doc/master/df026__AsNumpyArrays_8py.html

import ROOT

from sys import exit


# Let's create a simple dataframe with ten rows and two columns

df = ROOT.RDataFrame(10) \

         .Define("x", "(int)rdfentry_") \

         .Define("y", "1.f/(1.f+rdfentry_)")


# Next, we want to access the data from Python as Numpy arrays. To do so, the

# content of the dataframe is converted using the AsNumpy method. The returned

# object is a dictionary with the column names as keys and 1D numpy arrays with

# the content as values.

npy = df.AsNumpy()

print("Read-out of the full RDataFrame:\n{}\n".format(npy))


# Since reading out data to memory is expensive, always try to read-out only what

# is needed for your analysis. You can use all RDataFrame features to reduce your

# dataset, e.g., the Filter transformation. Furthermore, you can can pass to the

# AsNumpy method a whitelist of column names with the option `columns` or a blacklist

# with column names with the option `exclude`.

df2 = df.Filter("x>5")

npy2 = df2.AsNumpy()

print("Read-out of the filtered RDataFrame:\n{}\n".format(npy2))


npy3 = df2.AsNumpy(columns=["x"])

print("Read-out of the filtered RDataFrame with the columns option:\n{}\n".format(npy3))


npy4 = df2.AsNumpy(exclude=["x"])

print("Read-out of the filtered RDataFrame with the exclude option:\n{}\n".format(npy4))


# You can read-out all objects from ROOT files since these are wrapped by PyROOT

# in the Python world. However, be aware that objects other than fundamental types,

# such as complex C++ objects and not int or float, are costly to read-out.

ROOT.gInterpreter.Declare("""

// Inject the C++ class CustomObject in the C++ runtime.

class CustomObject {

public:

    int x = 42;

};

// Create a function that returns such an object. This is called to fill the dataframe.

CustomObject fill_object() { return CustomObject(); }

""")


df3 = df.Define("custom_object", "fill_object()")

npy5 = df3.AsNumpy()

print("Read-out of C++ objects:\n{}\n".format(npy5["custom_object"]))

print("Access to all methods and data members of the C++ object:\nObject: {}\nAccess data member: custom_object.x = {}\n".format(

    repr(npy5["custom_object"][0]), npy5["custom_object"][0].x))


# Note that you can pass the object returned by AsNumpy directly to pandas.DataFrame

# including any complex C++ object that may be read-out.

try:

    import pandas

except:

    print("Please install the pandas package to run this section of the tutorial.")

    exit(1)


df = pandas.DataFrame(npy5)

print("Content of the ROOT.RDataFrame as pandas.DataFrame:\n{}\n".format(df))

TRangeDynCast
ROOT::Detail::TRangeCast< T, true > TRangeDynCast
TRangeDynCast is an adapter class that allows the typed iteration through a TCollection.
Definition TCollection.h:358

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::Detail::TRangeCast
Definition TCollection.h:311

ROOT::RDataFrame
ROOT's RDataFrame offers a modern, high-level interface for analysis of data stored in TTree ,...
Definition RDataFrame.hxx:44