data-manipulation-utilities 0.2.8.dev927__tar.gz → 0.2.8.dev950__tar.gz

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: data-manipulation-utilities
-Version: 0.2.8.dev927
+Version: 0.2.8.dev950
 Summary: Project storing utilities needed to reduce boilerplate code when analyzing data
 Requires-Python: >=3.10,<3.13
 Classifier: Programming Language :: Python :: 3
@@ -1514,6 +1514,16 @@ df_2 = put.from_yaml(yml_path)
 ```
 
 and is meant to be less verbose than doing it through the YAML module.
+
+### Dataframe to markdown
+
+```python
+import dmu.pdataframe.utilities as put
+
+df = _get_df()
+put.to_markdown(df, '/path/to/simple.md')
+```
+
 # Rdataframes
 
 These are utility functions meant to be used with ROOT dataframes.

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/README.md

@@ -1479,6 +1479,16 @@ df_2 = put.from_yaml(yml_path)
 ```
 
 and is meant to be less verbose than doing it through the YAML module.
+
+### Dataframe to markdown
+
+```python
+import dmu.pdataframe.utilities as put
+
+df = _get_df()
+put.to_markdown(df, '/path/to/simple.md')
+```
+
 # Rdataframes
 
 These are utility functions meant to be used with ROOT dataframes.

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name           = 'data-manipulation-utilities'
 description    = 'Project storing utilities needed to reduce boilerplate code when analyzing data'
-version        = "0.2.8.dev927"
+version        = "0.2.8.dev950"
 readme         = 'README.md'
 package-mode   = true 
 packages       = [

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/src/dmu/logging/log_store.py

@@ -41,8 +41,7 @@ class LogStore:
     backend       = 'logging'
     #--------------------------
     @staticmethod
-    @contextlib.contextmanager
-    def level(name : str, lvl : int) -> None:
+    def level(name : str, lvl : int):
         '''
         Context manager used to set the logging level of a given logger
 
@@ -51,17 +50,22 @@ class LogStore:
         name : Name of logger
         lvl  : Integer representing logging level
         '''
-        log       = LogStore.get_logger(name=name)
+        log = LogStore.get_logger(name=name)
         if log is None:
             raise ValueError(f'Cannot find logger {name}')
 
         old_lvl = log.getEffectiveLevel()
 
         LogStore.set_level(name, lvl)
-        try:
-            yield
-        finally:
-            LogStore.set_level(name, old_lvl)
+
+        @contextlib.contextmanager
+        def _context():
+            try:
+                yield
+            finally:
+                LogStore.set_level(name, old_lvl)
+
+        return _context()
     #--------------------------
     @staticmethod
     def get_logger(name : str) -> Union[Logger,None]:

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/src/dmu/pdataframe/utilities.py

@@ -55,6 +55,21 @@ def to_yaml(df : pnd.DataFrame, path : str):
 
     with open(path, 'w', encoding='utf-8') as ofile:
         yaml.dump(data, ofile, Dumper=yaml.CDumper)
+# ----------------------
+def to_markdown(df : pnd.DataFrame, path : str) -> None:
+    '''
+    Parameters
+    -------------
+    df  : Pandas dataframe
+    path: Path to markdown file
+    '''
+    dir_path = os.path.dirname(path)
+    if dir_path != '':
+        os.makedirs(dir_path, exist_ok=True)
+
+    text = df.to_markdown()
+    with open(path, 'w', encoding='utf-8') as ofile:
+        ofile.write(text)
 # -------------------------------------
 def from_yaml(path : str) -> pnd.DataFrame:
     '''

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/src/dmu/rdataframe/utilities.py

@@ -11,7 +11,7 @@ import pandas  as pnd
 import awkward as ak
 import numpy
 
-from ROOT import RDataFrame, RDF, Numba
+from ROOT import RDataFrame, RDF, Numba # type: ignore
 
 from dmu.logging.log_store import LogStore
 
@@ -97,16 +97,19 @@ def add_column_with_numba(
 
     return rdf
 # ---------------------------------------------------------------------
-def rdf_report_to_df(rep : RDF.RCutFlowReport) -> Union[pnd.DataFrame, None]:
+def rdf_report_to_df(rep : RDF.RCutFlowReport) -> pnd.DataFrame:
     '''
-    Takes the output of rdf.Report(), i.e. an RDataFrame cutflow report.
+    Parameters
+    ------------------
+    rep: output of rdf.Report(), i.e. an RDataFrame cutflow report.
 
