11#ifndef ROOT_RLOOPMANAGER
12#define ROOT_RLOOPMANAGER
28#include <unordered_map>
29#include <unordered_set>
50class RDefinesWithReaders;
51class RVariationsWithReaders;
53namespace GraphDrawing {
129 std::shared_ptr<TTree>
fTree{
nullptr};
134 std::unordered_map<std::string, ROOT::RDF::Experimental::RSample *>
fSampleMap;
136 std::vector<ROOT::RDF::Experimental::RSample>
fSamples;
181 void UpdateSampleInfo(
unsigned int slot,
const std::pair<ULong64_t, ULong64_t> &range);
185 std::set<std::pair<std::string_view, std::unique_ptr<ROOT::Internal::RDF::RDefinesWithReaders>>>
187 std::set<std::pair<std::string_view, std::unique_ptr<ROOT::Internal::RDF::RVariationsWithReaders>>>
208 void Run(
bool jit =
true);
229 void SetTree(std::shared_ptr<TTree> tree);
232 void ToJitExec(
const std::string &)
const;
237 const std::type_info &ti);
239 std::unique_ptr<RColumnReaderBase> &&reader,
const std::type_info &ti);
252 std::vector<RDFInternal::RActionBase *>
GetAllActions()
const;
254 std::shared_ptr<ROOT::Internal::RDF::GraphDrawing::GraphNode>
255 GetGraph(std::unordered_map<
void *, std::shared_ptr<ROOT::Internal::RDF::GraphDrawing::GraphNode>> &visitedMap)
final;
265 std::set<std::pair<std::string_view, std::unique_ptr<ROOT::Internal::RDF::RDefinesWithReaders>>> &
270 std::set<std::pair<std::string_view, std::unique_ptr<ROOT::Internal::RDF::RVariationsWithReaders>>> &
283std::shared_ptr<ROOT::Detail::RDF::RLoopManager>
285 const std::vector<std::string> &defaultColumns,
bool checkFile =
true);
293std::shared_ptr<ROOT::Detail::RDF::RLoopManager>
294CreateLMFromTTree(std::string_view datasetName,
const std::vector<std::string> &fileNameGlobs,
295 const std::vector<std::string> &defaultColumns,
bool checkFile =
true);
304std::shared_ptr<ROOT::Detail::RDF::RLoopManager> CreateLMFromRNTuple(std::string_view datasetName,
305 std::string_view fileNameGlob,
306 const std::vector<std::string> &defaultColumns);
314std::shared_ptr<ROOT::Detail::RDF::RLoopManager> CreateLMFromRNTuple(std::string_view datasetName,
315 const std::vector<std::string> &fileNameGlobs,
316 const std::vector<std::string> &defaultColumns);
325std::shared_ptr<ROOT::Detail::RDF::RLoopManager> CreateLMFromFile(std::string_view datasetName,
326 std::string_view fileNameGlob,
327 const std::vector<std::string> &defaultColumns);
336std::shared_ptr<ROOT::Detail::RDF::RLoopManager> CreateLMFromFile(std::string_view datasetName,
337 const std::vector<std::string> &fileNameGlobs,
338 const std::vector<std::string> &defaultColumns);
unsigned long long ULong64_t
Option_t Option_t TPoint TPoint const char GetTextMagnitude GetFillStyle GetLineColor GetLineWidth GetMarkerStyle GetTextAlign GetTextColor GetTextSize void char Point_t Rectangle_t WindowAttributes_t Float_t r
The head node of a RDF computation graph.
void StopProcessing() final
void UpdateSampleInfo(unsigned int slot, const std::pair< ULong64_t, ULong64_t > &range)
unsigned int fNRuns
Number of event loops run.
bool CheckFilters(unsigned int, Long64_t) final
void EvalChildrenCounts()
Trigger counting of number of children nodes for each node of the functional graph.
void CleanUpNodes()
Perform clean-up operations. To be called at the end of each event loop.
void RunEmptySource()
Run event loop with no source files, in sequence.
void SetEmptyEntryRange(std::pair< ULong64_t, ULong64_t > &&newRange)
void Report(ROOT::RDF::RCutFlowReport &rep) const final
Call FillReport on all booked filters.
void AddSampleCallback(void *nodePtr, ROOT::RDF::SampleCallback_t &&callback)
std::vector< RFilterBase * > fBookedNamedFilters
Contains a subset of fBookedFilters, i.e. only the named filters.
void RunEmptySourceMT()
Run event loop with no source files, in parallel.
