data-manipulation-utilities 0.2.8.dev720__py3-none-any.whl → 0.2.8.dev730__py3-none-any.whl

{data_manipulation_utilities-0.2.8.dev720.dist-info → data_manipulation_utilities-0.2.8.dev730.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: data-manipulation-utilities
-Version: 0.2.8.dev720
+Version: 0.2.8.dev730
 Summary: Project storing utilities needed to reduce boilerplate code when analyzing data
 Requires-Python: >=3.10,<3.13
 Classifier: Programming Language :: Python :: 3
@@ -1483,6 +1483,7 @@ stats:
 ```
 
 it's up to the user to build this dictionary and load it.
+this can also be a `DictConfig` from the `OmegaConf` project.
 
 ### Pluggins
 

data_manipulation_utilities-0.2.8.dev730.dist-info/RECORD

@@ -0,0 +1,82 @@
+dmu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dmu/arrays/utilities.py,sha256=PKoYyybPptA2aU-V3KLnJXBudWxTXu4x1uGdIMQ49HY,1722
+dmu/generic/hashing.py,sha256=QR5Gbv6-ANvi5hL232UNMrw9DONpU27BWTynXGxQLGU,1806
+dmu/generic/utilities.py,sha256=0tT93vF_x0q8STRrTD0GvBEpALz-mqE-vJyen4zWCO8,6861
+dmu/generic/version_management.py,sha256=j0ImlAq6SVNjTh3xRsF6G7DSoyr1w8kTRY84dNriGRE,3750
+dmu/logging/log_store.py,sha256=eRSy8Y4fuiDFJK02Z6fq67XQzOrhQ7GMr2LvvJQbJ40,5172
+dmu/logging/messages.py,sha256=Oj3O5EO2KOPtffyVq2P7RPzjpoXtxZ6yXO5HwTftVcM,2903
+dmu/ml/cv_classifier.py,sha256=6rjezMahwL-WzLGKU-fzMzNxJZAGbM7YAbhaZVcJ3F0,4258
+dmu/ml/cv_diagnostics.py,sha256=PLh41mSVE8Kagp9KcuRDN_7tDL9MjPxQzuewY8jDnNo,7600
+dmu/ml/cv_performance.py,sha256=q9sLxIx7GP-dand3tnhHCBJnT6xqssNdRYv_TVjYWUM,1910
+dmu/ml/cv_predict.py,sha256=0sc_OqwOewKvipcMyi3QqkgG30nkpZZjE-SOhHWHMd0,10778
+dmu/ml/train_mva.py,sha256=7KAFX_zOx8MGbYx62U81JbdBkrZvqclSSkgmYvWX-60,34861
+dmu/ml/utilities.py,sha256=A9j3tBh-jfaFdwwLUleo1QnttfawN7XDiQRh4VTvqVY,4597
+dmu/pdataframe/utilities.py,sha256=xl6iLVKUccqVXYjuHsDUZ6UrCKQPw1k8D-f6407Yq30,2742
+dmu/plotting/fwhm.py,sha256=4e8n6624pxWLcOOtayCQ_hDSSMKU21-3UsdmbkX1ojk,1949
+dmu/plotting/matrix.py,sha256=s_5W8O3yXF3u8OX3f4J4hCoxIVZt1TF8S-qJsFBh2Go,5005
+dmu/plotting/plotter.py,sha256=5N5mLdQAqOUs43ukX5mT9nRaYD5dkn_sED5NoZJV5A0,8483
+dmu/plotting/plotter_1d.py,sha256=Kyoyh-QyZLXXqX19wqEDUWCD1nJEvEonGp9nlgEaoZE,10936
+dmu/plotting/plotter_2d.py,sha256=dXC-7Rsquibe5cn7622ryoKpuv7KCAmouIIXwQ_VEFM,3172
+dmu/plotting/utilities.py,sha256=SI9dvtZq2gr-PXVz71KE4o0i09rZOKgqJKD1jzf6KXk,1167
+dmu/rdataframe/atr_mgr.py,sha256=FdhaQWVpsm4OOe1IRbm7rfrq8VenTNdORyI-lZ2Bs1M,2386
+dmu/rdataframe/utilities.py,sha256=cY1Na8HbJ7kB2dwmBagRdsRyCA4ZT_vyIU86ewREj2Y,5322
+dmu/rfile/ddfgetter.py,sha256=0jfNzpv72_NQUKOK5SBsn289rUqVt2BMvuL-Ro5oY7I,3316
+dmu/rfile/rfprinter.py,sha256=mp5jd-oCJAnuokbdmGyL9i6tK2lY72jEfROuBIZ_ums,3941
+dmu/rfile/utilities.py,sha256=XuYY7HuSBj46iSu3c60UYBHtI6KIPoJU_oofuhb-be0,945
+dmu/stats/fit_stats.py,sha256=wzkQT9U32ljGe4azUj1Fj0ECF3zmnH2Ncn0O-_Pl1zQ,4070
+dmu/stats/fitter.py,sha256=rm_fwjkq-0LSjXB_gt3y6BnHoK8Xvd4gHYwKBUJaItQ,19603
+dmu/stats/function.py,sha256=yzi_Fvp_ASsFzbWFivIf-comquy21WoeY7is6dgY0Go,9491
+dmu/stats/gof_calculator.py,sha256=63zNJJGKPy-j_hPNPfu9qNlhrHjYIgJOyL8-VDtbwuI,4894
+dmu/stats/minimizers.py,sha256=db9R2G0SOV-k0BKi6m4EyB_yp6AtZdP23_28B0315oo,7094
+dmu/stats/model_factory.py,sha256=0_o5OmiX0cNhp9_cNqBOYfasBgKlQkQPiy5nqi9qQKA,18966
