template<typename Proxied, typename DataSource = void>
class ROOT::RDF::RInterface< Proxied, DataSource >

The public interface to the RDataFrame federation of classes.

Template Parameters

Proxied	One of the "node" base types (e.g. RLoopManager, RFilterBase). The user never specifies this type manually.
DataSource	The type of the RDataSource which is providing the data to the data frame. There is no source by default.

The documentation of each method features a one liner illustrating how to use the method, for example showing how the majority of the template parameters are automatically deduced requiring no or very little effort by the user.

Definition at line 110 of file RInterface.hxx.

Public Member Functions
	RInterface (const RInterface &)=default
	Copy-ctor for RInterface.

template<typename T = Proxied, typename = std::enable_if_t<std::is_same<T, RLoopManager>::value, int>>
	RInterface (const std::shared_ptr< RLoopManager > &proxied)
	Build a RInterface from a RLoopManager.

	RInterface (RInterface &&)=default
	Move-ctor for RInterface.

template<typename F, typename std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>
RInterface< Proxied, DS_t >	Define (std::string_view name, F expression, const ColumnNames_t &columns={})
	Define a new column.

RInterface< Proxied, DS_t >	Define (std::string_view name, std::string_view expression)
	Define a new column.

template<typename F, typename RetType_t = typename TTraits::CallableTraits<F>::ret_type>
RInterface< Proxied, DS_t >	DefinePerSample (std::string_view name, F expression)
	Define a new column that is updated when the input sample changes.

RInterface< Proxied, DS_t >	DefinePerSample (std::string_view name, std::string_view expression)
	Define a new column that is updated when the input sample changes.

template<typename F>
RInterface< Proxied, DS_t >	DefineSlot (std::string_view name, F expression, const ColumnNames_t &columns={})
	Define a new column with a value dependent on the processing slot.

template<typename F>
RInterface< Proxied, DS_t >	DefineSlotEntry (std::string_view name, F expression, const ColumnNames_t &columns={})
	Define a new column with a value dependent on the processing slot and the current entry.

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>
RInterface< RDFDetail::RFilter< F, Proxied >, DS_t >	Filter (F f, const ColumnNames_t &columns={}, std::string_view name="")
	Append a filter to the call graph.

template<typename F>
RInterface< RDFDetail::RFilter< F, Proxied >, DS_t >	Filter (F f, const std::initializer_list< std::string > &columns)
	Append a filter to the call graph.

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>
RInterface< RDFDetail::RFilter< F, Proxied >, DS_t >	Filter (F f, std::string_view name)
	Append a filter to the call graph.

RInterface< RDFDetail::RJittedFilter, DS_t >	Filter (std::string_view expression, std::string_view name="")
	Append a filter to the call graph.

	operator RNode () const
	Cast any RDataFrame node to a common type ROOT::RDF::RNode.

RInterface &	operator= (const RInterface &)=default
	Copy-assignment operator for RInterface.

RInterface &	operator= (RInterface &&)=default
	Move-assignment operator for RInterface.

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>
RInterface< Proxied, DS_t >	Redefine (std::string_view name, F expression, const ColumnNames_t &columns={})
	Overwrite the value and/or type of an existing column.

RInterface< Proxied, DS_t >	Redefine (std::string_view name, std::string_view expression)
	Overwrite the value and/or type of an existing column.

template<typename F>
RInterface< Proxied, DS_t >	RedefineSlot (std::string_view name, F expression, const ColumnNames_t &columns={})
	Overwrite the value and/or type of an existing column.

template<typename F>
RInterface< Proxied, DS_t >	RedefineSlotEntry (std::string_view name, F expression, const ColumnNames_t &columns={})
	Overwrite the value and/or type of an existing column.

template<typename F>
RInterface< Proxied, DS_t >	Vary (const std::vector< std::string > &colNames, F &&expression, const ColumnNames_t &inputColumns, const std::vector< std::string > &variationTags, std::string_view variationName)
	Register systematic variations for multiple existing columns using custom variation tags.

template<typename F>
RInterface< Proxied, DS_t >	Vary (std::initializer_list< std::string > colNames, F &&expression, const ColumnNames_t &inputColumns, const std::vector< std::string > &variationTags, std::string_view variationName)
	Register systematic variations for multiple existing columns using custom variation tags.

template<typename F>
RInterface< Proxied, DS_t >	Vary (std::string_view colName, F &&expression, const ColumnNames_t &inputColumns, const std::vector< std::string > &variationTags, std::string_view variationName="")
	Register systematic variations for a single existing column using custom variation tags.

template<typename F>
RInterface< Proxied, DS_t >	Vary (std::string_view colName, F &&expression, const ColumnNames_t &inputColumns, std::size_t nVariations, std::string_view variationName="")
	Register systematic variations for a single existing column using auto-generated variation tags.

Public Member Functions inherited from ROOT::RDF::RInterfaceBase
	RInterfaceBase (RDFDetail::RLoopManager &lm, const RDFInternal::RColumnRegister &colRegister)

	RInterfaceBase (std::shared_ptr< RDFDetail::RLoopManager > lm)

RDFDescription	Describe ()
	Return information about the dataframe.