RLoopManager & operator=(RLoopManager &&)=delete
ULong64_t GetNEmptyEntries() const
std::unordered_map< std::string, ROOT::RDF::Experimental::RSample * > fSampleMap
Keys are fname + "/" + treename as RSampleInfo::fID; Values are pointers to the corresponding sample.
std::shared_ptr< ROOT::Internal::RDF::GraphDrawing::GraphNode > GetGraph(std::unordered_map< void *, std::shared_ptr< ROOT::Internal::RDF::GraphDrawing::GraphNode > > &visitedMap) final
RLoopManager & operator=(const RLoopManager &)=delete
void IncrChildrenCount() final
const ColumnNames_t & GetBranchNames()
Return all valid TTree::Branch names (caching results for subsequent calls).
void ToJitExec(const std::string &) const
unsigned int GetNRuns() const
std::vector< RDFInternal::RActionBase * > GetAllActions() const
Return all actions, either booked or already run.
std::vector< ROOT::RDF::RSampleInfo > fSampleInfos
::TDirectory * GetDirectory() const
bool fMustRunNamedFilters
void ChangeSpec(ROOT::RDF::Experimental::RDatasetSpec &&spec)
Changes the internal TTree held by the RLoopManager.
void SetTree(std::shared_ptr< TTree > tree)
std::set< std::pair< std::string_view, std::unique_ptr< ROOT::Internal::RDF::RVariationsWithReaders > > > & GetUniqueVariationsWithReaders()
std::shared_ptr< TTree > fTree
Shared pointer to the input TTree.
std::vector< RDefineBase * > fBookedDefines
void RunTreeReader()
Run event loop over one or multiple ROOT files, in sequence.
ROOT::Internal::TreeUtils::RNoCleanupNotifier fNoCleanupNotifier
std::vector< RDFInternal::RActionBase * > fRunActions
Non-owning pointers to actions already run.
RColumnReaderBase * GetDatasetColumnReader(unsigned int slot, const std::string &col, const std::type_info &ti) const
void AddFilterName(std::vector< std::string > &) final
End of recursive chain of calls, does nothing.
std::vector< RRangeBase * > fBookedRanges
std::vector< ROOT::RDF::Experimental::RSample > fSamples
Samples need to survive throughout the whole event loop, hence stored as an attribute.
std::vector< std::string > ColumnNames_t
void RunAndCheckFilters(unsigned int slot, Long64_t entry)
Execute actions and make sure named filters are called for each event.
std::unordered_set< std::string > & GetColumnNamesCache()
std::vector< RFilterBase * > fBookedFilters
void Run(bool jit=true)
Start the event loop with a different mechanism depending on IMT/no IMT, data source/no data source.
std::set< std::pair< std::string_view, std::unique_ptr< ROOT::Internal::RDF::RVariationsWithReaders > > > fUniqueVariationsWithReaders
std::unordered_map< void *, ROOT::RDF::SampleCallback_t > fSampleCallbacks
Registered callbacks to call at the beginning of each "data block".
std::vector< RDFInternal::RActionBase * > fBookedActions
Non-owning pointers to actions to be run.
RLoopManager(RLoopManager &&)=delete
RColumnReaderBase * AddTreeColumnReader(unsigned int slot, const std::string &col, std::unique_ptr< RColumnReaderBase > &&reader, const std::type_info &ti)
Register a new RTreeColumnReader with this RLoopManager.
const ELoopType fLoopType
The kind of event loop that is going to be run (e.g. on ROOT files, on no files)
void AddDataSourceColumnReaders(const std::string &col, std::vector< std::unique_ptr< RColumnReaderBase > > &&readers, const std::type_info &ti)
void SetupSampleCallbacks(TTreeReader *r, unsigned int slot)
ColumnNames_t fValidBranchNames
Cache of the tree/chain branch names. Never access directy, always use GetBranchNames().
void CleanUpTask(TTreeReader *r, unsigned int slot)
Perform clean-up operations. To be called at the end of each task execution.
std::vector< RDFInternal::RCallback > fCallbacksEveryNEvents
Registered callbacks to be executed every N events.
std::vector< std::unordered_map< std::string, std::unique_ptr< RColumnReaderBase > > > fDatasetColumnReaders
Readers for TTree/RDataSource columns (one per slot), shared by all nodes in the computation graph.
