Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"id": "6386344d-b7ac-440d-9926-f03af4ff9d6f",
"metadata": {},
"source": [
"# Training the Virtual Spectrometer with Viking and PES data"
]
},
{
"cell_type": "markdown",
"id": "1711c3b9-5065-4a44-8b1b-a3e861b92bc5",
"metadata": {},
"source": [
"The objective here is to use the Viking detector to train the Virtual Spectrometer. This means that we will fit (\"train\") a model, which maps the PES measurements with the Viking measurements and use their correlation to interpolate in cases where the Viking is not available.\n",
"\n",
"The following conditions must be satisfied for this to be possible:\n",
"* The PES settings are the same in the \"training\" run and interesting run.\n",
"* The photon energies of the beam in \"training\" and in the interesting run are similar.\n",
"* The beam intensities are similar.\n",
"* The sample between PES and Viking is transparent.\n",
"* 1 pulse trains in \"training\".\n",
"\n",
"The following software implements:\n",
"1. retrieve data and calibrate Viking using the SCS toolbox;\n",
"2. the Virtual Spectrometer training excluding the last 10 trains avalable so that we can use them for validation;\n",
"3. the Virtual Spectrometer resolution function plotting;\n",
"4. comparison of the Virtual spectrometer results in a selected set in which the Viking data was available.\n",
"\n",
"Finally, the model is applied in data without the grating. This last part may be applied independently from the rest if the modal has been written in a `joblib` file."
]
},
{
"cell_type": "code",
"id": "4a627555-522a-4c9d-b6b2-6ff77148eaab",
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"sys.path.append('/home/danilo/scratch/karabo/devices/pes_to_spec')"
]
},
{
"cell_type": "code",
"id": "78bbc433-ac5e-44c3-8740-3e93800c4532",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cupy is not installed in this environment, no access to the GPU\n"
]
}
],
"source": [
"import numpy as np\n",
"import dask.array as da\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"from pes_to_spec.model import Model\n",
"\n",
"import toolbox_scs as tb\n",
"from euxfel_bunch_pattern import indices_at_sase\n",
"\n",
"from scipy.signal import fftconvolve"
]
},
{
"cell_type": "markdown",
"id": "c7609899-5bc0-4211-ae97-010b3edcf676",
"metadata": {},
"source": [
"id": "95da5231-e454-4f7f-a1ce-eef7e52fe457",
"metadata": {},
"outputs": [],
"source": [
"# pes channel names to be used for reference later\n",
"pes_map = dict(channel_1_A=\"PES_S_raw\",\n",
" channel_1_B=\"PES_SSW_raw\",\n",
" channel_1_C=\"PES_SW_raw\",\n",
" channel_1_D=\"PES_WSW_raw\",\n",
" channel_2_A=\"PES_W_raw\",\n",
" channel_2_B=\"PES_WNW_raw\",\n",
" channel_2_C=\"PES_NW_raw\",\n",
" channel_2_D=\"PES_NNW_raw\",\n",
" channel_3_A=\"PES_E_raw\",\n",
" channel_3_B=\"PES_ESE_raw\",\n",
" channel_3_C=\"PES_SE_raw\",\n",
" channel_3_D=\"PES_SSE_raw\",\n",
" channel_4_A=\"PES_N_raw\",\n",
" channel_4_B=\"PES_NNE_raw\",\n",
