Struct Codebook 

pub struct Codebook {
    pub table_name: String,
    pub state_prior_process: Option<PriorProcess>,
    pub view_prior_process: Option<PriorProcess>,
    pub col_metadata: ColMetadataList,
    pub comments: Option<String>,
    pub row_names: RowNameList,
}

Codebook object for storing information about the dataset

Fields

table_name: String

The name of the table

state_prior_process: Option<PriorProcess>

Prior on State CRP alpha parameter

view_prior_process: Option<PriorProcess>

Prior on View CRP alpha parameters

col_metadata: ColMetadataList

The metadata for each column indexed by name

comments: Option<String>

Optional misc comments

row_names: RowNameList

Names of each row

Implementations

impl Codebook

pub fn new(table_name: String, col_metadata: ColMetadataList) -> Self

pub fn from_df( df: &DataFrame, cat_cutoff: Option<u32>, state_prior_process: Option<PriorProcess>, view_prior_process: Option<PriorProcess>, no_hypers: bool, ) -> Result<Self, CodebookError>

Create a codebook from a polars DataFrame

Arguments

• df: the dataframe
• cat_cutoff: the maximum value an integer column can take on before it is considered Count type instead of Categorical
• state_prior_process: The prior process on the column partition
• view_prior_process: The prior process on the row partitions
• no_hypers: if true do not do prior parameter inference

pub fn from_yaml<P: AsRef<Path>>(path: P) -> Result<Self>

pub fn zip_col_metadata(&self) -> Vec<(usize, String, ColMetadata)>

Return a vector of tuples containing the column ID, the column name, and the column metadata, sorted in ascending order by ID.

pub fn col_metadata(&self, col: String) -> Option<&ColMetadata>

pub fn n_cols(&self) -> usize

Get the number of columns

pub fn n_rows(&self) -> usize

Get the number of rows

pub fn merge_cols(&mut self, other: Codebook) -> Result<(), MergeColumnsError>

Add the columns of the other codebook into this codebook. Returns a map, indexed by the old column IDs, containing the new IDs.

pub fn append_col_metadata( &mut self, col_metadata: ColMetadataList, ) -> Result<(), MergeColumnsError>

Add the columns of the other codebook into this codebook. Returns a map, indexed by the old column IDs, containing the new IDs.

pub fn row_index(&self, row_name: &str) -> Option<usize>

Get the integer index of a row by name

pub fn column_index(&self, col_name: &str) -> Option<usize>

Get the integer index of a column by name

pub fn value_map(&self, col_ix: usize) -> Option<&ValueMap>

Return the ValueMap of the column if it exists

Will return None if the column is not categorical

Trait Implementations

impl Clone for Codebook

fn clone(&self) -> Codebook

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Codebook

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

Formats the value using the given formatter.

impl Default for Codebook

fn default() -> Codebook

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Codebook

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<Codebook> for Codebook

fn from(x: Codebook) -> Self

Converts to this type from the input type.

impl From<Codebook> for Codebook

fn from(x: Codebook) -> Self

Converts to this type from the input type.

impl PartialEq for Codebook

fn eq(&self, other: &Codebook) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Codebook

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Codebook