python - 合并列名在列表中的 Pandas 列中的列表

Question

我有三个 Pandas 列，其中元素是 list。为了组合这些列表，我可以通过显式写列的名称和 + 将它们放在一起

df = pd.DataFrame({'allmz':([[1,2,3],[2,4,5],[2,5,5],[2,3,5],[1,4,5]]),'allint':([[11,31,31],[21,41,51],[41,51,51],[11,31,51],[1,51,11]]), 'allx':([[6,7,3],[2,4,5],[2,5,5],[2,9,5],[3,4,5]])})
df['new'] = df['allmz'] + df['allint'] + df['allint']
print df

      allint      allmz       allx                                new
0  [11, 31, 31]  [1, 2, 3]  [6, 7, 3]  [1, 2, 3, 11, 31, 31, 11, 31, 31]
1  [21, 41, 51]  [2, 4, 5]  [2, 4, 5]  [2, 4, 5, 21, 41, 51, 21, 41, 51]
2  [41, 51, 51]  [2, 5, 5]  [2, 5, 5]  [2, 5, 5, 41, 51, 51, 41, 51, 51]
3  [11, 31, 51]  [2, 3, 5]  [2, 9, 5]  [2, 3, 5, 11, 31, 51, 11, 31, 51]
4   [1, 51, 11]  [1, 4, 5]  [3, 4, 5]    [1, 4, 5, 1, 51, 11, 1, 51, 11]

但是，如果我有太多的列名来写每个列名，有没有办法通过循环(或不循环)列名列表来做到这一点:columns = ['allmz','allint','allx'] 代替？

Answer 1

选项 1
在列上切片并沿第一个轴调用 sum。

df['new'] = df[['allmz','allint','allx']].sum(axis=1)

df
         allint      allmz       allx                             new
0  [11, 31, 31]  [1, 2, 3]  [6, 7, 3]  [1, 2, 3, 11, 31, 31, 6, 7, 3]
1  [21, 41, 51]  [2, 4, 5]  [2, 4, 5]  [2, 4, 5, 21, 41, 51, 2, 4, 5]
2  [41, 51, 51]  [2, 5, 5]  [2, 5, 5]  [2, 5, 5, 41, 51, 51, 2, 5, 5]
3  [11, 31, 51]  [2, 3, 5]  [2, 9, 5]  [2, 3, 5, 11, 31, 51, 2, 9, 5]
4   [1, 51, 11]  [1, 4, 5]  [3, 4, 5]   [1, 4, 5, 1, 51, 11, 3, 4, 5]

---

选项 2
np.concatenate 的另一种选择:

v = df[['allmz','allint','allx']].values.tolist()
df['new'] = np.concatenate(v, axis=0).reshape(len(df), -1).tolist()

df

         allint      allmz       allx                             new
0  [11, 31, 31]  [1, 2, 3]  [6, 7, 3]  [1, 2, 3, 11, 31, 31, 6, 7, 3]
1  [21, 41, 51]  [2, 4, 5]  [2, 4, 5]  [2, 4, 5, 21, 41, 51, 2, 4, 5]
2  [41, 51, 51]  [2, 5, 5]  [2, 5, 5]  [2, 5, 5, 41, 51, 51, 2, 5, 5]
3  [11, 31, 51]  [2, 3, 5]  [2, 9, 5]  [2, 3, 5, 11, 31, 51, 2, 9, 5]
4   [1, 51, 11]  [1, 4, 5]  [3, 4, 5]   [1, 4, 5, 1, 51, 11, 3, 4, 5]