replace hashable decorator with description class

Author: vorel99

src/ydata_profiling/model/pandas/describe_boolean_pandas.py

@@ -4,18 +4,14 @@
 
 from ydata_profiling.config import Settings
 from ydata_profiling.model.pandas.imbalance_pandas import column_imbalance_score
-from ydata_profiling.model.summary_algorithms import (
-    describe_boolean_1d,
-    series_hashable,
-)
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.summary_algorithms import describe_boolean_1d
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 
 
 @describe_boolean_1d.register
-@series_hashable
 def pandas_describe_boolean_1d(
-    config: Settings, series: pd.Series, summary: VarDescription
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    config: Settings, series: pd.Series, summary: VarDescriptionHashable
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe a boolean series.
 
     Args:

src/ydata_profiling/model/pandas/describe_categorical_pandas.py

@@ -14,9 +14,8 @@
     describe_categorical_1d,
     histogram_compute,
     series_handle_nulls,
-    series_hashable,
 )
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 
 
 def get_character_counts_vc(vc: pd.Series) -> pd.Series:
@@ -208,11 +207,10 @@ def length_summary_vc(vc: pd.Series) -> dict:
 
 
 @describe_categorical_1d.register
-@series_hashable
 @series_handle_nulls
 def pandas_describe_categorical_1d(
-    config: Settings, series: pd.Series, summary: VarDescription
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    config: Settings, series: pd.Series, summary: VarDescriptionHashable
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe a categorical series.
 
     Args:

src/ydata_profiling/model/pandas/describe_date_pandas.py

@@ -9,17 +9,15 @@
     describe_date_1d,
     histogram_compute,
     series_handle_nulls,
-    series_hashable,
 )
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 
 
 @describe_date_1d.register
-@series_hashable
 @series_handle_nulls
 def pandas_describe_date_1d(
-    config: Settings, series: pd.Series, summary: VarDescription
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    config: Settings, series: pd.Series, summary: VarDescriptionHashable
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe a date series.
 
     Args:

src/ydata_profiling/model/pandas/describe_numeric_pandas.py

@@ -3,7 +3,7 @@
 import numpy as np
 import pandas as pd
 
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 from ydata_profiling.utils.compat import pandas_version_info
 
 if pandas_version_info() >= (1, 5):
@@ -17,7 +17,6 @@
     describe_numeric_1d,
     histogram_compute,
     series_handle_nulls,
-    series_hashable,
 )
 
 
@@ -66,11 +65,10 @@ def numeric_stats_numpy(
 
 
 @describe_numeric_1d.register
-@series_hashable
 @series_handle_nulls
 def pandas_describe_numeric_1d(
-    config: Settings, series: pd.Series, summary: VarDescription
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    config: Settings, series: pd.Series, summary: VarDescriptionHashable
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe a numeric series.
 
     Args:

src/ydata_profiling/model/pandas/describe_supported_pandas.py

@@ -4,7 +4,7 @@
 
 from ydata_profiling.config import Settings
 from ydata_profiling.model.pandas.var_description.default_pandas import (
-    VarDescriptionPandas,
+    get_default_pandas_description,
 )
 from ydata_profiling.model.summary_algorithms import describe_supported
 from ydata_profiling.model.var_description.default import VarDescription
@@ -25,6 +25,6 @@ def pandas_describe_supported(
         A dict containing calculated series description values.
     """
 
-    series_description = VarDescriptionPandas(config, series, description)
+    series_description = get_default_pandas_description(config, series, description)
 
     return config, series, series_description

src/ydata_profiling/model/pandas/describe_text_pandas.py

@@ -12,19 +12,17 @@
     describe_text_1d,
     histogram_compute,
     series_handle_nulls,
-    series_hashable,
 )
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 
 
 @describe_text_1d.register
-@series_hashable
 @series_handle_nulls
 def pandas_describe_text_1d(
     config: Settings,
     series: pd.Series,
-    summary: VarDescription,
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    summary: VarDescriptionHashable,
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe string series.
 
     Args:

src/ydata_profiling/model/pandas/describe_timeseries_pandas.py

@@ -11,9 +11,8 @@
     describe_numeric_1d,
     describe_timeseries_1d,
     series_handle_nulls,
-    series_hashable,
 )
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import VarDescriptionHashable
 
 
 def stationarity_test(config: Settings, series: pd.Series) -> Tuple[bool, float]:
@@ -191,11 +190,10 @@ def compute_gap_stats(series: pd.Series) -> pd.Series:
 
 
 @describe_timeseries_1d.register
-@series_hashable
 @series_handle_nulls
 def pandas_describe_timeseries_1d(
-    config: Settings, series: pd.Series, summary: VarDescription
-) -> Tuple[Settings, pd.Series, VarDescription]:
+    config: Settings, series: pd.Series, summary: VarDescriptionHashable
+) -> Tuple[Settings, pd.Series, VarDescriptionHashable]:
     """Describe a timeseries.
 
