reciprocalspaceship 1.0.1__py3-none-any.whl → 1.0.2__py3-none-any.whl

reciprocalspaceship/VERSION

@@ -1 +1 @@
-1.0.1
+1.0.2

reciprocalspaceship/algorithms/scale_merged_intensities.py

@@ -185,6 +185,7 @@ def scale_merged_intensities(
     mean_intensity_method="isotropic",
     bins=100,
     bw=2.0,
+    minimum_sigma=-np.inf,
 ):
     """
     Scales merged intensities using Bayesian statistics in order to
@@ -240,6 +241,9 @@ def scale_merged_intensities(
         parameter controls the distance that each reflection impacts in
         reciprocal space. Only affects output if mean_intensity_method is
         \"anisotropic\".
+    minimum_sigma : float
+        Minimum value imposed on Sigma (default: -np.inf, that is: no minimum).
+
 
     Returns
     -------
@@ -281,14 +285,11 @@ def scale_merged_intensities(
     I, Sig = ds[intensity_key].to_numpy(), ds[sigma_key].to_numpy()
     if mean_intensity_method == "isotropic":
         dHKL = ds["dHKL"].to_numpy(dtype=np.float64)
-        Sigma = (
-            mean_intensity_by_resolution(I / multiplicity, dHKL, bins) * multiplicity
-        )
+        Sigma = mean_intensity_by_resolution(I / multiplicity, dHKL, bins)
     elif mean_intensity_method == "anisotropic":
-        Sigma = (
-            mean_intensity_by_miller_index(I / multiplicity, ds.get_hkls(), bw)
-            * multiplicity
-        )
+        Sigma = mean_intensity_by_miller_index(I / multiplicity, ds.get_hkls(), bw)
+    Sigma = np.clip(Sigma, a_min=minimum_sigma, a_max=np.inf)
+    Sigma = Sigma * multiplicity
 
     # Initialize outputs
     ds[outputI] = 0.0

reciprocalspaceship/dataset.py

@@ -1234,6 +1234,11 @@ class DataSet(pd.DataFrame):
         # Compute new HKLs and phase shifts
         hkls = dataset.get_hkls()
         compressed_hkls, inverse = np.unique(hkls, axis=0, return_inverse=True)
+
+        # The behavior of np.unique changed with v2.0. This block maintains v1 compatibility
+        if inverse.shape[-1] == 1:
+            inverse = inverse.squeeze(-1)
+
         asu_hkls, isym, phi_coeff, phi_shift = hkl_to_asu(
             compressed_hkls, dataset.spacegroup, return_phase_shifts=True
         )

reciprocalspaceship/decorators.py

@@ -100,7 +100,7 @@ def spacegroupify(func=None, *sg_args):
             for arg in sg_args:
                 if arg in bargs.arguments:
                     bargs.arguments[arg] = _convert_spacegroup(bargs.arguments[arg])
-            return f(**bargs.arguments)
+            return f(*bargs.args, **bargs.kwargs)
 
         return wrapped
 
@@ -155,7 +155,7 @@ def cellify(func=None, *cell_args):
             for arg in cell_args:
                 if arg in bargs.arguments:
                     bargs.arguments[arg] = _convert_unitcell(bargs.arguments[arg])
-            return f(**bargs.arguments)
+            return f(*bargs.args, **bargs.kwargs)
 
         return wrapped
 

reciprocalspaceship/dtypes/floating.py

@@ -34,7 +34,6 @@ from __future__ import annotations
 
 import numpy as np
 from pandas._libs import lib
-from pandas._libs import missing as libmissing
 from pandas._typing import ArrayLike, DtypeObj
 from pandas.util._decorators import cache_readonly
 
@@ -45,6 +44,7 @@ except:
 
 from pandas import Float32Dtype, Float64Dtype
 from pandas.core.arrays import ExtensionArray
+from pandas.core.dtypes.cast import np_find_common_type
 from pandas.core.dtypes.common import (
     is_bool_dtype,
     is_float,
@@ -58,7 +58,7 @@ from pandas.core.dtypes.dtypes import ExtensionDtype, register_extension_dtype
 from pandas.core.tools.numeric import to_numeric
 
 from reciprocalspaceship.dtypes.base import MTZDtype
-from reciprocalspaceship.dtypes.internals import NumericArray
+from reciprocalspaceship.dtypes.internals import NumericArray, is_numeric_na
 