ColumnNames_t	GetColumnNames ()
	Returns the names of the available columns.

std::string	GetColumnType (std::string_view column)
	Return the type of a given column as a string.

ColumnNames_t	GetDefinedColumnNames ()
	Returns the names of the defined columns.

unsigned int	GetNFiles ()

unsigned int	GetNRuns () const
	Gets the number of event loops run.

unsigned int	GetNSlots () const
	Gets the number of data processing slots.

RVariationsDescription	GetVariations () const
	Return a descriptor for the systematic variations registered in this branch of the computation graph.

bool	HasColumn (std::string_view columnName)
	Checks if a column is present in the dataset.

Public Attributes
	true
	Register systematic variations for multiple existing columns using auto-generated tags.

Private Types
using	DS_t = DataSource

using	RFilterBase = RDFDetail::RFilterBase

using	RLoopManager = RDFDetail::RLoopManager

using	RRangeBase = RDFDetail::RRangeBase

Private Attributes
std::shared_ptr< Proxied >	fProxiedPtr
	Smart pointer to the graph node encapsulated by this RInterface.

Friends
template<typename T, typename W>
class	RInterface

void	RDFInternal::ChangeEmptyEntryRange (const RNode &node, std::pair< ULong64_t, ULong64_t > &&newRange)

void	RDFInternal::ChangeSpec (const RNode &node, ROOT::RDF::Experimental::RDatasetSpec &&spec)

class	RDFInternal::GraphDrawing::GraphCreatorHelper

void	RDFInternal::TriggerRun (RNode node)

Additional Inherited Members
Protected Member Functions inherited from ROOT::RDF::RInterfaceBase
void	AddDefaultColumns ()

template<typename... ColumnTypes>
void	CheckAndFillDSColumns (ColumnNames_t validCols, TTraits::TypeList< ColumnTypes... > typeList)

void	CheckIMTDisabled (std::string_view callerName)

template<typename ActionTag, typename... ColTypes, typename ActionResultType, typename RDFNode, typename HelperArgType = ActionResultType, std::enable_if_t< RDFInternal::RNeedJitting< ColTypes... >::value, int > = 0>
RResultPtr< ActionResultType >	CreateAction (const ColumnNames_t &columns, const std::shared_ptr< ActionResultType > &r, const std::shared_ptr< HelperArgType > &helperArg, const std::shared_ptr< RDFNode > &proxiedPtr, const int nColumns=-1)
	Create RAction object, return RResultPtr for the action Overload for the case in which one or more column types were not specified (RTTI + jitting).

template<typename ActionTag, typename... ColTypes, typename ActionResultType, typename RDFNode, typename HelperArgType = ActionResultType, std::enable_if_t<!RDFInternal::RNeedJitting< ColTypes... >::value, int > = 0>
RResultPtr< ActionResultType >	CreateAction (const ColumnNames_t &columns, const std::shared_ptr< ActionResultType > &r, const std::shared_ptr< HelperArgType > &helperArg, const std::shared_ptr< RDFNode > &proxiedPtr, const int=-1)
	Create RAction object, return RResultPtr for the action Overload for the case in which all column types were specified (no jitting).

std::string	DescribeDataset () const

ColumnNames_t	GetColumnTypeNamesList (const ColumnNames_t &columnList)

RDFDetail::RLoopManager *	GetLoopManager () const

ColumnNames_t	GetValidatedColumnNames (const unsigned int nColumns, const ColumnNames_t &columns)

template<typename RetType>
void	SanityChecksForVary (const std::vector< std::string > &colNames, const std::vector< std::string > &variationTags, std::string_view variationName)

Protected Attributes inherited from ROOT::RDF::RInterfaceBase
RDFInternal::RColumnRegister	fColRegister
	Contains the columns defined up to this node.

RDataSource *	fDataSource = nullptr
	Non-owning pointer to a data-source object. Null if no data-source. RLoopManager has ownership of the object.

std::shared_ptr< ROOT::Detail::RDF::RLoopManager >	fLoopManager
	< The RLoopManager at the root of this computation graph. Never null.

#include <ROOT/RDF/RInterface.hxx>

Inheritance diagram for ROOT::RDF::RInterface< Proxied, DataSource >:

[legend]

Member Typedef Documentation

◆ DS_t

template<typename Proxied, typename DataSource = void>

using ROOT::RDF::RInterface< Proxied, DataSource >::DS_t = DataSource

private

Definition at line 111 of file RInterface.hxx.

◆ RFilterBase

template<typename Proxied, typename DataSource = void>

using ROOT::RDF::RInterface< Proxied, DataSource >::RFilterBase = RDFDetail::RFilterBase

private

Definition at line 112 of file RInterface.hxx.

◆ RLoopManager

template<typename Proxied, typename DataSource = void>

using ROOT::RDF::RInterface< Proxied, DataSource >::RLoopManager = RDFDetail::RLoopManager

private

Definition at line 114 of file RInterface.hxx.

◆ RRangeBase

template<typename Proxied, typename DataSource = void>

using ROOT::RDF::RInterface< Proxied, DataSource >::RRangeBase = RDFDetail::RRangeBase

private

Definition at line 113 of file RInterface.hxx.

