Improve fit

• Estimate peak using a simple Gaussian filter and np.argmax to speed up fitting.
• Calculate outliers with IsolationForest and per channel.
• Add possibility of a polynomial fit on pes and sqrt(pes).
• Add possibility of fitting with weights and function to get weights based on the XGM intensity to get a flatter response a as a function of intensity.

pes_to_spec/test/offline_analysis.py

@@ -8,7 +8,7 @@ import os
 import argparse
 
 import numpy as np
-from extra_data import open_run, by_id
+from extra_data import open_run, by_id, RunDirectory
 from pes_to_spec.model import Model, matching_two_ids
 
 from itertools import product
@@ -137,8 +137,10 @@ def main():
 
     args = parser.parse_args()
 
+    print("Opening run ...")
     # get run
     run = open_run(proposal=args.proposal, run=args.run)
+    #run = RunDirectory("/gpfs/exfel/data/scratch/tmichela/data/r0206")
 
     # ----------------Used in the first tests-------------------------
     # get train IDs and match them, so we are sure to have information from all needed sources
@@ -185,6 +187,8 @@ def main():
     pes_raw_t = {ch: run[pes_name, f"digitizers.{ch}.raw.samples"].select_trains(by_id[test_tids]).ndarray()
                for ch in channels}
 
+    print("Data in memory.")
+
     # read the XGM information
     #xgm_pressure = run['SA3_XTD10_XGM/XGM/DOOCS', "pressure.pressureFiltered.value"].select_trains(by_id[tids]).ndarray()
     #xgm_pe =  run['SA3_XTD10_XGM/XGM/DOOCS:output', "data.intensitySa3TD"].select_trains(by_id[tids]).ndarray()
@@ -230,7 +234,7 @@ def main():
     rmse = model.check_compatibility(pes_raw_t)
     print("Consistency check RMSE ratios:", rmse)
     rmse = model.check_compatibility_per_channel(pes_raw_t)
-    print("Consistency per channel check RMSE ratios:", rmse)
+    print("Consistency per channel check (chi2 - icdf(p=0.05))/ndof:", rmse)
     t += [time_ns() - start]
     t_names += ["Consistency"]
 
@@ -253,7 +257,7 @@ def main():
         spec_smooth = model.preprocess_high_res(spec_raw_int)
     first, last = model.get_low_resolution_range()
     first += 10
-    last -= 100
+    last -= 10
     pes_to_show = 'channel_1_D'
     # plot
     for tid in test_tids: