Update to latest version of metasyn

.github/workflows/python-package.yml

@@ -17,9 +17,9 @@ jobs:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
         metasyn-version: [ "git+https://github.com/sodascience/metasyn.git@main"]
-        include:
-          - python-version: "3.11"
-            metasyn-version: "metasyn==0.8.0"
+        # include:
+        #   - python-version: "3.11"
+        #     metasyn-version: "metasyn==0.8.0"
 
     steps:
     - uses: actions/checkout@v4

metasyncontrib/disclosure/base.py

@@ -1,5 +1,8 @@
 """Base class for all disclosure control distributions."""
 
+import polars as pl
+from metasyn.distribution.base import BaseDistribution
+
 
 def metadist_disclosure():
     """Decorate class to create a distribution with disclosure control.
@@ -17,3 +20,25 @@ def _wrap(cls):
         return cls
 
     return _wrap
+
+
+class DisclosureConstantMixin(BaseDistribution):
+    """Mixin class to overload fit method for constant distributions."""
+
+    @classmethod
+    def fit(cls, series, *args, n_avg: int = 11, **kwargs) -> BaseDistribution:
+        """Fit constant distributions with disclosure control rules in place."""
+        pl_series: pl.Series = cls._to_series(series)
+
+        # if unique, just get that value if it occurs at least n_avg times
+        if pl_series.n_unique() == 1 and pl_series.len() >= n_avg:
+            return cls._fit(pl_series, *args, **kwargs)
+
+        if pl_series.n_unique() > 1:
+            # if not unique, ensure most common value occurs at least n_avg times
+            _value, count = pl_series.value_counts(sort=True).row(0)
+            if count >= n_avg:
+                return cls._fit(pl_series, *args, **kwargs)
+
+        return cls.default_distribution()
+

metasyncontrib/disclosure/continuous.py

@@ -1,14 +1,15 @@
 """Disclosure control implementations for continuous distributions."""
 
 from metasyn.distribution.continuous import (
+    ConstantDistribution,
     ExponentialDistribution,
     LogNormalDistribution,
     NormalDistribution,
     TruncatedNormalDistribution,
     UniformDistribution,
 )
 
-from metasyncontrib.disclosure.base import metadist_disclosure
+from metasyncontrib.disclosure.base import DisclosureConstantMixin, metadist_disclosure
 from metasyncontrib.disclosure.numerical import DisclosureNumericalMixin
 
 
@@ -35,3 +36,7 @@ class DisclosureTruncatedNormal(DisclosureNumericalMixin, TruncatedNormalDistrib
 @metadist_disclosure()
 class DisclosureExponential(DisclosureNumericalMixin, ExponentialDistribution):
     """Disclosure exponential distribution."""
+
+@metadist_disclosure()
+class DisclosureConstant(DisclosureConstantMixin, ConstantDistribution):
+    """Disclosure controlled ConstantDistribution."""

metasyncontrib/disclosure/datetime.py

@@ -6,12 +6,15 @@
 
 import polars as pl
 from metasyn.distribution.datetime import (
+    DateConstantDistribution,
+    DateTimeConstantDistribution,
     DateTimeUniformDistribution,
     DateUniformDistribution,
+    TimeConstantDistribution,
     TimeUniformDistribution,
 )
 
-from metasyncontrib.disclosure.base import metadist_disclosure
+from metasyncontrib.disclosure.base import DisclosureConstantMixin, metadist_disclosure
 
 # from metasyncontrib.disclosure.base import BaseDisclosureDistribution
 from metasyncontrib.disclosure.utils import micro_aggregate
@@ -56,3 +59,17 @@ def _fit(cls, values: pl.Series, n_avg: int = 11) -> DisclosureDate:
         # Convert back into dates
         sub_series = pl.Series([dt_val.date() for dt_val in dt_sub_series])
         return cls(sub_series.min(), sub_series.max())
+
+@metadist_disclosure()
+class DisclosureDateTimeConstant(DisclosureConstantMixin, DateTimeConstantDistribution):
+    """Disclosure controlled DateTimeConstantDistribution."""
+
+
+@metadist_disclosure()
+class DisclosureTimeConstant(DisclosureConstantMixin, TimeConstantDistribution):
+    """Disclosure controlled TimeConstantDistribution."""
+
+
+@metadist_disclosure()
+class DisclosureDateConstant(DisclosureConstantMixin, DateConstantDistribution):
+    """Disclosure controlled DateConstantDistribution."""

metasyncontrib/disclosure/discrete.py

@@ -4,14 +4,15 @@
 
 import polars as pl
 from metasyn.distribution.discrete import (
+    DiscreteConstantDistribution,
     DiscreteNormalDistribution,
     DiscreteTruncatedNormalDistribution,
     DiscreteUniformDistribution,
     PoissonDistribution,
     UniqueKeyDistribution,
 )
 
-from metasyncontrib.disclosure.base import metadist_disclosure
+from metasyncontrib.disclosure.base import DisclosureConstantMixin, metadist_disclosure
 from metasyncontrib.disclosure.numerical import DisclosureNumericalMixin
 from metasyncontrib.disclosure.utils import micro_aggregate
 
