template<typename... ColumnTypes>
class ROOT::Internal::RDF::RVecDS< ColumnTypes >

A RDataSource implementation which takes a collection of RVecs, which are able to adopt data from Numpy arrays.

This component allows to create a data source on a set of columns with data coming from RVecs. The adoption of externally provided data, e.g., via Numpy arrays, with RVecs allows to read arbitrary data from memory. In addition, the data source has to keep a reference on the Python owned data so that the lifetime of the data is tied to the datasource.

Definition at line 45 of file RVecDS.hxx.

Public Member Functions
	RVecDS (std::function< void()> deleteRVecs, std::pair< std::string, ROOT::RVec< ColumnTypes > > const &...colsNameVals)

	~RVecDS ()

const std::vector< std::string > &	GetColumnNames () const
	Returns a reference to the collection of the dataset's column names.

std::vector< std::pair< ULong64_t, ULong64_t > >	GetEntryRanges ()
	Return ranges of entries to distribute to tasks.

std::string	GetLabel ()
	Return a string representation of the datasource type.

std::string	GetTypeName (std::string_view colName) const
	Type of a column as a string, e.g.

bool	HasColumn (std::string_view colName) const
	Checks if the dataset has a certain column.

void	Initialize ()
	Convenience method called before starting an event-loop.

bool	SetEntry (unsigned int slot, ULong64_t entry)
	Advance the "cursors" returned by GetColumnReaders to the selected entry for a particular slot.

void	SetNSlots (unsigned int nSlots)
	Inform RDataSource of the number of processing slots (i.e.

Public Member Functions inherited from ROOT::RDF::RDataSource
virtual	~RDataSource ()=default

virtual void	Finalize ()
	Convenience method called after concluding an event-loop.

virtual void	FinalizeSlot (unsigned int)
	Convenience method called at the end of the data processing associated to a slot.

template<typename T >
std::vector< T ** >	GetColumnReaders (std::string_view columnName)
	Called at most once per column by RDF.

virtual std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	GetColumnReaders (unsigned int, std::string_view, const std::type_info &)
	If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.

virtual std::size_t	GetNFiles () const
	Returns the number of files from which the dataset is constructed.

virtual void	InitSlot (unsigned int, ULong64_t)
	Convenience method called at the start of the data processing associated to a slot.

Protected Member Functions
std::string	AsString ()

Private Types
using	PointerHolderPtrs_t = std::vector< ROOT::Internal::TDS::TPointerHolder * >

Private Member Functions
template<std::size_t... S>
void	ColLengthChecker (std::index_sequence< S... >)

Record_t	GetColumnReadersImpl (std::string_view colName, const std::type_info &id)
	type-erased vector of pointers to pointers to column values - one per slot

size_t	GetEntriesNumber ()

template<std::size_t... S>
void	SetEntryHelper (unsigned int slot, ULong64_t entry, std::index_sequence< S... >)

Private Attributes
const std::vector< std::string >	fColNames

const std::map< std::string, std::string >	fColTypesMap

std::tuple< ROOT::RVec< ColumnTypes >... >	fColumns

std::function< void()>	fDeleteRVecs

std::vector< std::pair< ULong64_t, ULong64_t > >	fEntryRanges {}

unsigned int	fNSlots {0}

std::vector< PointerHolderPtrs_t >	fPointerHolders

const PointerHolderPtrs_t	fPointerHoldersModels

Additional Inherited Members
Protected Types inherited from ROOT::RDF::RDataSource
using	Record_t = std::vector< void * >

#include <ROOT/RVecDS.hxx>

Inheritance diagram for ROOT::Internal::RDF::RVecDS< ColumnTypes >:

[legend]

Member Typedef Documentation

◆ PointerHolderPtrs_t

template<typename... ColumnTypes>

using ROOT::Internal::RDF::RVecDS< ColumnTypes >::PointerHolderPtrs_t = std::vector<ROOT::Internal::TDS::TPointerHolder *>

private

Definition at line 46 of file RVecDS.hxx.

Constructor & Destructor Documentation

◆ RVecDS()

template<typename... ColumnTypes>

ROOT::Internal::RDF::RVecDS< ColumnTypes >::RVecDS	(	std::function< void()>	deleteRVecs,
		std::pair< std::string, ROOT::RVec< ColumnTypes > > const &...	colsNameVals
	)

inline

Definition at line 125 of file RVecDS.hxx.

