data-manipulation-utilities 0.2.4__tar.gz → 0.2.6__tar.gz

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: data_manipulation_utilities
-Version: 0.2.4
+Version: 0.2.6
 Description-Content-Type: text/markdown
 Requires-Dist: logzero
 Requires-Dist: PyYAML
@@ -26,7 +26,7 @@ These are tools that can be used for different data analysis tasks.
 
 ## Pushing
 
-From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory) 
+From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory)
 using a `pyproject.toml` file, run:
 
 ```bash
@@ -36,10 +36,10 @@ 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 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. 
+Then, for each remote it pushes the tags and the commits.
 
 *Why?*
 
@@ -137,7 +137,17 @@ pdf   = mod.get_pdf()
 ```
 
 where the model is a sum of three `CrystallBall` PDFs, one with a right tail and two with a left tail.
-The `mu` and `sg` parameters are shared.
+The `mu` and `sg` parameters are shared. The elementary components that can be plugged are:
+
+```
+exp: Exponential
+pol1: Polynomial of degree 1
+pol2: Polynomial of degree 2
+cbr : CrystallBall with right tail
+cbl : CrystallBall with left tail
+gauss : Gaussian 
+dscb : Double sided CrystallBall
+```
 
 ### Printing PDFs
 
@@ -299,7 +309,7 @@ this will:
 - Try fitting at most 10 times
 - After each fit, calculate the goodness of fit (in this case the p-value)
 - Stop when the number of tries has been exhausted or the p-value reached is higher than `0.05`
-- If the fit has not succeeded because of convergence, validity or goodness of fit issues, 
+- If the fit has not succeeded because of convergence, validity or goodness of fit issues,
 randomize the parameters and try again.
 - If the desired goodness of fit has not been achieved, pick the best result.
 - Return the `FitResult` object and set the PDF to the final fit result.
@@ -337,11 +347,11 @@ bkg = zfit.pdf.Exponential(obs=obs, lam=lm)
 nbk = zfit.Parameter('nbk', 1000, 0, 10000)
 ebkg= bkg.create_extended(nbk, name='expo')
 
-# Add them 
+# Add them
 pdf = zfit.pdf.SumPDF([ebkg, esig])
 sam = pdf.create_sampler()
 
-# Plot them 
+# Plot them
 obj   = ZFitPlotter(data=sam, model=pdf)
 d_leg = {'gauss': 'New Gauss'}
 obj.plot(nbins=50, d_leg=d_leg, stacked=True, plot_range=(0, 10), ext_text='Extra text here')
@@ -353,7 +363,7 @@ obj.axs[1].plot([0, 10], [0, 0], linestyle='--', color='black')
 this class supports:
 
 - Handling title, legend, plots size.
-- Adding pulls. 
+- Adding pulls.
 - Stacking and overlaying of PDFs.
 - Blinding.
 
@@ -417,7 +427,7 @@ rdf_bkg = _get_rdf(kind='bkg')
 cfg     = _get_config()
 
 obj= TrainMva(sig=rdf_sig, bkg=rdf_bkg, cfg=cfg)
-obj.run()
+obj.run(skip_fit=False) # by default it will be false, if true, it will only make plots of features
 ```
 
 where the settings for the training go in a config dictionary, which when written to YAML looks like:
@@ -434,7 +444,7 @@ dataset:
     nan:
         x : 0
         y : 0
-        z : -999 
+        z : -999
 training :
     nfold    : 10
     features : [x, y, z]
@@ -497,7 +507,7 @@ When training on real data, several things might go wrong and the code will try
 will end up in different folds. The tool checks for wether a model is evaluated for an entry that was used for training and raise an exception. Thus, repeated
 entries will be removed before training.
 
-- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we: 
+- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we:
     - Can use the `nan` section shown above to replace `NaN` values with something else
     - For whatever remains we remove the entries from the training.
 
@@ -539,7 +549,7 @@ When evaluating the model with real data, problems might occur, we deal with the
     ```python
     model.cfg
     ```
-    - For whatever entries that are still NaN, they will be _patched_  with zeros and evaluated. However, before returning, the probabilities will be
+    - For whatever features that are still NaN, they will be _patched_  with zeros when evaluated. However, the returned probabilities will be
 saved as -1. I.e. entries with NaNs will have probabilities of -1.
 
 # Pandas dataframes
@@ -674,6 +684,9 @@ ptr.run()
 where the config dictionary `cfg_dat` in YAML would look like:
 
