Revised CalCat API

This is based on our discussion last week, but it's still a WIP. In particular, I haven't implemented actually loading the constants yet.

I've tweaked the design slightly: rather than having CalibrationData subclasses for each detector type, you use CalibrationData.from_conditions() with a detector specific object like AGIPDConditions. Jump to the tests to see what this looks like.

Questions:

• How to deal with missing modules?
  • A module may be missing for one type of constant but not for another
  • How do we even tell if modules are missing - should we query the PDUs so we know how many modules to expect?
• How to deal with missing calibration types (e.g. SlopesPC)
  • Especially if one group (e.g. illuminated) not found - this currently raises an error, even if we have other constants we could return
• Naming:
  • 'Calibrations' vs 'calibration' types vs 'constant types' (e.g. Offset, SlopesPC
  • 'Modules' vs 'aggregators'
• How many of SingleConstantVersion fields do we actually want?
• Should .select_modules() and .select_calibrations() take *args or a list?

cc @schmidtp @ahmedk @hammerd

src/cal_tools/calcat_interface2.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from typing import Dict, Optional, Sequence, Union
 
 import h5py
+import numpy as np
 import pasha as psh
 from calibration_client import CalibrationClient
 from calibration_client.modules import CalibrationConstantVersion
@@ -98,7 +99,7 @@ class SingleConstantVersion:
             physical_name=ccv["physical_detector_unit"]["physical_name"],
         )
 
-    def dataset_obj(self, caldb_root=None):
+    def dataset_obj(self, caldb_root=None) -> h5py.Dataset:
         if caldb_root is not None:
             caldb_root = Path(caldb_root)
         else:
@@ -133,6 +134,36 @@ class ModulesConstantVersions:
     def qm_names(self):
         return [module_index_to_qm(n) for n in self.module_nums]
 
+    def ndarray(self, caldb_root=None):
+        eg_dset = self.constants[self.aggregators[0]].dataset_obj(caldb_root)
+        shape = (len(self.constants),) + eg_dset.shape
+        arr = np.zeros(shape, eg_dset.dtype)
+        for i, agg in enumerate(self.aggregators):
+            dset = self.constants[agg].dataset_obj(caldb_root)
+            dset.read_direct(arr[i])
+        return arr
+
+    def xarray(self, module_naming="da", caldb_root=None):
+        import xarray
+
+        if module_naming == "da":
+            modules = self.aggregators
+        elif module_naming == "modno":
+            modules = self.module_nums
+        elif module_naming == "qm":
+            modules = self.qm_names
+        else:
+            raise ValueError(f"{module_naming=} (must be 'da', 'modno' or 'qm'")
+
+        ndarr = self.ndarray(caldb_root)
+
+        # Dimension labels
+        dims = ["module"] + ["dim_%d" % i for i in range(ndarr.ndim - 1)]
+        coords = {"module": modules}
+        name = self.constants[self.aggregators[0]].constant_name
+
+        return xarray.DataArray(ndarr, dims=dims, coords=coords, name=name)
+
 
 class CalibrationData(Mapping):
     """Collected constants for a given detector"""
@@ -325,6 +356,7 @@ class CalibrationData(Mapping):
             dset.read_direct(res[cal_type][mod])
 
         const_load_mp.map(_load_constant_dataset, keys)
+        return res
 
 
 class ConditionsBase:
@@ -421,3 +453,30 @@ class LPDConditions(ConditionsBase):
         "FFMap": _illuminated_parameters,
         "BadPixelsFF": _illuminated_parameters,
     }
+
+
+@dataclass
+class DSSCConditions(ConditionsBase):
+    sensor_bias_voltage: float
+    memory_cells: int
+    pulse_id_checksum: Optional[float] = None
+    acquisition_rate: Optional[float] = None
+    target_gain: Optional[int] = None
+    encoded_gain: Optional[int] = None
+    pixels_x: int = 512
+    pixels_y: int = 128
+
+    _params = [
+        "Sensor Bias Voltage",
+        "Memory cells",
+        "Pixels X",
+        "Pixels Y",
+        "Pulse id checksum",
+        "Acquisition rate",
+        "Target gain",
+        "Encoded gain",
+    ]
+    calibration_types = {
+        "Offset": _params,
+        "Noise": _params,
+    }