Struct DataConfig 

pub struct DataConfig {
    pub train: PathBuf,
    pub val: Option<PathBuf>,
    pub batch_size: usize,
    pub auto_infer_types: bool,
    pub seq_len: Option<usize>,
    pub tokenizer: Option<PathBuf>,
    pub input_column: Option<String>,
    pub output_column: Option<String>,
    pub max_length: Option<usize>,
}

Data configuration

Fields

train: PathBuf

Training data path

val: Option<PathBuf>

Optional validation data path

batch_size: usize

Batch size

auto_infer_types: bool

Auto-infer feature types from data

seq_len: Option<usize>

Sequence length (for transformers)

tokenizer: Option<PathBuf>

Path to HuggingFace tokenizer.json (for transformer mode)

input_column: Option<String>

Input text column name (for transformer mode)

output_column: Option<String>

Output/target text column name (for transformer mode)

max_length: Option<usize>

Maximum sequence length for tokenization

Trait Implementations

impl Clone for DataConfig

fn clone(&self) -> DataConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DataConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for DataConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for DataConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DataConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.