 ```yaml
+general:
+    # This will set the figure size
+    size : [20, 10]
 selection:
     #Will do at most 50K random entries. Will only happen if the dataset has more than 50K entries
     max_ran_entries : 50000
@@ -703,6 +716,16 @@ plots:
         yscale     : 'linear'
         labels     : ['x + y', 'Entries']
         normalized : true #This should normalize to the area
+# Some vertical dashed lines are drawn by default
+# If you see them, you can turn them off with this
+style:
+  skip_lines : true
+  # This can pass arguments to legend making function `plt.legend()` in matplotlib
+  legend:
+    # The line below would place the legend outside the figure to avoid ovelaps with the histogram
+    bbox_to_anchor : [1.2, 1]
+stats:
+  nentries : '{:.2e}' # This will add number of entries in legend box
 ```
 
 it's up to the user to build this dictionary and load it.
@@ -724,14 +747,19 @@ The config would look like:
 ```yaml
 saving:
     plt_dir : tests/plotting/2d
+selection:
+  cuts:
+    xlow : x > -1.5
 general:
     size : [20, 10]
 plots_2d:
     # Column x and y
     # Name of column where weights are, null for not weights
     # Name of output plot, e.g. xy_x.png
-    - [x, y, weights, 'xy_w']
-    - [x, y,    null, 'xy_r']
+    # Book signaling to use log scale for z axis
+    - [x, y, weights, 'xy_w', false]
+    - [x, y,    null, 'xy_r', false]
+    - [x, y,    null, 'xy_l',  true]
 axes:
     x :
         binning : [-5.0, 8.0, 40]
@@ -823,7 +851,7 @@ Directory/Treename
     B_ENDVERTEX_CHI2DOF           Double_t
 ```
 
-## Comparing ROOT files 
+## Comparing ROOT files
 
 Given two ROOT files the command below:
 
@@ -885,7 +913,7 @@ last_file = get_latest_file(dir_path = file_dir, wc='name_*.txt')
 # 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 
+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.

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/README.md

@@ -6,7 +6,7 @@ These are tools that can be used for different data analysis tasks.
 
 ## Pushing
 
-From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory) 
+From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory)
 using a `pyproject.toml` file, run:
 
 ```bash
@@ -16,10 +16,10 @@ 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 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. 
+Then, for each remote it pushes the tags and the commits.
 
 *Why?*
 
@@ -117,7 +117,17 @@ pdf   = mod.get_pdf()
 ```
 
 where the model is a sum of three `CrystallBall` PDFs, one with a right tail and two with a left tail.
-The `mu` and `sg` parameters are shared.
+The `mu` and `sg` parameters are shared. The elementary components that can be plugged are:
+
+```
+exp: Exponential
+pol1: Polynomial of degree 1
+pol2: Polynomial of degree 2
+cbr : CrystallBall with right tail
+cbl : CrystallBall with left tail
+gauss : Gaussian 
+dscb : Double sided CrystallBall
+```
 
 ### Printing PDFs
 
@@ -279,7 +289,7 @@ this will:
 - Try fitting at most 10 times
 - After each fit, calculate the goodness of fit (in this case the p-value)
 - Stop when the number of tries has been exhausted or the p-value reached is higher than `0.05`
-- If the fit has not succeeded because of convergence, validity or goodness of fit issues, 
+- If the fit has not succeeded because of convergence, validity or goodness of fit issues,
 randomize the parameters and try again.
 - If the desired goodness of fit has not been achieved, pick the best result.
 - Return the `FitResult` object and set the PDF to the final fit result.
@@ -317,11 +327,11 @@ bkg = zfit.pdf.Exponential(obs=obs, lam=lm)
 nbk = zfit.Parameter('nbk', 1000, 0, 10000)
 ebkg= bkg.create_extended(nbk, name='expo')
 
-# Add them 
+# Add them
 pdf = zfit.pdf.SumPDF([ebkg, esig])
 sam = pdf.create_sampler()
 
-# Plot them 
+# Plot them
 obj   = ZFitPlotter(data=sam, model=pdf)
 d_leg = {'gauss': 'New Gauss'}
 obj.plot(nbins=50, d_leg=d_leg, stacked=True, plot_range=(0, 10), ext_text='Extra text here')
@@ -333,7 +343,7 @@ obj.axs[1].plot([0, 10], [0, 0], linestyle='--', color='black')
 this class supports:
 
 - Handling title, legend, plots size.
-- Adding pulls. 
+- Adding pulls.
 - Stacking and overlaying of PDFs.
 - Blinding.
 
@@ -397,7 +407,7 @@ rdf_bkg = _get_rdf(kind='bkg')
 cfg     = _get_config()
 
 obj= TrainMva(sig=rdf_sig, bkg=rdf_bkg, cfg=cfg)
-obj.run()
+obj.run(skip_fit=False) # by default it will be false, if true, it will only make plots of features
 ```
 
