UsefulLinks
Computer Science
Artificial Intelligence
Machine Learning
Machine Learning with Scikit-Learn
1. Introduction to Scikit-Learn
2. Core Scikit-Learn Concepts and API
3. Machine Learning Fundamentals
4. Data Preprocessing and Feature Engineering
5. Supervised Learning: Regression
6. Supervised Learning: Classification
7. Model Evaluation and Metrics
8. Improving Model Performance
9. Unsupervised Learning
10. Building Machine Learning Pipelines
11. Working with Text Data
12. Advanced Topics
13. Model Persistence and Deployment
14. Performance Optimization
15. Best Practices and Common Pitfalls
10.
Building Machine Learning Pipelines
10.1.
Pipeline Concepts
10.1.1.
Benefits of Pipelines
10.1.2.
Data Leakage Prevention
10.1.3.
Code Organization
10.1.4.
Reproducibility
10.2.
The Pipeline Class
10.2.1.
Creating Pipelines
10.2.2.
Pipeline Steps
10.2.3.
Chaining Transformers and Estimators
10.2.4.
Named Steps
10.2.5.
Pipeline Methods
10.3.
The ColumnTransformer
10.3.1.
Column-specific Transformations
10.3.2.
Handling Mixed Data Types
10.3.3.
Remainder Parameter
10.3.4.
Sparse Matrix Handling
10.4.
Feature Union
10.4.1.
Parallel Feature Processing
10.4.2.
Combining Features
10.5.
Pipeline with Preprocessing
10.5.1.
Standard Preprocessing Pipeline
10.5.2.
Categorical and Numerical Features
10.5.3.
Missing Value Handling
10.6.
Pipeline with Feature Selection
10.6.1.
Integrated Feature Selection
10.6.2.
SelectFromModel
10.6.3.
RFE in Pipelines
10.7.
Pipeline Hyperparameter Tuning
10.7.1.
Parameter Naming Conventions
10.7.2.
Grid Search with Pipelines
10.7.3.
Nested Cross-Validation
10.8.
Custom Transformers
10.8.1.
Creating Custom Transformers
10.8.2.
BaseEstimator and TransformerMixin
10.8.3.
fit and transform Methods
10.9.
Pipeline Persistence
10.9.1.
Saving Complete Pipelines
10.9.2.
Loading and Using Saved Pipelines
10.10.
Pipeline Debugging
10.10.1.
Intermediate Results
10.10.2.
Step-by-step Execution
10.10.3.
Memory Usage
Previous
9. Unsupervised Learning
Go to top
Next
11. Working with Text Data