 
 class MTZFloat32Dtype(MTZDtype):
@@ -80,14 +80,14 @@ class MTZFloat32Dtype(MTZDtype):
             return self
         if not all(isinstance(t, MTZFloat32Dtype) for t in dtypes):
             return None
-        np_dtype = np.find_common_type(
+        np_dtype = np_find_common_type(
             # error: Item "ExtensionDtype" of "Union[Any, ExtensionDtype]" has no
             # attribute "numpy_dtype"
             [t.numpy_dtype for t in dtypes],  # type: ignore[union-attr]
             [],
         )
         if np.issubdtype(np_dtype, np.floating):
-            return FLOAT_STR_TO_DTYPE[str(np_dtype)]
+            return Float32Dtype()
         return None
 
 
@@ -136,7 +136,11 @@ def coerce_to_array(
             mask = mask.copy()
         return values, mask
 
-    values = np.array(values, copy=copy)
+    if copy:
+        values = np.array(values, copy=copy)
+    else:
+        values = np.asarray(values)
+
     if is_object_dtype(values.dtype):
         inferred_type = lib.infer_dtype(values, skipna=True)
         if inferred_type == "empty":
@@ -160,7 +164,7 @@ def coerce_to_array(
         raise TypeError("values must be a 1D list-like")
 
     if mask is None:
-        mask = libmissing.is_numeric_na(values)
+        mask = is_numeric_na(values)
 
     else:
         assert len(mask) == len(values)
@@ -286,6 +290,20 @@ class MTZFloatArray(NumericArray):
     def _coerce_to_array(self, value) -> tuple[np.ndarray, np.ndarray]:
         return coerce_to_array(value, dtype=self.dtype)
 
+    def _maybe_mask_result(self, result, mask):
+        """
+        Parameters
+        ----------
+        result : array-like
+        mask : array-like bool
+        """
+        # if we have a float operand we are by-definition
+        # a float result
+        # or our op is a divide
+        if result.dtype.kind == "f":
+            return type(self)(result, mask, copy=False)
+        return super()._maybe_mask_result(result=result, mask=mask)
+
     def astype(self, dtype, copy: bool = True) -> ArrayLike:
         """
         Cast to a NumPy array or ExtensionArray with 'dtype'.
@@ -328,28 +346,6 @@ class MTZFloatArray(NumericArray):
         data = self.to_numpy(dtype=dtype, **kwargs)  # type: ignore[arg-type]
         return astype_nansafe(data, dtype, copy=False)
 
-    def _maybe_mask_result(self, result, mask, other, op_name: str):
-        """
-        Parameters
-        ----------
-        result : array-like
-        mask : array-like bool
-        other : scalar or array-like
-        op_name : str
-        """
-        # if we have a float operand we are by-definition
-        # a float result
-        # or our op is a divide
-        if (
-            (is_float_dtype(other) or is_float(other))
-            or (op_name in ["rtruediv", "truediv"])
-            or (is_float_dtype(self.dtype) and is_numeric_dtype(result.dtype))
-        ):
-            return type(self)(result, mask, copy=False)
-        return super()._maybe_mask_result(
-            result=result, mask=mask, other=other, op_name=op_name
-        )
-
     def _values_for_argsort(self) -> np.ndarray:
         return self._data
 

reciprocalspaceship/dtypes/integer.py

@@ -33,12 +33,12 @@
 from __future__ import annotations
 
 import numpy as np
-from pandas import Int32Dtype, Int64Dtype
+from pandas import Float32Dtype, Int32Dtype, Int64Dtype
 from pandas._libs import lib
-from pandas._libs import missing as libmissing
 from pandas._typing import ArrayLike, Dtype, DtypeObj
 from pandas.core.arrays import ExtensionArray
 from pandas.core.dtypes.base import ExtensionDtype, register_extension_dtype
+from pandas.core.dtypes.cast import np_find_common_type
 from pandas.core.dtypes.common import (
     is_bool_dtype,
     is_float_dtype,
@@ -51,7 +51,11 @@ from pandas.core.tools.numeric import to_numeric
 from pandas.util._decorators import cache_readonly
 
 from reciprocalspaceship.dtypes.base import MTZDtype
-from reciprocalspaceship.dtypes.internals import BaseMaskedDtype, NumericArray
+from reciprocalspaceship.dtypes.internals import (
+    BaseMaskedDtype,
+    NumericArray,
+    is_numeric_na,
+)
 
