Cache various statistics to improve performance

pyproject.toml

@@ -48,6 +48,7 @@ dependencies = [
   "matplotlib>=3.3",
   "numpy>=1.20",
   "pandas>=1.2",
+  "sortedcounter",
   "tqdm>=4.64.1",
 ]
 optional-dependencies.dev = [

src/data_morph/data/dataset.py

@@ -50,6 +50,9 @@ def __init__(
         self.df: pd.DataFrame = self._validate_data(df).pipe(self._scale_data, scale)
         """pandas.DataFrame: DataFrame containing columns x and y."""
 
+        self._x = self.df['x'].to_numpy()
+        self._y = self.df['y'].to_numpy()
+
         self.name: str = name
         """str: The name to use for the dataset."""