Merge pull request #10 from FAIRmat-NFDI/add_NVRS_schema

Add nvrs and IR schema

pyproject.toml

@@ -74,7 +74,7 @@ select = [
     "UP",
     # isort
     "I",
-    # pylint 
+    # pylint
     "PL",
 ]
 

src/nomad_unisyscat/schema_packages/mypackage.py

@@ -1,19 +1,20 @@
+import os
 from typing import (
     TYPE_CHECKING,
 )
 
+import numpy as np
+
 if TYPE_CHECKING:
-    from nomad.datamodel.datamodel import (
-        EntryArchive,
-    )
-    from structlog.stdlib import (
-        BoundLogger,
-    )
+    pass
 
+import plotly.express as px
 from nomad.config import config
 from nomad.datamodel.data import Schema
-from nomad.datamodel.metainfo.annotations import ELNAnnotation, ELNComponentEnum
-from nomad.metainfo import Quantity, SchemaPackage
+from nomad.datamodel.metainfo.annotations import ELNAnnotation
+from nomad.datamodel.metainfo.basesections import Measurement, MeasurementResult
+from nomad.datamodel.metainfo.plot import PlotlyFigure, PlotSection
+from nomad.metainfo import Quantity, SchemaPackage, Section
 
 configuration = config.get_plugin_entry_point(
     'nomad_unisyscat.schema_packages:mypackage'
@@ -22,17 +23,194 @@
 m_package = SchemaPackage()
 
 
-class MySchema(Schema):
-    name = Quantity(
-        type=str, a_eln=ELNAnnotation(component=ELNComponentEnum.StringEditQuantity)
+class NRVSResult(MeasurementResult):
+    m_def = Section()
+
+    array_index = Quantity(
+        type=np.float64,
+        shape=['*'],
+        description=(
+            'A placeholder for the indices of vectorial quantities. '
+            'Used as x-axis for plots within quantities.'
+        ),
+        a_display={'visible': False},
+    )
+    intensity = Quantity(
+        type=np.float64,
+        shape=['*'],
+        unit='dimensionless',
+        description='The 57Fe PVDOS count at each wavenumber value, dimensionless',
+        a_plot={'x': 'array_index', 'y': 'intensity'},
+    )
+    wavenumber = Quantity(
+        type=np.float64,
+        shape=['*'],
+        unit='1/cm',
+        description='The wavenumber range of the spectrum',
+        a_eln=ELNAnnotation(defaultDisplayUnit='1/cm'),
+        a_plot={'x': 'array_index', 'y': 'wavenumber'},
+    )
+
+
+class NRVSpectroscopy(Measurement, PlotSection, Schema):
+    measurement_data_file = Quantity(
+        type=str,
+        description="""
+            experimental tab data file
+            """,
+        a_eln=ELNAnnotation(component='FileEditQuantity'),
+        a_browser=dict(adaptor='RawFileAdaptor'),
     )
-    message = Quantity(type=str)
 
