Icon

04_​Data_​Preprocessing_​for_​ML_​Models1

There has been no title set for this workflow's metadata.

Data Preprocessing for ML Models

This workflow demonstrates the following standard preprocessing steps before training a machine learning model:
- Partitioning
- Outlier detection
- Missing value handling
- Dimensionality reduction
- Conversion
- Feature selection

URL: House Prices Dataset https://www.kaggle.com/marcopale/housing

This workflow demonstrates the standard preprocessing steps before training a machine learning model.
Normalization
Z-Score Normalization (Gaussian) Transform the columns into thecolumns with mean 0.0 and standard deviation 1.0
Missing Values Handling
Dimensionality Reduction
Outlier Detection
Workflow Executor
Z-Score
Normalizer
execute up-stream before configuration
AutoML (Regression)
Z-Score
Normalizer (Apply)
Conversion
Partition randomly 80% for training 20% for test
Partitioning
Feature Selection
Numeric Scorer
CSV Reader
Denormalize from [0,1] back into original range
Denormalizer

Nodes

Extensions

Links