csv file time history

CITATION.md

@@ -11,7 +11,7 @@ A BibTeX entry for LaTeX users is
 ```TeX
 @misc{PyKED,
     author = {Kyle E Niemeyer and Bryan W Weber},
-    year = 2017,
+    year = 2018,
     title = {PyKED v0.4.1},
     doi = {10.5281/zenodo.597935},
     url = {https://github.com/pr-omethe-us/PyKED},

pyked/chemked.py

@@ -9,6 +9,9 @@
 import xml.etree.ElementTree as etree
 import xml.dom.minidom as minidom
 from itertools import chain
+from pathlib import Path
+from distutils.version import LooseVersion
+import sys
 
 import numpy as np
 
@@ -78,6 +81,15 @@
 Composition.amount.__doc__ = '(`~pint.Quantity`) The amount of this species'
 
 
+if LooseVersion(sys.version) < '3.6':
+    # Allow old version of python to open Path objects.
+    oldopen = open
+
+    def open(file, mode='r', buffering=-1, encoding=None, errors=None,
+             newline=None, closefd=True, opener=None):
+        return oldopen(str(file), mode, buffering, encoding, errors, newline, closefd, opener)
+
+
 class ChemKED(object):
     """Main ChemKED class.
 
@@ -109,6 +121,7 @@ class ChemKED(object):
     """
     def __init__(self, yaml_file=None, dict_input=None, *, skip_validation=False):
         if yaml_file is not None:
+            yaml_file = Path(yaml_file)
             with open(yaml_file, 'r') as f:
                 self._properties = yaml.safe_load(f)
         elif dict_input is not None:
@@ -121,6 +134,17 @@ def __init__(self, yaml_file=None, dict_input=None, *, skip_validation=False):
 
         self.datapoints = []
         for point in self._properties['datapoints']:
+            if 'time-histories' in point:
+                for th in point['time-histories']:
+                    try:
+                        filename = Path(th['values']['filename'])
+                    except TypeError:
+                        pass
+                    else:
+                        if yaml_file is not None:
+                            th['values']['filename'] = (yaml_file.parent / filename).resolve()
+                        else:
+                            th['values']['filename'] = filename.resolve()
             self.datapoints.append(DataPoint(point))
 
         self.reference = Reference(

pyked/tests/test_chemked.py

@@ -96,6 +96,27 @@ def test_missing_input(self, capfd):
         with pytest.raises(ValueError):
             ChemKED(dict_input=properties)
 
+    def test_csv_time_history(self):
+        file_path = os.path.join('testfile_rcm3.yaml')
+        filename = pkg_resources.resource_filename(__name__, file_path)
+        csv_filename = pkg_resources.resource_filename(__name__, 'rcm_history.csv')
+        from_file = ChemKED(filename)
+
+        with open(filename, 'r') as f:
+            properties = yaml.safe_load(f)
+        properties['datapoints'][0]['time-histories'][0]['values']['filename'] = csv_filename
+        from_dict = ChemKED(dict_input=properties)
+
+        for exp in [from_file, from_dict]:
+            exp_fname = exp._properties['datapoints'][0]['time-histories'][0]['values']['filename']
+            assert(str(exp_fname) == csv_filename)
+
+        # Test case where 'values' is a dict, but doesn't contain 'filename'
+        del properties['datapoints'][0]['time-histories'][0]['values']['filename']
+        with pytest.raises(NotImplementedError):
+            ChemKED(dict_input=properties)
+
+
 
 class TestDataFrameOutput(object):
     """

pyked/tests/test_validation.py

@@ -363,7 +363,7 @@ def properties(self, request):
 
     @pytest.mark.parametrize("properties", [
         'testfile_st.yaml', 'testfile_st2.yaml', 'testfile_rcm.yaml', 'testfile_required.yaml',
-        'testfile_uncertainty.yaml', 'testfile_rcm2.yaml',
+        'testfile_uncertainty.yaml', 'testfile_rcm2.yaml', 'testfile_rcm3.yaml'
     ], indirect=['properties'])
     def test_valid_yaml(self, properties):
         """Ensure ChemKED YAML is validated

pyked/tests/testfile_rcm3.yaml

@@ -0,0 +1,66 @@
+---
+file-authors:
+  - name: Kyle E Niemeyer
+    ORCID: 0000-0003-4425-7097
+file-version: 0
+chemked-version: 0.0.1
+reference:
+  doi: 10.1002/kin.20180
+  authors:
+    - name: Gaurav Mittal
+    - name: Chih-Jen Sung
+      ORCID: 0000-0003-2046-8076
+    - name: Richard A Yetter
+  journal: International Journal of Chemical Kinetics
+  year: 2006
+  volume: 38
+  pages: 516-529
+  detail: Fig. 6, open circle
+experiment-type: ignition delay
+apparatus:
+  kind: rapid compression machine
+  institution: Case Western Reserve University
+  facility: CWRU RCM
+datapoints:
+  - temperature:
+      - 297.4 kelvin
+    ignition-delay:
+      - 1.0 ms
+    pressure:
+      - 958.0 torr
+    composition:
+      kind: mole fraction
+      species:
+        - species-name: H2
+          InChI: 1S/H2/h1H
+          amount:
+            - 0.12500
+        - species-name: O2
+          InChI: 1S/O2/c1-2
+          amount:
+            - 0.06250
+        - species-name: N2
+          InChI: 1S/N2/c1-2
+          amount:
+            - 0.18125
+        - species-name: Ar
+          InChI: 1S/Ar
+          amount:
+            - 0.63125
+    ignition-type:
+      target: pressure
+      type: d/dt max
+    rcm-data:
+      compression-time:
+        - 38.0 ms
+    time-histories:
+      - type: volume
+        time:
+          units: s
+          column: 0
+        quantity:
+          units: cm3
+          column: 1
+        values:
+          filename: rcm_history.csv 
+...

pyked/validation.py

@@ -251,15 +251,21 @@ def _validate_isvalid_history(self, isvalid_history, field, value):
             self._error(field, 'incompatible units; should be consistent '
                         'with ' + property_units['time'])
 
-        # Check that the values have the right number of columns
-        n_cols = len(value['values'][0])
-        max_cols = max(value['time']['column'],
-                       value['quantity']['column'],
-                       value.get('uncertainty', {}).get('column', 0)) + 1
-        if n_cols > max_cols:
-            self._error(field, 'too many columns in the values')
-        elif n_cols < max_cols:
-            self._error(field, 'not enough columns in the values')
+        try:
+            if 'filename' not in value['values'].keys():
+                self._error(field, 'must include filename or list of values')
+            # If reading from a file, the file will not be validated.
+            # A file can have an arbitrary number of columns, and the columns
+            # to be used are specified.
+        except AttributeError:
+            n_cols = len(value['values'][0])
+            max_cols = max(value['time']['column'],
+                           value['quantity']['column'],
+                           value.get('uncertainty', {}).get('column', 0)) + 1
+            if n_cols > max_cols:
+                self._error(field, 'too many columns in the values')
+            elif n_cols < max_cols:
+                self._error(field, 'not enough columns in the values')
 
     def _validate_isvalid_quantity(self, isvalid_quantity, field, value):
         """Checks for valid given value and appropriate units.