test

omc3/scripts/bad_bpms_summary.py

@@ -64,7 +64,7 @@
 from generic_parser import EntryPointParameters, entrypoint
 
 from omc3.utils import logging_tools
-from omc3.utils.iotools import PathOrStr
+from omc3.utils.iotools import PathOrStr, OptionalFloat
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
@@ -119,7 +119,7 @@ def get_params():
     )
     params.add_parameter(
         name="print_percentage",
-        type=float,
+        type=OptionalFloat,
         help="Print out BPMs that appear in more than this percentage of measurements." 
     )
     params.add_parameter(
@@ -132,15 +132,12 @@ def get_params():
 
 
 @entrypoint(get_params(), strict=True)
-def bad_bpms_summary(opt: DotDict):
+def bad_bpms_summary(opt: DotDict) -> tfs.TfsDataFrame:
     outfile = None
     if opt.outfile is not None:
         outfile = Path(opt.outfile)
         outfile.parent.mkdir(parents=True, exist_ok=True)
 
-    if opt.outfile is None and opt.print_percentage is None:
-        raise ValueError("Either `outfile` or `print_percentage` must be specified.")
-
     df_collection = collect_bad_bpms(Path(opt.root), opt.dates, opt.accel_glob)
     if outfile is not None:
         tfs.write(outfile.with_stem(f"{outfile.stem}_collected"), df_collection)
@@ -152,6 +149,8 @@ def bad_bpms_summary(opt: DotDict):
     if opt.print_percentage is not None:
         print_results(df_evaluated, opt.print_percentage)
 
+    return df_evaluated
+
 
 # Collection of Data ---
 
@@ -383,6 +382,8 @@ def print_results(df_counted: tfs.TfsDataFrame, print_percentage: float):
                 df_merged['max_pct'] = df_merged[[f"{PERCENTAGE}X", f"{PERCENTAGE}Y"]].max(axis=1)
                 df_merged = df_merged.sort_values(by='max_pct', ascending=False)
                 df_merged = df_merged.loc[df_merged['max_pct'] >= print_percentage, :]
+
+                # Print Table ---
                 header = f"{'BPM':>20s}  {'X':^18s}  {'Y':^18s}\n"
                 msg = header + "\n".join(
                     f"{name:>20s}  " + 
@@ -398,6 +399,7 @@ def print_results(df_counted: tfs.TfsDataFrame, print_percentage: float):
                 )
 
             else:
+                # Print a list ---
                 df_filtered = df_counted.loc[percentage_mask & source_mask & accel_mask, :]
                 msg = "\n".join(
                     f"{row[NAME]:>20s} {row[PLANE]}: {row[PERCENTAGE]:5.1f}% ({row[COUNT]}/{row[FILE_COUNT]})" 

tests/inputs/bad_bpms/LHCB1/Measurements/example/bad_bpms_iforest_x.tfs

@@ -0,0 +1,9 @@
+*                 NAME              FEATURE                VALUE                  AVG                SCORE
+$                   %s                   %s                  %le                  %le                  %le
+           BPM.20R5.B1                 AMPX      0.2739793273915      0.1983870023371    -0.08321628370052
+           BPM.22R5.B1                 AMPX      0.1645414911027      0.1983870023371     -0.1192688174725
+           BPM.34R7.B1                 AMPX      0.1608806519601      0.1983870023371     -0.1121605330153
+           BPM.27R8.B1                 AMPX      0.1164325835062      0.1983870023371    -0.08355632185117
+           BPMS.2L5.B1         NOISE_SCALED   0.0006165859078803   0.0009016042719894     -0.1390448828672
+           BPMW.5L7.B1                 AMPX      0.1645414911027      0.2062029479469     -0.2122963397363
+          BPMSW.1L8.B1         NOISE_SCALED    0.001344342784781   0.0009016042719894     -0.1248972948542