Constructor & Destructor Documentation

◆ RInterface() [1/3]

template<typename Proxied, typename DataSource = void>

ROOT::RDF::RInterface< Proxied, DataSource >::RInterface ( const RInterface< Proxied, DataSource > & )

default

Copy-ctor for RInterface.

◆ RInterface() [2/3]

template<typename Proxied, typename DataSource = void>

ROOT::RDF::RInterface< Proxied, DataSource >::RInterface ( RInterface< Proxied, DataSource > && )

default

Move-ctor for RInterface.

◆ RInterface() [3/3]

template<typename Proxied, typename DataSource = void>

template<typename T = Proxied, typename = std::enable_if_t<std::is_same<T, RLoopManager>::value, int>>

ROOT::RDF::RInterface< Proxied, DataSource >::RInterface ( const std::shared_ptr< RLoopManager > & proxied )

inline

Build a RInterface from a RLoopManager.

This constructor is only available for RInterface<RLoopManager>.

Definition at line 148 of file RInterface.hxx.

Member Function Documentation

◆ Define() [1/2]

template<typename Proxied, typename DataSource = void>

template<typename F, typename std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Define	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Define a new column.

Parameters

[in]	name	The name of the defined column.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the producer function.

Returns: the first node of the computation graph for which the new quantity is defined.

Define a column that will be visible from all subsequent nodes of the functional chain. The expression is only evaluated for entries that pass all the preceding filters. A new variable is created called name, accessible as if it was contained in the dataset from subsequent transformations/actions.

Use cases include:

caching the results of complex calculations for easy and efficient multiple access
extraction of quantities of interest from complex objects

An exception is thrown if the name of the new column is already in use in this branch of the computation graph.

Example usage:

// assuming a function with signature:
double myComplexCalculation(const RVec<float> &muon_pts);
// we can pass it directly to Define
auto df_with_define = df.Define("newColumn", myComplexCalculation, {"muon_pts"});
// alternatively, we can pass the body of the function as a string, as in Filter:
auto df_with_define = df.Define("newColumn", "x*x + y*y");

Note: If the body of the string expression contains an explicit return statement (even if it is in a nested scope), RDataFrame will not add another one in front of the expression. So this will not work:
df.Define("x2", "Map(v, [](float e) { return e*e; })")

but instead this will:
df.Define("x2", "return Map(v, [](float e) { return e*e; })")

Definition at line 338 of file RInterface.hxx.

◆ Define() [2/2]

template<typename Proxied, typename DataSource = void>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Define	(	std::string_view	name,
		std::string_view	expression )

inline

Define a new column.

Parameters

[in]	name	The name of the defined column.
[in]	expression	An expression in C++ which represents the defined value

Returns: the first node of the computation graph for which the new quantity is defined.

The expression is just-in-time compiled and used to produce the column entries. It must be valid C++ syntax in which variable names are substituted with the names of branches/columns.

Note: If the body of the string expression contains an explicit return statement (even if it is in a nested scope), RDataFrame will not add another one in front of the expression. So this will not work:
df.Define("x2", "Map(v, [](float e) { return e*e; })")

but instead this will:
df.Define("x2", "return Map(v, [](float e) { return e*e; })")

Refer to the first overload of this method for the full documentation.

Definition at line 425 of file RInterface.hxx.

◆ DefinePerSample() [1/2]

template<typename Proxied, typename DataSource = void>

template<typename F, typename RetType_t = typename TTraits::CallableTraits<F>::ret_type>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::DefinePerSample	(	std::string_view	name,
		F	expression )

inline

Define a new column that is updated when the input sample changes.

Parameters

[in]	name	The name of the defined column.
[in]	expression	A C++ callable that computes the new value of the defined column.

Returns: the first node of the computation graph for which the new quantity is defined.

The signature of the callable passed as second argument should be T(unsigned int slot, const ROOT::RDF::RSampleInfo &id) where:

T is the type of the defined column
slot is a number in the range [0, nThreads) that is different for each processing thread. This can simplify the definition of thread-safe callables if you are interested in using parallel capabilities of RDataFrame.
id is an instance of a ROOT::RDF::RSampleInfo object which contains information about the sample which is being processed (see the class docs for more information).

DefinePerSample() is useful to e.g. define a quantity that depends on which TTree in which TFile is being processed or to inject a callback into the event loop that is only called when the processing of a new sample starts rather than at every entry.

The callable will be invoked once per input TTree or once per multi-thread task, whichever is more often.

Example usage:

ROOT::RDataFrame df{"mytree", {"sample1.root","sample2.root"}};
df.DefinePerSample("weightbysample",
                   [](unsigned int slot, const ROOT::RDF::RSampleInfo &id)
                   { return id.Contains("sample1") ? 1.0f : 2.0f; });

Definition at line 566 of file RInterface.hxx.

◆ DefinePerSample() [2/2]

template<typename Proxied, typename DataSource = void>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::DefinePerSample	(	std::string_view	name,
		std::string_view	expression )

inline

Define a new column that is updated when the input sample changes.

Parameters

[in]	name	The name of the defined column.
[in]	expression	A valid C++ expression as a string, which will be used to compute the defined value.

Returns: the first node of the computation graph for which the new quantity is defined.

