data-manipulation-utilities 0.2.2__tar.gz → 0.2.3__tar.gz

{data_manipulation_utilities-0.2.2/src/data_manipulation_utilities.egg-info → data_manipulation_utilities-0.2.3}/PKG-INFO

@@ -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/PKG-INFO → data_manipulation_utilities-0.2.3/README.md

@@ -1,23 +1,3 @@
-Metadata-Version: 2.2
-Name: data_manipulation_utilities
-Version: 0.2.2
-Description-Content-Type: text/markdown
-Requires-Dist: logzero
-Requires-Dist: PyYAML
-Requires-Dist: scipy
-Requires-Dist: awkward
-Requires-Dist: tqdm
-Requires-Dist: joblib
-Requires-Dist: scikit-learn
-Requires-Dist: toml
-Requires-Dist: numpy
-Requires-Dist: matplotlib
-Requires-Dist: mplhep
-Requires-Dist: hist[plot]
-Requires-Dist: pandas
-Provides-Extra: dev
-Requires-Dist: pytest; extra == "dev"
-
 # D(ata) M(anipulation) U(tilities)
 
 These are tools that can be used for different data analysis tasks.
@@ -578,6 +558,24 @@ 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 → data_manipulation_utilities-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name        = 'data_manipulation_utilities'
-version     = '0.2.2'
+version     = '0.2.3'
 readme      = 'README.md'
 dependencies= [
 'logzero',

data_manipulation_utilities-0.2.2/README.md → data_manipulation_utilities-0.2.3/src/data_manipulation_utilities.egg-info/PKG-INFO

@@ -1,3 +1,23 @@
+Metadata-Version: 2.2
+Name: data_manipulation_utilities
+Version: 0.2.3
+Description-Content-Type: text/markdown
+Requires-Dist: logzero
+Requires-Dist: PyYAML
+Requires-Dist: scipy
+Requires-Dist: awkward
+Requires-Dist: tqdm
+Requires-Dist: joblib
+Requires-Dist: scikit-learn
+Requires-Dist: toml
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: mplhep
+Requires-Dist: hist[plot]
+Requires-Dist: pandas
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+
 # D(ata) M(anipulation) U(tilities)
 
 These are tools that can be used for different data analysis tasks.
@@ -558,6 +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 → data_manipulation_utilities-0.2.3}/src/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.