◆ ~RVecDS()

template<typename... ColumnTypes>

ROOT::Internal::RDF::RVecDS< ColumnTypes >::~RVecDS ( )

inline

Definition at line 134 of file RVecDS.hxx.

Member Function Documentation

◆ AsString()

template<typename... ColumnTypes>

std::string ROOT::Internal::RDF::RVecDS< ColumnTypes >::AsString ( )

inlineprotectedvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 122 of file RVecDS.hxx.

◆ ColLengthChecker()

template<typename... ColumnTypes>

template<std::size_t... S>

void ROOT::Internal::RDF::RVecDS< ColumnTypes >::ColLengthChecker ( std::index_sequence< S... > )

inlineprivate

Definition at line 101 of file RVecDS.hxx.

◆ GetColumnNames()

template<typename... ColumnTypes>

const std::vector< std::string > & ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetColumnNames ( ) const

inlinevirtual

Returns a reference to the collection of the dataset's column names.

Implements ROOT::RDF::RDataSource.

Definition at line 145 of file RVecDS.hxx.

◆ GetColumnReadersImpl()

template<typename... ColumnTypes>

Record_t ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetColumnReadersImpl	(	std::string_view	name,
		const std::type_info &
	)

inlineprivatevirtual

type-erased vector of pointers to pointers to column values - one per slot

Implements ROOT::RDF::RDataSource.

Definition at line 61 of file RVecDS.hxx.

◆ GetEntriesNumber()

template<typename... ColumnTypes>

size_t ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetEntriesNumber ( )

inlineprivate

Definition at line 91 of file RVecDS.hxx.

◆ GetEntryRanges()

template<typename... ColumnTypes>

std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetEntryRanges ( )

inlinevirtual

Return ranges of entries to distribute to tasks.

They are required to be contiguous intervals with no entries skipped. Supposing a dataset with nEntries, the intervals must start at 0 and end at nEntries, e.g. [0-5],[5-10] for 10 entries. This function will be invoked repeatedly by RDataFrame as it needs additional entries to process. The same entry range should not be returned more than once. Returning an empty collection of ranges signals to RDataFrame that the processing can stop.

Implements ROOT::RDF::RDataSource.

Definition at line 147 of file RVecDS.hxx.

◆ GetLabel()

template<typename... ColumnTypes>

std::string ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetLabel ( )

inlinevirtual

Return a string representation of the datasource type.

The returned string will be used by ROOT::RDF::SaveGraph() to represent the datasource in the visualization of the computation graph. Concrete datasources can override the default implementation.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 211 of file RVecDS.hxx.

◆ GetTypeName()

template<typename... ColumnTypes>

std::string ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetTypeName ( std::string_view colName ) const

inlinevirtual

Type of a column as a string, e.g.

GetTypeName("x") == "double". Required for jitting e.g. df.Filter("x>0").

Parameters

[in] colName The name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 153 of file RVecDS.hxx.

◆ HasColumn()

template<typename... ColumnTypes>

bool ROOT::Internal::RDF::RVecDS< ColumnTypes >::HasColumn ( std::string_view colName ) const

inlinevirtual

Checks if the dataset has a certain column.

Parameters

[in] colName The name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 159 of file RVecDS.hxx.

◆ Initialize()

template<typename... ColumnTypes>

void ROOT::Internal::RDF::RVecDS< ColumnTypes >::Initialize ( )

inlinevirtual

Convenience method called before starting an event-loop.

This method might be called multiple times over the lifetime of a RDataSource, since users can run multiple event-loops with the same RDataFrame. Ideally, Initialize should set the state of the RDataSource so that multiple identical event-loops will produce identical results.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 190 of file RVecDS.hxx.

◆ SetEntry()

template<typename... ColumnTypes>

bool ROOT::Internal::RDF::RVecDS< ColumnTypes >::SetEntry	(	unsigned int	slot,
		ULong64_t	entry
	)

inlinevirtual

Advance the "cursors" returned by GetColumnReaders to the selected entry for a particular slot.

