data-manipulation-utilities 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

{data_manipulation_utilities-0.0.6.data → data_manipulation_utilities-0.0.8.data}/scripts/publish

@@ -69,9 +69,20 @@ create_tag()
     git tag -a $VERSION
 }
 # --------------------------
+push_all()
+{
+    for REMOTE in $(git remote);do
+        echo "Pushing tags and commits to remote: $REMOTE"
+        git add pyproject.toml
+        git commit -m "Publication commit"
+
+        git push -u $REMOTE HEAD
+        git push    $REMOTE --tags
+    done
+}
+# --------------------------
 get_opts "$@"
 
 get_version
 create_tag
-git push -u origin HEAD
-git push --tags
+push_all

{data_manipulation_utilities-0.0.6.dist-info → data_manipulation_utilities-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation_utilities
-Version: 0.0.6
+Version: 0.0.8
 Description-Content-Type: text/markdown
 Requires-Dist: zfit
 Requires-Dist: logzero
@@ -18,12 +18,39 @@ Requires-Dist: hist[plot]
 Requires-Dist: polars
 Requires-Dist: pandas
 Provides-Extra: dev
-Requires-Dist: pytest ; 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.
 
+For LHCb specific tools (not useful for people outside LHCb) see [this](doc/lhcb.md)
+
+# GIT
+
+## Pushing
+
+From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory) 
+using a `pyproject.toml` file, run:
+
+```bash
+publish
+```
+
+such that:
+
+1. The `pyproject.toml` file is checked and the version of the project is extracted.
+1. If a tag named as the version exists move to the steps below. 
+1. If it does not, make a new tag with the name as the version
+
+Then, for each remote it pushes the tags and the commits. 
+
+*Why?* 
+
+1. Tags should be named as the project's version
+1. As soon as a new version is created, that version needs to be tagged.
+1. In GitHub, one can configure actions to publish projects when the commits are tagged.
+
 # Generic
 
 This section describes generic tools that could not be put in a specific category, but tend to be useful.

{data_manipulation_utilities-0.0.6.dist-info → data_manipulation_utilities-0.0.8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-data_manipulation_utilities-0.0.6.data/scripts/publish,sha256=9DPzH1NcyuyXo6uHjQitIce192jugsoCCjRY7HR7mCg,1684
+data_manipulation_utilities-0.0.8.data/scripts/publish,sha256=MHDsn93GTeJxpsM3hNbOJ7JEtsugX21WOFQ2PGWairU,1943
 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
@@ -6,6 +6,7 @@ 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
 dmu/ml/utilities.py,sha256=Nue7O9zi1QXgjGRPH6wnSAW9jusMQ2ZOSDJzBqJKIi0,3687
+dmu/physics/utilities.py,sha256=SGUNZT9qHvo6hpS12857cJRd4BPEwGDLpWaO5BhUJDk,1579
 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
@@ -33,14 +34,15 @@ dmu_data/text/transform.txt,sha256=EX760da6Vkf-_EPxnQlC5hGSkfFhJCCGCD19NU-1Qto,4
 dmu_data/text/transform_set.toml,sha256=Jeh7BTz82idqvbOQJtl9-ur56mZkzDn5WtvmIb48LoE,150
 dmu_data/text/transform_set.txt,sha256=1KivMoP9LxPn9955QrRmOzjEqduEjhTetQ9MXykO5LY,46
 dmu_data/text/transform_trf.txt,sha256=zxBRTgcSmX7RdqfmWF88W1YqbyNHa4Ccruf1MmnYv2A,74
-dmu_scripts/git/publish,sha256=9DPzH1NcyuyXo6uHjQitIce192jugsoCCjRY7HR7mCg,1684
+dmu_scripts/git/publish,sha256=MHDsn93GTeJxpsM3hNbOJ7JEtsugX21WOFQ2PGWairU,1943
 dmu_scripts/physics/check_truth.py,sha256=b1P_Pa9ef6VcFtyY6Y9KS9Om9L-QrCBjDKp4dqca0PQ,3964
+dmu_scripts/physics/update_decinfo.py,sha256=Y5cO3GdUWtVHeXVd37Q04xlFtQBMTLlqCF-medL8SM8,3322
 dmu_scripts/rfile/compare_root_files.py,sha256=T8lDnQxsRNMr37x1Y7YvWD8ySHrJOWZki7ZQynxXX9Q,9540
 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-0.0.6.dist-info/METADATA,sha256=t5uc_pnOn1_UBjs2HCrpiNY5Kg4saETW4BsbdVOAvQo,19299
-data_manipulation_utilities-0.0.6.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-data_manipulation_utilities-0.0.6.dist-info/entry_points.txt,sha256=1TIZDed651KuOH-DgaN5AoBdirKmrKE_oM1b6b7zTUU,270
-data_manipulation_utilities-0.0.6.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
-data_manipulation_utilities-0.0.6.dist-info/RECORD,,
+data_manipulation_utilities-0.0.8.dist-info/METADATA,sha256=sILwDHBZyO7OvdF1XkfC4fMzeZquVmZoHea3ytZz8lY,20074
+data_manipulation_utilities-0.0.8.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+data_manipulation_utilities-0.0.8.dist-info/entry_points.txt,sha256=-nNgwig7t-dba8EXsI5TxmvLaDet9_qQAbpusuq64Xc,327
+data_manipulation_utilities-0.0.8.dist-info/top_level.txt,sha256=n_x5J6uWtSqy9mRImKtdA2V2NJNyU8Kn3u8DTOKJix0,25
+data_manipulation_utilities-0.0.8.dist-info/RECORD,,

