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 53 of file RVecDS.hxx.

Public Member Functions
	RVecDS (const RVecDS &)=delete

	RVecDS (RVecDS &&)=delete

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

	~RVecDS () final

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

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

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.

RVecDS &	operator= (const RVecDS &)=delete

RVecDS &	operator= (RVecDS &&)=delete

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

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

	RDataSource (const RDataSource &)=delete

	RDataSource (RDataSource &&)=delete

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::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.

RDataSource &	operator= (const RDataSource &)=delete

RDataSource &	operator= (RDataSource &&)=delete

virtual void	SetGlobalEntryRange (std::pair< ULong64_t, ULong64_t > entryRange)
	Restrict processing to a [begin, end) range of entries.

Protected Member Functions
std::string	AsString ()

Protected Member Functions inherited from ROOT::RDF::RDataSource
virtual std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase >	CreateColumnReader (unsigned int slot, std::string_view col, const std::type_info &tid, TTreeReader *)
	Creates a column reader for the requested column.

virtual ROOT::RDF::RSampleInfo	CreateSampleInfo (unsigned int, const std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > &) const

virtual std::string	DescribeDataset ()

virtual const std::vector< std::string > &	GetColumnNamesNoDuplicates () const

virtual const std::vector< std::string > &	GetTopLevelFieldNames () const

virtual std::string	GetTypeNameWithOpts (std::string_view colName, bool) const

virtual void	InitializeWithOpts (const std::set< std::string > &)

virtual void	ProcessMT (ROOT::Detail::RDF::RLoopManager &)

virtual void	RunFinalChecks (bool) const

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

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

Record_t	GetColumnReadersImpl (std::string_view, const std::type_info &)
	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
std::vector< std::string >	fColNames

std::unordered_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 {}

std::vector< PointerHolderPtrs_t >	fPointerHolders

PointerHolderPtrs_t	fPointerHoldersModels

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

Protected Attributes inherited from ROOT::RDF::RDataSource
std::optional< std::pair< ULong64_t, ULong64_t > >	fGlobalEntryRange {}

unsigned int	fNSlots {}

#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::RDF::TPointerHolder *>

private

Definition at line 54 of file RVecDS.hxx.

Constructor & Destructor Documentation

◆ RVecDS() [1/3]

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 104 of file RVecDS.hxx.

◆ RVecDS() [2/3]

template<typename... ColumnTypes>

ROOT::Internal::RDF::RVecDS< ColumnTypes >::RVecDS ( const RVecDS< ColumnTypes > & )

delete

◆ RVecDS() [3/3]

template<typename... ColumnTypes>

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

delete

◆ ~RVecDS()

template<typename... ColumnTypes>

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

inlinefinal

Definition at line 118 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 101 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 80 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 156 of file RVecDS.hxx.

◆ GetColumnReaders()

template<typename... ColumnTypes>

std::unique_ptr< ROOT::Detail::RDF::RColumnReaderBase > ROOT::Internal::RDF::RVecDS< ColumnTypes >::GetColumnReaders	(	unsigned int	,
		std::string_view	,
		const std::type_info &	)

inlinefinalvirtual

If the other GetColumnReaders overload returns an empty vector, this overload will be called instead.

Parameters

[in]	slot	The data processing slot that needs to be considered
[in]	name	The name of the column for which a column reader needs to be returned
[in]	tid	A type_info At least one of the two must return a non-empty/non-null value.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 130 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 68 of file RVecDS.hxx.

◆ GetEntriesNumber()

template<typename... ColumnTypes>

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

inlineprivate

Definition at line 70 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 158 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 222 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 164 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 170 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 201 of file RVecDS.hxx.

◆ operator=() [1/2]

template<typename... ColumnTypes>

RVecDS & ROOT::Internal::RDF::RVecDS< ColumnTypes >::operator= ( const RVecDS< ColumnTypes > & )

delete

◆ operator=() [2/2]

template<typename... ColumnTypes>

RVecDS & ROOT::Internal::RDF::RVecDS< ColumnTypes >::operator= ( RVecDS< ColumnTypes > && )

delete

◆ 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 177 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 72 of file RVecDS.hxx.

◆ SetNSlots()

template<typename... ColumnTypes>

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

inlinefinalvirtual

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.

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 183 of file RVecDS.hxx.

Member Data Documentation

◆ fColNames

template<typename... ColumnTypes>

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

private

Definition at line 57 of file RVecDS.hxx.

◆ fColTypesMap

template<typename... ColumnTypes>

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

private

Definition at line 58 of file RVecDS.hxx.

◆ fColumns

template<typename... ColumnTypes>

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

private

Definition at line 56 of file RVecDS.hxx.

◆ fDeleteRVecs

template<typename... ColumnTypes>

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

private

Definition at line 66 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 65 of file RVecDS.hxx.

◆ fPointerHolders

template<typename... ColumnTypes>

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

private

Definition at line 64 of file RVecDS.hxx.

◆ fPointerHoldersModels

template<typename... ColumnTypes>

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

private

Definition at line 63 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() [1/3]

◆ RVecDS() [2/3]

◆ RVecDS() [3/3]

◆ ~RVecDS()

Member Function Documentation

◆ AsString()

◆ ColLengthChecker()

◆ GetColumnNames()

◆ GetColumnReaders()

◆ GetColumnReadersImpl()

◆ GetEntriesNumber()

◆ GetEntryRanges()

◆ GetLabel()

◆ GetTypeName()

◆ HasColumn()

◆ Initialize()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ SetEntry()

◆ SetEntryHelper()

◆ SetNSlots()

Member Data Documentation

◆ fColNames

◆ fColTypesMap

◆ fColumns

◆ fDeleteRVecs

◆ fEntryRanges

◆ fPointerHolders

◆ fPointerHoldersModels