R, Python 분석과 프로그래밍의 친구 (by R Friend)

  (1) pd.to_numeric() 함수를 이용한 문자열 칼럼의 숫자형 변환

import numpy as np

import pandas as pd

# make a DataFrame

df = pd.DataFrame({'col_str': ['1', '2', '3', '4', '5']})

df

# check data types 

df.dtypes

col_str    object
dtype: object

df['col_int'] = pd.to_numeric(df['col_str'])

df

df.dtypes

col_str    object
col_int     int64
dtype: object

# make a DataFrame with 3 string columns

df2 = pd.DataFrame({'col_str_1': ['1', '2', '3'], 

                   'col_str_2': ['4', '5', '6'], 

                   'col_str_3': ['7.0', '8.1', '9.2']})

df2

df2.dtypes

col_str_1    object
col_str_2    object
col_str_3    object
dtype: object

# convert 'col_str_1' and 'col_str_2' to numeric

df2[['col_int_1', 'col_int_2']] = df2[['col_str_1', 'col_str_2']].apply(pd.to_numeric)

df2

df2.dtypes

col_str_1    object
col_str_2    object
col_str_3    object
col_int_1     int64
col_int_2     int64
dtype: object

# convert all columns of a DataFrame to numeric using apply() and to_numeric together

df3 = df2.apply(pd.to_numeric)

df3.dtypes

col_str_1      int64
col_str_2      int64
col_str_3    float64
col_int_1      int64
col_int_2      int64
dtype: object

  (2) astype() 메소드를 이용한 문자열 칼럼의 숫자형 변환

df4 = pd.DataFrame({'col_str_1': ['1', '2', '3'], 

                   'col_str_2': ['4.1', '5.5', '6.0']}) 

df4.dtypes

col_str_1    object
col_str_2    object
dtype: object

df5 = df4.astype(float)

df5

df5.dtypes

col_str_1    float64
col_str_2    float64
dtype: object

df6 = df4.astype({'col_str_1': int, 

                  'col_str_2': np.float})

df6

 df6.dtypes

col_str_1      int64
col_str_2    float64
dtype: object

  DataFrame에 문자가 포함된 칼럼이 같이 있을 경우 ValueError

df7 = pd.DataFrame({'col_1': ['1', '2', '3'], 

                   'col_2': ['aaa', 'bbb', 'ccc']})

df7

df7.dtypes

col_1    object
col_2    object
dtype: object

# ValueError

df7 = df7.apply(pd.to_numeric)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
pandas/_libs/src/inference.pyx in pandas._libs.lib.maybe_convert_numeric()

ValueError: Unable to parse string "aaa"

During handling of the above exception, another exception occurred:
-- 중간 생략 --

~/anaconda3/lib/python3.6/site-packages/pandas/core/tools/numeric.py in to_numeric(arg, errors, downcast)
    124             coerce_numeric = False if errors in ('ignore', 'raise') else True
    125             values = lib.maybe_convert_numeric(values, set(),
--> 126                                                coerce_numeric=coerce_numeric)
    127 
    128     except Exception:

pandas/_libs/src/inference.pyx in pandas._libs.lib.maybe_convert_numeric()

ValueError: ('Unable to parse string "aaa" at position 0', 'occurred at index col_2')

# ValueError

df7 = df7.astype(int)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-124-f50dad302c83> in <module>()
----> 1 df7 = df7.astype(int)

-- 중간 생략 --

~/anaconda3/lib/python3.6/site-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy)
    623     elif arr.dtype == np.object_ and np.issubdtype(dtype.type, np.integer):
    624         # work around NumPy brokenness, #1987
--> 625         return lib.astype_intsafe(arr.ravel(), dtype).reshape(arr.shape)
    626 
    627     if dtype.name in ("datetime64", "timedelta64"):

pandas/_libs/lib.pyx in pandas._libs.lib.astype_intsafe()

pandas/_libs/src/util.pxd in util.set_value_at_unsafe()
 

ValueError: invalid literal for int() with base 10: 'aaa' 

 문자열을 숫자형으로 변환 시 ValueError 를 무시하기: df.apply(pd.to_numeric, errors = 'coerce') 

df8 = pd.DataFrame({'col_1': ['1', '2', '3'], 

                   'col_2': ['4', 'bbb', '6']})

df8

df8 = df8.apply(pd.to_numeric)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
pandas/_libs/src/inference.pyx in pandas._libs.lib.maybe_convert_numeric()

ValueError: Unable to parse string "bbb"

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-130-9e8d711c10d5> in <module>()
----> 1 df8 = df8.apply(pd.to_numeric)

~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in apply(self, func, axis, broadcast, raw, reduce, args, **kwds)
   4260                         f, axis,
   4261                         reduce=reduce,
-> 4262                         ignore_failures=ignore_failures)
   4263             else:
   4264                 return self._apply_broadcast(f, axis)

~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in _apply_standard(self, func, axis, ignore_failures, reduce)
   4356             try:
   4357                 for i, v in enumerate(series_gen):
-> 4358                     results[i] = func(v)
   4359                     keys.append(v.name)
   4360             except Exception as e:

~/anaconda3/lib/python3.6/site-packages/pandas/core/tools/numeric.py in to_numeric(arg, errors, downcast)
    124             coerce_numeric = False if errors in ('ignore', 'raise') else True
    125             values = lib.maybe_convert_numeric(values, set(),
--> 126                                                coerce_numeric=coerce_numeric)
    127 
    128     except Exception:

pandas/_libs/src/inference.pyx in pandas._libs.lib.maybe_convert_numeric()

ValueError: ('Unable to parse string "bbb" at position 1', 'occurred at index col_2')

df8