doc/master/df001__introduction_8py.html

import ROOT


# A simple helper function to fill a test tree: this makes the example stand-alone.

def fill_tree(treeName, fileName):

    df = ROOT.RDataFrame(10)

    df.Define("b1", "(double) rdfentry_")\

      .Define("b2", "(int) rdfentry_ * rdfentry_").Snapshot(treeName, fileName)


# We prepare an input tree to run on

fileName = "df001_introduction_py.root"

treeName = "myTree"

fill_tree(treeName, fileName)


# We read the tree from the file and create a RDataFrame, a class that

# allows us to interact with the data contained in the tree.

d = ROOT.RDataFrame(treeName, fileName)


# Operations on the dataframe

# We now review some *actions* which can be performed on the data frame.

# Actions can be divided into instant actions (e. g. Foreach()) and lazy

# actions (e. g. Count()), depending on whether they trigger the event

# loop immediately or only when one of the results is accessed for the

# first time. Actions that return "something" either return their result

# wrapped in a RResultPtr or in a RDataFrame.

# But first of all, let us we define now our cut-flow with two strings.

# Filters can be expressed as strings. The content must be C++ code. The

# name of the variables must be the name of the branches. The code is

# just-in-time compiled.

cutb1 = 'b1 < 5.'

cutb1b2 = 'b2 % 2 && b1 < 4.'


# `Count` action

# The `Count` allows to retrieve the number of the entries that passed the

# filters. Here we show how the automatic selection of the column kicks

# in in case the user specifies none.

entries1 = d.Filter(cutb1) \

            .Filter(cutb1b2) \

            .Count();


print('{} entries passed all filters'.format(entries1.GetValue()))


entries2 = d.Filter("b1 < 5.").Count();

print('{} entries passed all filters'.format(entries2.GetValue()))


# `Min`, `Max` and `Mean` actions

# These actions allow to retrieve statistical information about the entries

# passing the cuts, if any.

b1b2_cut = d.Filter(cutb1b2)

minVal = b1b2_cut.Min('b1')

maxVal = b1b2_cut.Max('b1')

meanVal = b1b2_cut.Mean('b1')

nonDefmeanVal = b1b2_cut.Mean("b2")

print('The mean is always included between the min and the max: {0} <= {1} <= {2}'.format(minVal.GetValue(), meanVal.GetValue(), maxVal.GetValue()))


# `Histo1D` action

# The `Histo1D` action allows to fill an histogram. It returns a TH1F filled

# with values of the column that passed the filters. For the most common

# types, the type of the values stored in the column is automatically

# guessed.

hist = d.Filter(cutb1).Histo1D('b1')

print('Filled h {0} times, mean: {1}'.format(hist.GetEntries(), hist.GetMean()))


# Express your chain of operations with clarity!

# We are discussing an example here but it is not hard to imagine much more

# complex pipelines of actions acting on data. Those might require code

# which is well organised, for example allowing to conditionally add filters

# or again to clearly separate filters and actions without the need of

# writing the entire pipeline on one line. This can be easily achieved.

# We'll show this re-working the `Count` example:

cutb1_result = d.Filter(cutb1);

cutb1b2_result = d.Filter(cutb1b2);

cutb1_cutb1b2_result = cutb1_result.Filter(cutb1b2)


# Now we want to count:

evts_cutb1_result = cutb1_result.Count()

evts_cutb1b2_result = cutb1b2_result.Count()

evts_cutb1_cutb1b2_result = cutb1_cutb1b2_result.Count()


print('Events passing cutb1: {}'.format(evts_cutb1_result.GetValue()))

print('Events passing cutb1b2: {}'.format(evts_cutb1b2_result.GetValue()))

print('Events passing both: {}'.format(evts_cutb1_cutb1b2_result.GetValue()))


# Calculating quantities starting from existing columns

# Often, operations need to be carried out on quantities calculated starting

# from the ones present in the columns. We'll create in this example a third

# column, the values of which are the sum of the *b1* and *b2* ones, entry by

# entry. The way in which the new quantity is defined is via a callable.

# It is important to note two aspects at this point:

# - The value is created on the fly only if the entry passed the existing

# filters.

# - The newly created column behaves as the one present on the file on disk.

# - The operation creates a new value, without modifying anything. De facto,

# this is like having a general container at disposal able to accommodate

# any value of any type.

# Let's dive in an example:

entries_sum = d.Define('sum', 'b2 + b1') \

               .Filter('sum > 4.2') \

               .Count()

print(entries_sum.GetValue())


format
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 Float_t Float_t Int_t Int_t UInt_t UInt_t Rectangle_t Int_t Int_t Window_t TString Int_t GCValues_t GetPrimarySelectionOwner GetDisplay GetScreen GetColormap GetNativeEvent const char const char dpyName wid window const char font_name cursor keysym reg const char only_if_exist regb h Point_t winding char text const char depth char const char Int_t count const char ColorStruct_t color const char Pixmap_t Pixmap_t PictureAttributes_t attr const char char ret_data h unsigned char height h Atom_t Int_t ULong_t ULong_t unsigned char prop_list Atom_t Atom_t Atom_t Time_t format
Definition TGWin32VirtualXProxy.cxx:249

ROOT::RDataFrame
ROOT's RDataFrame offers a modern, high-level interface for analysis of data stored in TTree ,...
Definition RDataFrame.hxx:41