" channel_4_C=\"PES_NE_raw\",\n",
" channel_4_D=\"PES_ENE_raw\",\n",
" )"
]
},
{
"cell_type": "code",
"id": "48bb4c8c-04ad-44d5-b123-643ce3253ceb",
"metadata": {},
"outputs": [],
"source": [
"proposal = 2953\n",
"runTrain = 322 # run containing the data without sample\n",
"darkNB = 375 # dark run"
]
},
{
"cell_type": "code",
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
"id": "0a467b2f-5f99-4ed8-bb1d-cb429454d3ce",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"newton: only 50.0% of trains (629 out of 1259) contain data.\n"
]
}
],
"source": [
"v = tb.Viking(proposal)\n",
"fields = ['XTD10_SA3',\n",
" *list(pes_map.values()) # add PES\n",
" ]\n",
"v.FIELDS += fields\n",
"v.X_RANGE = slice(0, 1500) # define the dispersive axis range of interest (in pixels)\n",
"v.Y_RANGE = slice(29, 82) # define the non-dispersive axis range of interest (in pixels)\n",
"v.ENERGY_CALIB = [1.47802667e-06, 2.30600328e-02, 5.15884589e+02] # energy calibration, see further below\n",
"v.BL_POLY_DEG = 1 # define the polynomial degree for baseline subtraction\n",
"v.BL_SIGNAL_RANGE = [500, 545] # define the range containing the signal, to be excluded for baseline subtraction\n",
"\n",
"v.load_dark(darkNB) # load a dark image (averaged over the dark run number)"
]
},
{
"cell_type": "code",
"id": "4f6124d9-8c1b-44f8-a078-07475a9674fc",
"metadata": {
"tags": []
},
"outputs": [],
"data_train = v.from_run(runTrain) # load refNB. The `newton` variable contains the CCD images.\n",
"v.integrate(data_train) # integrate over the non-dispersive dimension \n",
"v.removePolyBaseline(data_train) # remove baseline\n",
"data_train"
]
},
{
"cell_type": "code",
"id": "294b5f3a-1d59-444e-80ab-4834d26d62dc",
"metadata": {},
"outputs": [],
"source": [
"# transform PES data into the format expected\n",
"pes_data = {k: da.from_array(data_train[item].to_numpy())\n",
" for k, item in pes_map.items() if item in data_train}\n",
"xgm = data_train.XTD10_SA3.isel(sa3_pId=0).to_numpy()[:, np.newaxis]"
]
},
{
"cell_type": "code",
"id": "b477bf49-f5ca-4df0-b6ed-a270ee35cd28",
"metadata": {},
"outputs": [],
"source": [
"channels = tuple(pes_data.keys())"
]
},
{
"cell_type": "code",
"id": "8f154e38-d208-477e-9d9c-ef2a632514c8",
"metadata": {},
"outputs": [],
"source": [
"energy = data_train.newt_x.to_numpy()"
]
},
{
"cell_type": "code",
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
"id": "0c5ff2a0-0737-417d-9f57-158d4fbd8090",
"metadata": {},
"outputs": [],
"source": [
"vik = data_train.spectrum.to_numpy()"
]
},
{
"cell_type": "markdown",
"id": "995e2ac0-1898-46dd-b95f-f65a24496871",
"metadata": {},
"source": [
"## Train Virtual Spectrometer"
]
},
{
"cell_type": "markdown",
"id": "9cbf75c8-fbe0-42ec-af85-6194aede91f5",
"metadata": {},
"source": [
"So far we have only done pre-processing due to experimental problems with some data not being available in certain train IDs.\n",
"\n",
"Let's finally take a look at the data before training the model."