 
 class MTZInt32Dtype(MTZDtype):
@@ -88,25 +92,25 @@ class MTZInt32Dtype(MTZDtype):
             for t in dtypes
         ):
             return None
-        np_dtype = np.find_common_type(
+        np_dtype = np_find_common_type(
             # error: List comprehension has incompatible type List[Union[Any,
             # dtype, ExtensionDtype]]; expected List[Union[dtype, None, type,
             # _SupportsDtype, str, Tuple[Any, Union[int, Sequence[int]]],
             # List[Any], _DtypeDict, Tuple[Any, Any]]]
             [
-                t.numpy_dtype  # type: ignore[misc]
-                if isinstance(t, BaseMaskedDtype)
-                else t
+                (
+                    t.numpy_dtype  # type: ignore[misc]
+                    if isinstance(t, BaseMaskedDtype)
+                    else t
+                )
                 for t in dtypes
             ],
             [],
         )
         if np.issubdtype(np_dtype, np.integer):
-            return INT_STR_TO_DTYPE[str(np_dtype)]
+            return Int32Dtype()
         elif np.issubdtype(np_dtype, np.floating):
-            from pandas.core.arrays.floating import FLOAT_STR_TO_DTYPE
-
-            return FLOAT_STR_TO_DTYPE[str(np_dtype)]
+            return Float32Dtype()
         return None
 
 
@@ -175,7 +179,11 @@ def coerce_to_array(
             mask = mask.copy()
         return values, mask
 
-    values = np.array(values, copy=copy)
+    if copy:
+        values = np.array(values, copy=copy)
+    else:
+        values = np.asarray(values)
+
     inferred_type = None
     if is_object_dtype(values.dtype) or is_string_dtype(values.dtype):
         inferred_type = lib.infer_dtype(values, skipna=True)
@@ -202,7 +210,7 @@ def coerce_to_array(
         raise TypeError("values must be a 1D list-like")
 
     if mask is None:
-        mask = libmissing.is_numeric_na(values)
+        mask = is_numeric_na(values)
     else:
         assert len(mask) == len(values)
 
@@ -227,7 +235,12 @@ def coerce_to_array(
         # a ValueError if the str cannot be parsed into an int
         values = values.astype(dtype, copy=copy)
     else:
-        values = safe_cast(values, dtype, copy=False)
+        try:
+            values = safe_cast(values, dtype, copy=False)
+        except:
+            # certain outputs cannot be coerced to int32
+            dtype = np.dtype("float64")
+            values = safe_cast(values, dtype, copy=False)
 
     return values, mask
 
@@ -310,14 +323,6 @@ class MTZIntegerArray(NumericArray):
     def dtype(self) -> MTZInt32Dtype:
         return self._dtype
 
-    def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
-        if not (isinstance(values, np.ndarray) and values.dtype.kind in ["i", "u"]):
-            raise TypeError(
-                "values should be integer numpy array. Use "
-                "the 'pd.array' function instead"
-            )
-        super().__init__(values, mask, copy=copy)
-
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Dtype | None = None, copy: bool = False
@@ -335,6 +340,17 @@ class MTZIntegerArray(NumericArray):
     def _coerce_to_array(self, value) -> tuple[np.ndarray, np.ndarray]:
         return coerce_to_array(value, dtype=self.dtype)
 
+    def _maybe_mask_result(self, result, mask):
+        """
+        Parameters
+        ----------
+        result : array-like
+        mask : array-like bool
+        """
+        if result.dtype.kind in "iu":
+            return type(self)(result, mask, copy=False)
+        return super()._maybe_mask_result(result=result, mask=mask)
+
     def astype(self, dtype, copy: bool = True) -> ArrayLike:
         """
         Cast to a NumPy array or ExtensionArray with 'dtype'.
@@ -375,21 +391,6 @@ class MTZIntegerArray(NumericArray):
 
         return self.to_numpy(dtype=dtype, na_value=na_value, copy=False)
 
-    def _maybe_mask_result(self, result, mask, other, op_name: str):
-        """
-        Parameters
-        ----------
-        result : array-like
-        mask : array-like bool
-        other : scalar or array-like
-        op_name : str
-        """
-        if is_integer_dtype(result):
-            return type(self)(result, mask, copy=False)
-        return super()._maybe_mask_result(
-            result=result, mask=mask, other=other, op_name=op_name
-        )
-
     def _values_for_argsort(self) -> np.ndarray:
         """
         Return values for sorting.