Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
ROOT::RDF::RLazyDS< ColumnTypes > Class Template Referencefinal

template<typename... ColumnTypes>
class ROOT::RDF::RLazyDS< ColumnTypes >

A RDataSource implementation which is built on top of result proxies.

This component allows to create a data source on a set of columns coming from one or multiple data frames. The processing of the parent data frames starts only when the event loop is triggered in the data frame initialized with a RLazyDS.

The implementation takes care of matching compile time information with runtime information, e.g. expanding in a smart way the template parameters packs.

Definition at line 41 of file RLazyDSImpl.hxx.

Public Member Functions

 RLazyDS (std::pair< std::string, RResultPtr< std::vector< ColumnTypes > > >... colsNameVals)
 
 ~RLazyDS ()
 
const std::vector< std::string > & GetColumnNames () const final
 Returns a reference to the collection of the dataset's column names.
 
std::vector< std::pair< ULong64_t, ULong64_t > > GetEntryRanges () final
 Return ranges of entries to distribute to tasks.
 
std::string GetLabel () final
 Return a string representation of the datasource type.
 
std::string GetTypeName (std::string_view colName) const final
 Type of a column as a string, e.g.
 
bool HasColumn (std::string_view colName) const final
 Checks if the dataset has a certain column.
 
void Initialize () final
 Convenience method called before starting an event-loop.
 
bool SetEntry (unsigned int slot, ULong64_t entry) final
 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
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::RColumnReaderBaseGetColumnReaders (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 () final
 

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) final
 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< RResultPtr< std::vector< ColumnTypes > >... > fColumns
 
std::vector< std::pair< ULong64_t, ULong64_t > > fEntryRanges {}
 
unsigned int fNSlots {0}
 
std::vector< PointerHolderPtrs_tfPointerHolders
 
const PointerHolderPtrs_t fPointerHoldersModels
 

Additional Inherited Members

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

#include <ROOT/RDF/RLazyDSImpl.hxx>

Inheritance diagram for ROOT::RDF::RLazyDS< ColumnTypes >:
[legend]

Member Typedef Documentation

◆ PointerHolderPtrs_t

template<typename... ColumnTypes>
using ROOT::RDF::RLazyDS< ColumnTypes >::PointerHolderPtrs_t = std::vector<ROOT::Internal::TDS::TPointerHolder *>
private

Definition at line 42 of file RLazyDSImpl.hxx.

Constructor & Destructor Documentation

◆ RLazyDS()

template<typename... ColumnTypes>
ROOT::RDF::RLazyDS< ColumnTypes >::RLazyDS ( std::pair< std::string, RResultPtr< std::vector< ColumnTypes > > >...  colsNameVals)
inline

Definition at line 120 of file RLazyDSImpl.hxx.

◆ ~RLazyDS()

template<typename... ColumnTypes>
ROOT::RDF::RLazyDS< ColumnTypes >::~RLazyDS ( )
inline

Definition at line 128 of file RLazyDSImpl.hxx.

Member Function Documentation

◆ AsString()

template<typename... ColumnTypes>
std::string ROOT::RDF::RLazyDS< ColumnTypes >::AsString ( )
inlinefinalprotectedvirtual

Reimplemented from ROOT::RDF::RDataSource.

Definition at line 117 of file RLazyDSImpl.hxx.

◆ ColLengthChecker()

template<typename... ColumnTypes>
template<std::size_t... S>
void ROOT::RDF::RLazyDS< ColumnTypes >::ColLengthChecker ( std::index_sequence< S... >  )
inlineprivate

Definition at line 96 of file RLazyDSImpl.hxx.

◆ GetColumnNames()

template<typename... ColumnTypes>
const std::vector< std::string > & ROOT::RDF::RLazyDS< ColumnTypes >::GetColumnNames ( ) const
inlinefinalvirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 137 of file RLazyDSImpl.hxx.

◆ GetColumnReadersImpl()

template<typename... ColumnTypes>
Record_t ROOT::RDF::RLazyDS< ColumnTypes >::GetColumnReadersImpl ( std::string_view  name,
const std::type_info &   
)
inlinefinalprivatevirtual

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

Implements ROOT::RDF::RDataSource.

Definition at line 56 of file RLazyDSImpl.hxx.

◆ GetEntriesNumber()

template<typename... ColumnTypes>
size_t ROOT::RDF::RLazyDS< ColumnTypes >::GetEntriesNumber ( )
inlineprivate

Definition at line 86 of file RLazyDSImpl.hxx.