tests/inputs/bad_bpms/LHCB1/Measurements/example/bad_bpms_iforest_y.tfs

@@ -0,0 +1,9 @@
+*                 NAME              FEATURE                VALUE                  AVG                SCORE
+$                   %s                   %s                  %le                  %le                  %le
+           BPM.34R2.B1                 AMPY      0.1684687445507      0.2816166477169    -0.07696353786083
+           BPM.28R3.B1                 AMPY      0.2274634866394      0.2816166477169    -0.07844693271801
+           BPM.15R7.B1                 AMPY      0.1987839789693      0.2816166477169    -0.08603128649899
+           BPM.19L8.B1         NOISE_SCALED    0.000701003563438   0.0006483937620229      -0.120787110444
+          BPMWI.4L2.B1         NOISE_SCALED    0.001066794573165    0.000649595233316     -0.1719495412989
+           BPMS.2R5.B1         NOISE_SCALED   0.0007888325396217    0.000649595233316     -0.1308678268808
+           BPMS.2R1.B1                TUNEY      0.3219851293843      0.3219858241878       -0.13606497737

tests/inputs/bad_bpms/LHCB1/Measurements/example/example.sdds.bad_bpms_x

@@ -0,0 +1,4 @@
+BPMSI.A4R6.B1 not found in model
+BPMSI.B4R6.B1 not found in model
+BPMSE.4L6.B1 Spiky BPM, found spike higher than 20.0
+BPMSX.4L8.B1 Detected from SVD, single peak value is greater then 0.925

tests/inputs/bad_bpms/LHCB1/Measurements/example/example.sdds.bad_bpms_y

@@ -0,0 +1,8 @@
+BPMSI.A4R6.B1 not found in model
+BPMSI.B4R6.B1 not found in model
+BPM.31L5.B1 Flat BPM, the difference between min/max is smaller than 1e-05
+BPMSX.A4L6.B1 Flat BPM, the difference between min/max is smaller than 1e-05
+BPM.31L5.B1 Found an exact zero
+BPMSX.A4L6.B1 Found an exact zero
+BPMSE.4L6.B1 Detected from SVD, single peak value is greater then 0.925
+BPMWI.A5L4.B1 Detected from SVD, single peak value is greater then 0.925

tests/unit/test_bad_bpms_summary.py

@@ -0,0 +1,41 @@
+import pytest
+import tfs 
+
+from tests.conftest import INPUTS, assert_tfsdataframe_equal
+from omc3.scripts.bad_bpms_summary import NAME, SOURCE, bad_bpms_summary, IFOREST, HARPY
+import logging
+
+
+@pytest.mark.extended
+def test_bad_bpms_summary(tmp_path, caplog):
+
+    outfile = tmp_path / "bad_bpms_summary.tfs"
+    with caplog.at_level(logging.INFO):
+        df_eval = bad_bpms_summary(
+            root=INPUTS,
+            outfile=outfile,
+            dates=["bad_bpms"],
+            accel_glob="LHCB1",
+            print_percentage=50,
+        )
+
+    # Test Data has been written
+    assert df_eval is not None
+    assert_tfsdataframe_equal(df_eval, tfs.read(outfile))
+
+    # Test some random BPMs
+    not_in_model = ["BPMSI.A4R6.B1", ]
+    for bpm in not_in_model:
+        assert bpm not in df_eval[NAME].tolist()
+
+    iforest_bpms = ["BPM.27R8.B1", "BPMS.2R1.B1"]
+    df_iforest = df_eval[df_eval[SOURCE] == IFOREST]
+    for bpm in iforest_bpms:
+        assert bpm in df_iforest[NAME].tolist()
+        assert bpm in caplog.text
+
+    harpy_bpms = ["BPMSE.4L6.B1", "BPM.31L5.B1"]
+    df_harpy = df_eval[df_eval[SOURCE] == HARPY]
+    for bpm in harpy_bpms:
+        assert bpm in df_harpy[NAME].tolist()
+        assert bpm in caplog.text