1、处理数据简介
下载链接:https://www.kaggle.com/maxhorowitz/nflplaybyplay2009to2016?select=NFL+Play+by+Play+2009-2016+%28v3%29.csv
2、空值探索
(1)每列空值数量
missing_values_count = nfl_data.isnull().sum()
(2)空值比例计算
total_cells = np.product(nfl_data.shape)
total_missing = missing_values_count.sum()
percent_missing = (total_missing/total_cells) * 100
3、空值处理
(1)全部删除
nfl_data.dropna()
(2)按列方向删除
nfl_data.dropna(axis=1)
(3)补0操作
subset_nfl_data.fillna(0)
(4)就近补0操作
subset_nfl_data.fillna(method=‘bfill’, axis=0)