{data_manipulation_utilities-0.0.6.dist-info → data_manipulation_utilities-0.0.8.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{data_manipulation_utilities-0.0.6.dist-info → data_manipulation_utilities-0.0.8.dist-info}/entry_points.txt

@@ -4,3 +4,4 @@ compare_root_files = dmu_scripts.rfile.compare_root_files:main
 coned = dmu_scripts.ssh.coned:main
 print_trees = dmu_scripts.rfile.print_trees:main
 transform_text = dmu_scripts.text.transform_text:main
+update_decinfo = dmu_scripts.physics.update_decinfo:main

dmu/physics/utilities.py

@@ -0,0 +1,57 @@
+'''
+Module containing utility functions
+'''
+from importlib.resources import files
+from functools           import cache
+
+import yaml
+
+# ---------------------------------
+@cache
+def _get_evt_name() -> dict[str,str]:
+    file_path = files('dmu_data').joinpath('physics/evt_name.yaml')
+    file_path = str(file_path)
+    with open(file_path, encoding='utf-8') as ifile:
+        d_data = yaml.safe_load(ifile)
+
+    return d_data
+# ---------------------------------
+def _format_nickname(nickname : str, style : str) -> str:
+    if style == 'literal':
+        return nickname
+
+    if style != 'safe_1':
+        raise ValueError(f'Invalid style: {style}')
+
+    nickname = nickname.replace('.',   'p')
+    nickname = nickname.replace('-',   'mn')
+    nickname = nickname.replace('+',   'pl')
+    nickname = nickname.replace('=', '_eq_')
+    nickname = nickname.replace(',',    '_')
+
+    return nickname
+# ---------------------------------
+def read_decay_name(event_type : str, style : str = 'safe_1') -> str:
+    '''
+    Takes event type, and style strings, returns nickname of decay as defined in DecFiles package
+
+    Styles:
+
+    literal         : No change is made to nickname
+    safe_1 (default): With following replacements:
+        . -> p
+        = -> _eq_
+        - -> mn
+        + -> pl
+        , -> _
+    '''
+    d_evt_name = _get_evt_name()
+
+    if event_type not in d_evt_name:
+        raise ValueError(f'Event type {event_type} not found')
+
+    value = d_evt_name[event_type]
+    value = _format_nickname(value, style)
+
+    return value
+# ---------------------------------

dmu_scripts/git/publish

@@ -69,9 +69,20 @@ create_tag()
     git tag -a $VERSION
 }
 # --------------------------
+push_all()
+{
+    for REMOTE in $(git remote);do
+        echo "Pushing tags and commits to remote: $REMOTE"
+        git add pyproject.toml
+        git commit -m "Publication commit"
+
+        git push -u $REMOTE HEAD
+        git push    $REMOTE --tags
+    done
+}
+# --------------------------
 get_opts "$@"
 