]
},
{
"cell_type": "code",
"id": "63b35dac-ad50-4124-b6f8-e1ceea667b4d",
"metadata": {},
"source": [
"plt.plot(energy, vik[2])"
]
},
{
"cell_type": "code",
"id": "d0b70fef-5e27-4cb1-90e7-2653989cf48a",
"metadata": {},
"source": [
"plt.plot(-pes_data[\"channel_1_A\"][0,31400:31700])"
]
},
{
"cell_type": "markdown",
"id": "a6606c28-28c8-4d27-9f38-4a7ca88ee397",
"metadata": {},
"source": [
"Now, let's fit the model:"
]
},
{
"cell_type": "code",
"id": "5690cf09-4fed-497d-a09d-0f3cdceea04d",
"metadata": {},
"outputs": [],
"source": [
"n_test = 10 # exclude some trains to validate the training"
]
},
{
"cell_type": "code",
"id": "cb86aa32-dc1d-4684-bd62-25aa77a97245",
"metadata": {},
"source": [
"# exclude the last n_test train IDs so we can use them for validation later\n",
"pes_train = {ch: pes_data[ch][:-n_test, :] for ch in pes_data.keys()}\n",
"vik_train = vik[:-n_test, :]\n",
"xgm_train = xgm[:-n_test,:]\n",
"\n",
"model = Model(channels=channels)\n",
"model.fit(pes_train,\n",
" vik_train,\n",
" np.broadcast_to(energy, (vik_train.shape[0], vik_train.shape[-1])),\n",
" pulse_energy=xgm_train)"
]
},
{
"cell_type": "markdown",
"id": "52c038c5-d86e-4e5a-9214-5e1878dd77e8",
"metadata": {},
"source": [
"The resolution of the Virtual Spectrometer relative to the Viking has also been estimated (in eV):"
]
},
{
"cell_type": "code",
"id": "a084b920-0006-4859-80f9-ff81f3c1f6b0",
"metadata": {},
"source": [
"model.resolution"
]
},
{
"cell_type": "markdown",
"id": "c1f47e6e-3b62-4c8a-8573-8eb4bd40f2ff",
"metadata": {},
"source": [
"We can look at the Virtual Spectrometer to Viking response function as well."
]
},
{
"cell_type": "code",
"id": "f752a9e0-8484-4381-8bb5-5eb27bd82670",
"metadata": {},
"source": [
"plt.figure(figsize=(12, 8))\n",
"plt.plot(model.impulse_axis, model.impulse_response)\n",
"plt.xlabel('Energy [eV]')\n",
"plt.ylabel('Intensity [a.u.]')"
]
},
{
"cell_type": "markdown",
"id": "3842cb23-a961-4a60-9e9e-d341256e1bb7",
"metadata": {},
"source": [
"## Save model"
]
},
{
"cell_type": "code",
"id": "4e612338-401e-4fd5-bef7-a6579af0d3d3",
"metadata": {},
"outputs": [],
"source": [
"model.save(\"VS_p5576_viking.joblib\")"
]
},
{
"cell_type": "markdown",
"id": "4d7f95c2-e16d-43b2-a0c5-28a968490bb0",
"metadata": {},
"source": [
"# Validation: Apply model in data not used in training"
]
},
{
"cell_type": "code",
"id": "dc56d30b-7db8-49ce-82ed-d01d8b6670d8",
"metadata": {},
"outputs": [],
"source": [
"pes_test = {ch: pes_data[ch][n_test:, :] for ch in pes_data.keys()}\n",
"vik_test = vik[n_test:, :]\n",
"xgm_test = xgm[n_test:,:]"
]
},
{
"cell_type": "code",
"id": "0d8054bb-8ad6-4ee4-8d0c-8ac4ee990179",
"metadata": {},
"outputs": [],
"source": [
"vs_test = model.predict(pes_test, pulse_energy=xgm_test)"
]
},
{
"cell_type": "code",
"id": "e087883a-43e3-4e19-9041-6740704d7df7",
"metadata": {},
"outputs": [],
"source": [
"vs_test[\"energy\"] = model.get_energy_values()"
]
},
{
"cell_type": "markdown",
"id": "c4f0861c-a124-4812-beb1-0b8cd56d89c1",
"metadata": {},
"source": [
"Add Viking in the same dictionary for convinience. In practice this would not be done in inference: it is done here to validate the results obtained."
