fixed zero devision bug which occured while testing with fake data; extended tests

Author: btschwertfeger

Diff for: .github/workflows/python-package.yml

@@ -1,7 +1,7 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: Python package
+name: Python-Package
 
 on:
   push:
@@ -36,4 +36,4 @@ jobs:
           flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
       - name: Test with pytest
         run: |
-          pytest cmethods/tests/testing.py
+          pytest

Diff for: .gitignore

@@ -1,8 +1,139 @@
-.DS_Store
-__pycache__
-.ipynb_checkpoints
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+# C extensions
+*.so
+*.zip
 
+# Distribution / packaging
+.Python
 build/
+develop-eggs/
 dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+del*.py
+
+# Pyre type checker
+.pyre/
+
+# misc
+.DS_Store
+*.csv
+*.log
+*.zip
+
 *.egg-info/
 conda.stuff/

Diff for: README.md

@@ -43,14 +43,14 @@ These programs and data structures are designed to help minimize discrepancies b
   <figcaption>Figure 1: Schematic representation of a bias adjustment procedure</figcaption>
 </figure>
 
-In this way, for example, modeled data, which on average represent values that are too cold, can be adjusted by applying an adjustment procedure. The following figure shows the observed, the modeled and the adjusted values. It is directly visible that the delta adjusted time series ($T^{*DM}_{sim,p}$) are much more similar to the observed data ($T_{obs,p}$) than the raw modeled data ($T_{sim,p}$).
+In this way, for example, modeled data, which on average represent values that are too cold, can be adjusted by applying an adjustment procedure. The following figure shows the observed, the modeled, and the adjusted values. It is directly visible that the delta adjusted time series ($T^{*DM}_{sim,p}$) are much more similar to the observed data ($T_{obs,p}$) than the raw modeled data ($T_{sim,p}$).
 
 <figure>
   <img
   src="images/dm-doy-plot.png?raw=true"
   alt="Temperature per day of year in modeled, observed and bias-adjusted climate data"
   style="background-color: white; border-radius: 7px">
-  <figcaption>Figure 2: Temperature per day of year in observed, modeled and bias-adjusted climate data</figcaption>
+  <figcaption>Figure 2: Temperature per day of year in observed, modeled, and bias-adjusted climate data</figcaption>
 </figure>
 
 ---
@@ -61,14 +61,14 @@ In this way, for example, modeled data, which on average represent values that a
 
 All methods except the `adjust_3d` function requires the application on one time series.
 
-| Function name            | Description                                                                                                |
-| ------------------------ | ---------------------------------------------------------------------------------------------------------- |
-| `linear_scaling`         | Linear Scaling (additive and multiplicative)                                                               |
-| `variance_scaling`       | Variance Scaling (additive)                                                                                |
-| `delta_method`           | Delta (Change) Method (additive and multiplicative)                                                        |
-| `quantile_mapping`       | Quantile Mapping (additive) and Detrended Quantile Mapping (additive and multiplicative)                   |
-| `quantile_delta_mapping` | Quantile Delta Mapping (additive and multiplicative)                                                       |
-| `adjust_3d`              | requires a method name and the respective parameters to adjust all time series of a 3-dimensional data set |
+| Function name            | Description                                                                                                                                                  |
+| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `linear_scaling`         | Linear Scaling (additive and multiplicative)                                                                                                                 |
+| `variance_scaling`       | Variance Scaling (additive)                                                                                                                                  |
+| `delta_method`           | Delta (Change) Method (additive and multiplicative)                                                                                                          |
+| `quantile_mapping`       | Quantile Mapping (additive and multiplicative) and Detrended Quantile Mapping (additive and multiplicative; to use DQM, set parameter `detrended` to `True`) |
+| `quantile_delta_mapping` | Quantile Delta Mapping (additive and multiplicative)                                                                                                         |
+| `adjust_3d`              | requires a method name and the respective parameters to adjust all time series of a 3-dimensional data set                                                   |
 
 ---
 
@@ -148,7 +148,7 @@ python3 do_bias_correction.py         \
 
 ## 5. Notes
 
-- Computation in Python takes some time, so this is only for demonstration. When adjusting large datasets, its best to use the C++ implementation mentioned above.
+- Computation in Python takes some time, so this is only for demonstration. When adjusting large datasets, its best to use the C++ implementation mentioned earlier.
 - Formulas and references can be found in the implementations of the corresponding functions.
 