 where the settings for the training go in a config dictionary, which when written to YAML looks like:
@@ -414,7 +424,7 @@ dataset:
     nan:
         x : 0
         y : 0
-        z : -999 
+        z : -999
 training :
     nfold    : 10
     features : [x, y, z]
@@ -477,7 +487,7 @@ When training on real data, several things might go wrong and the code will try
 will end up in different folds. The tool checks for wether a model is evaluated for an entry that was used for training and raise an exception. Thus, repeated
 entries will be removed before training.
 
-- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we: 
+- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we:
     - Can use the `nan` section shown above to replace `NaN` values with something else
     - For whatever remains we remove the entries from the training.
 
@@ -519,7 +529,7 @@ When evaluating the model with real data, problems might occur, we deal with the
     ```python
     model.cfg
     ```
-    - For whatever entries that are still NaN, they will be _patched_  with zeros and evaluated. However, before returning, the probabilities will be
+    - For whatever features that are still NaN, they will be _patched_  with zeros when evaluated. However, the returned probabilities will be
 saved as -1. I.e. entries with NaNs will have probabilities of -1.
 
 # Pandas dataframes
@@ -654,6 +664,9 @@ ptr.run()
 where the config dictionary `cfg_dat` in YAML would look like:
 
 ```yaml
+general:
+    # This will set the figure size
+    size : [20, 10]
 selection:
     #Will do at most 50K random entries. Will only happen if the dataset has more than 50K entries
     max_ran_entries : 50000
@@ -683,6 +696,16 @@ plots:
         yscale     : 'linear'
         labels     : ['x + y', 'Entries']
         normalized : true #This should normalize to the area
+# Some vertical dashed lines are drawn by default
+# If you see them, you can turn them off with this
+style:
+  skip_lines : true
+  # This can pass arguments to legend making function `plt.legend()` in matplotlib
+  legend:
+    # The line below would place the legend outside the figure to avoid ovelaps with the histogram
+    bbox_to_anchor : [1.2, 1]
+stats:
+  nentries : '{:.2e}' # This will add number of entries in legend box
 ```
 
 it's up to the user to build this dictionary and load it.
@@ -704,14 +727,19 @@ The config would look like:
 ```yaml
 saving:
     plt_dir : tests/plotting/2d
+selection:
+  cuts:
+    xlow : x > -1.5
 general:
     size : [20, 10]
 plots_2d:
     # Column x and y
     # Name of column where weights are, null for not weights
     # Name of output plot, e.g. xy_x.png
-    - [x, y, weights, 'xy_w']
-    - [x, y,    null, 'xy_r']
+    # Book signaling to use log scale for z axis
+    - [x, y, weights, 'xy_w', false]
+    - [x, y,    null, 'xy_r', false]
+    - [x, y,    null, 'xy_l',  true]
 axes:
     x :
         binning : [-5.0, 8.0, 40]
@@ -803,7 +831,7 @@ Directory/Treename
     B_ENDVERTEX_CHI2DOF           Double_t
 ```
 
-## Comparing ROOT files 
+## Comparing ROOT files
 
 Given two ROOT files the command below:
 
@@ -865,7 +893,7 @@ last_file = get_latest_file(dir_path = file_dir, wc='name_*.txt')
 # 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 
+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.

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name        = 'data_manipulation_utilities'
-version     = '0.2.4'
+version     = '0.2.6'
 readme      = 'README.md'
 dependencies= [
 'logzero',

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/src/data_manipulation_utilities.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: data_manipulation_utilities
-Version: 0.2.4
+Version: 0.2.6
 Description-Content-Type: text/markdown
 Requires-Dist: logzero
 Requires-Dist: PyYAML
@@ -26,7 +26,7 @@ These are tools that can be used for different data analysis tasks.
 
