SpecificationError: Function names must be unique if there is no new column names assigned - pandas

Question

I want to create a new column in the clin dataframe based on the following conditions:
1 if vals>=2*365 or is NAN
otherwise 0
I then assign the new column name as SURV.
import numpy as np
vals = clin['days_to_death'].astype(np.float32)
# non-LTS is 0, LTS is 1
surv = [1 if ( v>=2*365 or np.isnan(v) ) else 0 for v in vals ]
clin['SURV'] = clin.apply(surv, axis=1)
Traceback:
SpecificationError: Function names must be unique if there is no new column names assigned
---------------------------------------------------------------------------
SpecificationError Traceback (most recent call last)
<ipython-input-31-603dee8413ce> in <module>
5 # non-LTS is 0, LTS is 1
6 surv = [1 if ( v>=2*365 or np.isnan(v) ) else 0 for v in vals ]
----> 7 clin['SURV'] = clin.apply(surv, axis=1)
/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/frame.py in apply(self, func, axis, raw, result_type, args, **kwds)
7766 kwds=kwds,
7767 )
-> 7768 return op.get_result()
7769
7770 def applymap(self, func, na_action: Optional[str] = None) -> DataFrame:
/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/apply.py in get_result(self)
146 # multiple values for keyword argument "axis"
147 return self.obj.aggregate( # type: ignore[misc]
--> 148 self.f, axis=self.axis, *self.args, **self.kwds
149 )
150
/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/frame.py in aggregate(self, func, axis, *args, **kwargs)
7572 axis = self._get_axis_number(axis)
7573
-> 7574 relabeling, func, columns, order = reconstruct_func(func, **kwargs)
7575
7576 result = None
/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/aggregation.py in reconstruct_func(func, **kwargs)
93 # there is no reassigned name
94 raise SpecificationError(
---> 95 "Function names must be unique if there is no new column names "
96 "assigned"
97 )
SpecificationError: Function names must be unique if there is no new column names assigned
clin
clin = pd.DataFrame([[1, '466', '47', 0, '90'],
[1, '357', '54', 1, '80'],
[1, '108', '72', 1, '60'],
[1, '254', '51', 0, '80'],
[1, '138', '78', 1, '80'],
[0, nan, '67', 0, '60']], columns=['vital_status', 'days_to_death', 'age_at_initial_pathologic_diagnosis',
'gender', 'karnofsky_performance_score'], index=['TCGA-06-1806', 'TCGA-06-5408', 'TCGA-06-5410', 'TCGA-06-5411',
'TCGA-06-5412', 'TCGA-06-5413'])
Expected output:
vital_status
days_to_death
age_at_initial_pathologic_diagnosis
gender
karnofsky_performance_score
SURV
TCGA-06-1806
1
466
47
0
90
0
TCGA-06-5408
1
357
54
1
80
0
TCGA-06-5410
1
108
72
1
60
0
TCGA-06-5411
1
254
51
0
80
0
TCGA-06-5412
1
138
78
1
80
0
TCGA-06-5413
0
nan
67
0
60
1

Answer 1

Make a new column of all 0's and then update the column with your desired parameters.
clin['SURV'] = 0
clin.loc[pd.to_numeric(clin.days_to_death).ge(2*365) | clin.days_to_death.isna(), 'SURV'] = 1
print(clin)
Output:
vital_status days_to_death age_at_initial_pathologic_diagnosis gender karnofsky_performance_score SURV
TCGA-06-1806 1 466 47 0 90 0
TCGA-06-5408 1 357 54 1 80 0
TCGA-06-5410 1 108 72 1 60 0
TCGA-06-5411 1 254 51 0 80 0
TCGA-06-5412 1 138 78 1 80 0
TCGA-06-5413 0 NaN 67 0 60 1