+dmu/stats/parameters.py,sha256=9lycexTT5ZcxXciiQY9HoJV8O1ahrTEkagd7dYXcfj8,3224
+dmu/stats/utilities.py,sha256=7_tr1j-dl3lLNpxIMWruZs4yUtlNuUTknwGMERpfLhs,17338
+dmu/stats/wdata.py,sha256=IbjZFU9SHTLSYfaBgqamDvqy1K7-3-SaKbU4bGsamK0,6799
+dmu/stats/zfit.py,sha256=aSZj_4IHi9IBthfqlNJeA8YSoMmXO5WipgiKnXKGbnM,286
+dmu/stats/zfit_models.py,sha256=SI61KJ-OG1UAabDICU1iTh6JPKM3giR2ErDraRjkCV8,1842
+dmu/stats/zfit_plotter.py,sha256=gbN5KxhJcP4ItCi98c-fj5_UtvVWL_NA9jkTHiRjvnE,23854
+dmu/testing/utilities.py,sha256=WYlz7Ve5lQjuWhhNL4gWe6_qcByBLV762Lhrc6A0P9E,7421
+dmu/text/transformer.py,sha256=4lrGknbAWRm0-rxbvgzOO-eR1-9bkYk61boJUEV3cQ0,6100
+dmu/workflow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dmu/workflow/cache.py,sha256=CtkGwxuF4UJlD55SmUJcRgWYLsbZOyUvYLI8oTVzk_g,8768
+dmu_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dmu_data/ml/tests/diagnostics_from_file.yaml,sha256=quvXOPkRducnBsctyape_Rn5_aqMEpPo6nO_UweMORo,404
+dmu_data/ml/tests/diagnostics_from_model.yaml,sha256=rtCQlmGS9ld2xoQJEE35nA07yfRMklEfQEW0w3gRv2A,261
+dmu_data/ml/tests/diagnostics_multiple_methods.yaml,sha256=w8Fpmr7kX1Jsb_h6LL2hiuYKf5lYpckFCpYKzWetbA0,265
+dmu_data/ml/tests/diagnostics_overlay.yaml,sha256=ZVOsxLL8_JQtf41n8Ct-M9Ch10xBwHK54q1fttWPDlE,866
+dmu_data/ml/tests/train_mva.yaml,sha256=KArbTkaj6FqerrUhlkgyBde_4DfkpVza6kCMgMQPi9g,1388
+dmu_data/ml/tests/train_mva_def.yaml,sha256=UyPMo-9nshoB8BHxm9E6S0xd9ngRARdgUq6vnuMlhwI,1765
+dmu_data/ml/tests/train_mva_with_diagnostics.yaml,sha256=-2KKIJ8CiNgMlgpCXkmZRdPEo-sJmAqr01vizfeqkj0,2098
+dmu_data/ml/tests/train_mva_with_preffix.yaml,sha256=Q9SsJSXGbkHWGBvMZIkTZlKNUz5ZcSVBscrKgeMWBvE,1386
+dmu_data/plotting/tests/2d.yaml,sha256=40wKQmNbIabZ7CI8-2QnD6mG1a_B7vEcPdzvehHkseY,520
+dmu_data/plotting/tests/fig_size.yaml,sha256=7ROq49nwZ1A2EbPiySmu6n3G-Jq6YAOkc3d2X3YNZv0,294
+dmu_data/plotting/tests/high_stat.yaml,sha256=bLglBLCZK6ft0xMhQ5OltxE76cWsBMPMjO6GG0OkDr8,522
+dmu_data/plotting/tests/legend.yaml,sha256=wGpj58ig-GOlqbWoN894zrCet2Fj9f5QtY0rig_UC-c,213
+dmu_data/plotting/tests/line.yaml,sha256=EERDeTctbauwqAvmKFXC4Ot3Tgx-8kcIniGbepXwsKs,305
+dmu_data/plotting/tests/name.yaml,sha256=mkcPAVg8wBAmlSbSRQ1bcaMl4vOS6LXMtpqQeDrrtO4,312
+dmu_data/plotting/tests/no_bounds.yaml,sha256=8e1QdphBjz-suDr857DoeUC2DXiy6SE-gvkORJQYv80,257
+dmu_data/plotting/tests/normalized.yaml,sha256=Y0eKtyV5pvlSxvqfsLjytYtv8xYF3HZ5WEdCJdeHGQI,193
+dmu_data/plotting/tests/plug_fwhm.yaml,sha256=xl5LXc9Nt66anM-HOXAxCtlaxWNM7zzIXf1Y6U8M4Wg,449
+dmu_data/plotting/tests/plug_stats.yaml,sha256=ROO8soYXBbZIFYZcGngA_K5XHgIAFCmuAGfZCJgMmd0,384
+dmu_data/plotting/tests/simple.yaml,sha256=Xc59Pjfb3BKMicLVBxODVqomHFupcb5GvefKbKHCQWQ,195
+dmu_data/plotting/tests/stats.yaml,sha256=fSZjoV-xPnukpCH2OAXsz_SNPjI113qzDg8Ln3spaaA,165
+dmu_data/plotting/tests/styling.yaml,sha256=ZglA4fG6gr5Q_K2VinwVDPjIitiFizCzxr-KsHw2ERI,370
+dmu_data/plotting/tests/title.yaml,sha256=bawKp9aGpeRrHzv69BOCbFX8sq9bb3Es9tdsPTE7jIk,333
+dmu_data/plotting/tests/weights.yaml,sha256=RWQ1KxbCq-uO62WJ2AoY4h5Umc37zG35s-TpKnNMABI,312
+dmu_data/rfile/friends.yaml,sha256=sEGKFKK0q1U6b9qlfHUFBLZW0FeruR1t2LCOo6Ck1Rg,264
+dmu_data/stats/fitter/test_simple.yaml,sha256=lBw6igBT57BZnuG3GgoxOiXTMFHfs5LchbI3Ubb8Qz0,1549