]
},
{
"cell_type": "code",
"id": "a5bd5573-afc9-45b3-9f25-7c713e08dfa9",
"metadata": {},
"outputs": [],
"source": [
"vs_test[\"viking\"] = vik_test"
]
},
{
"cell_type": "markdown",
"id": "6e30cc51-41e0-4458-8867-f43605324fc6",
"metadata": {},
"source": [
"Now we can plot it:"
]
},
{
"cell_type": "code",
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
"id": "44e5df6a-dfc9-47ab-9f37-03fdd0687698",
"metadata": {},
"outputs": [],
"source": [
"def plot(data, i):\n",
" \"\"\"Plot prediction and expectation.\"\"\"\n",
" from matplotlib.gridspec import GridSpec\n",
" fig = plt.figure(figsize=(24, 8))\n",
" gs = GridSpec(1, 2)\n",
" ax = fig.add_subplot(gs[0, 0])\n",
" ax.plot(data[\"energy\"], data[\"viking\"][i], c='b', lw=3, label=\"Viking\")\n",
" ax.plot(data[\"energy\"], data[\"expected\"][i,0], c='r', ls='--', lw=3, label=\"Prediction\")\n",
" ax.fill_between(data[\"energy\"],\n",
" data[\"expected\"][i,0] - data[\"residual\"][i,0],\n",
" data[\"expected\"][i,0] + data[\"residual\"][i,0],\n",
" facecolor='gold', alpha=0.5, label=\"68% unc.\")\n",
" ax.legend(frameon=False, borderaxespad=0, loc='upper left')\n",
" ax.spines['top'].set_visible(False)\n",
" ax.spines['right'].set_visible(False)\n",
" ax.set(\n",
" xlabel=\"Photon energy [eV]\",\n",
" ylabel=\"Intensity [a.u.]\",\n",
" title=\"Comparing with the original Viking\",\n",
" )\n",
" ax = fig.add_subplot(gs[0, 1])\n",
" viking_smooth = fftconvolve(data[\"viking\"][i], model.impulse_response, mode=\"same\")\n",
" ax.plot(data[\"energy\"], viking_smooth, c='b', lw=3, label=\"Viking (convolved to VS resolution)\")\n",
" ax.plot(data[\"energy\"], data[\"expected\"][i,0], c='r', ls='--', lw=3, label=\"Prediction\")\n",
" ax.fill_between(data[\"energy\"],\n",
" data[\"expected\"][i,0] - data[\"residual\"][i,0],\n",
" data[\"expected\"][i,0] + data[\"residual\"][i,0],\n",
" facecolor='gold', alpha=0.5, label=\"68% unc.\")\n",
" ax.legend(frameon=False, borderaxespad=0, loc='upper left')\n",
" ax.spines['top'].set_visible(False)\n",
" ax.spines['right'].set_visible(False)\n",
" ax.set(\n",
" xlabel=\"Photon energy [eV]\",\n",
" ylabel=\"Intensity [a.u.]\",\n",
" title=\"Same, with smoothened Viking\",\n",
" )\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"id": "f9bb6495-51db-4775-ba91-c7b936dc0b33",
"metadata": {},
"source": [
"These are the last 10 train IDs, which were not used in training."
]
},
{
"cell_type": "code",
"id": "c8ffc289-c10a-48bb-b1e0-1ebeb61880dd",
"metadata": {},
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
"outputs": [],
"source": [
"plot(vs_test, 0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8c61b6fe-111f-4c2f-91b6-2fb83c56c9d7",
"metadata": {},
"outputs": [],
"source": [
"plot(vs_test, 1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "373ca950-0378-4d7d-96ca-57ad951ebbf3",
"metadata": {},
"outputs": [],
"source": [
"plot(vs_test, 2)"
]
},
{
"cell_type": "markdown",
"id": "1f0f3f20-060a-488a-9f61-6b4cb3cf1614",
"metadata": {},
"source": [
"# Inference: Apply it in new data without Viking"
]
},
{
"cell_type": "markdown",
"id": "377c6993-a1a4-45c7-ae6b-2b533d893b6f",
"metadata": {},
"source": [
