data-manipulation-utilities 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

{data_manipulation_utilities-0.1.4.dist-info → data_manipulation_utilities-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation_utilities
-Version: 0.1.4
+Version: 0.1.6
 Description-Content-Type: text/markdown
 Requires-Dist: logzero
 Requires-Dist: PyYAML

{data_manipulation_utilities-0.1.4.dist-info → data_manipulation_utilities-0.1.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
-data_manipulation_utilities-0.1.4.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
+data_manipulation_utilities-0.1.6.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
+dmu/logging/log_store.py,sha256=umdvjNDuV3LdezbG26b0AiyTglbvkxST19CQu9QATbA,4184
 dmu/ml/cv_classifier.py,sha256=n81m7i2M6Zq96AEd9EZGwXSrbG5m9jkS5RdeXvbsAXU,3712
 dmu/ml/cv_predict.py,sha256=Bqxu-f6qquKJokFljhCzL_kiGcjLJLQFhVBD130fsyw,4893
 dmu/ml/train_mva.py,sha256=d_n-A07DFweikz5nXap4OE_Mqx8VprFT7zbxmnQAbac,9638
@@ -10,8 +10,8 @@ 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/rfile/rfprinter.py,sha256=vGdqyHT_GwGBhrY7KG63EAUGWEOqobz_5yTL6goXbfk,2722
+dmu/rdataframe/utilities.py,sha256=x8r379F2-vZPYzAdMFCn_V4Kx2Tx9t9pn_QHcZ1euew,2756
+dmu/rfile/rfprinter.py,sha256=mp5jd-oCJAnuokbdmGyL9i6tK2lY72jEfROuBIZ_ums,3941
 dmu/rfile/utilities.py,sha256=XuYY7HuSBj46iSu3c60UYBHtI6KIPoJU_oofuhb-be0,945
 dmu/stats/fitter.py,sha256=LDvFNyhgO0OzXN7aH3kfHe6LzuPqdQfPcKR_IegDcaU,18204
 dmu/stats/function.py,sha256=yzi_Fvp_ASsFzbWFivIf-comquy21WoeY7is6dgY0Go,9491
@@ -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-0.1.6.dist-info/METADATA,sha256=1ttATABwWcdqqPJM72_4s_ZQjtbFp9MzkfsprkDJTv8,19946
+data_manipulation_utilities-0.1.6.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+data_manipulation_utilities-0.1.6.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
+data_manipulation_utilities-0.1.6.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
+data_manipulation_utilities-0.1.6.dist-info/RECORD,,

dmu/logging/log_store.py

@@ -3,6 +3,8 @@ Module holding LogStore
 '''
 
 import logging
+from logging import Logger
+
 import logzero
 
 #------------------------------------------------------------
@@ -31,26 +33,28 @@ class LogStore:
     Class used to make loggers, set log levels, print loggers, e.g. interface to logging/logzero, etc.
     '''
     #pylint: disable = invalid-name
-    d_logger      = {}
-    d_levels      = {}
+    d_logger      : dict[str,Logger] = {}
+    d_levels      : dict[str,   int] = {}
     log_level     = logging.INFO
     is_configured = False
     backend       = 'logging'
     #--------------------------
     @staticmethod
-    def add_logger(name=None):
+    def add_logger(name : str, exists_ok : bool = False) -> Logger:
         '''
         Will use underlying logging library logzero/logging, etc to make logger
 
         name (str): Name of logger
         '''
 
-        if   name is None:
-            raise ValueError('Logger name missing')
-
-        if name in LogStore.d_logger:
+        if name in LogStore.d_logger and not exists_ok:
             raise ValueError(f'Logger name {name} already found')
 
