orto 1.12.0__py3-none-any.whl → 1.13.0__py3-none-any.whl

orto/data.py

@@ -1,5 +1,6 @@
 import numpy as np
 from numpy.typing import NDArray, ArrayLike
+import pandas as pd
 
 from .exceptions import DataFormattingError
 from . import constants as const
@@ -188,11 +189,11 @@ class AbsorptionData():
     def from_extractor(cls, extractor: oe.AbsorptionExtractor,
                        remove_zero_osc: float = 1E-4) -> list['AbsorptionData']: # noqa
         '''
-        Creates AbsorptionData object from data extractor
+        Creates AbsorptionData object(s) from data extractor
 
         Parameters
         ----------
-        extractor: Extractor
+        extractor: oe.AbsorptionExtractor
             Data extractor object containing transition data
         remove_zero_osc: float, default=1E-4
             Remove transitions with oscillator strength below this value
@@ -220,7 +221,7 @@ class AbsorptionData():
                                operator: str,
                                remove_zero_osc: float = 1E-7) -> 'AbsorptionData': # noqa
         '''
-        Creates AbsorptionData object from data extractor
+        Creates AbsorptionData object(s) from data extractor
 
         Parameters
         ----------
@@ -458,3 +459,128 @@ class AbsorptionData():
             header=header,
             comments='#',
         )
+
+
+class SusceptibilityData():
+    '''
+    Stores magnetic susceptibility data
+
+    Parameters
+    ----------
+    chis: array_like
+        Susceptibility values in cm^3 K mol^-1
+    temperatures: array_like
+        Temperatures in K
+    field: float
+        Static magnetic field in Oe
+
+    Attributes
+    ----------
+    chis: ndarray of floats
+        Susceptibility values in cm^3 K mol^-1
+    temperature: ndarray of floats
+        Temperatures in K
+    field: float
+        Static magnetic field in Oe
+    '''
+
+    def __init__(self, chis: ArrayLike, temperatures: ArrayLike,
+                 field: float) -> None:
+        self.chis = chis
+        self.temperatures = temperatures
+        self.field = field
+        return
+
+    @property
+    def chis(self) -> NDArray:
+        '''Magnetic susceptibility values in cm^3 K mol^-1'''
+        return self._chis
+
+    @chis.setter
+    def chis(self, chis: ArrayLike) -> None:
+        self._chis = np.asarray(chis)
+        return
+
+    @property
+    def temperatures(self) -> NDArray:
+        '''Temperature values in K`'''
+        return self._temperatures
+
+    @temperatures.setter
+    def temperatures(self, temperatures: ArrayLike) -> None:
+        self._temperatures = np.asarray(temperatures)
+        return
+
+    @property
+    def field(self) -> float:
+        '''Static magnetic field in Oe'''
+        return self._field
+
+    @field.setter
+    def field(self, field: float) -> None:
+        self._field = float(field)
+        return
+
+    @classmethod
+    def from_extractor(cls, extractor: oe.AbsorptionExtractor) -> list['SusceptibilityData']: # noqa
+        '''
+        Creates SusceptibilityData object(s) from data extractor
+
+        Parameters
+        ----------
+        extractor: oe.SusceptibilityExtractor
+            Data extractor object containing susceptibility data
+
+        Returns
+        -------
+        list['SusceptibilityData']
+            SusceptibilityData objects, one for each section in extractor
+        '''
+
+        all_abs_data = [
+            cls.from_extractor_dataset(
+                dataset
+            )
+            for dataset in extractor.data
+        ]
+
+        return all_abs_data
+
+    @classmethod
+    def from_extractor_data(cls, data: list[pd.DataFrame]) -> list['SusceptibilityData']: # noqa
+        '''
+        Creates SusceptibilityData object(s) extractor.data attribute
+
+        Parameters
+        ----------
+        data: list[pd.DataFrame]
+            List of dataframes from orto SusceptibilityExtractor.data attribute
+
+        Returns
+        -------
+        list['SusceptibilityData']
+            SusceptibilityData objects, one for each dataframe in data
+        '''
+
+        all_data = []
+
+        # Generate a susceptibility data object for each dataframe
+        # and static field value
+        for dataset in data:
+            # Get unique fields and split indices
+            ufields, splindices = np.unique(
+                dataset['Static Field (Gauss)'],
+                return_index=True
+            )
+            splindices = list(splindices) + [len(dataset)]
+
+            for it, field in enumerate(ufields):
+                subdata = dataset[splindices[it]:splindices[it + 1]]
+
+                temperatures = subdata['Temperature (K)']
+                chis = subdata['chi*T (cm3*K/mol)'] / temperatures
+                all_data.append(
+                    cls(chis, temperatures, field)
+                )
+
+        return all_data

orto/extractor.py

@@ -17,6 +17,16 @@ from . import constants as const
 def EPRNMRDetector(file_name: str | pathlib.Path) -> bool:
     '''
     Detects if Orca output file contains an EPRNMR section
+
+    Parameters
+    ----------
+    file_name: str | pathlib.Path
+        File to parse
+
+    Returns
+    -------
+    bool
+        True if EPRNMR present, else False
     '''
     with open(file_name, 'rb') as f:
         file_content = f.read()
@@ -27,6 +37,30 @@ def EPRNMRDetector(file_name: str | pathlib.Path) -> bool:
         return False
 
