I'm trying to find the ratio of 2 columns in a dataframe and store it in a new column in the same dataframe while doing that i'm facing the following error TypeError: unsupported operand type(s) for /: 'float' and 'method' .
My dataset has is nearly 8950 rows and 21 column and i have removed all the NAN's.
>> credit.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8950 entries, 0 to 8949
Data columns (total 21 columns):
CUST_ID 8950 non-null object
BALANCE 8950 non-null float64
BALANCE_FREQUENCY 8950 non-null float64
PURCHASES 8950 non-null float64
ONEOFF_PURCHASES 8950 non-null float64
INSTALLMENTS_PURCHASES 8950 non-null float64
CASH_ADVANCE 8950 non-null float64
PURCHASES_FREQUENCY 8950 non-null float64
ONEOFF_PURCHASES_FREQUENCY 8950 non-null float64
PURCHASES_INSTALLMENTS_FREQUENCY 8950 non-null float64
CASH_ADVANCE_FREQUENCY 8950 non-null float64
CASH_ADVANCE_TRX 8950 non-null int64
PURCHASES_TRX 8950 non-null int64
CREDIT_LIMIT 8950 non-null object
PAYMENTS 8950 non-null float64
MINIMUM_PAYMENTS 8950 non-null object
PRC_FULL_PAYMENT 8950 non-null float64
TENURE 8950 non-null int64
Monthly_avg_purchase 8950 non-null float64
Monthly_cash_advance 8950 non-null float64
purchase_type 8950 non-null object
dtypes: float64(14), int64(3), object(4)
memory usage: 1.3+ MB
and when i'm trying to find the ratio i'm hitting error. the error string and the code are below.
>> credit['LIMIT_USAGE'] = credit['BALANCE']/credit['CREDIT_LIMIT']
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\ops\__init__.py in na_op(x, y)
967 try:
--> 968 result = expressions.evaluate(op, str_rep, x, y, **eval_kwargs)
969 except TypeError:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\computation\expressions.py in evaluate(op, op_str, a, b, use_numexpr, **eval_kwargs)
220 if use_numexpr:
--> 221 return _evaluate(op, op_str, a, b, **eval_kwargs)
222 return _evaluate_standard(op, op_str, a, b)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\computation\expressions.py in _evaluate_numexpr(op, op_str, a, b, truediv, reversed, **eval_kwargs)
126 if result is None:
--> 127 result = _evaluate_standard(op, op_str, a, b)
128
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\computation\expressions.py in _evaluate_standard(op, op_str, a, b, **eval_kwargs)
69 with np.errstate(all="ignore"):
---> 70 return op(a, b)
71
TypeError: unsupported operand type(s) for /: 'float' and 'method'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-40-b24cdb4eaf3e> in <module>
----> 1 credit['LIMIT_USAGE'] = credit['BALANCE']/credit['CREDIT_LIMIT']
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\ops\__init__.py in wrapper(left, right)
1046
1047 with np.errstate(all="ignore"):
-> 1048 result = na_op(lvalues, rvalues)
1049 return construct_result(
1050 left, result, index=left.index, name=res_name, dtype=None
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\ops\__init__.py in na_op(x, y)
968 result = expressions.evaluate(op, str_rep, x, y, **eval_kwargs)
969 except TypeError:
--> 970 result = masked_arith_op(x, y, op)
971
972 return missing.dispatch_fill_zeros(op, x, y, result)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\ops\__init__.py in masked_arith_op(x, y, op)
445 if mask.any():
446 with np.errstate(all="ignore"):
--> 447 result[mask] = op(xrav[mask], com.values_from_object(yrav[mask]))
448
449 else:
TypeError: unsupported operand type(s) for /: 'float' and 'method'
I have tried using apply function also and even that did not work. the code and error for the apply is pasted below
>> credit['limit_usage']=credit.apply(lambda x: x['BALANCE']/x['CREDIT_LIMIT'], axis=1)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-43-2b06fadbf803> in <module>
----> 1 credit['limit_usage']=credit.apply(lambda x: x['BALANCE']/x['CREDIT_LIMIT'], axis=1)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
6911 kwds=kwds,
6912 )
-> 6913 return op.get_result()
6914
6915 def applymap(self, func):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\apply.py in get_result(self)
184 return self.apply_raw()
185
--> 186 return self.apply_standard()
187
188 def apply_empty_result(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\apply.py in apply_standard(self)
290
291 # compute the result using the series generator
--> 292 self.apply_series_generator()
293
294 # wrap results
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
319 try:
320 for i, v in enumerate(series_gen):
--> 321 results[i] = self.f(v)
322 keys.append(v.name)
323 except Exception as e:
<ipython-input-43-2b06fadbf803> in <lambda>(x)
----> 1 credit['limit_usage']=credit.apply(lambda x: x['BALANCE']/x['CREDIT_LIMIT'], axis=1)
TypeError: ("unsupported operand type(s) for /: 'float' and 'method'", 'occurred at index 5203')
Please suggest a quick solution for this.
Thanks in advance.
Just a slight modification to your code is needed to make it work.
>>> df = pd.DataFrame({"BALANCE": [100, 255], "CREDIT_BALANCE": [10, 15]})
>>> df
BALANCE CREDIT_BALANCE
0 100 10
1 255 15
>>>
>>> df["limit_usage"] = df.apply(lambda row: row.BALANCE / row.CREDIT_BALANCE, axis=1)
>>> df
BALANCE CREDIT_BALANCE limit_usage
0 100 10 10.0
1 255 15 17.0
>>>
Try something like that and see if that makes a difference.
The Apply-function above works only if both values can be divided.
If you have a custom class, then you can do something like this to make it work:
class things:
def __init__(self, var):
self.var = var
def __int__(self):
return int(self.var)
def __repr__(self):
return "things({})".format(self.var)
df = pd.DataFrame({"BALANCE": [100, 255], "CREDIT_BALANCE": [things(10), things(15)]})
df["limit_usage"] = df.apply(lambda row: row.BALANCE / int(row.CREDIT_BALANCE), axis=1)
print(df)
Output:
BALANCE CREDIT_BALANCE limit_usage
0 100 things(10) 10.0
1 255 things(15) 17.0