data-manipulation-utilities 0.2.2__py3-none-any.whl → 0.2.4__py3-none-any.whl

{data_manipulation_utilities-0.2.2.dist-info → data_manipulation_utilities-0.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: data_manipulation_utilities
-Version: 0.2.2
+Version: 0.2.4
 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
@@ -838,6 +856,40 @@ Trees only in file_2.root:
   - Hlt2RD_BsToPhiMuMu_MVA/DecayTree
 ```
 
+# File system
+
+## Versions
+
+The utilities below allow the user to deal with versioned files and directories
+
+```python
+from dmu.generic.version_management import get_last_version
+from dmu.generic.version_management import get_next_version
+from dmu.generic.version_management import get_latest_file
+
+# get_next_version will take a version and provide the next one, e.g.
+get_next_version('v1')           # -> 'v2'
+get_next_version('v1.1')         # -> 'v2.1'
+get_next_version('v10.1')        # -> 'v11.1'
+
+get_next_version('/a/b/c/v1')    # -> '/a/b/c/v2'
+get_next_version('/a/b/c/v1.1')  # -> '/a/b/c/v2.1'
+get_next_version('/a/b/c/v10.1') # -> '/a/b/c/v11.1'
+
+# `get_latest_file` will return the path to the file with the highest version
+# in the `dir_path` directory that matches a wildcard, e.g.:
+
+last_file = get_latest_file(dir_path = file_dir, wc='name_*.txt')
+
+# `get_last_version` will return the string with the latest version
+# of directories in `dir_path`, e.g.:
+
+oversion=get_last_version(dir_path=dir_path, version_only=True)  # This will return only the version, e.g. v3.2
+oversion=get_last_version(dir_path=dir_path, version_only=False) # This will return full path, e.g. /a/b/c/v3.2 
+```
+
+The function above should work for numeric (e.g. `v1.2`) and non-numeric (e.g. `va`, `vb`) versions.
+
 # Text manipulation
 
 ## Transformations

{data_manipulation_utilities-0.2.2.dist-info → data_manipulation_utilities-0.2.4.dist-info}/RECORD

@@ -1,6 +1,7 @@
-data_manipulation_utilities-0.2.2.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
+data_manipulation_utilities-0.2.4.data/scripts/publish,sha256=-3K_Y2_4CfWCV50rPB8CRuhjxDu7xMGswinRwPovgLs,1976
 dmu/arrays/utilities.py,sha256=PKoYyybPptA2aU-V3KLnJXBudWxTXu4x1uGdIMQ49HY,1722
 dmu/generic/utilities.py,sha256=0Xnq9t35wuebAqKxbyAiMk1ISB7IcXK4cFH25MT1fgw,1741
+dmu/generic/version_management.py,sha256=G_HjGY-hu8lotZuTdVAg0B8yD0AltE866q2vJxvTg1g,3749
 dmu/logging/log_store.py,sha256=umdvjNDuV3LdezbG26b0AiyTglbvkxST19CQu9QATbA,4184
 dmu/ml/cv_classifier.py,sha256=8Jwx6xMhJaRLktlRdq0tFl32v6t8i63KmpxrlnXlomU,3759
 dmu/ml/cv_predict.py,sha256=4G7F_1yOvnLftsDC6zUpdvkxuHXGkPemhj0RsYySYDM,6708
@@ -13,7 +14,7 @@ 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 +48,8 @@ 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-0.2.4.dist-info/METADATA,sha256=Gc-ZuL88YHEK3pOK1IfQmaN6rKCcVVqrFS2VlT70jyk,29229
+data_manipulation_utilities-0.2.4.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+data_manipulation_utilities-0.2.4.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
+data_manipulation_utilities-0.2.4.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
+data_manipulation_utilities-0.2.4.dist-info/RECORD,,

dmu/generic/version_management.py

@@ -0,0 +1,132 @@
+'''
+Module containing functions used to find latest, next version, etc of a path.
