Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
|
software_development:python_pandas [2022/08/04 15:00] prgram [order of columns] |
software_development:python_pandas [2023/05/16 15:09] prgram [encoding_errors - 'ignore'] |
||
|---|---|---|---|
| Line 27: | Line 27: | ||
| <code python> | <code python> | ||
| df.groupby([컬럼들]).agg({'컬럼':sum}).reset_index() | df.groupby([컬럼들]).agg({'컬럼':sum}).reset_index() | ||
| + | |||
| + | df.groupby([COLUMNS])['COLUMN'].max().reset_index() | ||
| df = df.assign(date=pd.to_numeric(df['date'], errors='coerce')).groupby(['코드', '종목명']).agg({'date':np.min}).reset_index().drop_duplicates() | df = df.assign(date=pd.to_numeric(df['date'], errors='coerce')).groupby(['코드', '종목명']).agg({'date':np.min}).reset_index().drop_duplicates() | ||
| Line 105: | Line 107: | ||
| iloc: Select by position | iloc: Select by position | ||
| loc: Select by label | loc: Select by label | ||
| + | | ||
| + | df.loc[:,~df.columns.isin(['a','b'])] | ||
| + | |||
| + | df[~( df['a'].isin(['1','2','3']) & df['b']=='3' )] #row-wise | ||
| + | df.loc[~( df['a'].isin(['1','2','3']) & df['b']=='3' ), 8] #row-wise & column | ||
| </code> | </code> | ||
| Line 116: | Line 123: | ||
| | | ||
| =====I/O file===== | =====I/O file===== | ||
| + | |||
| + | === encoding_errors - 'ignore'=== | ||
| + | Encoding 제대로 했는데도 안되면.. | ||
| + | 공공데이터가 이런 경우가 많음. | ||
| + | |||
| + | <code python> | ||
| + | import chardet | ||
| + | with open(file, 'rb') as rawdata: | ||
| + | result = chardet.detect(rawdata.read(100000)) | ||
| + | result | ||
| + | |||
| + | |||
| + | data = pd.read_csv( file, encoding='cp949', encoding_errors='ignore') | ||
| + | # on_bad_lines='skip' | ||
| + | # error_bad_lines=False | ||
| + | </code> | ||
| === to_numberic === | === to_numberic === | ||
