merge

Documentation

Index

• func InjectFileLinks(meta *model.Metadata, merged []byte, rawDataPath string, mergedDataPath string) (*model.DataResource, []byte, error)
• func InjectFileLinksFromFile(meta *model.Metadata, inputFilename string, rawDataPath string, ...) (*model.DataResource, []byte, error)
• func LeftJoin(leftFile string, leftCol int, rightFile string, rightCol int, hasHeader bool) ([]byte, int, int, error)
• type FileLink
• type JoinIndices
  • func GetColIndices(schemaPath string, columnName string) (*JoinIndices, error)

Functions

func InjectFileLinks

func InjectFileLinks(meta *model.Metadata, merged []byte, rawDataPath string, mergedDataPath string) (*model.DataResource, []byte, error)

InjectFileLinks traverses all file links and injests the relevant data.

func InjectFileLinksFromFile

func InjectFileLinksFromFile(meta *model.Metadata, inputFilename string, rawDataPath string, mergedDataPath string, hasHeader bool) (*model.DataResource, []byte, error)

InjectFileLinksFromFile traverses all file links and injests the relevant data.

func LeftJoin

func LeftJoin(leftFile string, leftCol int, rightFile string, rightCol int, hasHeader bool) ([]byte, int, int, error)

LeftJoin provides a function to join to csv files based on the specified column

Types

type FileLink

type FileLink struct {
	Name      string
	IndexVar  *model.Variable
	Lookup    map[string][]string
	Header    []string
	Variables []*model.Variable
}

FileLink represents a link between a dataset col and a file.

type JoinIndices

type JoinIndices struct {
	LeftColIdx  int
	RightColIdx int
}

JoinIndices provides the column indices to join the left and right csvs on

func GetColIndices

func GetColIndices(schemaPath string, columnName string) (*JoinIndices, error)

GetColIndices will get the indices of the 'd3mIndex' column for the training and training target files from a dataset schema