adapt species data

FAIRChemistry · Mar 4, 2024 · 5006171 · 5006171
1 parent a31a446
commit 5006171
Show file tree

Hide file tree

Showing 6 changed files with 233 additions and 87 deletions.
diff --git a/FAIRFlowChemistry/core/calibration.py b/FAIRFlowChemistry/core/calibration.py
@@ -1,4 +1,5 @@
 import sdRDM
+import numpy as np
 
 from typing import Dict, List, Optional
 from pydantic import PrivateAttr, model_validator
@@ -67,3 +68,25 @@ def _parse_raw_xml_data(self):
             elif isinstance(value, _Element):
                 self._raw_xml_data[attr] = elem2dict(value)
         return self
+
+    def calibrate(self):
+        """
+        Calibrate the regression model on seen data
+        """
+
+        self.regression_coefficients = np.polynomial.polynomial.polyfit(
+            self.peak_areas.values, self.concentrations.values, self.degree
+        ).tolist()
+
+    def predict(self, x: list) -> np.ndarray:
+        """
+        Predict with regression model
+
+        Args:
+            x (1D list): New locations for which predictions should be made
+
+        Returns:
+           (1D numpy array): Predicted data at new locations
+        """
+
+        return np.polynomial.Polynomial(self.regression_coefficients)(np.array(x))
diff --git a/FAIRFlowChemistry/core/experiment.py b/FAIRFlowChemistry/core/experiment.py
@@ -1,4 +1,5 @@
 import sdRDM
+import pandas as pd
 
 from typing import Dict, List, Optional
 from pydantic import PrivateAttr, model_validator
@@ -16,7 +17,8 @@
 from .plantsetup import PlantSetup
 from .metadata import Metadata
 from .calibration import Calibration
-
+from .quantity import Quantity
+from .datatype import DataType
 
 @forge_signature
 class Experiment(sdRDM.DataModel):
@@ -133,3 +135,37 @@ def add_to_species_data(
             params["id"] = id
         self.species_data.append(SpeciesData(**params))
         return self.species_data[-1]
+
+    @property
+    def volumetric_flow_time_course(self) -> list:
+        """This property extracts the volumetric flow time as well as the flow it self from the experiment class
+
+        Returns:
+            list: Datetime list and flow value list
+        """
+        volumetric_flow_datetime_list = []
+        volumetric_flow_values_list = []
+
+        mfm_measurements = self.get(
+            "measurements", "measurement_type", "MFM measurement"
+        )[0]
+        for mfm_measurement in mfm_measurements:
+            volumetric_flow_datetime_list.extend(
+                mfm_measurement.get(
+                    "experimental_data", "quantity", Quantity.DATETIME.value
+                )[0][0].values
+            )
+            volumetric_flow_values_list.extend(
+                mfm_measurement.get(
+                    "experimental_data", "quantity", Quantity.VOLUMETRICFLOWRATE.value
+                )[0][0].values
+            )
+
+        # If data is directly read in from the experiment, it is the correct format, if read from json dataset, it is a string and needs to be converted
+        if not type(volumetric_flow_datetime_list[0]) == DataType.DATETIME.value:
+            volumetric_flow_datetime_list = [
+                pd.to_datetime(timestamp, format="%Y-%m-%dT%H:%M:%S").to_pydatetime()
+                for timestamp in volumetric_flow_datetime_list
+            ]
+
+        return [volumetric_flow_datetime_list, volumetric_flow_values_list]
diff --git a/FAIRFlowChemistry/tools/reader.py b/FAIRFlowChemistry/tools/reader.py
@@ -14,6 +14,8 @@
 from FAIRFlowChemistry.core import ComponentType
 
 
+
+
 def gc_parser(metadata_path: Path, experimental_data_path: Path):
     """
     Function that reads in a file from a gas chromotography. Important information that is extracted is the