@@ -49,3 +50,7 @@ def _fit(cls, values: pl.Series, n_avg: int = 11):
             return cls(0, True)
         sub_values = micro_aggregate(values, n_avg)
         return super()._fit(sub_values)
+
+@metadist_disclosure()
+class DisclosureDiscreteConstant(DisclosureConstantMixin, DiscreteConstantDistribution):
+    """Disclosure controlled DiscreteConstantDistribution."""

metasyncontrib/disclosure/provider.py

@@ -5,35 +5,37 @@
 from metasyn.provider import BaseDistributionProvider
 
 from metasyncontrib.disclosure.categorical import DisclosureMultinoulli
-from metasyncontrib.disclosure.constant import (
-    DisclosureConstant,
-    DisclosureDateConstant,
-    DisclosureDateTimeConstant,
-    DisclosureDiscreteConstant,
-    DisclosureStringConstant,
-    DisclosureTimeConstant,
-)
 from metasyncontrib.disclosure.continuous import (
+    DisclosureConstant,
     DisclosureExponential,
     DisclosureLogNormal,
     DisclosureNormal,
     DisclosureTruncatedNormal,
     DisclosureUniform,
 )
-from metasyncontrib.disclosure.datetime import DisclosureDate, DisclosureDateTime, DisclosureTime
+from metasyncontrib.disclosure.datetime import (
+    DisclosureDate,
+    DisclosureDateConstant,
+    DisclosureDateTime,
+    DisclosureDateTimeConstant,
+    DisclosureTime,
+    DisclosureTimeConstant,
+)
 from metasyncontrib.disclosure.discrete import (
+    DisclosureDiscreteConstant,
     DisclosureDiscreteNormal,
     DisclosureDiscreteTruncatedNormal,
     DisclosureDiscreteUniform,
     DisclosurePoisson,
     DisclosureUniqueKey,
 )
-from metasyncontrib.disclosure.faker import (
+from metasyncontrib.disclosure.na import DisclosureNA
+from metasyncontrib.disclosure.string import (
     DisclosureFaker,
     DisclosureFreetext,
+    DisclosureStringConstant,
     DisclosureUniqueFaker,
 )
-from metasyncontrib.disclosure.na import DisclosureNA
 
 
 class DisclosureProvider(BaseDistributionProvider):

metasyncontrib/disclosure/faker.py → metasyncontrib/disclosure/string.py

@@ -1,12 +1,13 @@
 """Module for disclosure control for string distributions."""
 
-from metasyn.distribution.faker import (
+from metasyn.distribution.string import (
     FakerDistribution,
     FreeTextDistribution,
+    StringConstantDistribution,
     UniqueFakerDistribution,
 )
 
-from metasyncontrib.disclosure.base import metadist_disclosure
+from metasyncontrib.disclosure.base import DisclosureConstantMixin, metadist_disclosure
 
 
 @metadist_disclosure()
@@ -34,3 +35,7 @@ class DisclosureFreetext(FreeTextDistribution):
     @classmethod
     def _fit(cls, values, max_values: int = 50, n_avg: int = 11):  # pylint: disable=unused-argument
         return super()._fit(values, max_values=max_values)
+
+@metadist_disclosure()
+class DisclosureStringConstant(DisclosureConstantMixin, StringConstantDistribution):
+    """Disclosure controlled StringConstantDistribution."""

tests/test_constant.py

@@ -1,21 +1,21 @@
-from metasyn.distribution.constant import (
-    ConstantDistribution,
+from metasyn.distribution.continuous import ConstantDistribution
+from metasyn.distribution.datetime import (
     DateConstantDistribution,
     DateTimeConstantDistribution,
-    DiscreteConstantDistribution,
-    StringConstantDistribution,
     TimeConstantDistribution,
 )
+from metasyn.distribution.discrete import DiscreteConstantDistribution
+from metasyn.distribution.string import StringConstantDistribution
 from pytest import mark
 
-from metasyncontrib.disclosure.constant import (
-    DisclosureConstant,
+from metasyncontrib.disclosure.continuous import DisclosureConstant
+from metasyncontrib.disclosure.datetime import (
     DisclosureDateConstant,
     DisclosureDateTimeConstant,
-    DisclosureDiscreteConstant,
-    DisclosureStringConstant,
     DisclosureTimeConstant,
 )
+from metasyncontrib.disclosure.discrete import DisclosureDiscreteConstant
+from metasyncontrib.disclosure.string import DisclosureStringConstant
 
 
 @mark.parametrize(

tests/test_other_dist.py

@@ -12,7 +12,7 @@
 
 from metasyncontrib.disclosure.categorical import DisclosureMultinoulli
 from metasyncontrib.disclosure.datetime import DisclosureDate, DisclosureDateTime, DisclosureTime
-from metasyncontrib.disclosure.faker import DisclosureFaker
+from metasyncontrib.disclosure.string import DisclosureFaker
 
 
 @mark.parametrize(