+
+        if name in LogStore.d_logger and     exists_ok:
+            print(f'Logger {name} already found, reusing it')
+            return LogStore.d_logger[name]
+
         level  = LogStore.log_level if name not in LogStore.d_levels else LogStore.d_levels[name]
 
         if   LogStore.backend == 'logging':
@@ -65,14 +69,14 @@ class LogStore:
         return logger
     #--------------------------
     @staticmethod
-    def _get_logzero_logger(name : str, level : int):
+    def _get_logzero_logger(name : str, level : int) -> Logger:
         log = logzero.setup_logger(name=name)
         log.setLevel(level)
 
         return log
     #--------------------------
     @staticmethod
-    def _get_logging_logger(name : str, level : int):
+    def _get_logging_logger(name : str, level : int) -> Logger:
         logger = logging.getLogger(name=name)
 
         logger.setLevel(level)

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

dmu/rfile/rfprinter.py

@@ -3,7 +3,8 @@ Module containing RFPrinter
 '''
 import os
 
-from ROOT import TFile
+from typing import Union
+from ROOT   import TFile
 
 from dmu.logging.log_store import LogStore
 
@@ -22,7 +23,6 @@ class RFPrinter:
             raise FileNotFoundError(f'Cannot find {path}')
 
         self._root_path = path
-        self._text_path = path.replace('.root', '.txt')
     #-----------------------------------------
     def _get_trees(self, ifile):
         '''
@@ -54,29 +54,38 @@ class RFPrinter:
         for branch in l_branch:
             bname = branch.GetName()
             leaf  = branch.GetLeaf(bname)
-            btype = leaf.GetTypeName()
+            try:
+                btype = leaf.GetTypeName()
+            except:
+                log.warning(f'Cannot read {bname}')
+                continue
 
             l_line.append(f'{"":4}{bname:<100}{btype:<40}')
 
         return l_line
     #-----------------------------------------
-    def _save_info(self, l_info):
+    def _get_summary_path(self, file_name : Union[str,None]) -> str:
+        if file_name is None:
+            text_path = self._root_path.replace('.root', '.txt')
+            return text_path
+
+        root_dir = os.path.dirname(self._root_path)
+
+        return f'{root_dir}/{file_name}'
+    #-----------------------------------------
+    def _save_info(self, l_info : list[str], file_name : Union[str,None]) -> None:
         '''
         Takes list of strings, saves it to text file
         '''
 
-        with open(self._text_path, 'w', encoding='utf-8') as ofile:
+        text_path = self._get_summary_path(file_name)
+        with open(text_path, 'w', encoding='utf-8') as ofile:
             for info in l_info:
                 ofile.write(f'{info}\n')
 
-        log.info(f'Saved to: {self._text_path}')
+        log.info(f'Saved to: {text_path}')
     #-----------------------------------------
-    def save(self, to_screen=False):
-        '''
-        Will save a text file with the summary of the ROOT file contents
-
-        to_screen (bool) : If true, will print to screen, default=False
-        '''
+    def _get_info(self) -> list[str]:
         l_info = []
         log.info(f'Reading from : {self._root_path}')
         with TFile.Open(self._root_path) as ifile:
@@ -84,7 +93,27 @@ class RFPrinter:
             for tree in l_tree:
                 l_info+= self._get_tree_info(tree)
 
-        self._save_info(l_info)
+        return l_info
+    #-----------------------------------------
+    def save(self, file_name : Union[str,None] = None, to_screen : bool = False, raise_on_fail : bool = True) -> None:
+        '''
+        Will save a text file with the summary of the ROOT file contents
+
+        file_name    : If used, name the file with the summary this way. Othewise, use ROOT file with .txt extension
+        to_screen    : If true, will print to screen, default=False
+        raise_on_fail: If cannot open ROOT file, will raise exeption (default), otherwise will only show warning.
+        '''
+
+        try:
+            l_info = self._get_info()
+        except OSError as exc:
+            if raise_on_fail:
+                raise OSError(f'Cannot open: {self._root_path}') from exc
+
+            log.warning(f'Cannot open: {self._root_path}')
+            return
+
+        self._save_info(l_info, file_name=file_name)
         if to_screen:
             for info in l_info:
                 log.info(info)