-    def normalize(self, archive: 'EntryArchive', logger: 'BoundLogger') -> None:
+    # simulation_data_file = Quantity(
+    #     type=str,
+    #     description="""
+    #         simulated tab data file
+    #         """,
+    #     a_eln=dict(component='FileEditQuantity'),
+    #     a_browser=dict(adaptor='RawFileAdaptor')
+    # )
+
+    method = Quantity(
+        type=str,
+        description="""
+            name of the method
+            """,
+        a_eln=ELNAnnotation(
+            component='StringEditQuantity',
+            default='nuclear resonance vibrational spectroscopy',
+            props=dict(
+                suggestions=[
+                    'experimental nuclear resonance vibrational spectroscopy',
+                    'simulated nuclear resonance vibrational spectroscopy',
+                ]
+            ),
+        ),
+    )
+
+    results = Measurement.results.m_copy()
+    results.section_def = NRVSResult
+
+    def normalize(self, archive, logger):
         super().normalize(archive, logger)
+        if self.measurement_data_file is None:
+            return
+
+        if (self.measurement_data_file is not None) and (
+            os.path.splitext(self.measurement_data_file)[-1] != '.dat'
+        ):
+            raise ValueError('Unsupported file format. Only .dat file')
+
+        if self.measurement_data_file.endswith('.dat'):
+            with archive.m_context.raw_file(self.measurement_data_file) as f:
+                import pandas as pd
+
+                col_names = ['wavenumber, cm-1', '57Fe PVDOS']
+                data = pd.read_csv(f.name, header=None, names=col_names)
+        result = NRVSResult()
+        result.wavenumber = data['wavenumber, cm-1']
+        result.intensity = data['57Fe PVDOS']
+        results = []
+        results.append(result)
+        self.results = results
+
+        self.figures = []
+
+        fig = px.line(x=data['wavenumber, cm-1'], y=data['57Fe PVDOS'])
+        fig.update_xaxes(title_text=col_names[0])
+        fig.update_yaxes(title_text=col_names[1])
+        self.figures.append(PlotlyFigure(label='NRVS', figure=fig.to_plotly_json()))
+
+
+class IRResult(MeasurementResult):
+    m_def = Section()
+
+    array_index = Quantity(
+        type=np.float64,
+        shape=['*'],
+        description=(
+            'A placeholder for the indices of vectorial quantities. '
+            'Used as x-axis for plots within quantities.'
+        ),
+        a_display={'visible': False},
+    )
+    intensity = Quantity(
+        type=np.float64,
+        shape=['*'],
+        unit='dimensionless',
+        description='The absorbance at each wavenumber value, dimensionless',
+        a_plot={'x': 'array_index', 'y': 'intensity'},
+    )
+    wavenumber = Quantity(
+        type=np.float64,
+        shape=['*'],
+        unit='1/cm',
+        description='The wavenumber range of the spectrum',
+        a_eln=ELNAnnotation(defaultDisplayUnit='1/cm'),
+        a_plot={'x': 'array_index', 'y': 'wavenumber'},
+    )
+
+
+class IRSpectroscopy(Measurement, PlotSection, Schema):
+    data_file = Quantity(
+        type=str,
+        description="""
+            csv data file ending .dat
+            """,
+        a_eln=ELNAnnotation(component='FileEditQuantity'),
+        a_browser=dict(adaptor='RawFileAdaptor'),
+    )
+
+    method = Quantity(
+        type=str,
+        description="""
+            name of the method
+            """,
+        a_eln=ELNAnnotation(
+            component='StringEditQuantity',
+            default='infra red vibrational spectroscopy',
+            props=dict(
+                suggestions=[
+                    'experimental IR vibrational spectroscopy',
+                    'simulated IR vibrational spectroscopy',
+                ]
+            ),
+        ),
+    )
+
+    results = Measurement.results.m_copy()
+    results.section_def = IRResult
+
+    def normalize(self, archive, logger):
+        super().normalize(archive, logger)
+        if self.data_file is None:
+            return
+
+        if (self.data_file is not None) and (
+            os.path.splitext(self.data_file)[-1] != '.dat'
+        ):
+            raise ValueError('Unsupported file format. Only .dat file')
+
+        if self.data_file.endswith('.dat'):
+            with archive.m_context.raw_file(self.data_file) as f:
+                import pandas as pd
+
+                col_names = ['wavenumber, cm-1', 'Absorbance']
+                data = pd.read_csv(f.name, header=None, names=col_names)
+
+        result = IRResult()
+        result.wavenumber = data['wavenumber, cm-1']
+        result.intensity = data['Absorbance']
+        results = []
+        results.append(result)
+        self.results = results
+
+        self.figures = []
 
-        logger.info('MySchema.normalize', parameter=configuration.parameter)
-        self.message = f'Hello {self.name}!'
+        fig = px.line(x=data['wavenumber, cm-1'], y=data['Absorbance'])
+        fig.update_xaxes(title_text=col_names[0])
+        fig.update_yaxes(title_text=col_names[1])
+        self.figures.append(PlotlyFigure(label='IR', figure=fig.to_plotly_json()))
 
 
 m_package.__init_metainfo__()

tests/data/ir_test.archive.yaml

@@ -0,0 +1,3 @@
+data:
+  m_def: nomad_unisyscat.schema_packages.mypackage.IRSpectroscopy
+  data_file: ReRH_Nia-C_H_IR_exp.dat

tests/data/nrvs_test.archive.yaml

@@ -0,0 +1,3 @@
+data:
+  m_def: nomad_unisyscat.schema_packages.mypackage.NRVSpectroscopy
+  measurement_data_file: ReRH_Nia-C_H_NRVS_exp.dat

tests/schema_packages/test_schema.py

@@ -3,9 +3,9 @@
 from nomad.client import normalize_all, parse
 
 
-def test_schema():
-    test_file = os.path.join('tests', 'data', 'test.archive.yaml')
+def test_ir_schema():
+    test_file = os.path.join('tests', 'data', 'ir_test.archive.yaml')
     entry_archive = parse(test_file)[0]
     normalize_all(entry_archive)
 
-    assert entry_archive.data.message == 'Hello Markus!'
+    assert entry_archive.data.results[0].wavenumber is not None