+dmu_data/stats/kde_optimizer/control.json,sha256=EiArsHUAHBmzw4gmaNyOOW1ziYtNhdelIAqc3EH0K_M,1327616
+dmu_data/stats/kde_optimizer/signal.json,sha256=MocwnYizcKki4dlxEIsWwE8HzY-ZBQaUo-lrCR5N3Tw,1327616
+dmu_data/stats/parameters/data.yaml,sha256=lNmuolhUQmwB6sxHQvBRm-Kz5MUW_H1qAouynzBiWvs,2087
+dmu_data/tests/config.json,sha256=QSfx-irgPV-BHAVe1Xe1dgiVkZGPp0fxb9OhXeVaEBg,60
+dmu_data/tests/config.yaml,sha256=rFTk9PSFOgEVEcGDxr4K9vFIUrCVhbEMUoj683Py1AQ,38
+dmu_data/tests/pdf_to_tex.txt,sha256=yzzH1L7P2SOFrVxS737Ykg1SlcD0jhrrBwQGsui2oAQ,3854
+dmu_data/text/transform.toml,sha256=R-832BZalzHZ6c5gD6jtT_Hj8BCsM5vxa1v6oeiwaP4,94
+dmu_data/text/transform.txt,sha256=EX760da6Vkf-_EPxnQlC5hGSkfFhJCCGCD19NU-1Qto,44
+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
+data_manipulation_utilities-0.2.8.dev730.dist-info/METADATA,sha256=p6CwOJiDGK5kQwCGIg9i6AoNvSE9VDKFbGa7OG_od0M,51215
+data_manipulation_utilities-0.2.8.dev730.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+data_manipulation_utilities-0.2.8.dev730.dist-info/entry_points.txt,sha256=M0C8_u9B_xSmyfemdPwdIBh9QuPIkjhEpG060Y5_Pjw,321
+data_manipulation_utilities-0.2.8.dev730.dist-info/RECORD,,

dmu/plotting/plotter.py

@@ -5,12 +5,12 @@ Module containing plotter class
 import os
 import json
 import math
-from typing import Union
 
 import numpy
 import matplotlib.pyplot as plt
 
-from ROOT                  import RDataFrame
+from ROOT                  import RDataFrame, RDF
+from omegaconf             import DictConfig
 from dmu.logging.log_store import LogStore
 
 log = LogStore.add_logger('dmu:plotting:Plotter')
@@ -20,16 +20,28 @@ class Plotter:
     Base class of Plotter1D and Plotter2D
     '''
     #-------------------------------------
-    def __init__(self, d_rdf=None, cfg=None):
-        if not isinstance(  cfg, dict):
+    def __init__(
+            self,
+            d_rdf: dict|None            =None,
+            cfg  : dict|DictConfig|None =None):
+        '''
+        Parameters
+        --------------
+        d_rdf: Dictionary where
+            key  : Identifier of dataset
+            value: ROOT dataframe representing dataset
+
+        cfg  : Dictionary or DictConfig instance holding configuration
+        '''
+        if not isinstance(  cfg, (dict,DictConfig)):
             raise ValueError('Config dictionary not passed')
 
         if not isinstance(d_rdf, dict):
             raise ValueError('Dataframe dictionary not passed')
 
         self._d_cfg = cfg
-        self._d_rdf : dict[str, RDataFrame]    = { name : self._preprocess_rdf(rdf) for name, rdf in d_rdf.items()}
-        self._d_wgt : Union[dict[str, Union[numpy.ndarray, None]], None]
+        self._d_rdf : dict[str, RDF.RNode]    = { name : self._preprocess_rdf(rdf) for name, rdf in d_rdf.items()}
+        self._d_wgt : dict[str, numpy.ndarray|None] | None
 
         self._title : str = ''
     #-------------------------------------
@@ -68,9 +80,9 @@ class Plotter:
 
         return minx, maxx
     #-------------------------------------
-    def _preprocess_rdf(self, rdf : RDataFrame) -> RDataFrame:
+    def _preprocess_rdf(self, rdf : RDF.RNode) -> RDF.RNode:
         '''
-        rdf (RDataFrame): ROOT dataframe
+        rdf (RDF.RNode): ROOT dataframe
 
         returns preprocessed dataframe