"The configuration for inference must be the same as in training. This can be checked as follows."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "3aecfa9c-6335-4c92-9483-d2192ca159c1",
"metadata": {},
"outputs": [],
"source": [
"runTest = 321"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "9e2388e6-5b88-4c10-901b-1538d9fa0870",
"metadata": {},
"outputs": [],
"source": [
"from pes_to_spec.config import VSConfig\n",
"\n",
"training_config = VSConfig.load(proposal, runTrain)\n",
"inference_config = VSConfig.load(proposal, runTest)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "8b916fa4-e1ef-43b0-93a5-0967892c2d70",
"metadata": {},
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mean_u110</th>\n",
" <th>mean_u108</th>\n",
" <th>mean_u114</th>\n",
" <th>mean_u115</th>\n",
" <th>mean_u113</th>\n",
" <th>mean_u205</th>\n",
" <th>mean_u203</th>\n",
" <th>mean_u213</th>\n",
" <th>mean_u112</th>\n",
" <th>mean_u3</th>\n",
" <th>...</th>\n",
" <th>std_u206</th>\n",
" <th>std_u204</th>\n",
" <th>std_u201</th>\n",
" <th>std_u208</th>\n",
" <th>std_u209</th>\n",
" <th>std_u215</th>\n",
" <th>std_u104</th>\n",
" <th>pressure_mean</th>\n",
" <th>pressure_std</th>\n",
" <th>gas_active</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>2249.998207</td>\n",
" <td>-78.010137</td>\n",
" <td>-0.10791</td>\n",
" <td>-120.001891</td>\n",
" <td>2249.992845</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.001</td>\n",
" <td>0.001089</td>\n",
" <td>0.0</td>\n",
" <td>0.000763</td>\n",
" <td>0.000995</td>\n",
" <td>0.000626</td>\n",
" <td>0.002382</td>\n",
" <td>0.000001</td>\n",
" <td>4.456064e-08</td>\n",
" <td>NITROGEN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 65 columns</p>\n",
"</div>"
],
" mean_u110 mean_u108 mean_u114 mean_u115 mean_u113 mean_u205 \\\n",
"0 0.0 0.0 0.0 0.0 2249.998207 -78.010137 \n",
"\n",
" mean_u203 mean_u213 mean_u112 mean_u3 ... std_u206 std_u204 \\\n",
"0 -0.10791 -120.001891 2249.992845 0.0 ... 0.001 0.001089 \n",
"\n",
" std_u201 std_u208 std_u209 std_u215 std_u104 pressure_mean \\\n",
"0 0.0 0.000763 0.000995 0.000626 0.002382 0.000001 \n",
"\n",
" pressure_std gas_active \n",
"0 4.456064e-08 NITROGEN \n",
"\n",
"[1 rows x 65 columns]"
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "84ece2bd-c11a-42a5-9cd9-9f253c850562",
"metadata": {},
"outputs": [
{
"data": {
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mean_u110</th>\n",
" <th>mean_u108</th>\n",
" <th>mean_u114</th>\n",
" <th>mean_u115</th>\n",
" <th>mean_u113</th>\n",
" <th>mean_u205</th>\n",
" <th>mean_u203</th>\n",
" <th>mean_u213</th>\n",
" <th>mean_u112</th>\n",
" <th>mean_u3</th>\n",
" <th>mean_u105</th>\n",
" <th>mean_u212</th>\n",
" <th>mean_u103</th>\n",
" <th>mean_u207</th>\n",
" <th>mean_u210</th>\n",
" <th>mean_u102</th>\n",
" <th>mean_u106</th>\n",
" <th>mean_u107</th>\n",
" <th>mean_u109</th>\n",
" <th>mean_u111</th>\n",
" <th>mean_u200</th>\n",
" <th>mean_u214</th>\n",
" <th>mean_u211</th>\n",
" <th>mean_u202</th>\n",
" <th>mean_u206</th>\n",
" <th>mean_u204</th>\n",
" <th>mean_u201</th>\n",
" <th>mean_u208</th>\n",
" <th>mean_u209</th>\n",
" <th>mean_u215</th>\n",
" <th>mean_u104</th>\n",
" <th>std_u110</th>\n",
" <th>std_u108</th>\n",
" <th>std_u114</th>\n",
" <th>std_u115</th>\n",
" <th>std_u113</th>\n",
" <th>std_u205</th>\n",
" <th>std_u203</th>\n",
