data-manipulation-utilities 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

{data_manipulation_utilities-0.1.4.dist-info → data_manipulation_utilities-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation_utilities
-Version: 0.1.4
+Version: 0.1.5
 Description-Content-Type: text/markdown
 Requires-Dist: logzero
 Requires-Dist: PyYAML

{data_manipulation_utilities-0.1.4.dist-info → data_manipulation_utilities-0.1.5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-data_manipulation_utilities-0.1.4.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
+data_manipulation_utilities-0.1.5.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=v0tiNz-6ktT_afD5DuvCZ8Nmr82JKQOPli8hgd28P1Q,3960
@@ -10,7 +10,7 @@ dmu/plotting/plotter.py,sha256=laa6Kl7P-ZOIhaOFBVjOH4XQ4kPCV7wBNvLIMBnyCwM,7181
 dmu/plotting/plotter_1d.py,sha256=G-i94uzm2TjNaog1A4agAKar_G0qNdkAqIPCmzhe85Y,3660
 dmu/plotting/plotter_2d.py,sha256=SWPKns-CfpUZHgBXvwm3gceH3k2eL_mKGXQ8sWpZJB0,2919
 dmu/rdataframe/atr_mgr.py,sha256=FdhaQWVpsm4OOe1IRbm7rfrq8VenTNdORyI-lZ2Bs1M,2386
-dmu/rdataframe/utilities.py,sha256=a31PdUz12sC2bx78LK6gvACh1M_eFaIVwuZEvOTcvcc,2084
+dmu/rdataframe/utilities.py,sha256=x8r379F2-vZPYzAdMFCn_V4Kx2Tx9t9pn_QHcZ1euew,2756
 dmu/rfile/rfprinter.py,sha256=vGdqyHT_GwGBhrY7KG63EAUGWEOqobz_5yTL6goXbfk,2722
 dmu/rfile/utilities.py,sha256=XuYY7HuSBj46iSu3c60UYBHtI6KIPoJU_oofuhb-be0,945
 dmu/stats/fitter.py,sha256=LDvFNyhgO0OzXN7aH3kfHe6LzuPqdQfPcKR_IegDcaU,18204
@@ -39,8 +39,8 @@ 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-0.1.4.dist-info/METADATA,sha256=22y3wi2wh7fXUPYixxLJVDr0qyu0eeicGikPI4phUvg,19946
-data_manipulation_utilities-0.1.4.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-data_manipulation_utilities-0.1.4.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
-data_manipulation_utilities-0.1.4.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
-data_manipulation_utilities-0.1.4.dist-info/RECORD,,
+data_manipulation_utilities-0.1.5.dist-info/METADATA,sha256=FDasFTGm3SS2psyLpYbGkWFuKw42ejctM5_mJUEY_9Y,19946
+data_manipulation_utilities-0.1.5.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+data_manipulation_utilities-0.1.5.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
+data_manipulation_utilities-0.1.5.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
+data_manipulation_utilities-0.1.5.dist-info/RECORD,,

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