The expression is just-in-time compiled and used to produce the column entries. It must be valid C++ syntax and the usage of the special variable names rdfslot_ and rdfsampleinfo_ is permitted, where these variables will take the same values as the slot and id parameters described at the DefinePerSample(std::string_view name, F expression) overload. See the documentation of that overload for more information.

Example usage:

df = ROOT.RDataFrame('mytree', ['sample1.root','sample2.root'])

df.DefinePerSample('weightbysample', 'rdfsampleinfo_.Contains("sample1") ? 1.0f : 2.0f')

Note: If you have declared some C++ function to the interpreter, the correct syntax to call that function with this overload of DefinePerSample is by calling it explicitly with the special names rdfslot_ and rdfsampleinfo_ as input parameters. This is for example the correct way to call this overload when working in PyROOT:
ROOT.gInterpreter.Declare(

"""

float weights(unsigned int slot, const ROOT::RDF::RSampleInfo &id){

return id.Contains("sample1") ? 1.0f : 2.0f;

}

""")

df = ROOT.RDataFrame("mytree", ["sample1.root","sample2.root"])

df.DefinePerSample("weightsbysample", "weights(rdfslot_, rdfsampleinfo_)"); Differently from what happens in Define(), the string expression passed to DefinePerSample cannot contain column names other than those mentioned above: the expression is evaluated once before the processing of the sample even starts, so column values are not accessible.

Definition at line 627 of file RInterface.hxx.

◆ DefineSlot()

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::DefineSlot	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Define a new column with a value dependent on the processing slot.

Parameters

[in]	name	The name of the defined column.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the producer function (excluding the slot number).

Returns: the first node of the computation graph for which the new quantity is defined.

This alternative implementation of Define is meant as a helper to evaluate new column values in a thread-safe manner. The expression must be a callable of signature R(unsigned int, T1, T2, ...) where T1, T2... are the types of the columns that the expression takes as input. The first parameter is reserved for an unsigned integer representing a "slot number". RDataFrame guarantees that different threads will invoke the expression with different slot numbers - slot numbers will range from zero to ROOT::GetThreadPoolSize()-1.

The following two calls are equivalent, although DefineSlot is slightly more performant:

int function(unsigned int, double, double);
df.Define("x", function, {"rdfslot_", "column1", "column2"})
df.DefineSlot("x", function, {"column1", "column2"})

See Define() for more information.

Definition at line 367 of file RInterface.hxx.

◆ DefineSlotEntry()

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::DefineSlotEntry	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Define a new column with a value dependent on the processing slot and the current entry.

Parameters

[in]	name	The name of the defined column.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the producer function (excluding slot and entry).

Returns: the first node of the computation graph for which the new quantity is defined.

This alternative implementation of Define is meant as a helper in writing entry-specific, thread-safe custom columns. The expression must be a callable of signature R(unsigned int, ULong64_t, T1, T2, ...) where T1, T2... are the types of the columns that the expression takes as input. The first parameter is reserved for an unsigned integer representing a "slot number". RDataFrame guarantees that different threads will invoke the expression with different slot numbers - slot numbers will range from zero to ROOT::GetThreadPoolSize()-1. The second parameter is reserved for a ULong64_t representing the current entry being processed by the current thread.

The following two Defines are equivalent, although DefineSlotEntry is slightly more performant:

int function(unsigned int, ULong64_t, double, double);
Define("x", function, {"rdfslot_", "rdfentry_", "column1", "column2"})
DefineSlotEntry("x", function, {"column1", "column2"})

See Define() for more information.

Definition at line 397 of file RInterface.hxx.

◆ Filter() [1/4]

template<typename Proxied, typename DataSource = void>

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>

RInterface< RDFDetail::RFilter< F, Proxied >, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Filter	(	F	f,
		const ColumnNames_t &	columns = {},
		std::string_view	name = "" )

inline

Append a filter to the call graph.

Parameters

[in]	f	Function, lambda expression, functor class or any other callable object. It must return a `bool` signalling whether the event has passed the selection (true) or not (false).
[in]	columns	Names of the columns/branches in input to the filter function.
[in]	name	Optional name of this filter. See `Report`.

Returns: the filter node of the computation graph.

Append a filter node at the point of the call graph corresponding to the object this method is called on. The callable f should not have side-effects (e.g. modification of an external or static variable) to ensure correct results when implicit multi-threading is active.

RDataFrame only evaluates filters when necessary: if multiple filters are chained one after another, they are executed in order and the first one returning false causes the event to be discarded. Even if multiple actions or transformations depend on the same filter, it is executed once per entry. If its result is requested more than once, the cached result is served.

Example usage:

// C++ callable (function, functor class, lambda...) that takes two parameters of the types of "x" and "y"
auto filtered = df.Filter(myCut, {"x", "y"});
 
// String: it must contain valid C++ except that column names can be used instead of variable names
auto filtered = df.Filter("x*y > 0");

Note: If the body of the string expression contains an explicit return statement (even if it is in a nested scope), RDataFrame will not add another one in front of the expression. So this will not work:
df.Filter("Sum(Map(vec, [](float e) { return e*e > 0.5; }))")

but instead this will:
df.Filter("return Sum(Map(vec, [](float e) { return e*e > 0.5; }))")

Definition at line 216 of file RInterface.hxx.

