wassname/catalyst
1
0
Fork 0
mirror of https://github.com/wassname/catalyst.git synced 2026-09-13 12:20:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "MAINT: Remove support for custom string Column missing values."

Browse Source 
This reverts commit 1b1e842e2339d6d0ee40cdfe34dcd27b4e4a7c0c.
This commit is contained in:
Scott Sanderson
2016-09-20 17:12:07 -04:00
parent 16f4944232
commit 0ff13e7fdc
6 changed files with 38 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/pipeline/test_classifier.py
+11 -10
View File
@@ -51,7 +51,7 @@ class ClassifierTestCase(BasePipelineTestCase):
mask=self.build_mask(self.ones_mask(shape=data.shape)),
)
@parameter_space(mv=[None])
@parameter_space(mv=['0', None])
def test_string_isnull(self, mv):
class C(Classifier):
@@ -126,7 +126,7 @@ class ClassifierTestCase(BasePipelineTestCase):
class C(Classifier):
dtype = categorical_dtype
missing_value = None
missing_value = ''
inputs = ()
window_length = 0
@@ -162,7 +162,7 @@ class ClassifierTestCase(BasePipelineTestCase):
)
def test_disallow_comparison_to_missing_value(self, missing, dtype_):
if dtype_ == categorical_dtype:
missing = None
missing = str(missing)
class C(Classifier):
dtype = dtype_
@@ -224,7 +224,7 @@ class ClassifierTestCase(BasePipelineTestCase):
class C(Classifier):
dtype = categorical_dtype
missing_value = None
missing_value = missing
inputs = ()
window_length = 0
@@ -245,7 +245,7 @@ class ClassifierTestCase(BasePipelineTestCase):
expected = (
(data.as_int_array() != data.reverse_categories.get(compval, -1)) &
(data.as_int_array() != data.reverse_categories[missing])
(data.as_int_array() != data.reverse_categories[C.missing_value])
)
self.check_terms(
@@ -271,6 +271,7 @@ class ClassifierTestCase(BasePipelineTestCase):
labelarray_dtype):
if labelarray_dtype == bytes_dtype:
compval = compval.encode('utf-8')
missing = missing.encode('utf-8')
startswith_re = b'^' + compval + b'.*'
endswith_re = b'.*' + compval + b'$'
@@ -282,7 +283,7 @@ class ClassifierTestCase(BasePipelineTestCase):
class C(Classifier):
dtype = categorical_dtype
missing_value = None
missing_value = missing
inputs = ()
window_length = 0
@@ -337,7 +338,7 @@ class ClassifierTestCase(BasePipelineTestCase):
class C(Classifier):
dtype = categorical_dtype
missing_value = None
missing_value = missing
inputs = ()
window_length = 0
@@ -417,7 +418,7 @@ class ClassifierTestCase(BasePipelineTestCase):
Test that element_of raises a useful error if we attempt to pass it an
array of choices that include the classifier's missing_value.
"""
missing = None
missing = "not in the array"
class C(Classifier):
dtype = categorical_dtype
@@ -432,7 +433,7 @@ class ClassifierTestCase(BasePipelineTestCase):
c.element_of(bad_elems)
errmsg = str(e.exception)
expected = (
"Found self.missing_value (None) in choices"
"Found self.missing_value ('not in the array') in choices"
" supplied to C.element_of().\n"
"Missing values have NaN semantics, so the requested"
" comparison would always produce False.\n"
@@ -446,7 +447,7 @@ class ClassifierTestCase(BasePipelineTestCase):
class C(Classifier):
dtype = dtype_
missing_value = None if dtype_ is categorical_dtype else -1
missing_value = dtype.type('1')
inputs = ()
window_length = 0