Add AgeFractional logical type (#1112)

* Add AgeFractional logical type

* fix imports

* add release note

* pr comment

* update serialization schema

Author: tamargrey

docs/source/api_reference.rst

@@ -138,6 +138,7 @@ Logical Types
 
     Address
     Age
+    AgeFractional
     AgeNullable
     Boolean
     BooleanNullable

docs/source/guides/logical_types_and_semantic_tags.ipynb

@@ -174,14 +174,22 @@
     "\n",
     "##### Age\n",
     "\n",
-    "Represents Logical Types that contain non-negative numbers indicating a person’s age.\n",
+    "Represents Logical Types that contain whole numbers indicating a person’s age.\n",
     "\n",
     "- **physical type**: `int64`\n",
     "- **standard tags**: `{'numeric'}`\n",
     "\n",
+    "##### AgeFractional\n",
+    "\n",
+    "Represents Logical Types that contain non-negative floating point numbers indicating a person’s age. May contain null values.\n",
+    "\n",
+    "- **physical type**: `float64`\n",
+    "- **standard tags**: `{'numeric'}`\n",
+    "\n",
+    "\n",
     "##### AgeNullable\n",
     "\n",
-    "Represents Logical Types that contain non-negative numbers indicating a person’s age. May contain null values.\n",
+    "Represents Logical Types that contain whole numbers indicating a person’s age. May contain null values.\n",
     "\n",
     "- **physical type**: `Int64`\n",
     "- **standard tags**: `{'numeric'}`\n",

docs/source/guides/working_with_types_and_tags.ipynb

@@ -100,6 +100,9 @@
     "The standard tags are as follows:\n",
     "\n",
     "* `'numeric'` - The tag applied to numeric Logical Types.\n",
+    "    * `Age`\n",
+    "    * `AgeFractional`\n",
+    "    * `AgeNullable`\n",
     "    * `Integer`\n",
     "    * `IntegerNullable`\n",
     "    * `Double`\n",

docs/source/release_notes.rst

@@ -9,6 +9,7 @@ Future Release
         * Add ``'passthrough'`` and ``'ignore'`` to tags in ``list_semantic_tags`` (:pr:`1094`)
         * Add initialize with partial table schema  (:pr:`1100`)
         * Apply ordering specified by the ``Ordinal`` logical type to underlying series (:pr:`1097`)
+        * Add ``AgeFractional`` logical type (:pr:`1112`)
     * Fixes
     * Changes
     * Documentation Changes

woodwork/logical_types.py

@@ -74,7 +74,8 @@ class Address(LogicalType):
 
 
 class Age(LogicalType):
-    """Represents Logical Types that contain non-negative numbers indicating a person's age. Has 'numeric' as a standard tag.
+    """Represents Logical Types that contain whole numbers indicating a person's age.
+    Has 'numeric' as a standard tag.
 
     Examples:
         .. code-block:: python
@@ -86,8 +87,23 @@ class Age(LogicalType):
     standard_tags = {'numeric'}
 
 
+class AgeFractional(LogicalType):
+    """Represents Logical Types that contain non-negative floating point numbers indicating a person's age.
+    Has 'numeric' as a standard tag. May also contain null values.
+
+    Examples:
+        .. code-block:: python
+
+            [0.34, 24.34, 45.0]
+            [30.5, 62.82, np.nan]
+    """
+    primary_dtype = 'float64'
+    standard_tags = {'numeric'}
+
+
 class AgeNullable(LogicalType):
-    """Represents Logical Types that contain non-negative numbers indicating a person's age. Has 'numeric' as a standard tag. May also contain null values.
+    """Represents Logical Types that contain whole numbers indicating a person's age.
+    Has 'numeric' as a standard tag. May also contain null values.
 
