data-manipulation-utilities 0.1.3__tar.gz → 0.1.5__tar.gz

{data_manipulation_utilities-0.1.3 → data_manipulation_utilities-0.1.5}/PKG-INFO

@@ -1,8 +1,7 @@
 Metadata-Version: 2.1
 Name: data_manipulation_utilities
-Version: 0.1.3
+Version: 0.1.5
 Description-Content-Type: text/markdown
-Requires-Dist: zfit
 Requires-Dist: logzero
 Requires-Dist: PyYAML
 Requires-Dist: scipy

{data_manipulation_utilities-0.1.3 → data_manipulation_utilities-0.1.5}/pyproject.toml

@@ -1,9 +1,8 @@
 [project]
 name        = 'data_manipulation_utilities'
-version     = '0.1.3'
+version     = '0.1.5'
 readme      = 'README.md'
 dependencies= [
-'zfit',
 'logzero',
 'PyYAML',
 'scipy',

{data_manipulation_utilities-0.1.3 → data_manipulation_utilities-0.1.5}/src/data_manipulation_utilities.egg-info/PKG-INFO

@@ -1,8 +1,7 @@
 Metadata-Version: 2.1
 Name: data_manipulation_utilities
-Version: 0.1.3
+Version: 0.1.5
 Description-Content-Type: text/markdown
-Requires-Dist: zfit
 Requires-Dist: logzero
 Requires-Dist: PyYAML
 Requires-Dist: scipy

{data_manipulation_utilities-0.1.3 → data_manipulation_utilities-0.1.5}/src/data_manipulation_utilities.egg-info/requires.txt

@@ -1,4 +1,3 @@
-zfit
 logzero
 PyYAML
 scipy

{data_manipulation_utilities-0.1.3 → data_manipulation_utilities-0.1.5}/src/dmu/rdataframe/utilities.py

@@ -4,11 +4,13 @@ Module containing utility functions to be used with ROOT dataframes
 
 import re
 from dataclasses import dataclass
+from typing      import Union
 
+import pandas  as pnd
 import awkward as ak
 import numpy
 
-from ROOT import RDataFrame
+from ROOT import RDataFrame, RDF
 
 from dmu.logging.log_store import LogStore
 
@@ -23,7 +25,7 @@ class Data:
     l_good_type = [int, numpy.bool_, numpy.int32, numpy.uint32, numpy.int64, numpy.uint64, numpy.float32, numpy.float64]
     d_cast_type = {'bool': numpy.int32}
 # ---------------------------------------------------------------------
-def add_column(rdf : RDataFrame, arr_val : numpy.ndarray | None, name : str, d_opt : dict | None = None):
+def add_column(rdf : RDataFrame, arr_val : Union[numpy.ndarray,None], name : str, d_opt : Union[dict,None] = None):
     '''
     Will take a dataframe, an array of numbers and a string
     Will add the array as a colunm to the dataframe
@@ -70,3 +72,24 @@ def add_column(rdf : RDataFrame, arr_val : numpy.ndarray | None, name : str, d_o
 
     return rdf
 # ---------------------------------------------------------------------
+def rdf_report_to_df(rep : RDF.RCutFlowReport) -> pnd.DataFrame:
+    '''
+    Takes the output of rdf.Report(), i.e. an RDataFrame cutflow report.
+
+    Produces a pandas dataframe with
+    '''
+    d_data = {'cut' : [], 'All' : [], 'Passed' : []}
+    for cut in rep:
+        name=cut.GetName()
+        pas =cut.GetPass()
+        tot =cut.GetAll()
+
+        d_data['cut'   ].append(name)
+        d_data['All'   ].append(tot)
+        d_data['Passed'].append(pas)
+
+    df = pnd.DataFrame(d_data)
+    df['Efficiency' ] = df['Passed'] / df['All']
+    df['Cummulative'] = df['Efficiency'].cumprod()
+
+    return df