◆ GetEntryRanges()

template<typename... ColumnTypes>
std::vector< std::pair< ULong64_t, ULong64_t > > ROOT::RDF::RLazyDS< ColumnTypes >::GetEntryRanges ( )
inlinefinalvirtual

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 139 of file RLazyDSImpl.hxx.

◆ GetLabel()

template<typename... ColumnTypes>
std::string ROOT::RDF::RLazyDS< ColumnTypes >::GetLabel ( )
inlinefinalvirtual

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 203 of file RLazyDSImpl.hxx.

◆ GetTypeName()

template<typename... ColumnTypes>
std::string ROOT::RDF::RLazyDS< ColumnTypes >::GetTypeName ( std::string_view  colName) const
inlinefinalvirtual

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

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

Parameters
[in]colNameThe name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 145 of file RLazyDSImpl.hxx.

◆ HasColumn()

template<typename... ColumnTypes>
bool ROOT::RDF::RLazyDS< ColumnTypes >::HasColumn ( std::string_view  colName) const
inlinefinalvirtual

Checks if the dataset has a certain column.

Parameters
[in]colNameThe name of the column

Implements ROOT::RDF::RDataSource.

Definition at line 151 of file RLazyDSImpl.hxx.

◆ Initialize()

template<typename... ColumnTypes>
void ROOT::RDF::RLazyDS< ColumnTypes >::Initialize ( )
inlinefinalvirtual

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 182 of file RLazyDSImpl.hxx.

◆ SetEntry()

template<typename... ColumnTypes>
bool ROOT::RDF::RLazyDS< ColumnTypes >::SetEntry ( unsigned int  slot,
ULong64_t  entry 
)
inlinefinalvirtual

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

Parameters
[in]slotThe data processing slot that needs to be considered
[in]entryThe 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 158 of file RLazyDSImpl.hxx.

◆ SetEntryHelper()

template<typename... ColumnTypes>
template<std::size_t... S>
void ROOT::RDF::RLazyDS< ColumnTypes >::SetEntryHelper ( unsigned int  slot,
ULong64_t  entry,
std::index_sequence< S... >   
)
inlineprivate

Definition at line 88 of file RLazyDSImpl.hxx.

◆ SetNSlots()

template<typename... ColumnTypes>
void ROOT::RDF::RLazyDS< 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.

Implements ROOT::RDF::RDataSource.

Definition at line 164 of file RLazyDSImpl.hxx.

Member Data Documentation

◆ fColNames

template<typename... ColumnTypes>
const std::vector<std::string> ROOT::RDF::RLazyDS< ColumnTypes >::fColNames
private

Definition at line 45 of file RLazyDSImpl.hxx.

◆ fColTypesMap

template<typename... ColumnTypes>
const std::map<std::string, std::string> ROOT::RDF::RLazyDS< ColumnTypes >::fColTypesMap
private

Definition at line 46 of file RLazyDSImpl.hxx.

◆ fColumns

template<typename... ColumnTypes>
std::tuple<RResultPtr<std::vector<ColumnTypes> >...> ROOT::RDF::RLazyDS< ColumnTypes >::fColumns
private

Definition at line 44 of file RLazyDSImpl.hxx.

◆ fEntryRanges

template<typename... ColumnTypes>
std::vector<std::pair<ULong64_t, ULong64_t> > ROOT::RDF::RLazyDS< ColumnTypes >::fEntryRanges {}
private

Definition at line 53 of file RLazyDSImpl.hxx.

◆ fNSlots

template<typename... ColumnTypes>
unsigned int ROOT::RDF::RLazyDS< ColumnTypes >::fNSlots {0}
private

Definition at line 54 of file RLazyDSImpl.hxx.

◆ fPointerHolders

template<typename... ColumnTypes>
std::vector<PointerHolderPtrs_t> ROOT::RDF::RLazyDS< ColumnTypes >::fPointerHolders
private

Definition at line 52 of file RLazyDSImpl.hxx.

◆ fPointerHoldersModels

template<typename... ColumnTypes>
const PointerHolderPtrs_t ROOT::RDF::RLazyDS< ColumnTypes >::fPointerHoldersModels
private

Definition at line 51 of file RLazyDSImpl.hxx.

  • tree/dataframe/inc/ROOT/RDF/RLazyDSImpl.hxx