Parameters

[in]	slot	The data processing slot that needs to be considered
[in]	entry	The entry which needs to be pointed to by the reader pointers Slots are adopted to accommodate parallel data processing. Different workers will loop over different ranges and will be labelled by different "slot" values. Returns true if the entry has to be processed, false otherwise.

Implements ROOT::RDF::RDataSource.

Definition at line 166 of file RVecDS.hxx.

◆ SetEntryHelper()

template<typename... ColumnTypes>

template<std::size_t... S>

void ROOT::Internal::RDF::RVecDS< ColumnTypes >::SetEntryHelper	(	unsigned int	slot,
		ULong64_t	entry,
		std::index_sequence< S... >
	)

inlineprivate

Definition at line 93 of file RVecDS.hxx.

◆ SetNSlots()

template<typename... ColumnTypes>

void ROOT::Internal::RDF::RVecDS< ColumnTypes >::SetNSlots ( unsigned int nSlots )

inlinevirtual

Inform RDataSource of the number of processing slots (i.e.

worker threads) used by the associated RDataFrame. Slots numbers are used to simplify parallel execution: RDataFrame guarantees that different threads will always pass different slot values when calling methods concurrently.

Implements ROOT::RDF::RDataSource.

Definition at line 172 of file RVecDS.hxx.

Member Data Documentation

◆ fColNames

template<typename... ColumnTypes>

const std::vector<std::string> ROOT::Internal::RDF::RVecDS< ColumnTypes >::fColNames

private

Definition at line 49 of file RVecDS.hxx.

◆ fColTypesMap

template<typename... ColumnTypes>

const std::map<std::string, std::string> ROOT::Internal::RDF::RVecDS< ColumnTypes >::fColTypesMap

private

Definition at line 50 of file RVecDS.hxx.

◆ fColumns

template<typename... ColumnTypes>

std::tuple<ROOT::RVec<ColumnTypes>...> ROOT::Internal::RDF::RVecDS< ColumnTypes >::fColumns

private

Definition at line 48 of file RVecDS.hxx.

◆ fDeleteRVecs

template<typename... ColumnTypes>

std::function<void()> ROOT::Internal::RDF::RVecDS< ColumnTypes >::fDeleteRVecs

private

Definition at line 59 of file RVecDS.hxx.

◆ fEntryRanges

template<typename... ColumnTypes>

std::vector<std::pair<ULong64_t, ULong64_t> > ROOT::Internal::RDF::RVecDS< ColumnTypes >::fEntryRanges {}

private

Definition at line 57 of file RVecDS.hxx.

◆ fNSlots

template<typename... ColumnTypes>

unsigned int ROOT::Internal::RDF::RVecDS< ColumnTypes >::fNSlots {0}

private

Definition at line 58 of file RVecDS.hxx.

◆ fPointerHolders

template<typename... ColumnTypes>

std::vector<PointerHolderPtrs_t> ROOT::Internal::RDF::RVecDS< ColumnTypes >::fPointerHolders

private

Definition at line 56 of file RVecDS.hxx.

◆ fPointerHoldersModels

template<typename... ColumnTypes>

const PointerHolderPtrs_t ROOT::Internal::RDF::RVecDS< ColumnTypes >::fPointerHoldersModels

private

Definition at line 55 of file RVecDS.hxx.

tree/dataframe/inc/ROOT/RVecDS.hxx

Public Member Functions

Protected Member Functions

Private Types

Private Member Functions

Private Attributes

Additional Inherited Members

Member Typedef Documentation

◆ PointerHolderPtrs_t

Constructor & Destructor Documentation

◆ RVecDS()

◆ ~RVecDS()

Member Function Documentation

◆ AsString()

◆ ColLengthChecker()

◆ GetColumnNames()

◆ GetColumnReadersImpl()

◆ GetEntriesNumber()

◆ GetEntryRanges()

◆ GetLabel()

◆ GetTypeName()

◆ HasColumn()

◆ Initialize()

◆ SetEntry()

◆ SetEntryHelper()

◆ SetNSlots()

Member Data Documentation

◆ fColNames

◆ fColTypesMap

◆ fColumns

◆ fDeleteRVecs

◆ fEntryRanges

◆ fNSlots

◆ fPointerHolders

◆ fPointerHoldersModels