-    Produces a pandas dataframe with the total, failed, efficiency, and cummulative efficiency
-    If no cut was applied, i.e. the cutflow is empty, will return None and show warning
+    Returns 
+    ------------------
+    A pandas dataframe with the total, failed, efficiency, and cumulative efficiency
+    If no cut was applied, raises ValueError 
     '''
     if rep.begin() == rep.end():
-        log.warning('Empty cutflow')
-        return None
+        raise ValueError('Empty cutflow report')
 
     d_data = {'cut' : [], 'All' : [], 'Passed' : []}
     for cut in rep:
@@ -119,10 +122,10 @@ def rdf_report_to_df(rep : RDF.RCutFlowReport) -> Union[pnd.DataFrame, None]:
         d_data['Passed'].append(pas)
 
     df = pnd.DataFrame(d_data)
-    df['Efficiency' ] = df['Passed'] / df['All']
+    df['Efficiency' ] = df['Passed'] / df['All'].replace(0, pnd.NA)
     df['Cummulative'] = df['Efficiency'].cumprod()
 
-    return df
+    return df 
 # ---------------------------------------------------------------------
 def random_filter(rdf : RDataFrame, entries : int) -> RDataFrame:
     '''

{data_manipulation_utilities-0.2.8.dev927 → data_manipulation_utilities-0.2.8.dev950}/src/dmu/stats/utilities.py

@@ -9,6 +9,7 @@ import re
 import pickle
 from typing import Union
 
+import yaml
 import numpy
 import pandas            as pnd
 import matplotlib.pyplot as plt
@@ -83,6 +84,12 @@ def range_from_obs(obs : zobs) -> tuple[float,float]:
 
     minx, maxx = obs.limits
 
+    if not isinstance(minx, numpy.ndarray):
+        raise ValueError(f'Minx is not an array but: {minx}')
+
+    if not isinstance(maxx, numpy.ndarray):
+        raise ValueError(f'Minx is not an array but: {maxx}')
+
     return float(minx[0][0]), float(maxx[0][0])
 #-------------------------------------------------------
 def yield_from_zdata(data : zdata) -> float:
@@ -109,16 +116,23 @@ def yield_from_zdata(data : zdata) -> float:
 #-------------------------------------------------------
 # Check PDF
 #-------------------------------------------------------
-def is_pdf_usable(pdf : zpdf) -> zpdf:
+def is_pdf_usable(pdf : zpdf) -> bool:
     '''
-    Will check if the PDF is usable
+    Parameters
+    ---------------
+    pdf: PDF to check
+
+    Returns
+    ---------------
+    True if PDF is usable
     '''
-    [[[minx]], [[maxx]]]= pdf.space.limits
+    minx, maxx = range_from_obs(obs=pdf.space)
 
     arr_x = numpy.linspace(minx, maxx, 100)
+    tf_x  = tf.convert_to_tensor(arr_x)
 
     try:
-        pdf.pdf(arr_x)
+        pdf.pdf(tf_x)
     except tf.errors.InvalidArgumentError:
         log.warning('PDF cannot be evaluated')
         return False
@@ -194,7 +208,7 @@ def _is_par_blinded(name : str, l_blind : list[str]) -> bool:
     return False
 #-------------------------------------------------------
 def _get_pars(
-    pdf   : zpdf,
+    pdf   : zpdf|zmod,
     blind : None|list[str]) -> tuple[list, list]:
     '''
     Parameters
@@ -224,7 +238,7 @@ def _get_pars(
     return l_par_flt, l_par_fix
 #-------------------------------------------------------
 def _get_messages(
-    pdf       : zpdf,
+    pdf       : zpdf|zmod,
     l_par_flt : list,
     l_par_fix : list,
     d_const   : None|dict[str,tuple[float,float]] = None) -> list[str]:
@@ -327,13 +341,19 @@ def _parameters_from_result(result : zres) -> dict[str,tuple[float,float]]:
 
         log.debug(f'{name:<20}{value:<20.3f}{error}')
 
+        if value is None:
+            raise ValueError(f'No value found for parameter {name}')
+
+        if error is None:
+            raise ValueError(f'No value found for parameter {name}')
+
         d_par[name] = float(value), float(error)
 
     return d_par
 #---------------------------------------------
 def save_fit(
     data    : zdata,
-    model   : zpdf|None,
+    model   : zpdf|zmod|None,
     res     : zres|None,
     fit_dir : str,
     d_const : dict[str,tuple[float,float]]|None = None) -> None:
@@ -591,7 +611,7 @@ def placeholder_fit(
     else:
         data = zfit.Data.from_pandas(df, obs=pdf.space, weights=Data.weight_name)
 
-    d_const = {'sg' : [50, 3]}
+    d_const = {'sg' : (50., 3.)}
 
     obj = Fitter(pdf, data)
     res = obj.fit(cfg={'constraints' : d_const})
@@ -623,7 +643,12 @@ def _reformat_values(d_par : dict) -> dict:
     }
     '''
 
-    error = d_par['minuit_hesse']['error']
+    try:
+        error = d_par['minuit_hesse']['error']
+    except KeyError as exc:
+        log.error(yaml.dump(d_par))
+        raise KeyError('Cannot extract error from parameters') from exc
+
     error = float(error)
 
     value = d_par['value']
@@ -647,7 +672,12 @@ def zres_to_cres(res : zres) -> DictConfig:
         pass
 
     par   = res.params
-    d_par = { name : _reformat_values(d_par=d_par) for name, d_par in par.items()}
+    try:
+        d_par = { name : _reformat_values(d_par=d_par) for name, d_par in par.items()}
+    except KeyError as exc:
+        print(res)
+        raise KeyError('Fit parameters cannot be used') from exc
+
     cfg   = OmegaConf.create(d_par)
 
     return cfg