+'''
+
+import glob
+import os
+import re
+
+from dmu.logging.log_store import LogStore
+
+log=LogStore.add_logger('dmu:version_management')
+#---------------------------------------
+def _get_numeric_version(version : str) -> int:
+    '''
+    Takes string with numbers at the end (padded or not)
+    Returns integer version of numbers
+    '''
+    #Skip these directories
+    if version in ['__pycache__']:
+        return -1
+
+    regex=r'[a-z]+(\d+)'
+    mtch =re.match(regex, version)
+    if not mtch:
+        log.debug(f'Cannot extract numeric version from: {version}')
+        return -1
+
+    str_val = mtch.group(1)
+    val     = int(str_val)
+
+    return val
+#---------------------------------------
+def get_last_version(dir_path : str, version_only : bool = True, main_only : bool = False):
+    '''Returns path or just version associated to latest version found in given path
+
+    Parameters
+    ---------------------
+    dir_path (str) : Path to directory where versioned subdirectories exist
+    version_only (bool): Returns only vxxxx if True, otherwise, full path to directory
+    main_only (bool): Returns vX where X is a number. Otherwise it will return vx.y in case version has subversion
+    '''
+    l_obj = glob.glob(f'{dir_path}/*')
+
+    if len(l_obj) == 0:
+        log.error(f'Nothing found in {dir_path}')
+        raise ValueError
+
+    d_dir_org = { os.path.basename(obj).replace('.', '') : obj for obj in l_obj if os.path.isdir(obj) }
+    d_dir_num = { _get_numeric_version(name) : dir_path for name, dir_path in d_dir_org.items() }
+
+    c_dir = sorted(d_dir_num.items())
+
+    try:
+        _, path = c_dir[-1]
+    except:
+        log.error(f'Cannot find path in: {dir_path}')
+        raise
+
+    name = os.path.basename(path)
+    dirn = os.path.dirname(path)
+
+    if main_only and '.' in name:
+        ind = name.index('.')
+        name= name[:ind]
+
+    if version_only:
+        return name
+
+    return f'{dirn}/{name}'
+#---------------------------------------
+def get_latest_file(dir_path : str, wc : str) -> str:
+    '''Will find latest file in a given directory
+
+    Parameters
+    --------------------
+    dir_path (str): Directory where files are found
+    wc (str): Wildcard associated to files, e.g. file_*.txt
+
+    Returns
+    --------------------
+    Path to latest file, according to version
+    '''
+    l_path = glob.glob(f'{dir_path}/{wc}')
+    if len(l_path) == 0:
+        log.error(f'Cannot find files in: {dir_path}/{wc}')
+        raise ValueError
+
+    l_path.sort()
+
+    return l_path[-1]
+#---------------------------------------
+def get_next_version(version : str) -> str:
+    '''Pick up string symbolizing version and return next version
+    Parameters
+    -------------------------
+    version (str) : Of the form vx.y or vx where x and y are integers. It can also be a full path
+
+    Returns
+    -------------------------
+    String equal to the argument, but with the main version augmented by 1, e.g. vx+1.y
+
+    Examples:
+    -------------------------
+
+    get_next_version('v1.1') = 'v2.1'
+    get_next_version('v1'  ) = 'v2'
+    '''
+    if '/' in version:
+        path    = version
+        dirname = os.path.dirname(path)
+        version = os.path.basename(path)
+    else:
+        dirname = None
+
+    rgx = r'v(\d+)(\.\d+)?'
+
+    mtch = re.match(rgx, version)
+    if not mtch:
+        log.error(f'Cannot match {version} with {rgx}')
+        raise ValueError
+
+    ver_org = mtch.group(1)
+    ver_nxt = int(ver_org) + 1
+    ver_nxt = str(ver_nxt)
+
+    version = version.replace(f'v{ver_org}', f'v{ver_nxt}')
+
+    if dirname is not None:
+        version = f'{dirname}/{version}'
+
+    return version
+#---------------------------------------

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.