pandas一些tips

## 异常点去除
for i in COLUMNS_c:
    df[i] = df[np.abs(df[i]-df[i].mean())<=(3*df[i].std())][i] #keep only the ones that are within +3 to -3 standard deviations in the column 'Data'.

## 设置格式，显示多一些
pd.set_option('display.height', 1000)
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.width', 1000)

## 自定义na的值
pd.read_csv('20170524.train.csv.sample', names=COLUMNS,
    na_values='null')