const unsigned int fNSlots
void Register(RDFInternal::RActionBase *actionPtr)
const ColumnNames_t & GetDefaultColumnNames() const
Return the list of default columns – empty if none was provided when constructing the RDataFrame.
std::vector< RDFInternal::RVariationBase * > fBookedVariations
std::vector< RNodeBase * > GetGraphEdges() const
Return all graph edges known to RLoopManager This includes Filters and Ranges but not Defines.
std::set< std::pair< std::string_view, std::unique_ptr< ROOT::Internal::RDF::RDefinesWithReaders > > > & GetUniqueDefinesWithReaders()
RDataSource * GetDataSource() const
unsigned int GetNSlots() const
void RunDataSourceMT()
Run event loop over data accessed through a DataSource, in parallel.
void PartialReport(ROOT::RDF::RCutFlowReport &) const final
End of recursive chain of calls, does nothing.
std::vector< std::string > GetFiltersNames()
For each booked filter, returns either the name or "Unnamed Filter".
RLoopManager(const RLoopManager &)=delete
const std::unique_ptr< RDataSource > fDataSource
Owning pointer to a data-source object.
RDFInternal::RNewSampleNotifier fNewSampleNotifier
std::pair< ULong64_t, ULong64_t > fEmptyEntryRange
Range of entries created when no data source is specified.
std::set< std::pair< std::string_view, std::unique_ptr< ROOT::Internal::RDF::RDefinesWithReaders > > > fUniqueDefinesWithReaders
const ColumnNames_t fDefaultColumns
void InitNodeSlots(TTreeReader *r, unsigned int slot)
Build TTreeReaderValues for all nodes This method loops over all filters, actions and other booked ob...
std::unordered_set< std::string > fCachedColNames
std::vector< RDFInternal::ROneTimeCallback > fCallbacksOnce
Registered callbacks to invoke just once before running the loop.
void RegisterCallback(ULong64_t everyNEvents, std::function< void(unsigned int)> &&f)
void RunDataSource()
Run event loop over data accessed through a DataSource, in sequence.
void Jit()
Add RDF nodes that require just-in-time compilation to the computation graph.
void RunTreeProcessorMT()
Run event loop over one or multiple ROOT files, in parallel.
void Deregister(RDFInternal::RActionBase *actionPtr)
void InitNodes()
Initialize all nodes of the functional graph before running the event loop.
RLoopManager * GetLoopManagerUnchecked() final
std::vector< std::unique_ptr< TChain > > fFriends
Friends of the fTree. Only used if we constructed fTree ourselves.
bool HasDataSourceColumnReaders(const std::string &col, const std::type_info &ti) const
Return true if AddDataSourceColumnReaders was called for column name col.
Base class for non-leaf nodes of the computational graph.
unsigned int fNStopsReceived
Number of times that a children node signaled to stop processing entries.
unsigned int fNChildren
Number of nodes of the functional graph hanging from this object.
Helper class that provides the operation graph nodes.
RCallback(ULong64_t everyN, Callback_t &&f, unsigned int nSlots)
std::vector< ULong64_t > fCounters
void operator()(unsigned int slot)
void operator()(unsigned int slot)
std::vector< int > fHasBeenCalled
ROneTimeCallback(Callback_t &&f, unsigned int nSlots)
This type includes all parts of RVariation that do not depend on the callable signature.
The dataset specification for RDataFrame.
RDataSource defines an API that RDataFrame can use to read arbitrary data formats.
Describe directory structure in memory.
A simple, robust and fast interface to read values from ROOT columnar datasets such as TTree,...
A TTree represents a columnar dataset.
std::shared_ptr< ROOT::Detail::RDF::RLoopManager > CreateLMFromTTree(std::string_view datasetName, std::string_view fileNameGlob, const std::vector< std::string > &defaultColumns, bool checkFile=true)
Create an RLoopManager that reads a TChain.
std::vector< std::string > GetBranchNames(TTree &t, bool allowDuplicates=true)
Get all the branches names, including the ones of the friend trees.
std::function< void(unsigned int)> Callback_t
std::function< void(unsigned int, const ROOT::RDF::RSampleInfo &)> SampleCallback_t
The type of a data-block callback, registered with an RDataFrame computation graph via e....
tbb::task_arena is an alias of tbb::interface7::task_arena, which doesn't allow to forward declare tb...
A RAII object that calls RLoopManager::CleanUpTask at destruction.