 get_version
 create_tag
-git push -u origin HEAD
-git push --tags
+push_all

dmu_scripts/physics/update_decinfo.py

@@ -0,0 +1,111 @@
+'''
+Script meant to read information from files in
+
+https://gitlab.cern.ch/lhcb-datapkg/Gen/DecFiles
+
+and store it in current project as data
+'''
+import os
+import re
+import glob
+from dataclasses           import dataclass
+from importlib.resources   import files
+
+import tqdm
+import yaml
+from dmu.logging.log_store import LogStore
+
+log=LogStore.add_logger('dmu_scripts:physics:update_decinfo')
+# ------------------------------
+@dataclass
+class Data:
+    '''
+    Class used to store shared data
+    '''
+    dec_path : str
+    regex    : str = r'#[\s]*[a-zA-Z]+:[\s]*(.*)'
+# ------------------------------
+def _setup() -> None:
+    if 'DECPATH' not in os.environ:
+        raise ValueError('DECPATH, path to root of DecFiles, not found')
+
+    Data.dec_path = os.environ['DECPATH']
+# ------------------------------
+def _line_from_list(file_path : str, contains : str, l_line : list[str]) -> str:
+    l_value = [ line for line in l_line if contains in line ]
+
+    if len(l_value) == 0:
+        log.warning(f'Could not extract {contains} line in: {file_path}')
+        return 'not_found'
+
+    return l_value[0]
+# ------------------------------
+def _val_from_line(file_path : str, line : str) -> str:
+    if line == 'not_found':
+        return line
+
+    mtch = re.match(Data.regex, line)
+    if not mtch:
+        log.warning(f'Cannot extract value from \"{line}\" in file {file_path}')
+        return 'not_found'
+
+    value = mtch.group(1)
+    value = value.replace(' ', '')
+
+    return value
+# ------------------------------
+def _get_evt_name(file_path : str) -> tuple[str,str]:
+    with open(file_path, encoding='utf-8') as ifile:
+        l_line = ifile.read().splitlines()
+
+    evt_line = _line_from_list(file_path, 'EventType', l_line)
+    nam_line = _line_from_list(file_path, 'NickName' , l_line)
+
+    evt_type = _val_from_line(file_path, evt_line)
+    nickname = _val_from_line(file_path, nam_line)
+
+    return evt_type, nickname
+# ------------------------------
+def _read_info() -> dict[str,str]:
+    dec_file_wc = f'{Data.dec_path}/dkfiles/*.dec'
+    l_dec_file  = glob.glob(dec_file_wc)
+    nfiles      = len(l_dec_file)
+    if nfiles == 0:
+        raise ValueError(f'No dec file foudn in {dec_file_wc}')
+
+    log.info(f'Found {nfiles} decay files')
+
+    l_evt_name = [ _get_evt_name(file_path) for file_path in tqdm.tqdm(l_dec_file, ascii=' -') ]
+    d_evt_name = _dict_from_tup_list(l_evt_name)
+
+    return d_evt_name
+# ------------------------------
+def _dict_from_tup_list(l_evt_name : list[tuple[str,str]]) -> dict[str,str]:
+    d_res = {}
+    for key, val in l_evt_name:
+        if key in d_res:
+            old_val = d_res[key]
+            log.warning(f'Key {key} with value {old_val} already found, overriding with {val}')
+
+        d_res[key] = val
+
+    return d_res
+# ------------------------------
+def _dump_info(d_evt_name : dict[str,str]) -> None:
+    yaml_path = files('dmu_data').joinpath('physics/evt_name.yaml')
+    yaml_path = str(yaml_path)
+
+    log.info(f'Saving to: {yaml_path}')
+    with open(yaml_path, 'w', encoding='utf-8') as ofile:
+        yaml.dump(d_evt_name, ofile)
+# ------------------------------
+def main():
+    '''
+    Script starts here
+    '''
+    _setup()
+    d_evt_name = _read_info()
+    _dump_info(d_evt_name)
+# ------------------------------
+if __name__ == '__main__':
+    main()