mlsampler 0.3.3__tar.gz → 0.3.4__tar.gz

{mlsampler-0.3.3/src/mlsampler.egg-info → mlsampler-0.3.4}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: mlsampler
-Version: 0.3.3
-Summary: Flexible constrained random sampler for reverse analysis in machine learning
+Version: 0.3.4
+Summary: Flexible constrained random sampler for doe sampling or reverse analysis in machine learning
 Author: Jugai O
 License: LICENSE
 Requires-Python: >=3.11
@@ -9,6 +9,10 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy
 Requires-Dist: joblib
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: scipy; extra == "docs"
 Dynamic: license-file
 
 # RandomSampler

{mlsampler-0.3.3 → mlsampler-0.3.4}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mlsampler"
-version = "0.3.3"
-description = "Flexible constrained random sampler for reverse analysis in machine learning"
+version = "0.3.4"
+description = "Flexible constrained random sampler for doe sampling or reverse analysis in machine learning"
 authors = [
   { name="Jugai O" }
 ]
@@ -19,4 +19,7 @@ dependencies = [
 license = { text= "LICENSE" }
 
 [tool.setuptools.packages.find]
-where = ["src"]
+where = ["src"]
+
+[project.optional-dependencies]
+docs = ["sphinx", "sphinx-rtd-theme", "scipy"]

{mlsampler-0.3.3 → mlsampler-0.3.4}/src/mlsampler/constraints/constraints.py

@@ -165,6 +165,7 @@ class RangeConstraint(Constraints):
         super().__init__(cols, **kwargs)
         self.low = low
         self.high = high
+        v.validate_range(low, high)
 
     def _constrain(self, row: np.ndarray, rng: Optional[np.random.Generator] = None) -> np.ndarray:
         # No need to reset cols here
@@ -175,13 +176,20 @@ class RangeConstraint(Constraints):
 class StepConstraint(Constraints):
     def __init__(self, col:int, step: float, low: float, high: float,  **kwargs):
         super().__init__(cols=[col], **kwargs)
-        self.values = np.arange(low, high + step, step)
         self.col = col
+
+        n_steps = int(np.floor((high - low) / step))
+        self.values = low + np.arange(n_steps + 1) * step
+
+        self.low = low
+        self.high = high
         self.step = step
 
+        v.validate_range(low, high, step)
+
     def _constrain(
-            self, 
-            row: np.ndarray, 
+            self,
+            row: np.ndarray,
             rng: Optional[np.random.Generator] = None
         ) -> np.ndarray:
         rng = self._rng(rng)
@@ -246,7 +254,9 @@ class SumStepConstraint(StepConstraint):
             ]
             
             if not eligible_indices:
-                raise ConstraintViolationError("Target sum_value is unreachable within defined highs.")
+                raise ConstraintViolationError(
+                    "Target sum_value is unreachable within defined highs."
+                )
             
             target_idx = rng.choice(eligible_indices)
             current_values[target_idx] += self.step
@@ -274,4 +284,6 @@ class FunctionConstraint(Constraints):
             row[self.cols] = result
             return row
         else:
-            raise ConstraintTypeError("Constraint function must return either a boolean or a numpy array")
+            raise ConstraintTypeError(
+                "Constraint function must return either a boolean or a numpy array"
+            )

{mlsampler-0.3.3 → mlsampler-0.3.4}/src/mlsampler/engine/hypergrid.py

@@ -1,9 +1,12 @@
 import numpy as np
 from typing import Optional
-from scipy.stats import qmc
 from ..base import BaseSampler, DtypeMeta as dm
 from ..errors import ConstraintViolationError
 from ..terminals import spinning
+try:
+    from scipy.stats import qmc
+except:
+    qmc = None
 
 class HyperGridSampler(BaseSampler):
     """
@@ -47,10 +50,14 @@ class HyperGridSampler(BaseSampler):
 
     def _lhs(self, n_samples: int, float_features: list):
         """LHS sampling for float columns"""
+        if qmc is None:
+            raise ImportError("scipy is required for HyperGridSampler")
+        
         if not float_features:
             return np.empty((n_samples, 0))
 
         dim = len(float_features)
+        
         sampler = qmc.LatinHypercube(d=dim, seed=self.config.random_state)
         sample = sampler.random(n=n_samples)
 