 
+def NEVDetector(file_name: str | pathlib.Path) -> re.Match | None:
+    '''
+    Detects NEVPT2 section of output file
+
+    Parameters
+    ----------
+    file_name: str | pathlib.Path
+        File to parse
+
+    Returns
+    -------
+    re.Match | None
+        re Match object, or None if no match found
+    '''
+
+    with open(file_name, 'rb') as f:
+        file_content = f.read()
+
+    # Find line containing < NEVPT2  >
+    match = re.search(rb'< NEVPT2  >', file_content)
+
+    return match
+
+
 class OrcaVersionExtractor(extto.LineExtractor):
     '''
     Extracts Orca version from Orca output file
@@ -213,7 +247,8 @@ class SusceptibilityExtractor(extto.BetweenExtractor):
         return data
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[pd.DataFrame]:
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None, after: str = None) -> list[pd.DataFrame]:
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -222,6 +257,10 @@ class SusceptibilityExtractor(extto.BetweenExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -229,7 +268,7 @@ class SusceptibilityExtractor(extto.BetweenExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, before=before, after=after)
         return _ext.data
 
 
@@ -2676,7 +2715,9 @@ class GMatrixDFTExtractor(extto.BetweenExtractor):
         return data
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray]]: # noqa
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None,
+                after: str = None) -> list[dict[str, NDArray]]:
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -2685,6 +2726,10 @@ class GMatrixDFTExtractor(extto.BetweenExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -2692,7 +2737,7 @@ class GMatrixDFTExtractor(extto.BetweenExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, after=after, before=before)
         return _ext.data
 
 
@@ -2766,7 +2811,9 @@ class GMatrixExtractor(extto.BetweenExtractor):
         return data
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray]]: # noqa
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None,
+                after: str = None) -> list[dict[str, NDArray]]:
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -2775,6 +2822,10 @@ class GMatrixExtractor(extto.BetweenExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -2782,7 +2833,7 @@ class GMatrixExtractor(extto.BetweenExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, after=after, before=before)
         return _ext.data
 
 
@@ -2853,7 +2904,9 @@ class GMatrixEffectiveExtractor(GMatrixExtractor):
         return data
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray | int]]: # noqa
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None,
+                after: str = None) -> list[dict[str, NDArray | int]]:
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -2862,6 +2915,10 @@ class GMatrixEffectiveExtractor(GMatrixExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -2869,7 +2926,7 @@ class GMatrixEffectiveExtractor(GMatrixExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, after=after, before=before)
         return _ext.data
 
 
@@ -2962,7 +3019,9 @@ class SpinFreeEnergyExtractor(extto.BetweenExtractor):
         return data
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray]]: # noqa
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None,
+                after: str = None) -> list[dict[str, NDArray]]:
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -2971,6 +3030,10 @@ class SpinFreeEnergyExtractor(extto.BetweenExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -2978,7 +3041,7 @@ class SpinFreeEnergyExtractor(extto.BetweenExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, before=before, after=after)
         return _ext.data
 
 
@@ -3026,7 +3089,9 @@ class SpinOrbitEnergyExtractor(extto.BetweenExtractor):
         return result
 
     @classmethod
-    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray]]: # noqa
+    def extract(cls, file_name: str | pathlib.Path,
+                before: str = None,
+                after: str = None) -> list[dict[str, NDArray]]: # noqa
         '''
         Convenience method which instantiates class, extracts blocks, and
         returns processed datasets
@@ -3035,6 +3100,10 @@ class SpinOrbitEnergyExtractor(extto.BetweenExtractor):
         ----------
         file_name: str | pathlib.Path
             File to parse
+        before: str, default None
+            Only consider data before this string (first occurrence, exclusive)
+        after: str, default None
+            Only consider data after this string (first occurrence, inclusive)
 
         Returns
         -------
@@ -3042,5 +3111,5 @@ class SpinOrbitEnergyExtractor(extto.BetweenExtractor):
             Each entry contains processed data, as defined in cls.data
         '''
         _ext = cls()
-        _ext(file_name, process=True)
+        _ext(file_name, process=True, before=before, after=after)
         return _ext.data