iterrows效率测试

%%timeit
def compare(A, B):
    x = A[0]
    out = []
    for a,b in zip(A,B):
        if b>x:
            out.append(True)
            x = a
        else:
            out.append(False)
    return out

df['compare'] = compare(df['A'], df['B'])
#73.2 µs ± 570 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)

%%timeit
a = df.iloc[0].A#改成a = df['A'][0]效率并没提高
b = []
for idx, row in df.iterrows():
    if row.B > a:
        a = row.A
        b.append(True)
    else:
        b.append(False)
        
df['Expected'] = b
#575 µs ± 7.42 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

进行更复杂的测试，差距还是很大

25万条数据的测试，iterrows内容很简单，速度依然没法跟zip比较