@@ -82,32 +89,6 @@ class HyperGridSampler(BaseSampler):
         return np.column_stack(cols) if cols else np.empty((n_samples, 0))
 
     def _sample(self, n_samples: int) -> np.ndarray:
-        """
-        Generate samples based on feature data types.
-
-        Continuous features are sampled using Latin Hypercube Sampling (LHS),
-        while discrete features (e.g., "int", "binary", "categorical", "constant") are
-        sampled using uniform random selection over their respective value spaces.
-
-        Parameters
-        ----------
-        n_samples : int
-            Total number of samples to generate.
-
-        Returns
-        -------
-        np.ndarray
-            Array of shape (n_samples, n_features) containing the generated samples.
-            The column order matches the input feature configuration.
-
-        Notes
-        -----
-        - Float features are scaled to their respective [low, high] ranges.
-        - Integer features are sampled from the inclusive range [low, high].
-        - Categorical features are sampled from the provided category list.
-        - Constant features return the same value for all samples.
-        """
-
         float_feats = [f for f in self.config.features if f.dtype == dm.float]
         discrete_feats = [f for f in self.config.features if f.dtype != dm.float]
 
@@ -130,6 +111,26 @@ class HyperGridSampler(BaseSampler):
         return result
 
     def sample(self, n_samples: int) -> np.ndarray:
+        """
+        Parameters
+        ----------
+        n_samples : int
+            Total number of samples to generate.
+
+        Returns
+        -------
+        np.ndarray
+            Array of shape (n_samples, n_features) containing the generated samples.
+            The column order matches the input feature configuration.
+
+        Notes
+        -----
+        - Float features are scaled to their respective [low, high] ranges.
+        - Integer features are sampled from the inclusive range [low, high].
+        - Categorical features are sampled from the provided category list.
+        - Constant features return the same value for all samples.
+        """
+        
         with spinning():
             samples = self._sample(n_samples)
         return samples

{mlsampler-0.3.3 → mlsampler-0.3.4}/src/mlsampler/validate.py

@@ -35,7 +35,7 @@ def validate_values(value: Numeric):
     if value < 0:
         warnings.warn("Value should be non-negative", ConstraintWarning)
         
-def validate_range(low: Numeric, high: Numeric):
+def validate_range(low: Numeric, high: Numeric, step: Numeric = 0):
     if not isinstance(low, Numeric):
         raise ConstraintTypeError("low must be a numeric")
     
@@ -45,4 +45,6 @@ def validate_range(low: Numeric, high: Numeric):
     if low > high:
         raise ConstraintValidationError("low must be <= high")
     
+    if step < 0:
+        raise ConstraintValidationError("step must be non-negative")
         

{mlsampler-0.3.3 → mlsampler-0.3.4/src/mlsampler.egg-info}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: mlsampler
-Version: 0.3.3
-Summary: Flexible constrained random sampler for reverse analysis in machine learning
+Version: 0.3.4
+Summary: Flexible constrained random sampler for doe sampling or reverse analysis in machine learning
 Author: Jugai O
 License: LICENSE
 Requires-Python: >=3.11
@@ -9,6 +9,10 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy
 Requires-Dist: joblib
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: scipy; extra == "docs"
 Dynamic: license-file
 
 # RandomSampler

mlsampler-0.3.4/src/mlsampler.egg-info/requires.txt

@@ -0,0 +1,7 @@
+numpy
+joblib
+
+[docs]
+sphinx
+sphinx-rtd-theme
+scipy

mlsampler-0.3.3/src/mlsampler.egg-info/requires.txt

@@ -1,2 +0,0 @@
-numpy
-joblib