 ### Space for improvements:

Diff for: cmethods/CMethods.py

@@ -409,6 +409,7 @@ def delta_method(cls,
             https://svn.oss.deltares.nl/repos/openearthtools/trunk/python/applications/hydrotools/hydrotools/statistics/bias_correction.py
 
         '''
+
         if group is not None: return cls.grouped_correction(method='delta_method', obs=obs, simh=simh, simp=simp, group=group, kind=kind, **kwargs)
         if kind in cls.ADDITIVE: return np.array(obs) + (np.nanmean(simp) - np.nanmean(simh))     # Eq. 1
         if kind in cls.MULTIPLICATIVE:
@@ -484,7 +485,7 @@ def quantile_mapping(cls,
         cdf_obs = cls.get_cdf(obs, xbins)
         cdf_simh = cls.get_cdf(simh, xbins)
 
-        if kwargs.get('detrended', False) or kind in cls.MULTIPLICATIVE:
+        if kwargs.get('detrended', False):
             # detrended => shift mean of $X_{sim,p}$ to range of $X_{sim,h}$ to adjust extremes
             for _, idxs in res.groupby('time.month').groups.items():
                 m_simh, m_simp = [], []
@@ -498,18 +499,34 @@ def quantile_mapping(cls,
                 m_simp_mean = np.nanmean(m_simp)
 
                 if kind in cls.ADDITIVE:
-                    epsilon = np.interp(m_simp - m_simp_mean + m_simh_mean, xbins, cdf_simh)         # Eq. 1
+                    epsilon = np.interp(m_simp - m_simp_mean + m_simh_mean, xbins, cdf_simh)          # Eq. 1
                     X = cls.get_inverse_of_cdf(cdf_obs, epsilon, xbins) + m_simp_mean - m_simh_mean   # Eq. 1
-                else:
-                    epsilon = np.interp((m_simh_mean * m_simp) / m_simp_mean, xbins, cdf_simh, left=.0, right=999.0)    # Eq. 2
-                    X = np.interp(epsilon, cdf_obs, xbins, left=.0, right=999.9) * (m_simp_mean / m_simh_mean)          # Eq. 2
-                    #x = cm.get_inverse_of_cdf(cdf_obs, epsilon, xbins) * (m_simp_mean / m_simh_mean)
+
+                elif kind in cls.MULTIPLICATIVE:
+                    epsilon = np.interp(                                                              # Eq. 2
+                        (m_simh_mean * m_simp) / m_simp_mean, 
+                        xbins, cdf_simh, 
+                        left=kwargs.get('val_min', 0.0), 
+                        right=kwargs.get('val_max', None)
+                    )   
+                    X = np.interp(epsilon, cdf_obs, xbins) * (m_simp_mean / m_simh_mean)              # Eq. 2
                 for i, idx in enumerate(idxs): res.values[idx] = X[i]
             return res
 
-        if kind in cls.ADDITIVE: # additive, no detrend
-            epsilon = np.interp(simp, xbins, cdf_simh)                                 # Eq. 1
-            res.values = cls.get_inverse_of_cdf(cdf_obs, epsilon, xbins)               # Eq. 1
+        if kind in cls.ADDITIVE: 
+            epsilon = np.interp(simp, xbins, cdf_simh)                     # Eq. 1
+            res.values = cls.get_inverse_of_cdf(cdf_obs, epsilon, xbins)   # Eq. 1
+            return res
+
+        if kind in cls.MULTIPLICATIVE:
+            epsilon = np.interp(                                           # Eq. 2
+                simp, 
+                xbins, 
+                cdf_simh, 
+                left=kwargs.get('val_min', 0.0), 
+                right=kwargs.get('val_max', None)
+            )     
+            res.values = cls.get_inverse_of_cdf(cdf_obs, epsilon, xbins)   # Eq. 2
             return res
 
         raise ValueError('Not implemented!')
@@ -527,37 +544,6 @@ def empirical_quantile_mapping(cls,
     ) -> xr.core.dataarray.DataArray:
         ''' Method to adjust 1 dimensional climate data by empirical quantile mapping
 