         '''
@@ -146,7 +158,7 @@ class Plotter:
 
         return rdf
     # --------------------------------------------
-    def _print_weights(self, arr_wgt : Union[numpy.ndarray, None], var : str, sample : str) -> None:
+    def _print_weights(self, arr_wgt : numpy.ndarray|None, var : str, sample : str) -> None:
         if arr_wgt is None:
             log.debug(f'Not using weights for {sample}:{var}')
             return
@@ -171,7 +183,7 @@ class Plotter:
 
         return fig_size
     #-------------------------------------
-    def _get_weights(self, var) -> Union[dict[str, Union[numpy.ndarray, None]], None]:
+    def _get_weights(self, var) -> dict[str, numpy.ndarray|None]| None:
         d_cfg = self._d_cfg['plots'][var]
         if 'weights' not in d_cfg:
             return None
@@ -186,7 +198,7 @@ class Plotter:
 
         return d_weight
     # --------------------------------------------
-    def _read_weights(self, name : str, rdf : RDataFrame) -> numpy.ndarray:
+    def _read_weights(self, name : str, rdf : RDF.RNode) -> numpy.ndarray:
         v_col = rdf.GetColumnNames()
         l_col = [ col.c_str() for col in v_col ]
 

dmu_data/ml/tests/diagnostics_from_file.yaml

@@ -0,0 +1,13 @@
+output         : /tmp/tests/dmu/ml/cv_diagnostics/from_rdf
+  # Will assume that the target is already in the input dataframe
+  # and will use it, instead of evaluating models
+score_from_rdf : w 
+correlations:
+  # Variables with respect to which the correlations with the features will be measured
+  target :
+    name : z
+  methods:
+    - Pearson
+  figure:
+    title: Scores from file 
+    size : [10, 8]

dmu_data/ml/tests/diagnostics_from_model.yaml

@@ -0,0 +1,10 @@
+output      : /tmp/tests/dmu/ml/cv_diagnostics/from_model
+correlations:
+  # Variables with respect to which the correlations with the features will be measured
+  target    : 
+    name    : z
+  methods:
+    - Pearson
+  figure:
+    size  : [10, 8]
+    rotate: 90

dmu_data/ml/tests/diagnostics_multiple_methods.yaml

@@ -0,0 +1,10 @@
+output : /tmp/tests/dmu/ml/cv_diagnostics/multiple_methods
+correlations:
+  # Variables with respect to which the correlations with the features will be measured
+  target    : 
+    name : z
+  methods:
+    - Pearson
+    - Kendall-$\tau$ 
+  figure:
+    size : [10, 8]

dmu_data/ml/tests/diagnostics_overlay.yaml

@@ -0,0 +1,33 @@
+output         : /tmp/tests/dmu/ml/cv_diagnostics/overlay
+  # Will assume that the target is already in the input dataframe
+  # and will use it, instead of evaluating models
+score_from_rdf : w
+correlations:
+  # Variables with respect to which the correlations with the features will be measured
+  target :
+    name : z
+    overlay :
+      wp :
+        - 0.2
+        - 0.5
+        - 0.7
+        - 0.9
+      general:
+        size : [12, 10]
+      saving:
+        plt_dir : /tmp/tests/dmu/ml/cv_diagnostics/overlay
+      plots:
+        z :
+          binning    : [-4, 4, 10]
+          yscale     : 'linear'
+          labels     : ['$z$', 'Entries']
+          normalized : true
+          styling :          
+            linestyle: '-'
+  methods:
+    - Pearson
+    - Kendall-$\tau$ 
+  figure:
+    title     : Scores from file
