Converting a string to number in jupyter - pandas

Question

Here is my code:
def value_and_wage_conversion(value):
if isinstance(value,str):
if 'M' in out:
out = float(out.replace('M', ''))*1000000
elif 'K' in value:
out = float(out.replace('K', ''))*1000
return float(out)
fifa_18['Value'] = fifa_18['Value'].apply(lambda x: value_and_wage_conversion(x))
fifa_18['Wage'] = fifa_18['Wage'].apply(lambda x: value_and_wage_conversion(x))
Here is the error message:
--------------------------------------------------------------------------- UnboundLocalError Traceback (most recent call
last) in
7 return float(out)
8
----> 9 fifa_18['Value'] = fifa_18['Value'].apply(lambda x: value_and_wage_conversion(x))
10 fifa_18['Wage'] = fifa_18['Wage'].apply(lambda x: value_and_wage_conversion(x))
c:\users\brain\appdata\local\programs\python\python39\lib\site-packages\pandas\core\series.py
in apply(self, func, convert_dtype, args, **kwds) 4136
else: 4137 values = self.astype(object)._values
-> 4138 mapped = lib.map_infer(values, f, convert=convert_dtype) 4139 4140 if len(mapped) and
isinstance(mapped[0], Series):
pandas_libs\lib.pyx in pandas._libs.lib.map_infer()
in (x)
7 return float(out)
8
----> 9 fifa_18['Value'] = fifa_18['Value'].apply(lambda x: value_and_wage_conversion(x))
10 fifa_18['Wage'] = fifa_18['Wage'].apply(lambda x: value_and_wage_conversion(x))
in value_and_wage_conversion(value)
1 def value_and_wage_conversion(value):
2 if isinstance(value,str):
----> 3 if 'M' in out:
4 out = float(out.replace('M', ''))*1000000
5 elif 'K' in value:
UnboundLocalError: local variable 'out' referenced before assignment

Answer 1

You were almost there but you need to fix your function
For example
import numpy as np
import pandas as pd
# generate a random sample
values = ['10M', '10K', 10.5, '200M', '200K', 200]
size = 100
np.random.seed(1)
df = pd.DataFrame({
'Value': np.random.choice(values, size),
'Wage': np.random.choice(values, size),
})
print(df)
Value Wage
0 200 200
1 200M 200M
2 200K 200
3 10M 10M
4 10K 200M
.. ... ...
95 200K 200
96 200 200M
97 10.5 200K
98 200K 10.5
99 200M 10M
[100 rows x 2 columns]
Define function and apply
def value_and_wage_conversion(value):
if isinstance(value, str):
if 'M' in value:
value = float(value.replace('M', ''))*1000000
elif 'K' in value:
value = float(value.replace('K', ''))*1000
return float(value)
df['Value'] = df['Value'].apply(lambda x: value_and_wage_conversion(x))
df['Wage'] = df['Wage'].apply(lambda x: value_and_wage_conversion(x))
print(df)
Value Wage
0 200.0 200.0
1 200000000.0 200000000.0
2 200000.0 200.0
3 10000000.0 10000000.0
4 10000.0 200000000.0
.. ... ...
95 200000.0 200.0
96 200.0 200000000.0
97 10.5 200000.0
98 200000.0 10.5
99 200000000.0 10000000.0
[100 rows x 2 columns]
and check
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100 entries, 0 to 99
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Value 100 non-null float64
1 Wage 100 non-null float64
dtypes: float64(2)
memory usage: 1.7 KB