pandas備忘録

• read_csv

data = pd.io.parsers.read_csv('c:\test.csv',
                                sep=',', header=None, na_values=['-'],
                                dtype={0:'str', 1:'str', 2:'str', 3:'str'})

• 文字列置換

data[0].replace('(\d{4})(\d{2})(\d{2})', '\\1-\\2-\\3', regex=True, inplace=True)

• groupby

data = data.groupby(0)[6].agg({'mean':np.mean, 'std':np.std,
                            'max':lambda x:np.max(x, axis=1),
                            'min':lambda x:np.min(x, axis=1)})