◆ Filter() [2/4]

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< RDFDetail::RFilter< F, Proxied >, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Filter	(	F	f,
		const std::initializer_list< std::string > &	columns )

inline

Append a filter to the call graph.

Parameters

[in]	f	Function, lambda expression, functor class or any other callable object. It must return a `bool` signalling whether the event has passed the selection (true) or not (false).
[in]	columns	Names of the columns/branches in input to the filter function.

Returns: the filter node of the computation graph.

Refer to the first overload of this method for the full documentation.

Definition at line 255 of file RInterface.hxx.

◆ Filter() [3/4]

template<typename Proxied, typename DataSource = void>

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>

RInterface< RDFDetail::RFilter< F, Proxied >, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Filter	(	F	f,
		std::string_view	name )

inline

Append a filter to the call graph.

Parameters

[in]	f	Function, lambda expression, functor class or any other callable object. It must return a `bool` signalling whether the event has passed the selection (true) or not (false).
[in]	name	Optional name of this filter. See `Report`.

Returns: the filter node of the computation graph.

Refer to the first overload of this method for the full documentation.

Definition at line 239 of file RInterface.hxx.

◆ Filter() [4/4]

template<typename Proxied, typename DataSource = void>

RInterface< RDFDetail::RJittedFilter, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Filter	(	std::string_view	expression,
		std::string_view	name = "" )

inline

Append a filter to the call graph.

Parameters

[in]	expression	The filter expression in C++
[in]	name	Optional name of this filter. See `Report`.

Returns: the filter node of the computation graph.

The expression is just-in-time compiled and used to filter entries. It must be valid C++ syntax in which variable names are substituted with the names of branches/columns.

Example usage:

auto filtered_df = df.Filter("myCollection.size() > 3");

auto filtered_name_df = df.Filter("myCollection.size() > 3", "Minumum collection size");

Note: If the body of the string expression contains an explicit return statement (even if it is in a nested scope), RDataFrame will not add another one in front of the expression. So this will not work:
df.Filter("Sum(Map(vec, [](float e) { return e*e > 0.5; }))")

but instead this will:
df.Filter("return Sum(Map(vec, [](float e) { return e*e > 0.5; }))")

Definition at line 285 of file RInterface.hxx.

◆ operator RNode()

template<typename Proxied, typename DataSource = void>

ROOT::RDF::RInterface< Proxied, DataSource >::operator RNode ( ) const

inline

Cast any RDataFrame node to a common type ROOT::RDF::RNode.

Different RDataFrame methods return different C++ types. All nodes, however, can be cast to this common type at the cost of a small performance penalty. This allows, for example, storing RDataFrame nodes in a vector, or passing them around via (non-template, C++11) helper functions. Example usage:

// a function that conditionally adds a Range to a RDataFrame node.
RNode MaybeAddRange(RNode df, bool mustAddRange)
{
   return mustAddRange ? df.Range(1) : df;
}
// use as :
ROOT::RDataFrame df(10);
auto maybeRanged = MaybeAddRange(df, true);

Note that it is not a problem to pass RNode's by value.

Definition at line 170 of file RInterface.hxx.

◆ operator=() [1/2]

template<typename Proxied, typename DataSource = void>

RInterface & ROOT::RDF::RInterface< Proxied, DataSource >::operator= ( const RInterface< Proxied, DataSource > & )

default

Copy-assignment operator for RInterface.

◆ operator=() [2/2]

template<typename Proxied, typename DataSource = void>

RInterface & ROOT::RDF::RInterface< Proxied, DataSource >::operator= ( RInterface< Proxied, DataSource > && )

default

Move-assignment operator for RInterface.

◆ Redefine() [1/2]

template<typename Proxied, typename DataSource = void>

template<typename F, std::enable_if_t<!std::is_convertible< F, std::string >::value, int > = 0>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Redefine	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Overwrite the value and/or type of an existing column.

Parameters

[in]	name	The name of the column to redefine.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the expression.

Returns: the first node of the computation graph for which the quantity is redefined.

The old value of the column can be used as an input for the expression.

An exception is thrown in case the column to redefine does not already exist. See Define() for more information.

Definition at line 457 of file RInterface.hxx.

◆ Redefine() [2/2]

template<typename Proxied, typename DataSource = void>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Redefine	(	std::string_view	name,
		std::string_view	expression )

inline

Overwrite the value and/or type of an existing column.

Parameters

[in]	name	The name of the column to redefine.
[in]	expression	An expression in C++ which represents the defined value

Returns: the first node of the computation graph for which the new quantity is defined.

The expression is just-in-time compiled and used to produce the column entries. It must be valid C++ syntax in which variable names are substituted with the names of branches/columns.

The old value of the column can be used as an input for the expression. An exception is thrown in case the column to re-define does not already exist.

Aliases cannot be overridden. See the corresponding Define() overload for more information.

Definition at line 515 of file RInterface.hxx.

◆ RedefineSlot()

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::RedefineSlot	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Overwrite the value and/or type of an existing column.