diff --git a/Main.ipynb b/Main.ipynb
@@ -139,111 +139,196 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 14,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "YAML Output:\n",
-      "Carbon dioxide:\n",
-      "  chemical_formula: CO2\n",
-      "  concentrations:\n",
-      "  - 0\n",
-      "  - 50\n",
-      "  peak_areas:\n",
-      "  - 0\n",
-      "  - 38653\n",
-      "Carbon monoxide:\n",
-      "  chemical_formula: CO\n",
-      "  concentrations:\n",
-      "  - 0.5\n",
-      "  - 1\n",
-      "  - 5\n",
-      "  peak_areas:\n",
-      "  - 797\n",
-      "  - 1328\n",
-      "  - 7223\n",
-      "Ethane:\n",
-      "  chemical_formula: C2H6\n",
-      "  concentrations:\n",
-      "  - 0\n",
-      "  - 5\n",
-      "  peak_areas:\n",
-      "  - 0\n",
-      "  - 12168\n",
-      "Ethene:\n",
-      "  chemical_formula: C2H4\n",
-      "  concentrations:\n",
-      "  - 0.5\n",
-      "  - 2\n",
-      "  - 3\n",
-      "  peak_areas:\n",
-      "  - 1122\n",
-      "  - 4864\n",
-      "  - 7297\n",
-      "Hydrogen:\n",
-      "  chemical_formula: H2\n",
-      "  concentrations:\n",
-      "  - 5\n",
-      "  - 10\n",
-      "  - 20\n",
-      "  peak_areas:\n",
-      "  - 71\n",
-      "  - 153\n",
-      "  - 330\n",
-      "Methane:\n",
-      "  chemical_formula: CH4\n",
-      "  concentrations:\n",
-      "  - 5\n",
-      "  - 10\n",
-      "  peak_areas:\n",
-      "  - 5727\n",
-      "  - 11991\n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "## Change initalizing species data!"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'Hydrogen': {'chemical_formula': 'H2',\n",
-       "  'peak_areas': [71, 153, 330],\n",
-       "  'concentrations': [5, 10, 20]},\n",
+       "{'Carbon dioxide': {'chemical_formula': 'CO2',\n",
+       "  'calibration': {'concentrations': [0, 50], 'peak_areas': [0, 38653]},\n",
+       "  'correction_factor': 0.74,\n",
+       "  'electron_transfer': 2},\n",
        " 'Carbon monoxide': {'chemical_formula': 'CO',\n",
-       "  'peak_areas': [797, 1328, 7223],\n",
-       "  'concentrations': [0.5, 1, 5]},\n",
-       " 'Carbon dioxide': {'chemical_formula': 'CO2',\n",
-       "  'peak_areas': [0, 38653],\n",
-       "  'concentrations': [0, 50]},\n",
-       " 'Methane': {'chemical_formula': 'CH4',\n",
-       "  'peak_areas': [5727, 11991],\n",
-       "  'concentrations': [5, 10]},\n",
-       " 'Ethene': {'chemical_formula': 'C2H4',\n",
-       "  'peak_areas': [1122, 4864, 7297],\n",
-       "  'concentrations': [0.5, 2, 3]},\n",
+       "  'calibration': {'concentrations': [0.5, 1, 5],\n",
+       "   'peak_areas': [797, 1328, 7223]},\n",
+       "  'correction_factor': 1.0,\n",
+       "  'electron_transfer': 2},\n",
+       " 'Hydrogen': {'chemical_formula': 'H2',\n",
+       "  'calibration': {'concentrations': [5, 10, 20], 'peak_areas': [71, 153, 330]},\n",
+       "  'correction_factor': 1.01,\n",
+       "  'electron_transfer': 2},\n",
        " 'Ethane': {'chemical_formula': 'C2H6',\n",
-       "  'peak_areas': [0, 12168],\n",
-       "  'concentrations': [0, 5]}}"
+       "  'calibration': {'concentrations': [0, 5], 'peak_areas': [0, 12168]},\n",
+       "  'correction_factor': None,\n",
+       "  'electron_transfer': 16},\n",
+       " 'Ethene': {'chemical_formula': 'C2H4',\n",
+       "  'calibration': {'concentrations': [0.5, 2, 3],\n",
+       "   'peak_areas': [1122, 4864, 7297]},\n",
+       "  'correction_factor': None,\n",
+       "  'electron_transfer': 12},\n",
+       " 'Methane': {'chemical_formula': 'CH4',\n",
+       "  'calibration': {'concentrations': [5, 10], 'peak_areas': [5727, 11991]},\n",
+       "  'correction_factor': 0.76,\n",
+       "  'electron_transfer': 8}}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "json_data"
+    "import yaml\n",
+    "from FAIRFlowChemistry.core import Calibration, Data, Quantity, Experiment\n",
+    "\n",
+    "\n",
+    "with open(\"data/additional_data/species_data.yaml\") as f:\n",
+    "    species_data = yaml.safe_load(f)\n",
+    "species_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test = Experiment()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = bcef0a33-0954-40e8-84ce-812c2aa34286\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 6dbccfbd-2c00-478e-89d9-f17a37cdad92\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.0, 38653.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 7824671b-6ad3-48e5-a08e-75fda85486bd\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.0, 50.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [-4.466559424312742e-15, 0.0012935606550591155, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n",
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = 66c51884-1dae-451e-b103-e6825139a3d4\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 23ce97b3-17cc-461d-9611-007fb871847e\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [797.0, 1328.0, 7223.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = aac491a0-c4f5-4089-bb3b-e6da4fa87d5b\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.5, 1.0, 5.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [0.012656829292048657, 0.0006912740171292097, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n",