+    size      : [12, 10]
+    xlabelsize: 30 

dmu_data/ml/tests/train_mva.yaml

@@ -0,0 +1,60 @@
+dataset:
+  define :
+    r : z + x
+  nan :
+    x : -3
+    y : -3
+training :
+    nfold    : 3
+    features :
+      - x
+      - y
+      - r
+    rdm_stat : 1
+    hyper    :
+      loss              : log_loss
+      max_features      : sqrt 
+      n_estimators      : 100
+      max_depth         : 5
+      min_samples_split : 2
+      subsample         : 0.8
+      learning_rate     : 0.1
+saving:
+    output : /tmp/tests/dmu/ml/train_mva
+plotting:
+    roc     :
+        min : [0.0, 0.0]
+        max : [1.2, 1.2]
+        annotate:
+          sig_eff : [0.5, 0.6, 0.7, 0.8, 0.9]
+          form : '{:.2f}'
+          color: 'green'
+          xoff : -15
+          yoff : -15
+          size :  10
+    correlation:
+      title      : 'Correlation matrix'
+      size       : [10, 10]
+      mask_value : 0
+    features:
+        plots:
+          r :
+            binning : [-6, 6, 100]
+            yscale  : 'linear'
+            labels  : ['$r$', '']
+          w :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$w$', '']
+          x :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$x$', '']
+          y :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$y$', '']
+          z :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$z$', '']

dmu_data/ml/tests/train_mva_def.yaml

@@ -0,0 +1,75 @@
+# This config file is used for testing training and evaluation
+# when there is a variable that is defined in different ways
+# for the `sig` and `bkg` samples
+
+dataset:
+  samples:
+    sig :
+      definitions:
+        n : x + y
+    bkg :
+      definitions:
+        n : x - y
+  define :
+    r : z + x
+  nan :
+    n : -3
+    y : -3
+training :
+    nfold    : 3
+    features :
+      - n
+      - y
+      - r
+    rdm_stat : 1
+    hyper    :
+      loss              : log_loss
+      max_features      : sqrt
+      n_estimators      : 100
+      max_depth         : 5
+      min_samples_split : 2
+      subsample         : 0.8
+      learning_rate     : 0.1
+saving:
+    output : /tmp/tests/dmu/ml/train_mva
+plotting:
+    roc     :
+        min : [0.0, 0.0]
+        max : [1.2, 1.2]
+        annotate:
+          sig_eff : [0.5, 0.6, 0.7, 0.8, 0.9]
+          form : '{:.2f}'
+          color: 'green'
+          xoff : -15
+          yoff : -15
+          size :  10
+    correlation:
+      title      : 'Correlation matrix'
+      size       : [10, 10]
+      mask_value : 0
+    features:
+        plots:
+          r :
+            binning : [-6, 6, 100]
+            yscale  : 'linear'
+            labels  : ['$r$', '']
+          n :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$n$', '']
+          w :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$w$', '']
+          x :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$x$', '']
+          y :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$y$', '']
+          z :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$z$', '']

dmu_data/ml/tests/train_mva_with_diagnostics.yaml

@@ -0,0 +1,87 @@
+dataset:
+  define :
+    r : z + x
+  nan :
+    x : -3
+    y : -3
+training :
+    nfold    : 3
