Inflearn Community Q&A

------------------------------------------------------------------------------------------------------------------------

import pandas as pd

def get_human_dataset( ):

    

    feature_name_df = pd.read_csv('./human_activity/features.txt',sep='\s+',

                        header=None,names=['column_index','column_name'])

    feature_name = feature_name_df.iloc[:, 1].values.tolist()

    

    X_train = pd.read_csv('./human_activity/train/X_train.txt',sep='\s+', names=feature_name)

    X_test = pd.read_csv('./human_activity/test/X_test.txt',sep='\s+', names=feature_name)

    

    y_train = pd.read_csv('./human_activity/train/y_train.txt',sep='\s+',header=None,names=['action'])

    y_test = pd.read_csv('./human_activity/test/y_test.txt',sep='\s+',header=None,names=['action'])

    

    # 로드된 학습/테스트용 DataFrame을 모두 반환 

    return X_train, X_test, y_train, y_test

X_train, X_test, y_train, y_test = get_human_dataset()

------------------------------------------------------------------------------------------------------------------------

위와 같이 작성된 코드를 활용해 run 시켰는데 왜인지 모르겠는 아래와 같은 에러가 납니다. 어떻게 수정을 해야하는 것인가요?

-----------------------------------------------------------------------------------------------------------------------

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-2-c35184a6df69> in <module>
     21 
     22 
---> 23 X_train, X_test, y_train, y_test = get_human_dataset()

<ipython-input-2-c35184a6df69> in get_human_dataset()
     10 
     11     # 학습 피처 데이터 셋과 테스트 피처 데이터을 DataFrame으로 로딩. 컬럼명은 feature_name 적용
---> 12     X_train = pd.read_csv('./human_activity/train/X_train.txt',sep='\s+', names=feature_name)
     13     X_test = pd.read_csv('./human_activity/test/X_test.txt',sep='\s+', names=feature_name)
     14 

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, dialect, error_bad_lines, warn_bad_lines, delim_whitespace, low_memory, memory_map, float_precision)
    683         )
    684 
--> 685         return _read(filepath_or_buffer, kwds)
    686 
    687     parser_f.__name__ = name

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in _read(filepath_or_buffer, kwds)
    452 
    453     # Check for duplicates in names.
--> 454     _validate_names(kwds.get("names", None))
    455 
    456     # Create the parser.

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in _validate_names(names)
    419     if names is not None:
    420         if len(names) != len(set(names)):
--> 421             raise ValueError("Duplicate names are not allowed.")
    422     return names
    423 

ValueError: Duplicate names are not allowed.
---------------------------------------------------------------------------------------------------------------------

코딩을 잘 몰라서 대략적으로는 '어떠한 이름자체가 중복되어 일어난일' 정도로 인지가 되는 데 어떤 부분을 수정해야하는 지 모르겠네요.