" <th>std_u213</th>\n",
" <th>std_u112</th>\n",
" <th>std_u3</th>\n",
" <th>std_u105</th>\n",
" <th>std_u212</th>\n",
" <th>std_u103</th>\n",
" <th>std_u207</th>\n",
" <th>std_u210</th>\n",
" <th>std_u102</th>\n",
" <th>std_u106</th>\n",
" <th>std_u107</th>\n",
" <th>std_u109</th>\n",
" <th>std_u111</th>\n",
" <th>std_u200</th>\n",
" <th>std_u214</th>\n",
" <th>std_u211</th>\n",
" <th>std_u202</th>\n",
" <th>std_u206</th>\n",
" <th>std_u204</th>\n",
" <th>std_u201</th>\n",
" <th>std_u208</th>\n",
" <th>std_u209</th>\n",
" <th>std_u215</th>\n",
" <th>std_u104</th>\n",
" <th>pressure_mean</th>\n",
" <th>pressure_std</th>\n",
" <th>gas_active</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.002567</td>\n",
" <td>-0.003455</td>\n",
" <td>0.0</td>\n",
" <td>-0.001019</td>\n",
" <td>0.002316</td>\n",
" <td>0.0</td>\n",
" <td>0.000926</td>\n",
" <td>-0.001261</td>\n",
" <td>0.001064</td>\n",
" <td>-0.003332</td>\n",
" <td>-0.001361</td>\n",
" <td>0.000324</td>\n",
" <td>-0.000565</td>\n",
" <td>-0.000565</td>\n",
" <td>0.0</td>\n",
" <td>0.002359</td>\n",
" <td>0.0</td>\n",
" <td>-0.000705</td>\n",
" <td>-0.000744</td>\n",
" <td>0.0</td>\n",
" <td>-0.002291</td>\n",
" <td>-0.003028</td>\n",
" <td>0.0</td>\n",
" <td>-0.000272</td>\n",
" <td>-0.000004</td>\n",
" <td>-0.001626</td>\n",
" <td>0.001178</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.001599</td>\n",
" <td>0.001134</td>\n",
" <td>0.0</td>\n",
" <td>0.000927</td>\n",
" <td>0.001987</td>\n",
" <td>0.0</td>\n",
" <td>0.003332</td>\n",
" <td>0.000681</td>\n",
" <td>0.003028</td>\n",
" <td>0.000873</td>\n",
" <td>0.000777</td>\n",
" <td>0.002459</td>\n",
" <td>0.002144</td>\n",
" <td>0.002144</td>\n",
" <td>0.0</td>\n",
" <td>0.001425</td>\n",
" <td>0.0</td>\n",
" <td>0.000929</td>\n",
" <td>0.000788</td>\n",
" <td>0.0</td>\n",
" <td>0.001</td>\n",
" <td>0.001089</td>\n",
" <td>0.0</td>\n",
" <td>0.000763</td>\n",
" <td>0.000995</td>\n",
" <td>0.000626</td>\n",
" <td>0.002382</td>\n",
" <td>1.268518e-09</td>\n",
" <td>4.456064e-08</td>\n",
" <td></td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
" mean_u110 mean_u108 mean_u114 mean_u115 mean_u113 mean_u205 \\\n",
"0 0.0 0.0 0.0 0.0 0.002567 -0.003455 \n",
"\n",
" mean_u203 mean_u213 mean_u112 mean_u3 mean_u105 mean_u212 mean_u103 \\\n",
"0 0.0 -0.001019 0.002316 0.0 0.000926 -0.001261 0.001064 \n",
"\n",
" mean_u207 mean_u210 mean_u102 mean_u106 mean_u107 mean_u109 \\\n",
"0 -0.003332 -0.001361 0.000324 -0.000565 -0.000565 0.0 \n",
"\n",
" mean_u111 mean_u200 mean_u214 mean_u211 mean_u202 mean_u206 \\\n",
"0 0.002359 0.0 -0.000705 -0.000744 0.0 -0.002291 \n",
"\n",
" mean_u204 mean_u201 mean_u208 mean_u209 mean_u215 mean_u104 std_u110 \\\n",
"0 -0.003028 0.0 -0.000272 -0.000004 -0.001626 0.001178 0.0 \n",
"\n",
" std_u108 std_u114 std_u115 std_u113 std_u205 std_u203 std_u213 \\\n",
"0 0.0 0.0 0.0 0.001599 0.001134 0.0 0.000927 \n",
"\n",
" std_u112 std_u3 std_u105 std_u212 std_u103 std_u207 std_u210 \\\n",
"0 0.001987 0.0 0.003332 0.000681 0.003028 0.000873 0.000777 \n",
"\n",
" std_u102 std_u106 std_u107 std_u109 std_u111 std_u200 std_u214 \\\n",
"0 0.002459 0.002144 0.002144 0.0 0.001425 0.0 0.000929 \n",
"\n",
" std_u211 std_u202 std_u206 std_u204 std_u201 std_u208 std_u209 \\\n",