+    features : [x, y, r]
+    rdm_stat : 1
+    hyper    :
+      loss              : log_loss
+      n_estimators      : 100
+      max_depth         : 3
+      learning_rate     : 0.1
+      min_samples_split : 2
+saving:
+    output : /tmp/tests/dmu/ml/train_mva
+plotting:
+    roc     :
+        min : [0.0, 0.0]
+        max : [1.2, 1.2]
+        annotate:
+          sig_eff : [0.5, 0.6, 0.7, 0.8, 0.9]
+          form : '{:.2f}'
+          color: 'green'
+          xoff : -15
+          yoff : -15
+          size :  10
+    correlation:
+      title      : 'Correlation matrix'
+      size       : [10, 10]
+      mask_value : 0
+    val_dir : '/tmp/tests/dmu/ml/train_mva'
+    features:
+        saving:
+            plt_dir : '/tmp/tests/dmu/ml/train_mva/features'
+        plots:
+          r :
+            binning : [-6, 6, 100]
+            yscale  : 'linear'
+            labels  : ['$r$', '']
+          w :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$w$', '']
+          x :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$x$', '']
+          y :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$y$', '']
+          z :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$z$', '']
+diagnostics:
+  output         : /tmp/tests/dmu/ml/train_mva/diagnostics
+  correlations:
+    target :
+      name : z
+      overlay :
+        wp :
+          - 0.2
+          - 0.6
+          - 0.8
+          - 0.9
+        general:
+          size : [20, 10]
+        saving:
+          plt_dir : /tmp/tests/dmu/ml/train_mva/diagnostics
+        plots:
+          z :
+            binning    : [-4, +4, 30]
+            yscale     : 'linear'
+            labels     : ['z', 'Entries']
+            normalized : true
+            styling :
+              linestyle: '-'
+    methods:
+      - Pearson
+      - Kendall-$\tau$
+    figure:
+      title: Training diagnostics
+      size : [10, 8]

dmu_data/ml/tests/train_mva_with_preffix.yaml

@@ -0,0 +1,58 @@
+dataset:
+  define :
+    r : z + preffix.x.suffix
+  nan :
+    preffix.x.suffix : -3
+    y : -3
+training :
+    nfold    : 2
+    features :
+      - preffix.x.suffix
+      - y
+      - r
+    rdm_stat : 1
+    hyper    :
+      loss              : log_loss
+      n_estimators      : 100
+      max_depth         : 3
+      learning_rate     : 0.1
+      min_samples_split : 2
+saving:
+    output : /tmp/tests/dmu/ml/train_mva
+plotting:
+    roc     :
+        min : [0.0, 0.0]
+        max : [1.2, 1.2]
+        annotate:
+          sig_eff : [0.5, 0.6, 0.7, 0.8, 0.9]
+          form : '{:.2f}'
+          color: 'green'
+          xoff : -15
+          yoff : -15
+          size :  10
+    correlation:
+      title      : 'Correlation matrix'
+      size       : [10, 10]
+      mask_value : 0
+    features:
+        plots:
+          r :
+            binning : [-6, 6, 100]
+            yscale  : 'linear'
+            labels  : ['$r$', '']
+          w :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$w$', '']
+          preffix.x.suffix :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$x$', '']
+          y :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$y$', '']
+          z :
+            binning : [-4, 4, 100]
