From 02d46aa05bb699e531a3cff33a1c91411213f783 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20Schr=C3=B6n?= <martin.schroen@ufz.de>
Date: Sun, 3 Mar 2024 12:19:06 +0100
Subject: [PATCH] New feature for outlier detection in other columns
---
VERSION | 2 +-
default.cfg | 4 ++++
instantPASDy.py | 12 ++++++++++++
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/VERSION b/VERSION
index 7ada0d3..7fc2521 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-0.8.5
+0.8.6
diff --git a/default.cfg b/default.cfg
index 65a7d7e..981bb32 100644
--- a/default.cfg
+++ b/default.cfg
@@ -296,6 +296,10 @@ sm_range =
# Units: cph
muon_range =
+## Other variables
+# Other columns that should be cleaned based on a valid range.
+other_names = SMT1
+other_range = 0.01, 1.0
## Split tracks
# Identify single tracks between locations A and B (yes/no)
diff --git a/instantPASDy.py b/instantPASDy.py
index 1457db9..7149533 100644
--- a/instantPASDy.py
+++ b/instantPASDy.py
@@ -719,6 +719,18 @@ def main(configfile=None, cfg_prefix=None):
#data[['GpsUTC', 'LatDec', 'LongDec', 'Alt']].to_csv('testgps.csv', index=False)
+ ####################################################
+ ###### Other variables
+
+ if cc(config, 'clean', 'other_names') and cc(config, 'clean', 'other_range'):
+ other_names = xsplit(gc(config,'clean','other_names'), type=str)
+ (a,b) = xsplit(gc(config, 'clean', 'other_range'), range=2, type=float)
+
+ for c in other_names:
+ if c in data.columns:
+ data[c] = find_outlier(data, c, lower=a, upper=b)
+
+
####################################################
###### Muons #######################################
####################################################
--
GitLab