DataCard Reference

The DataCard is a YAML file that describes your dataset for Pilz.

Complete Example

features:
  - name: age
    statistical: categorial
    type: int
    missing_value: 0
  - name: name
    statistical: categorial
    type: string
  - name: balance
    statistical: numerical
    type: float
    missing_value: 0.0

target:
  feature_name: churn
  values:
    - 'Yes'
    - 'No'

infos:
  source: https://example.com/data
  license: MIT
  date: '2024-01-01'

train_files:
  - /path/to/train.csv
  - /path/to/train2.csv

test_files:
  - /path/to/test.csv

Field Reference

features

List of feature definitions.

Field	Type	Required	Description
name	string	Yes	Column name in CSV
statistical	string	Yes	"categorial" or "numerical"
type	string	Yes	"int", "float", or "string"
missing_value	any	No	Value to replace nulls

target

Describes the target variable.

Field	Type	Required	Description
feature_name	string	Yes	Column name of target
values	list	Yes	All possible class values

infos (optional)

Metadata dictionary for documentation.

infos:
  source: https://example.com
  license: MIT
  description: Customer churn dataset
  version: '1.0'

train_files

Paths to training data files.

train_files:
  - /path/to/train.csv
  - /path/to/train2.csv  # Multiple files supported

test_files

Paths to test/evaluation data files.

test_files:
  - /path/to/test.csv

FeatureType Values

Value	Use For	Example
categorial	Discrete values	"yes", "no", "admin", "blue-collar"
numerical	Continuous values	1.5, 100, -42

!> Important: Use categorial (not categorical)

DataType Values

Value	Description
int	Integer numbers
float	Decimal numbers
string	Text values

Auto-Generation

Instead of writing manually, use:

pilz create-dc --src data.csv --out datacard.yaml

This interactive command will prompt you for feature types and target selection.

Validation

Pilz validates the DataCard:

• All feature names must exist in CSV
• Target column must exist
• All target values must exist in target column
• File paths must exist