Parameters

[in]	name	The name of the column to redefine.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the producer function (excluding slot).

Returns: the first node of the computation graph for which the new quantity is defined.

The old value of the column can be used as an input for the expression. An exception is thrown in case the column to redefine does not already exist.

See DefineSlot() for more information.

Definition at line 476 of file RInterface.hxx.

◆ RedefineSlotEntry()

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::RedefineSlotEntry	(	std::string_view	name,
		F	expression,
		const ColumnNames_t &	columns = {} )

inline

Overwrite the value and/or type of an existing column.

Parameters

[in]	name	The name of the column to redefine.
[in]	expression	Function, lambda expression, functor class or any other callable object producing the defined value. Returns the value that will be assigned to the defined column.
[in]	columns	Names of the columns/branches in input to the producer function (excluding slot and entry).

Returns: the first node of the computation graph for which the new quantity is defined.

The old value of the column can be used as an input for the expression. An exception is thrown in case the column to re-define does not already exist.

See DefineSlotEntry() for more information.

Definition at line 495 of file RInterface.hxx.

◆ Vary() [1/4]

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Vary	(	const std::vector< std::string > &	colNames,
		F &&	expression,
		const ColumnNames_t &	inputColumns,
		const std::vector< std::string > &	variationTags,
		std::string_view	variationName )

inline

Register systematic variations for multiple existing columns using custom variation tags.

Parameters

[in]	colNames	set of names of the columns for which varied values are provided.
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can take any column values as input, similarly to what happens during Filter and Define calls. It must return an RVec of varied values, one for each variation tag, in the same order as the tags.
[in]	inputColumns	the names of the columns to be passed to the callable.
[in]	variationTags	names for each of the varied values, e.g. `"up"` and `"down"`.
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`

This overload of Vary takes a list of column names as first argument and requires that the expression returns an RVec of RVecs of values: one inner RVec for the variations of each affected column. The variationTags are defined as {"down", "up"}.

Example usage:

// produce variations "ptAndEta:down" and "ptAndEta:up"
auto nominal_hx =
  df.Vary({"pt", "eta"}, // the columns that will vary simultaneously
        [](double pt, double eta) { return RVec<RVecF>{{pt*0.9, pt*1.1}, {eta*0.9, eta*1.1}}; },
        {"pt", "eta"},  // inputs to the Vary expression, independent of what columns are varied
        {"down", "up"}, // variation tags
        "ptAndEta")    // variation name
    .Histo1D("pt", "eta");
 
auto hx = ROOT::RDF::Experimental::VariationsFor(nominal_hx);
hx["nominal"].Draw();
hx["ptAndEta:down"].Draw("SAME");
hx["ptAndEta:up"].Draw("SAME");

See also: This Vary() overload for more information.

Definition at line 781 of file RInterface.hxx.

◆ Vary() [2/4]

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Vary	(	std::initializer_list< std::string >	colNames,
		F &&	expression,
		const ColumnNames_t &	inputColumns,
		const std::vector< std::string > &	variationTags,
		std::string_view	variationName )

inline

Register systematic variations for multiple existing columns using custom variation tags.

Parameters

[in]	colNames	set of names of the columns for which varied values are provided.
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can take any column values as input, similarly to what happens during Filter and Define calls. It must return an RVec of varied values, one for each variation tag, in the same order as the tags.
[in]	inputColumns	the names of the columns to be passed to the callable.
[in]	variationTags	names for each of the varied values, e.g. `"up"` and `"down"`.
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`. colName is used if none is provided.

Note: This overload ensures that the ambiguity between C++20 string, vector<string> construction from init list is avoided.

See also: This Vary() overload for more information.

Definition at line 803 of file RInterface.hxx.

◆ Vary() [3/4]

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Vary	(	std::string_view	colName,
		F &&	expression,
		const ColumnNames_t &	inputColumns,
		const std::vector< std::string > &	variationTags,
		std::string_view	variationName = "" )

inline

Register systematic variations for a single existing column using custom variation tags.

Parameters

[in]	colName	name of the column for which varied values are provided.
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can take any column values as input, similarly to what happens during Filter and Define calls. It must return an RVec of varied values, one for each variation tag, in the same order as the tags.
[in]	inputColumns	the names of the columns to be passed to the callable.
[in]	variationTags	names for each of the varied values, e.g. `"up"` and `"down"`.
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`.

Vary provides a natural and flexible syntax to define systematic variations that automatically propagate to Filters, Defines and results. RDataFrame usage of columns with attached variations does not change, but for results that depend on any varied quantity, a map/dictionary of varied results can be produced with ROOT::RDF::Experimental::VariationsFor (see the example below).

The dictionary will contain a "nominal" value (accessed with the "nominal" key) for the unchanged result, and values for each of the systematic variations that affected the result (via upstream Filters or via direct or indirect dependencies of the column values on some registered variations). The keys will be a composition of variation names and tags, e.g. "pt:up" and "pt:down" for the example below.