 ## Pushing
 
-From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory) 
+From the root directory of a version controlled project (i.e. a directory with the `.git` subdirectory)
 using a `pyproject.toml` file, run:
 
 ```bash
@@ -36,10 +36,10 @@ 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 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. 
+Then, for each remote it pushes the tags and the commits.
 
 *Why?*
 
@@ -137,7 +137,17 @@ pdf   = mod.get_pdf()
 ```
 
 where the model is a sum of three `CrystallBall` PDFs, one with a right tail and two with a left tail.
-The `mu` and `sg` parameters are shared.
+The `mu` and `sg` parameters are shared. The elementary components that can be plugged are:
+
+```
+exp: Exponential
+pol1: Polynomial of degree 1
+pol2: Polynomial of degree 2
+cbr : CrystallBall with right tail
+cbl : CrystallBall with left tail
+gauss : Gaussian 
+dscb : Double sided CrystallBall
+```
 
 ### Printing PDFs
 
@@ -299,7 +309,7 @@ this will:
 - Try fitting at most 10 times
 - After each fit, calculate the goodness of fit (in this case the p-value)
 - Stop when the number of tries has been exhausted or the p-value reached is higher than `0.05`
-- If the fit has not succeeded because of convergence, validity or goodness of fit issues, 
+- If the fit has not succeeded because of convergence, validity or goodness of fit issues,
 randomize the parameters and try again.
 - If the desired goodness of fit has not been achieved, pick the best result.
 - Return the `FitResult` object and set the PDF to the final fit result.
@@ -337,11 +347,11 @@ bkg = zfit.pdf.Exponential(obs=obs, lam=lm)
 nbk = zfit.Parameter('nbk', 1000, 0, 10000)
 ebkg= bkg.create_extended(nbk, name='expo')
 
-# Add them 
+# Add them
 pdf = zfit.pdf.SumPDF([ebkg, esig])
 sam = pdf.create_sampler()
 
-# Plot them 
+# Plot them
 obj   = ZFitPlotter(data=sam, model=pdf)
 d_leg = {'gauss': 'New Gauss'}
 obj.plot(nbins=50, d_leg=d_leg, stacked=True, plot_range=(0, 10), ext_text='Extra text here')
@@ -353,7 +363,7 @@ obj.axs[1].plot([0, 10], [0, 0], linestyle='--', color='black')
 this class supports:
 
 - Handling title, legend, plots size.
-- Adding pulls. 
+- Adding pulls.
 - Stacking and overlaying of PDFs.
 - Blinding.
 
@@ -417,7 +427,7 @@ rdf_bkg = _get_rdf(kind='bkg')
 cfg     = _get_config()
 
 obj= TrainMva(sig=rdf_sig, bkg=rdf_bkg, cfg=cfg)
-obj.run()
+obj.run(skip_fit=False) # by default it will be false, if true, it will only make plots of features
 ```
 
 where the settings for the training go in a config dictionary, which when written to YAML looks like:
@@ -434,7 +444,7 @@ dataset:
     nan:
         x : 0
         y : 0
-        z : -999 
+        z : -999
 training :
     nfold    : 10
     features : [x, y, z]
@@ -497,7 +507,7 @@ When training on real data, several things might go wrong and the code will try
 will end up in different folds. The tool checks for wether a model is evaluated for an entry that was used for training and raise an exception. Thus, repeated
 entries will be removed before training.
 
-- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we: 
+- **NaNs**: Entries with NaNs will break the training with the scikit `GradientBoostClassifier` base class. Thus, we:
     - Can use the `nan` section shown above to replace `NaN` values with something else
     - For whatever remains we remove the entries from the training.
 
@@ -539,7 +549,7 @@ When evaluating the model with real data, problems might occur, we deal with the
     ```python
     model.cfg
     ```
-    - For whatever entries that are still NaN, they will be _patched_  with zeros and evaluated. However, before returning, the probabilities will be
+    - For whatever features that are still NaN, they will be _patched_  with zeros when evaluated. However, the returned probabilities will be
 saved as -1. I.e. entries with NaNs will have probabilities of -1.
 
 # Pandas dataframes
@@ -674,6 +684,9 @@ ptr.run()
 where the config dictionary `cfg_dat` in YAML would look like:
 
