Fix categorical warnings and datetime dists (#20)

* Fix categorical warnings and datetime dists * Breaks backward compatibility --------- Co-authored-by: Raoul Schram <[email protected]>
sodascience · Dec 20, 2023 · cfdb407 · cfdb407
1 parent d73ff96
commit cfdb407
Show file tree

Hide file tree

Showing 4 changed files with 16 additions and 15 deletions.
diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
@@ -23,8 +23,8 @@ jobs:
         include:
           - metasyn-version: "git+https://github.com/sodascience/metasyn.git@main"
             python-version: "3.11"
-          - metasyn-version: "metasyn==0.6.0"
-            python-version: "3.11"
+          # - metasyn-version: "metasyn==0.6.0"
+            # python-version: "3.11"
 
     steps:
     - uses: actions/checkout@v2

diff --git a/metasyncontrib/disclosure/categorical.py b/metasyncontrib/disclosure/categorical.py
@@ -21,4 +21,5 @@ def _fit(cls, values: pl.Series, n_avg: int = 11):
         probs = dist.probs[dist.probs >= n_avg/len(values)]
         if len(probs) == 0 or probs.max() >= 0.9:
             return cls.default_distribution()
+        probs /= probs.sum()
         return cls(labels, probs)
diff --git a/metasyncontrib/disclosure/datetime.py b/metasyncontrib/disclosure/datetime.py
@@ -5,16 +5,16 @@
 
 import polars as pl
 
-from metasyn.distribution.datetime import UniformDateTimeDistribution
-from metasyn.distribution.datetime import UniformTimeDistribution
-from metasyn.distribution.datetime import UniformDateDistribution
+from metasyn.distribution.datetime import DateTimeUniformDistribution
+from metasyn.distribution.datetime import TimeUniformDistribution
+from metasyn.distribution.datetime import DateUniformDistribution
 # from metasyncontrib.disclosure.base import BaseDisclosureDistribution
 from metasyncontrib.disclosure.utils import micro_aggregate
 from metasyncontrib.disclosure.base import metadist_disclosure
 
 
 @metadist_disclosure()
-class DisclosureDateTime(UniformDateTimeDistribution):
+class DisclosureDateTime(DateTimeUniformDistribution):
     """Disclosure implementation for the datetime distribution."""
 
     @classmethod
@@ -24,7 +24,7 @@ def _fit(cls, values: pl.Series, n_avg: int = 11) -> DisclosureDateTime:
 
 
 @metadist_disclosure()
-class DisclosureTime(UniformTimeDistribution):
+class DisclosureTime(TimeUniformDistribution):
     """Disclosure implementation for the time distribution."""
 
     @classmethod
@@ -40,7 +40,7 @@ def _fit(cls, values: pl.Series, n_avg: int = 11):
 
 
 @metadist_disclosure()
-class DisclosureDate(UniformDateDistribution):
+class DisclosureDate(DateUniformDistribution):
     """Disclosure implementation for the date distribution."""
 
     @classmethod

diff --git a/tests/test_other_dist.py b/tests/test_other_dist.py
@@ -1,7 +1,7 @@
 import polars as pl
-from metasyn.distribution.datetime import UniformDateDistribution
-from metasyn.distribution.datetime import UniformDateTimeDistribution
-from metasyn.distribution.datetime import UniformTimeDistribution
+from metasyn.distribution.datetime import DateUniformDistribution
+from metasyn.distribution.datetime import DateTimeUniformDistribution
+from metasyn.distribution.datetime import TimeUniformDistribution
 from metasyncontrib.disclosure.datetime import DisclosureDate, DisclosureDateTime, DisclosureTime
 from pytest import mark
 from metasyn.distribution.categorical import MultinoulliDistribution
@@ -11,9 +11,9 @@
 
 @mark.parametrize(
     "class_norm,class_disc",
-    [(UniformDateDistribution, DisclosureDate),
-     (UniformDateTimeDistribution, DisclosureDateTime),
-     (UniformTimeDistribution, DisclosureTime)]
+    [(DateUniformDistribution, DisclosureDate),
+     (DateTimeUniformDistribution, DisclosureDateTime),
+     (TimeUniformDistribution, DisclosureTime)]
     )
 def test_datetime(class_norm, class_disc):
     dist_norm = class_norm.default_distribution()
@@ -22,7 +22,7 @@ def test_datetime(class_norm, class_disc):
     dist_disc = class_disc.fit(series)
     assert dist_norm.start < dist_disc.start
     assert dist_norm.end > dist_disc.end
-    if not isinstance(dist_norm, UniformDateDistribution):
+    if not isinstance(dist_norm, DateUniformDistribution):
         assert dist_norm.precision == dist_disc.precision