In the following example we add up/down variations of pt and fill a histogram with a quantity that depends on pt. We automatically obtain three histograms in output ("nominal", "pt:up" and "pt:down"):

auto nominal_hx =
    df.Vary("pt", [] (double pt) { return RVecD{pt*0.9, pt*1.1}; }, {"down", "up"})
      .Filter("pt > k")
      .Define("x", someFunc, {"pt"})
      .Histo1D("x");
 
auto hx = ROOT::RDF::Experimental::VariationsFor(nominal_hx);
hx["nominal"].Draw();
hx["pt:down"].Draw("SAME");
hx["pt:up"].Draw("SAME");

RDataFrame computes all variations as part of a single loop over the data. In particular, this means that I/O and computation of values shared among variations only happen once for all variations. Thus, the event loop run-time typically scales much better than linearly with the number of variations.

RDataFrame lazily computes the varied values required to produce the outputs of VariationsFor(). If VariationsFor() was not called for a result, the computations are only run for the nominal case.

See other overloads for examples when variations are added for multiple existing columns, or when the tags are auto-generated instead of being directly defined.

Definition at line 693 of file RInterface.hxx.

◆ Vary() [4/4]

template<typename Proxied, typename DataSource = void>

template<typename F>

RInterface< Proxied, DS_t > ROOT::RDF::RInterface< Proxied, DataSource >::Vary	(	std::string_view	colName,
		F &&	expression,
		const ColumnNames_t &	inputColumns,
		std::size_t	nVariations,
		std::string_view	variationName = "" )

inline

Register systematic variations for a single existing column using auto-generated variation tags.

Parameters

[in]	colName	name of the column for which varied values are provided.
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can take any column values as input, similarly to what happens during Filter and Define calls. It must return an RVec of varied values, one for each variation tag, in the same order as the tags.
[in]	inputColumns	the names of the columns to be passed to the callable.
[in]	nVariations	number of variations returned by the expression. The corresponding tags will be `"0"`, `"1"`, etc.
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`. colName is used if none is provided.

This overload of Vary takes an nVariations parameter instead of a list of tag names. The varied results will be accessible via the keys of the dictionary with the form variationName:N where N is the corresponding sequential tag starting at 0 and going up to nVariations - 1.

Example usage:

auto nominal_hx =
  df.Vary("pt", [] (double pt) { return RVecD{pt*0.9, pt*1.1}; }, 2)
    .Histo1D("x");
 
auto hx = ROOT::RDF::Experimental::VariationsFor(nominal_hx);
hx["nominal"].Draw();
hx["x:0"].Draw("SAME");
hx["x:1"].Draw("SAME");

See also: This Vary() overload for more information.

Definition at line 732 of file RInterface.hxx.

Friends And Related Symbol Documentation

◆ RInterface

template<typename Proxied, typename DataSource = void>

template<typename T, typename W>

friend class RInterface

friend

Definition at line 119 of file RInterface.hxx.

◆ RDFInternal::ChangeEmptyEntryRange

template<typename Proxied, typename DataSource = void>

void RDFInternal::ChangeEmptyEntryRange	(	const RNode &	node,
		std::pair< ULong64_t, ULong64_t > &&	newRange )

friend

◆ RDFInternal::ChangeSpec

template<typename Proxied, typename DataSource = void>

void RDFInternal::ChangeSpec	(	const RNode &	node,
		ROOT::RDF::Experimental::RDatasetSpec &&	spec )

friend

◆ RDFInternal::GraphDrawing::GraphCreatorHelper

template<typename Proxied, typename DataSource = void>

friend class RDFInternal::GraphDrawing::GraphCreatorHelper

friend

Definition at line 116 of file RInterface.hxx.

◆ RDFInternal::TriggerRun

template<typename Proxied, typename DataSource = void>

void RDFInternal::TriggerRun ( RNode node )

friend

Member Data Documentation

◆ fProxiedPtr

template<typename Proxied, typename DataSource = void>

std::shared_ptr<Proxied> ROOT::RDF::RInterface< Proxied, DataSource >::fProxiedPtr

private

Smart pointer to the graph node encapsulated by this RInterface.

Definition at line 125 of file RInterface.hxx.

◆ true

template<typename Proxied, typename DataSource = void>

ROOT::RDF::RInterface< Proxied, DataSource >::true

Register systematic variations for multiple existing columns using auto-generated tags.

Parameters

[in]	colNames	set of names of the columns for which varied values are provided.
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can take any column values as input, similarly to what happens during Filter and Define calls. It must return an RVec of varied values, one for each variation tag, in the same order as the tags.
[in]	inputColumns	the names of the columns to be passed to the callable.
[in]	nVariations	number of variations returned by the expression. The corresponding tags will be `"0"`, `"1"`, etc.
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`. colName is used if none is provided.

