From 946a8d8bcbd7350679186215e340ced2d2c090d3 Mon Sep 17 00:00:00 2001
From: Bert Palm <bert.palm@ufz.de>
Date: Tue, 16 Apr 2019 17:02:48 +0200
Subject: [PATCH] modified evaluator to new assign keyword
---
core.py | 6 +++---
dsl/evaluator.py | 42 ++++++++++++++++++++++++++++++++++--------
funcs/functions.py | 2 ++
3 files changed, 39 insertions(+), 11 deletions(-)
diff --git a/core.py b/core.py
index 82e90c98a..d1a49056f 100644
--- a/core.py
+++ b/core.py
@@ -82,12 +82,12 @@ def runner(meta, flagger, data, flags=None, nodata=np.nan):
# create a flag column if this is explicitly stated
# or if a variable is checked but no corresponding
# flag column exists
- if (flag_params.get(FlagParams.ASSIGN) or
- ((varname in data) and (varname not in flags))):
+ if flag_params.get(FlagParams.ASSIGN) or \
+ (varname in data and varname not in flags):
dummy = pd.DataFrame(index=data.index, columns=[varname])
flags = flags.join(flagger.initFlags(dummy))
- if varname not in data:
+ elif varname not in data and varname not in flags:
continue
dchunk = data.loc[start_date:end_date]
diff --git a/dsl/evaluator.py b/dsl/evaluator.py
index 1f6dee768..f91586190 100644
--- a/dsl/evaluator.py
+++ b/dsl/evaluator.py
@@ -103,15 +103,41 @@ def evalExpression(expr: str, flagger: BaseFlagger,
# name is not referring to an DataFrame field
return field
- try:
- flagcol = namespace["flags"][field]
- if namespace.get("target") == "flags":
- out = flagcol
- else:
+ fidx = namespace["flags"].columns
+ if isinstance(fidx, pd.MultiIndex):
+ fcols = fidx.get_level_values(0).unique()
+ else:
+ fcols = fidx.values
+ dcols = namespace["data"].columns.values
+
+ if namespace.get("target") == "flags":
+ # We are forced to work on flags
+ if field in fcols:
+ out = namespace["flags"][field]
+ elif field in dcols:
+ # Up to now there are no flagging information on the requested
+ # field, so return a fresh new unflagged vector
datacol = namespace["data"][field]
- out = np.ma.masked_array(datacol,
- mask=flagger.isFlagged(flagcol))
- except KeyError:
+ dummy = pd.DataFrame(index=datacol.index, columns=[field])
+ out = flagger.initFlags(dummy)
+ else:
+ _raiseNameError(field, expr)
+
+ elif field in dcols and field in fcols:
+ # Return all unflagged (original) data
+ datacol = namespace["data"][field]
+ flagcol = namespace["flags"][field]
+ out = np.ma.masked_array(datacol, mask=flagger.isFlagged(flagcol))
+
+ elif field in dcols and field not in fcols:
+ # Return all data, because we have no flagging information
+ out = namespace["data"][field].values
+
+ elif field not in dcols and field in fcols:
+ # Return only flag information, because we have no data
+ out = namespace["flags"][field].values
+
+ else:
_raiseNameError(field, expr)
return out
diff --git a/funcs/functions.py b/funcs/functions.py
index 94a65119d..a2c872cc0 100644
--- a/funcs/functions.py
+++ b/funcs/functions.py
@@ -29,6 +29,8 @@ def flagGeneric(data, flags, field, flagger, nodata=np.nan, **flag_params):
data, flags, field,
nodata=nodata)
+ result = result.squeeze()
+
if np.isscalar(result):
raise TypeError(f"expression '{expression}' does not return an array")
--
GitLab