 ```yaml
+general:
+    # This will set the figure size
+    size : [20, 10]
 selection:
     #Will do at most 50K random entries. Will only happen if the dataset has more than 50K entries
     max_ran_entries : 50000
@@ -703,6 +716,16 @@ plots:
         yscale     : 'linear'
         labels     : ['x + y', 'Entries']
         normalized : true #This should normalize to the area
+# Some vertical dashed lines are drawn by default
+# If you see them, you can turn them off with this
+style:
+  skip_lines : true
+  # This can pass arguments to legend making function `plt.legend()` in matplotlib
+  legend:
+    # The line below would place the legend outside the figure to avoid ovelaps with the histogram
+    bbox_to_anchor : [1.2, 1]
+stats:
+  nentries : '{:.2e}' # This will add number of entries in legend box
 ```
 
 it's up to the user to build this dictionary and load it.
@@ -724,14 +747,19 @@ The config would look like:
 ```yaml
 saving:
     plt_dir : tests/plotting/2d
+selection:
+  cuts:
+    xlow : x > -1.5
 general:
     size : [20, 10]
 plots_2d:
     # Column x and y
     # Name of column where weights are, null for not weights
     # Name of output plot, e.g. xy_x.png
-    - [x, y, weights, 'xy_w']
-    - [x, y,    null, 'xy_r']
+    # Book signaling to use log scale for z axis
+    - [x, y, weights, 'xy_w', false]
+    - [x, y,    null, 'xy_r', false]
+    - [x, y,    null, 'xy_l',  true]
 axes:
     x :
         binning : [-5.0, 8.0, 40]
@@ -823,7 +851,7 @@ Directory/Treename
     B_ENDVERTEX_CHI2DOF           Double_t
 ```
 
-## Comparing ROOT files 
+## Comparing ROOT files
 
 Given two ROOT files the command below:
 
@@ -885,7 +913,7 @@ last_file = get_latest_file(dir_path = file_dir, wc='name_*.txt')
 # 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 
+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.

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/src/data_manipulation_utilities.egg-info/SOURCES.txt

@@ -38,10 +38,12 @@ src/dmu_data/ml/tests/train_mva.yaml
 src/dmu_data/plotting/tests/2d.yaml
 src/dmu_data/plotting/tests/fig_size.yaml
 src/dmu_data/plotting/tests/high_stat.yaml
+src/dmu_data/plotting/tests/legend.yaml
 src/dmu_data/plotting/tests/name.yaml
 src/dmu_data/plotting/tests/no_bounds.yaml
 src/dmu_data/plotting/tests/normalized.yaml
 src/dmu_data/plotting/tests/simple.yaml
+src/dmu_data/plotting/tests/stats.yaml
 src/dmu_data/plotting/tests/title.yaml
 src/dmu_data/plotting/tests/weights.yaml
 src/dmu_data/text/transform.toml

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/src/dmu/ml/cv_classifier.py

@@ -1,15 +1,15 @@
 '''
 Module holding cv_classifier class
 '''
-
+import os
 from typing                  import Union
 from sklearn.ensemble        import GradientBoostingClassifier
 
+import yaml
 from dmu.logging.log_store import LogStore
 import dmu.ml.utilities    as ut
 
 log = LogStore.add_logger('dmu:ml:CVClassifier')
-
 # ---------------------------------------
 class CVSameData(Exception):
     '''
@@ -61,6 +61,20 @@ class CVClassifier(GradientBoostingClassifier):
 
         return self._cfg
     # ----------------------------------
+    def save_cfg(self, path : str):
+        '''
+        Will save configuration used to train this classifier to YAML
+
+        path: Path to YAML file
+        '''
+        dir_name = os.path.dirname(path)
+        os.makedirs(dir_name, exist_ok=True)
+
+        with open(path, 'w', encoding='utf-8') as ofile:
+            yaml.safe_dump(self._cfg, ofile, indent=2)
+
+        log.info(f'Saved config to: {path}')
+    # ----------------------------------
     def __str__(self):
         nhash = len(self._s_hash)
 

{data_manipulation_utilities-0.2.4 → data_manipulation_utilities-0.2.6}/src/dmu/ml/cv_predict.py

@@ -73,11 +73,11 @@ class CVPredict:
             log.debug('Not doing any NaN replacement')
             return df
 
-        log.debug(60 * '-')
+        log.info(60 * '-')
         log.info('Doing NaN replacements')
-        log.debug(60 * '-')
+        log.info(60 * '-')
         for var, val in self._d_nan_rep.items():
-            log.debug(f'{var:<20}{"--->":20}{val:<20.3f}')
+            log.info(f'{var:<20}{"--->":20}{val:<20.3f}')
             df[var] = df[var].fillna(val)
 
         return df
@@ -155,7 +155,7 @@ class CVPredict:
         ndif = len(s_dif_hash)
         ndat = len(s_dat_hash)
         nmod = len(s_mod_hash)
-        log.debug(f'{ndif:<20}{"=":10}{ndat:<20}{"-":10}{nmod:<20}')
+        log.debug(f'{ndif:<10}{"=":5}{ndat:<10}{"-":5}{nmod:<10}')
 
         df_ft_group= df_ft.loc[df_ft.index.isin(s_dif_hash)]
 
@@ -173,7 +173,7 @@ class CVPredict:
             return arr_prb
 
         nentries = len(self._arr_patch)
-        log.warning(f'Patching {nentries} probabilities')
+        log.warning(f'Patching {nentries} probabilities with -1')
         arr_prb[self._arr_patch] = -1
 
         return arr_prb