
  • Turning a dataframe into a numerical feature matrix
  • Encoding open-ended entries and dirty categories
  • Encoding dates
• Assembling: joining multiple tables
  • Fuzzy joining tables
  • Joining external tables for machine learning
  • Column selection inside a pipeline
  • Going further: embeddings for better analytics
• Cleaning
  • deduplicate(): merging variants of the same entry
• Development
  • Vision: where is skrub heading?
    • Vision statement
    • Roadmap
  • About
  • Contributing to skrub
    • I just have a question
    • What should I know before I get started?
    • How can I contribute?
      • Reporting bugs
        • How do I submit a bug report?
      • Suggesting enhancements
        • How do I submit an enhancement proposal?
          • If the enhancement proposal is validated
          • If the enhancement is refused
      • Writing your first Pull Request
        • Preparing the ground
        • Setting up the environment
        • Implementation
        • Submitting your code
        • Integration
      • Continuous Integration (CI)
    • Building the documentation
  • Changes
    • Ongoing development
      • Major changes
      • Minor changes
    • skrub release 0.1.0
      • Major changes
      • Minor changes
    • Before skrub: dirty_cat
    • Dirty-cat release 0.4.1
      • Major changes
      • Minor changes
    • Dirty-cat Release 0.4.0
      • Major changes
      • Minor changes
      • Bug fixes
    • Dirty-cat Release 0.3.0
      • Major changes
      • Notes
    • Dirty-cat Release 0.2.2
      • Bug fixes
    • Dirty-cat Release 0.2.1
      • Major changes
      • Bug-fixes
      • Notes
    • Dirty-cat Release 0.2.0
      • Major changes
      • Notes
    • Dirty-cat Release 0.2.0a1
      • Major changes
      • Bug-fixes
    • Dirty-cat Release 0.1.1
      • Major changes
      • Bug-fixes
    • Dirty-cat Release 0.1.0
      • Major changes
      • Bug-fixes
    • Dirty-cat Release 0.0.7
    • Dirty-cat Release 0.0.6
    • Dirty-cat Release 0.0.5