"0 0.000788 0.0 0.001 0.001089 0.0 0.000763 0.000995 \n",
"\n",
" std_u215 std_u104 pressure_mean pressure_std gas_active \n",
"0 0.000626 0.002382 1.268518e-09 4.456064e-08 "
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
"import pandas as pd\n",
"pd.set_option('display.max_columns', 500)\n",
"(training_config - inference_config).to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "d05998c1-7b30-4eaa-adb6-c041c247797a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
"training_config == inference_config"
]
},
{
"cell_type": "markdown",
"id": "d99852b3-ec27-44e7-bd63-056fa3804810",
"metadata": {},
"source": [
"Retrieve PES and XGM data into the expected format.\n"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "371f7583-5d0d-44d0-b41b-20cf4279da45",
"metadata": {},
"outputs": [],
"source": [
"\n",
"# bunch pattern table\n",
" 'bunchPatternTable',\n",
" #{'bunchPatternTable': {'source': 'SCS_RR_UTC/TSYS/TIMESERVER:outputBunchPattern',\n",
" # 'key': 'data.bunchPatternTable',\n",
" # 'dim': ['pulses'],\n",
" # },\n",
" #},\n",
]
},
{
"cell_type": "code",
"id": "83fe11bc-aa8b-4037-aa15-4a36e3104bf5",
"metadata": {},
"outputs": [],
"source": [
"from pes_to_spec.model import Model\n",
"model = Model.load(\"VS_p5576_viking.joblib\")"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "6115d454-d695-441e-b70f-40ac4a336355",
"metadata": {},
"_, data_inf = tb.load(proposal, runTest, fields + field_bpt)\n",
"\n",
"# transform PES data into the format expected\n",
"pes_data_inf = {k: da.from_array(data_inf[item].to_numpy())\n",
" for k, item in pes_map.items() if item in data_inf}\n",
"xgm_inf = data_inf.XTD10_SA3.to_numpy()\n",
"\n",
"# assume it does not change:\n",
"bpt_inf = data_inf.bunchPatternTable.isel(trainId=0).to_numpy()"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "056c231d-49cf-4280-b7b2-8884b50e710e",
"metadata": {},
"outputs": [],
"source": [
"# assume the same bunch pattern structure throughout the run!\n",
"fel_pos = indices_at_sase(bpt_inf, sase=3)\n",
"fel_pos -= fel_pos[0]\n",
"freq_ratio = {ch: 220 for ch in channels}\n",
"sample_pos = {ch: fel_pos * 2 * freq for ch, freq in freq_ratio.items()}\n",
"pulse_spacing = sample_pos"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "938f91a8-ab92-407e-a679-c5ce2c8589e5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"{'channel_1_A': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_1_B': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_1_C': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_1_D': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_2_A': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_2_B': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_2_C': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_2_D': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",
" 'channel_3_A': array([ 0, 14080, 28160, 42240, 56320, 70400, 84480, 98560,\n",
" 112640, 126720, 140800, 154880, 168960, 183040, 197120, 211200,\n",
" 225280, 239360, 253440, 267520, 281600, 295680, 309760, 323840,\n",
" 337920, 352000, 366080, 380160, 394240, 408320, 422400, 436480,\n",
" 450560, 464640, 478720, 492800, 506880, 520960, 535040, 549120,\n",
" 563200, 577280, 591360]),\n",