assign
与列表推导配合使用,从score
字典中获取值的元组(每行),如果未找到则默认为零。
>>> df.assign(score=[score.get(tuple(row), 0) for row in df.values])
gender age cholesterol smoke score
0 1 13 1 0 0
1 1 45 2 0 0
2 0 1 2 1 5
3 1 45 1 1 4
4 1 15 1 7 0
5 0 16 1 8 0
6 0 16 1 3 0
7 0 16 1 4 0
8 1 15 1 4 0
9 0 15 1 2 0
时机
考虑到方法的多样性,我比较一些时间可能会很有趣。
# Initial dataframe 100k rows (10 rows of identical data replicated 10k times).
df = pd.DataFrame(data = {
'gender' : [1, 1, 0, 1, 1, 0, 0, 0, 1, 0] * 10000,
'age' : [13, 45, 1, 45, 15, 16, 16, 16, 15, 15] * 10000,
'cholesterol' : [1, 2, 2, 1, 1, 1, 1, 1, 1, 1] * 10000,
'smoke' : [0, 0, 1, 1, 7, 8, 3, 4, 4, 2] * 10000},
dtype = np.int64)
%timeit -n 10 df.assign(score=[score.get(tuple(v), 0) for v in df.values])
# 223 ms ± 9.28 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
df.assign(score=[score.get(t, 0) for t in zip(*map(df.get, df))])
# 76.8 ms ± 2.8 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
df.assign(score=[score.get(v, 0) for v in df.itertuples(index=False)])
# 113 ms ± 2.58 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%timeit -n 10 df.assign(score=df.apply(lambda x: score.get(tuple(x), 0), axis=1))
# 1.84 s ± 77.3 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
(df
.set_index(['gender', 'age', 'cholesterol', 'smoke'])
.assign(score=pd.Series(score))
.fillna(0, downcast='infer')
.reset_index()
)
# 138 ms ± 11.5 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
s=pd.Series(score)
s.index.names=['gender','age','cholesterol','smoke']
df.merge(s.to_frame('score').reset_index(),how='left').fillna(0).astype(int)
# 24 ms ± 2.27 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
df.assign(score=pd.Series(zip(df.gender, df.age, df.cholesterol, df.smoke))
.map(score)
.fillna(0)
.astype(int))
# 191 ms ± 7.54 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit -n 10
df.assign(score=df[['gender', 'age', 'cholesterol', 'smoke']]
.apply(tuple, axis=1)
.map(score)
.fillna(0))
# 1.95 s ± 134 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
MultiIIndex
。替代方法:df['score'] =df.set_index(['gender', 'age', 'cholesterol', 'smoke']).index.map(score).fillna(0).to_numpy()
。