data-manipulation-utilities 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

{data_manipulation_utilities-0.2.2.dist-info → data_manipulation_utilities-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: data_manipulation_utilities
-Version: 0.2.2
+Version: 0.2.3
 Description-Content-Type: text/markdown
 Requires-Dist: logzero
 Requires-Dist: PyYAML
@@ -578,6 +578,24 @@ These are utility functions meant to be used with ROOT dataframes.
 
 ## Adding a column from a numpy array
 
+### With numba
+
+For this do:
+
+```python
+import dmu.rdataframe.utilities as ut
+
+arr_val = numpy.array([10, 20, 30])
+rdf     = ut.add_column_with_numba(rdf, arr_val, 'values', identifier='some_name')
+```
+
+where the identifier needs to be unique, every time the function is called.
+This is the case, because the addition is done internally by declaring a numba function whose name
+cannot be repeated as mentioned
+[here](https://root-forum.cern.ch/t/ways-to-work-around-the-redefinition-of-compiled-functions-in-one-single-notebook-session/41442/1)
+
+### With awkward
+
 For this do:
 
 ```python

{data_manipulation_utilities-0.2.2.dist-info → data_manipulation_utilities-0.2.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-data_manipulation_utilities-0.2.2.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
+data_manipulation_utilities-0.2.3.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
 dmu/arrays/utilities.py,sha256=PKoYyybPptA2aU-V3KLnJXBudWxTXu4x1uGdIMQ49HY,1722
 dmu/generic/utilities.py,sha256=0Xnq9t35wuebAqKxbyAiMk1ISB7IcXK4cFH25MT1fgw,1741
 dmu/logging/log_store.py,sha256=umdvjNDuV3LdezbG26b0AiyTglbvkxST19CQu9QATbA,4184
@@ -13,7 +13,7 @@ dmu/plotting/plotter_1d.py,sha256=g6H2xAgsL9a6vRkpbqHICb3qwV_qMiQPZxxw_oOSf9M,51
 dmu/plotting/plotter_2d.py,sha256=J-gKnagoHGfJFU7HBrhDFpGYH5Rxy0_zF5l8eE_7ZHE,2944
 dmu/plotting/utilities.py,sha256=SI9dvtZq2gr-PXVz71KE4o0i09rZOKgqJKD1jzf6KXk,1167
 dmu/rdataframe/atr_mgr.py,sha256=FdhaQWVpsm4OOe1IRbm7rfrq8VenTNdORyI-lZ2Bs1M,2386
-dmu/rdataframe/utilities.py,sha256=MDY3u_y0s-ANvHAWRzGyeuuZUKoaqilfmb8mqlgfrVc,2771
+dmu/rdataframe/utilities.py,sha256=pNcQARMP7txMhy6k27UnDcYf0buNy5U2fshaJDl_h8o,3661
 dmu/rfile/rfprinter.py,sha256=mp5jd-oCJAnuokbdmGyL9i6tK2lY72jEfROuBIZ_ums,3941
 dmu/rfile/utilities.py,sha256=XuYY7HuSBj46iSu3c60UYBHtI6KIPoJU_oofuhb-be0,945
 dmu/stats/fitter.py,sha256=vHNZ16U3apoQyeyM8evq-if49doF48sKB3q9wmA96Fw,18387
@@ -47,8 +47,8 @@ dmu_scripts/rfile/compare_root_files.py,sha256=T8lDnQxsRNMr37x1Y7YvWD8ySHrJOWZki
 dmu_scripts/rfile/print_trees.py,sha256=Ze4Ccl_iUldl4eVEDVnYBoe4amqBT1fSBR1zN5WSztk,941
 dmu_scripts/ssh/coned.py,sha256=lhilYNHWRCGxC-jtyJ3LQ4oUgWW33B2l1tYCcyHHsR0,4858
 dmu_scripts/text/transform_text.py,sha256=9akj1LB0HAyopOvkLjNOJiptZw5XoOQLe17SlcrGMD0,1456
-data_manipulation_utilities-0.2.2.dist-info/METADATA,sha256=0QwhQmQML65qk2kaXf1znMZOVNuvaY3l35E7cXLRCZ8,27359
-data_manipulation_utilities-0.2.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-data_manipulation_utilities-0.2.2.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
-data_manipulation_utilities-0.2.2.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
-data_manipulation_utilities-0.2.2.dist-info/RECORD,,
+data_manipulation_utilities-0.2.3.dist-info/METADATA,sha256=STJ7vYfcSIM9dtMRzywGLwDzH1sUBE5DL9FqvskMcxo,27923
+data_manipulation_utilities-0.2.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+data_manipulation_utilities-0.2.3.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
+data_manipulation_utilities-0.2.3.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
+data_manipulation_utilities-0.2.3.dist-info/RECORD,,

dmu/rdataframe/utilities.py

@@ -1,6 +1,7 @@
 '''
 Module containing utility functions to be used with ROOT dataframes
 '''
+# pylint: disable=no-name-in-module
 
 import re
 from dataclasses import dataclass
@@ -10,7 +11,7 @@ import pandas  as pnd
 import awkward as ak
 import numpy
 
-from ROOT import RDataFrame, RDF
+from ROOT import RDataFrame, RDF, Numba
 
 from dmu.logging.log_store import LogStore
 
@@ -34,6 +35,8 @@ def add_column(rdf : RDataFrame, arr_val : Union[numpy.ndarray,None], name : str
          exclude_re : Regex with patter of column names that we won't pick
     '''
 
+    log.warning(f'Adding column {name} with awkward')
+
     d_opt = {} if d_opt is None else d_opt
     if arr_val is None:
         raise ValueError('Array of values not introduced')
@@ -72,6 +75,29 @@ def add_column(rdf : RDataFrame, arr_val : Union[numpy.ndarray,None], name : str
 
     return rdf
 # ---------------------------------------------------------------------
+def add_column_with_numba(
+        rdf        : RDataFrame,
+        arr_val    : Union[numpy.ndarray,None],
+        name       : str,
+        identifier : str) -> RDataFrame:
+    '''
+    Will take a dataframe, an array of numbers and a string
+    Will add the array as a colunm to the dataframe
+
+    The `identifier` argument is a string need in order to avoid collisions
+    when using Numba to define a function to get the value from.
+    '''
+    identifier=f'fun_{identifier}'
+
+    @Numba.Declare(['int'], 'float', name=identifier)
+    def get_value(index):
+        return arr_val[index]
+
+    log.debug(f'Adding column {name} with numba')
+    rdf = rdf.Define(name, f'Numba::{identifier}(rdfentry_)')
+
+    return rdf
+# ---------------------------------------------------------------------
 def rdf_report_to_df(rep : RDF.RCutFlowReport) -> pnd.DataFrame:
     '''
     Takes the output of rdf.Report(), i.e. an RDataFrame cutflow report.