Preprocessing Result #35 — Analysis Report
Contents
- preprocessing (#35) completed
1. Preprocessing
2026-09-21 02:12:55 · preprocessing
Preprocessing transformed the dataset from 393 rows to 393 rows with 33 output features.
| n_rows_in | 393 |
|---|---|
| n_rows_out | 393 |
| n_features_out | 33 |
| target_col | PC_SHOOTMASS |
| derived_dataset_id | 695 |
outlier report
| name | value |
|---|---|
| method | iqr |
| handling | flag |
| n_outliers_detected | 17 |
| n_original | 393 |
| min_cols_required | 4 |
| n_removed | 0 |
| timing | before_split |
before after boxplot
missingness heatmap
Method & Provenance
- Method
- Preprocessing
- Engine
- Python · pandas/scikit-learn 3.0.3
- Input dataset
- gallery — catg_example_01_forage_biomass.csv
- Started
- 2026-09-21 02:12:55.894015
- Permanent link
- https://cat-g-omxpert.wishartlab.com/results/by-token/3496fe33b6fd47cc9409f0c0d5edb0d3
| Parameter | Value |
|---|---|
| normalization | {'method': 'min-max'} |
| outlier_handling | {'method': 'iqr', 'handling': 'flag', 'min_col_fraction': 0.1} |
| steps | missing_value_imputation → normalization → outlier_handling |
Command history
# python # app.services.preprocessing_service.PreprocessingService # python # step: missing_value_imputation # python # step: normalization # python # step: outlier_handling # python df_out = service.apply(df, steps=steps, params=params)