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = abcb5f13-bdc7-4184-81e3-72f43d209ba1\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = cf425f61-3655-40af-a425-e6b1d50b70df\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [71.0, 153.0, 330.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 0531cb42-b9e1-4065-a1cf-2e564f28084a\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [5.0, 10.0, 20.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [1.0135636425894583, 0.05768828352388381, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n",
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = 94115cf4-c6d5-4756-997c-e431378b28ac\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 41a4c0e7-46f6-4102-b790-54d8ef169a1c\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.0, 12168.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = e6ae0432-d07f-4d02-b56b-265045b8404e\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.0, 5.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [3.146078039972546e-16, 0.0004109138724523339, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n",
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = 683a26eb-79bc-4c6c-837f-617cb7f3577a\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = d894b18d-c1f7-4920-8553-64de6277e082\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [1122.0, 4864.0, 7297.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = 05af66ef-32ce-4a6e-86c7-d7e7353401ad\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [0.5, 2.0, 3.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [0.04225127219798618, 0.0004045205287514898, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n",
+      "\u001b[4mCalibration\u001b[0m\n",
+      "├── \u001b[94mid\u001b[0m = 98bc4c48-7644-4fbd-bd1f-ef2092ca2a5e\n",
+      "├── \u001b[94mpeak_areas\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = a30301a1-a5fc-4c40-9e05-1448cb73baf5\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Peak area\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [5727.0, 11991.0, ...]\n",
+      "├── \u001b[94mconcentrations\u001b[0m\n",
+      "│   └── \u001b[4mData\u001b[0m\n",
+      "│       ├── \u001b[94mid\u001b[0m = d38f9ca7-29bf-4547-a6d7-6899d29a4d33\n",
+      "│       ├── \u001b[94mquantity\u001b[0m = Concentration\n",
+      "│       └── \u001b[94mvalues\u001b[0m = [5.0, 10.0, ...]\n",
+      "├── \u001b[94mregression_coefficients\u001b[0m = [0.4286398467432958, 0.0007982120051085568, ...]\n",
+      "└── \u001b[94mdegree\u001b[0m = 1\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "for species,item in species_data.items():\n",
+    "\n",
+    "    # Create Calibration object and fit it to the given data\n",
+    "    calibration = Calibration(\n",
+    "        peak_areas=Data(\n",
+    "            quantity=\"Peak area\", values=item[\"calibration\"][\"peak_areas\"]\n",
+    "        ),\n",
+    "        concentrations=Data(\n",
+    "            quantity=Quantity.CONCENTRATION.value,\n",
+    "            values=item[\"calibration\"][\"concentrations\"],\n",
+    "        ),\n",
+    "    )\n",
+    "    calibration.calibrate()\n",
+    "    \n",
+    "    test.add_to_species_data( species = species, \n",
+    "                              chemical_formula = item[\"chemical_formula\"],\n",
+    "                              calibration = calibration,\n",
+    "                              correction_factor = item[\"correction_factor\"],\n",
+    "                              electron_transfer = item[\"electron_transfer\"]\n",
+    "                               )"
    ]
   },
   {

diff --git a/...additional_data/specific_information.yaml → data/additional_data/species_data.yaml b/...additional_data/specific_information.yaml → data/additional_data/species_data.yaml
diff --git a/specifications/datamodel.md b/specifications/datamodel.md
@@ -68,9 +68,9 @@ This is the perliminary data model for CRC 1333 project B07. At the current time
 - correction_factor
   - Type: float
   - Description: correction factors of the individual species.
-- faraday_coefficient
+- electron_transfer
   - Type: float
-  - Description: Faraday coefficients of the individual species.
+  - Description: Number of transfered electrons of the individual species.
 - faraday_efficiency
   - Type: Data
   - Description: Faraday efficiencies of the individual species.
-Original file line number
+Diff line change
@@ Expand Up / @@ -14,6 +14,8 @@ @@
     from FAIRFlowChemistry.core import ComponentType
     def gc_parser(metadata_path: Path, experimental_data_path: Path):
         """
         Function that reads in a file from a gas chromotography. Important information that is extracted is the
@@ Expand Down @@