     Args:

src/ydata_profiling/model/pandas/var_description/default_pandas.py

@@ -1,38 +1,77 @@
+from __future__ import annotations
+
 from dataclasses import dataclass
 
 import pandas as pd
 
 from ydata_profiling.config import Settings
 from ydata_profiling.model.pandas.var_description.counts_pandas import VarCountsPandas
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import (
+    VarDescription,
+    VarDescriptionHashable,
+)
 
 
 @dataclass
 class VarDescriptionPandas(VarDescription):
-    """Default description for pandas columns"""
+    """Default description for pandas columns."""
+
+    @classmethod
+    def from_var_counts(
+        cls, var_counts: VarCountsPandas, init_dict: dict
+    ) -> VarDescriptionPandas:
+        """Get a default description from a VarCountsPandas object."""
+        return VarDescriptionPandas(
+            n=var_counts.n,
+            count=var_counts.count,
+            n_missing=var_counts.n_missing,
+            p_missing=var_counts.p_missing,
+            hashable=var_counts.hashable,
+            memory_size=var_counts.memory_size,
+            ordering=var_counts.ordering,
+            value_counts_index_sorted=var_counts.value_counts_index_sorted,
+            value_counts_without_nan=var_counts.value_counts_without_nan,
+            var_specific=init_dict,
+        )
 
-    def __init__(self, config: Settings, series: pd.Series, init_dict: dict):
-        _var_counts = VarCountsPandas(config, series)
 
-        _count = _var_counts.count
-        value_counts = _var_counts.value_counts_without_nan
+@dataclass
+class VarDescriptionPandasHashable(VarDescriptionHashable):
+    """Default description for pandas columns that are hashable (common types)."""
+
+    @classmethod
+    def from_var_counts(
+        cls, var_counts: VarCountsPandas, init_dict: dict
+    ) -> VarDescriptionPandasHashable:
+        """Get a default description for a hashable column from a VarCountsPandas object."""
+        _count = var_counts.count
+        value_counts = var_counts.value_counts_without_nan
         distinct_count = len(value_counts)
         unique_count = value_counts.where(value_counts == 1).count()
 
-        super().__init__(
-            n=_var_counts.n,
-            count=_var_counts.count,
-            n_missing=_var_counts.n_missing,
-            p_missing=_var_counts.p_missing,
-            hashable=_var_counts.hashable,
-            memory_size=_var_counts.memory_size,
-            ordering=_var_counts.ordering,
-            value_counts_index_sorted=_var_counts.value_counts_index_sorted,
-            value_counts_without_nan=_var_counts.value_counts_without_nan,
+        return VarDescriptionPandasHashable(
+            n=var_counts.n,
+            count=var_counts.count,
+            n_missing=var_counts.n_missing,
+            p_missing=var_counts.p_missing,
+            hashable=var_counts.hashable,
+            memory_size=var_counts.memory_size,
+            ordering=var_counts.ordering,
+            value_counts_index_sorted=var_counts.value_counts_index_sorted,
+            value_counts_without_nan=var_counts.value_counts_without_nan,
             n_distinct=distinct_count,
             p_distinct=distinct_count / _count if _count > 0 else 0,
             is_unique=unique_count == _count and _count > 0,
             n_unique=unique_count,
             p_unique=unique_count / _count if _count > 0 else 0,
             var_specific=init_dict,
         )
+
+
+def get_default_pandas_description(
+    config: Settings, series: pd.Series, init_dict: dict
+) -> VarDescriptionPandas | VarDescriptionPandasHashable:
+    _var_counts = VarCountsPandas(config, series)
+    if _var_counts.hashable:
+        return VarDescriptionPandasHashable.from_var_counts(_var_counts, init_dict)
+    return VarDescriptionPandas.from_var_counts(_var_counts, init_dict)

src/ydata_profiling/model/var_description/default.py

@@ -12,16 +12,6 @@ class VarDescription(VarCounts):
     """Default description for one data column.
     Extends VarCounts class with information about distinct and unique values."""
 
-    n_distinct: int | list
-    """Number of distinct values"""
-    p_distinct: float | list
-    """Proportion of distinct values"""
-    is_unique: bool | list
-    """Whether the variable values are unique"""
-    n_unique: int | list
-    """Number of unique values"""
-    p_unique: float | list
-    """Proportion of unique values"""
     var_specific: dict
 
     def __getitem__(self, item: str):
@@ -47,3 +37,20 @@ def get(self, key: str, default: Any = None) -> Any:
     def __iter__(self) -> Iterator:
         """To support old dict like interface."""
         return self.var_specific.__iter__()
+
+
+@dataclass
+class VarDescriptionHashable(VarDescription):
+    """Default description for one data column that is hashable (common types).
+    Extends VarCounts class with information about distinct and unique values."""
+
+    n_distinct: int | list | None
+    """Number of distinct values"""
+    p_distinct: float | list | None
+    """Proportion of distinct values"""
+    is_unique: bool | list | None
+    """Whether the variable values are unique"""
+    n_unique: int | list | None
+    """Number of unique values"""
+    p_unique: float | list | None
+    """Proportion of unique values"""