ENH: Add custom validation functions for interpolator, wavelet, weightingNorm

Custom validation is needed for interpolator and weightingNorm, as regular Enum does not support a None value, causing validation to fail when user attempts to set None. By using custom validation, a None value will be accepted here.
Additionally validate the wavelet setting against the list of possible values in pyWavelets, ensuring no errors arrise when pyWavelet does not have the current set, as well as enabling any newly added wavelets when they are added to pyWavelet. Update the documentation to reflect this.

Author: JoostJM

data/paramSchema.yaml

@@ -20,17 +20,8 @@ mapping:
             range:
               min-ex: 0
       interpolator:
-        type: str
-        enum: ['sitkNearestNeighbor',
-               'sitkLinear',
-               'sitkBSpline',
-               'sitkGaussian',
-               'sitkLabelGaussian',
-               'sitkHammingWindowedSinc',
-               'sitkCosineWindowedSinc',
-               'sitkWelchWindowedSinc',
-               'sitkLanczosWindowedSinc',
-               'sitkBlackmanWindowedSinc']
+        type: any
+        func: checkInterpolator
       padDistance:
         type: int
         range:
@@ -50,14 +41,14 @@ mapping:
           min-ex: 0
       wavelet:
         type: str
-        pattern: ((haar|dmey)|(rbio|bior)(1.1|1.3|1.5|2.2|2.4|2.6|2.8|3.1|3.3|3.5|3.7|3.9|4.4|5.5|6.8)|coif[1-5]|db[1-20|sym[2-20])$
+        func: checkWavelet
       voxelArrayShift:
         type: int
       symmetricalGLCM:
         type: bool
       weightingNorm:
-        type: str
-        enum: ['infinity', 'euclidean', 'manhattan']
+        type: any
+        func: checkWeighting
       gldm_a:
         type: int
         range:

data/schemaFuncs.py

@@ -0,0 +1,43 @@
+import pywt
+
+def checkWavelet(value, rule_obj, path):
+  if not isinstance(value, basestring):
+    raise TypeError('Wavelet not expected type (str)')
+  wavelist = pywt.wavelist()
+  if value not in wavelist:
+    raise ValueError('Wavelet "%s" not available in pyWavelets %s' %(value, wavelist))
+  return True
+
+def checkInterpolator(value, rule_obj, path):
+  if value is None:
+    return True
+  if isinstance(value, basestring):
+    enum = {'sitkNearestNeighbor',
+           'sitkLinear',
+           'sitkBSpline',
+           'sitkGaussian',
+           'sitkLabelGaussian',
+           'sitkHammingWindowedSinc',
+           'sitkCosineWindowedSinc',
+           'sitkWelchWindowedSinc',
+           'sitkLanczosWindowedSinc',
+           'sitkBlackmanWindowedSinc'}
+    if value not in enum:
+      raise ValueError('Interpolator value "%s" not valid, possible values: %s' %(value, enum))
+  elif isinstance(value, int):
+    if value < 1 or value > 10:
+      raise ValueError('Intepolator value %i, must be in range of [1-10]' %(value))
+  else:
+    raise TypeError('Interpolator not expected type (str or int)')
+  return True
+
+def checkWeighting(value, rule_obj, path):
+  if value is None:
+    return True
+  elif isinstance(value, basestring):
+    enum = ['euclidean', 'manhattan', 'infinity', 'no_weighting']
+    if value not in enum:
+      raise ValueError('WeightingNorm value "%s" not valid, possible values: %s' % (value, enum))
+  else:
+    raise TypeError('WeightingNorm not expected type (str or None)')
+  return True

radiomics/featureextractor.py

@@ -127,8 +127,10 @@ def loadParams(self, paramsFile):
 
         If supplied params file does not match the requirements, a pykwalify error is raised.
         """
-        schemafile = os.path.abspath(os.path.join(radiomics.__path__[0], '..', 'data', 'paramSchema.yaml'))
-        c = pykwalify.core.Core(source_file=paramsFile, schema_files=[schemafile])
+        dataDir = os.path.abspath(os.path.join(radiomics.__path__[0], '..', 'data'))
+        schemaFile = os.path.join(dataDir, 'paramSchema.yaml')
+        schemaFuncs = os.path.join(dataDir, 'schemaFuncs.py')
+        c = pykwalify.core.Core(source_file=paramsFile, schema_files=[schemaFile], extensions=[schemaFuncs])
         params = c.validate()
 
         inputImages = params.get('inputImage', {})
@@ -428,8 +430,9 @@ def generate_wavelet(self, image, mask, **kwargs):
         - start_level [0]: integer, 0 based level of wavelet which should be used as first set of decompositions
           from which a signature is calculated
         - level [1]: integer, number of levels of wavelet decompositions from which a signature is calculated.
-        - wavelet ["coif1"]: string, type of wavelet decomposition. Enumerated value, possible values, where an
-          aditional number is needed, range of values is indicated in []:
+        - wavelet ["coif1"]: string, type of wavelet decomposition. Enumerated value, validated against possible values
+          present in the ``pyWavelet.wavelist()``. Current possible values (pywavelet version 0.4.0) (where an
+          aditional number is needed, range of values is indicated in []):
 
           - haar
           - dmey

setup.py

@@ -13,7 +13,7 @@
                         'PyWavelets>=0.4.0',
                         'pykwalify>=1.5.2',
                         'sphinx>=1.4'],
-      data_files=[('data', ['data/paramSchema.yaml'])],
+      data_files=[('data', ['data/paramSchema.yaml', 'data/schemaFuncs.py'])],
       description='Radiomics features library for python',
       url='http://github.com/Radiomics/pyradiomics',
       author='pyradiomics community',