-        ----- P A R A M E T E R S -----
-
-            obs (xarray.core.dataarray.DataArray): observed / obserence Data
-            simh (xarray.core.dataarray.DataArray): simulated historical Data
-            simp (xarray.core.dataarray.DataArray): future simulated Data
-            n_quantiles (int): Quantiles to involve, default: 10
-            extrapolate (str): [optional] 'linear' or 'constant', default: None
-            group (str): [optional] Group / Period (e.g.: 'time.month')
-
-        ----- R E T U R N -----
-
-            xarray.core.dataarray.DataArray: Adjusted data
-
-        ----- E X A M P L E -----
-
-            > obs = xarray.open_dataset('path/to/observed/data.nc')
-            > simh = xarray.open_dataset('path/to/simulated/data.nc')
-            > simp = xarray.open_dataset('path/to/future/data.nc')
-            > variable = 'tas'
-            > result = CMethods().empirical_quantile_mapping(
-            >    obs=obs[variable],
-            >    simh=simh[variable],
-            >    simp=simp[variable],
-            >    group='time.dayofyear'
-            >)
-
-        ----- R E F E R E N C E S -----
-
-            (April 2022) Taken from:
-            https://svn.oss.deltares.nl/repos/openearthtools/trunk/python/applications/hydrotools/hydrotools/statistics/bias_correction.py
-
         '''
         raise ValueError('not implemented; please have a look at: https://svn.oss.deltares.nl/repos/openearthtools/trunk/python/applications/hydrotools/hydrotools/statistics/bias_correction.py ')
         # if group is not None:
@@ -631,8 +617,8 @@ def quantile_delta_mapping(cls,
         if kind in cls.ADDITIVE:
             res = simp.copy(deep=True)
             obs, simh, simp = np.array(obs), np.array(simh), np.array(simp) # to achieve higher accuracy
-            global_max = max(np.amax(obs), np.amax(simh))
-            global_min = min(np.amin(obs), np.amin(simh))
+            global_max = kwargs.get('global_max', max(np.amax(obs), np.amax(simh)))
+            global_min = kwargs.get('global_min', min(np.amin(obs), np.amin(simh)))
             wide = abs(global_max - global_min) / n_quantiles
             xbins = np.arange(global_min, global_max + wide, wide)
 
@@ -650,17 +636,21 @@ def quantile_delta_mapping(cls,
         if kind in cls.MULTIPLICATIVE:
             res = simp.copy(deep=True)
             obs, simh, simp = np.array(obs), np.array(simh), np.array(simp)
-            global_max = max(np.amax(obs), np.amax(simh))
+            global_max = kwargs.get('global_max', max(np.amax(obs), np.amax(simh)))
             wide = global_max / n_quantiles
             xbins = np.arange(kwargs.get('global_min', .0), global_max + wide, wide)
 
-            cdf_obs = cls.get_cdf(obs,xbins)
-            cdf_simh = cls.get_cdf(simh,xbins)
+            cdf_obs = cls.get_cdf(obs, xbins)
+            cdf_simh = cls.get_cdf(simh, xbins)
             cdf_simp = cls.get_cdf(simp, xbins)
 
             epsilon = np.interp(simp, xbins, cdf_simp)                            # Eq. 1.1
             QDM1 = cls.get_inverse_of_cdf(cdf_obs, epsilon, xbins)                # Eq. 1.2
-            delta = simp / cls.get_inverse_of_cdf(cdf_simh, epsilon, xbins)       # Eq. 2.3
+            
+            with np.errstate(divide='ignore', invalid='ignore'):
+                delta = simp / cls.get_inverse_of_cdf(cdf_simh, epsilon, xbins)   # Eq. 2.3
+            delta[np.isnan(delta)] = 0
+            
             res.values = QDM1 * delta                                             # Eq. 2.4
             return res
         raise ValueError(f'Unknown kind {kind}!')

Diff for: cmethods/__version__.py

@@ -1,3 +1,3 @@
 '''version of this module'''
-VERSION = (0,5,4,2)
+VERSION = (0,6,1)
 __version__ = '.'.join(map(str, VERSION))