+            yscale  : 'linear'
+            labels  : ['$z$', '']

dmu_data/plotting/tests/2d.yaml

@@ -0,0 +1,24 @@
+saving:
+    plt_dir : /tmp/tests/dmu/plotting
+selection:
+  cuts:
+    xlow : x > -1.5
+definitions:
+  z : x + y
+general:
+    size : [20, 10]
+plots_2d:
+    - [x, y, weights, 'xy_wgt_lin', false]
+    - [x, z, weights, 'xz_wgt_log',  true]
+    - [x, y,    null, 'xy_raw_lin', false]
+    - [x, z,    null, 'xz_raw_log',  true]
+axes:
+    x :
+        binning : [-3.0, 3.0, 40]
+        label   : 'x'
+    y :
+        binning : [-5.0, 8.0, 40]
+        label   : 'y'
+    z :
+        binning : [-5.0, 16.0, 40]
+        label   : 'z'

dmu_data/plotting/tests/fig_size.yaml

@@ -0,0 +1,13 @@
+saving:
+    plt_dir : tests/plotting/fig_size
+general:
+    size : [20, 10]
+plots:
+    x : 
+        binning : [-5.0, 8.0, 40]
+        yscale  : 'linear' 
+        labels  : ['x', 'Entries']
+    y : 
+        binning : [-5.0, 8.0, 40]
+        yscale  : 'linear' 
+        labels  : ['y', 'Entries']

dmu_data/plotting/tests/high_stat.yaml

@@ -0,0 +1,22 @@
+selection:
+    max_ran_entries : 50000
+    cuts:
+      z : 'z > 0'
+saving:
+    plt_dir : tests/plotting/high_stat
+definitions:
+    z : 'x + y'
+plots:
+    x :
+        binning    : [-5.0, 8.0, 40]
+        yscale     : 'linear'
+        labels     : ['x', 'Entries']
+    y :
+        binning    : [-5.0, 8.0, 40]
+        yscale     : 'linear'
+        labels     : ['y', 'Entries']
+    z :
+        binning    : [-5.0, 8.0, 40]
+        yscale     : 'linear'
+        labels     : ['x + y', 'Normalized']
+        normalized : true

dmu_data/plotting/tests/legend.yaml

@@ -0,0 +1,12 @@
+saving:
+    plt_dir : tests/plotting/legend
+general:
+    size : [20, 10]
+plots:
+    x : 
+        binning : [-5.0, 8.0, 40]
+    y : 
+        binning : [-5.0, 8.0, 40]
+style:
+  legend:
+    bbox_to_anchor : [1.2, 1]

dmu_data/plotting/tests/line.yaml

@@ -0,0 +1,15 @@
+saving:
+    plt_dir : tests/plotting/line
+plots:
+    x :
+      binning : [-5.0, 8.0, 40]
+      title   : x distribution
+      vline   :
+        x     : 0
+        label : label
+        ls    : --
+        c     : blue
+        lw    : 1
+    y :
+      binning : [-5.0, 8.0, 40]
+      title   : y distribution

dmu_data/plotting/tests/name.yaml

@@ -0,0 +1,14 @@
+saving:
+    plt_dir : tests/plotting/name
+
+plots:
+    x : 
+        binning : [-5.0, 8.0, 40]
+        yscale  : 'linear' 
+        labels  : ['x', 'Entries']
+        name    : 'xvar'
+    y : 
+        binning : [-5.0, 8.0, 40]
+        yscale  : 'linear' 
+        labels  : ['y', 'Entries']
+        name    : 'yvar'

dmu_data/plotting/tests/no_bounds.yaml

@@ -0,0 +1,12 @@
+saving:
+    plt_dir : tests/plotting/no_bounds
+
+plots:
+    x : 
+        binning : [1, 1, 40]
+        yscale  : 'linear' 
+        labels  : ['x', 'Entries']
+    y : 
+        binning : [1, 1, 40]
+        yscale  : 'linear' 
+        labels  : ['y', 'Entries']

dmu_data/plotting/tests/normalized.yaml

@@ -0,0 +1,9 @@
+saving:
+    plt_dir : tests/plotting/normalized
+plots:
+    x : 
+      normalized : true
+      binning    : [-5.0, 8.0, 40]
+    y : 
+      normalized : false 
+      binning    : [-5.0, 8.0, 40]