This overload of Vary takes a list of column names as first argument. It takes an nVariations parameter instead of a list of tag names (variationTags). Tag names will be auto-generated as the sequence 0...nVariations-1. / / Example usage: / ~~~{.cpp} / auto nominal_hx = / df.Vary({"pt", "eta"}, // the columns that will vary simultaneously / [](double pt, double eta) { return RVec<RVecF>{{pt*0.9, pt*1.1}, {eta*0.9, eta*1.1}}; }, / {"pt", "eta"}, // inputs to the Vary expression, independent of what columns are varied / 2, // auto-generated variation tags / "ptAndEta") // variation name / .Histo1D("pt", "eta"); / / auto hx = ROOT::RDF::Experimental::VariationsFor(nominal_hx); / hx["nominal"].Draw(); / hx["ptAndEta:0"].Draw("SAME"); / hx["ptAndEta:1"].Draw("SAME"); / ~~~ / /

See also: This Vary() overload for more information. template <typename F> RInterface<Proxied, DS_t> Vary(const std::vector<std::string> &colNames, F &&expression, const ColumnNames_t &inputColumns, std::size_t nVariations, std::string_view variationName) { R__ASSERT(nVariations > 0 && "Must have at least one variation.");

std::vector<std::string> variationTags; variationTags.reserve(nVariations); for (std::size_t i = 0u; i < nVariations; ++i) variationTags.emplace_back(std::to_string(i));

return Vary(colNames, std::forward<F>(expression), inputColumns, std::move(variationTags), variationName); }

/ Register systematic variations for for multiple existing columns using custom variation tags. /

Parameters

[in]	colNames	set of names of the columns for which varied values are provided. /
[in]	expression	a callable that evaluates the varied values for the specified columns. The callable can / take any column values as input, similarly to what happens during Filter and Define calls. It must / return an RVec of varied values, one for each variation tag, in the same order as the tags. /
[in]	inputColumns	the names of the columns to be passed to the callable. /
[in]	inputColumns	the names of the columns to be passed to the callable. /
[in]	nVariations	number of variations returned by the expression. The corresponding tags will be `"0"`, / `"1"`, etc. /
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`. / colName is used if none is provided. / /

Note: This overload ensures that the ambiguity between C++20 string, vector<string> construction from init list / is avoided. / /

See also: This Vary() overload for more information. template <typename F> RInterface<Proxied, DS_t> Vary(std::initializer_list<std::string> colNames, F &&expression, const ColumnNames_t &inputColumns, std::size_t nVariations, std::string_view variationName) { return Vary(std::vector<std::string>(colNames), std::forward<F>(expression), inputColumns, nVariations, variationName); }

/ Register systematic variations for a single existing column using custom variation tags. /

Parameters

[in]	colName	name of the column for which varied values are provided. /
[in]	expression	a string containing valid C++ code that evaluates to an RVec containing the varied / values for the specified column. /
[in]	variationTags	names for each of the varied values, e.g. `"up"` and `"down"`. /
[in]	variationName	a generic name for this set of varied values, e.g. `"ptvariation"`. / colName is used if none is provided. / / This overload adds the possibility for the expression used to evaluate the varied values to be just-in-time / compiled. The example below shows how Vary() is used while dealing with a single column. The variation tags are / defined as `{"down", "up"}`. / ~~~{.cpp} / auto nominal_hx = / df.Vary("pt", "ROOT::RVecD{pt0.9, pt1.1}", {"down", "up"}) / .Filter("pt > k") / .Define("x", someFunc, {"pt"}) / .Histo1D("x"); / / auto hx = ROOT::RDF::Experimental::VariationsFor(nominal_hx); / hx["nominal"].Draw(); / hx["pt:down"].Draw("SAME"); / hx["pt:up"].Draw("SAME"); / ~~~ / /

See also: This Vary() overload for more information. RInterface<Proxied, DS_t> Vary(std::string_view colName, std::string_view expression, const std::vector<std::string> &variationTags, std::string_view variationName = "") { std::vector<std::string> colNames{{std::string(colName)}}; const std::string theVariationName{variationName.empty() ? colName : variationName};

return JittedVaryImpl(colNames, expression, variationTags, theVariationName, /*isSingleColumn=

Definition at line 911 of file RInterface.hxx.

tree/dataframe/inc/ROOT/RDF/InterfaceUtils.hxx

tree/dataframe/inc/ROOT/RDF/RInterface.hxx

Public Member Functions

Public Attributes

Private Types

Private Attributes

Friends

Additional Inherited Members

Member Typedef Documentation

◆ DS_t

◆ RFilterBase

◆ RLoopManager

◆ RRangeBase

Constructor & Destructor Documentation

◆ RInterface() [1/3]

◆ RInterface() [2/3]

◆ RInterface() [3/3]

Member Function Documentation

◆ Define() [1/2]

Example usage:

◆ Define() [2/2]

◆ DefinePerSample() [1/2]

Example usage:

◆ DefinePerSample() [2/2]

Example usage:

◆ DefineSlot()

◆ DefineSlotEntry()

◆ Filter() [1/4]

Example usage:

◆ Filter() [2/4]

◆ Filter() [3/4]

◆ Filter() [4/4]

Example usage:

◆ operator RNode()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ Redefine() [1/2]

◆ Redefine() [2/2]

◆ RedefineSlot()

◆ RedefineSlotEntry()

◆ Vary() [1/4]

◆ Vary() [2/4]

◆ Vary() [3/4]

◆ Vary() [4/4]

Friends And Related Symbol Documentation

◆ RInterface

◆ RDFInternal::ChangeEmptyEntryRange

◆ RDFInternal::ChangeSpec

◆ RDFInternal::GraphDrawing::GraphCreatorHelper

◆ RDFInternal::TriggerRun

Member Data Documentation

◆ fProxiedPtr

◆ true