     Examples:
         .. code-block:: python

woodwork/serialize.py

@@ -15,7 +15,7 @@
 )
 from woodwork.utils import _is_s3, _is_url
 
-SCHEMA_VERSION = '11.1.0'
+SCHEMA_VERSION = '11.1.1'
 FORMATS = ['csv', 'pickle', 'parquet', 'arrow', 'feather', 'orc']
 
 

woodwork/table_accessor.py

@@ -779,7 +779,7 @@ def mutual_information_dict(self, num_bins=10, nrows=None, include_index=False,
         """
         Calculates mutual information between all pairs of columns in the DataFrame that
         support mutual information. Logical Types that support mutual information are as
-        follows:  Age, AgeNullable, Boolean, BooleanNullable, Categorical, CountryCode, Datetime, Double,
+        follows:  Age, AgeFractional, AgeNullable, Boolean, BooleanNullable, Categorical, CountryCode, Datetime, Double,
         Integer, IntegerNullable, Ordinal, PostalCode, and SubRegionCode
 
         Args:
@@ -811,7 +811,7 @@ def mutual_information_dict(self, num_bins=10, nrows=None, include_index=False,
     def mutual_information(self, num_bins=10, nrows=None, include_index=False, callback=None):
         """Calculates mutual information between all pairs of columns in the DataFrame that
         support mutual information. Logical Types that support mutual information are as
-        follows:  Age, AgeNullable, Boolean, BooleanNullable, Categorical, CountryCode, Datetime, Double,
+        follows:  Age, AgeFractional, AgeNullable, Boolean, BooleanNullable, Categorical, CountryCode, Datetime, Double,
         Integer, IntegerNullable, Ordinal, PostalCode, and SubRegionCode
 
         Args:

woodwork/tests/accessor/test_statistics.py

@@ -10,6 +10,7 @@
 from woodwork.logical_types import (
     URL,
     Age,
+    AgeFractional,
     AgeNullable,
     Boolean,
     BooleanNullable,
@@ -291,7 +292,7 @@ def test_describe_accessor_method(describe_df):
     datetime_ltypes = [Datetime]
     formatted_datetime_ltypes = [Datetime(datetime_format='%Y~%m~%d')]
     timedelta_ltypes = [Timedelta]
-    nullable_numeric_ltypes = [Double, IntegerNullable, AgeNullable]
+    nullable_numeric_ltypes = [Double, IntegerNullable, AgeNullable, AgeFractional]
     non_nullable_numeric_ltypes = [Integer, Age]
     natural_language_ltypes = [EmailAddress, Filepath, PersonFullName, IPAddress,
                                PhoneNumber, URL]

woodwork/tests/accessor/test_table_accessor.py

@@ -26,6 +26,7 @@
     URL,
     Address,
     Age,
+    AgeFractional,
     AgeNullable,
     Boolean,
     BooleanNullable,
@@ -878,16 +879,17 @@ def test_sets_float64_dtype_on_init():
         pd.Series([1.1, np.nan, 3], name=column_name),
     ]
 
-    logical_type = Double
+    logical_types = [Double, AgeFractional]
     for series in series_list:
         series = series.astype('object')
-        ltypes = {
-            column_name: logical_type,
-        }
-        df = pd.DataFrame(series)
-        df.ww.init(logical_types=ltypes)
-        assert isinstance(df.ww.columns[column_name].logical_type, logical_type)
-        assert df[column_name].dtype == logical_type.primary_dtype
+        for logical_type in logical_types:
+            ltypes = {
+                column_name: logical_type,
+            }
+            df = pd.DataFrame(series)
+            df.ww.init(logical_types=ltypes)
+            assert isinstance(df.ww.columns[column_name].logical_type, logical_type)
+            assert df[column_name].dtype == logical_type.primary_dtype
 
 
 def test_sets_datetime64_dtype_on_init():

woodwork/tests/utils/test_utils.py

@@ -9,6 +9,7 @@
 import woodwork as ww
 from woodwork.logical_types import (
     Age,
+    AgeFractional,
     AgeNullable,
     Boolean,
     BooleanNullable,
@@ -383,6 +384,7 @@ def test_get_valid_mi_types():
     valid_types = get_valid_mi_types()
     expected_types = [
         Age,
+        AgeFractional,
         AgeNullable,
         Boolean,
         BooleanNullable,