pandas dataframe: loc vs query performance

pandas dataframe: loc vs query performance

For improve performance is possible use

numexpr

:

import numexprnp.random.seed(125)N = 40000000df = pd.Dataframe({'A':np.random.randint(10, size=N)})def ne(df):    x = df.A.values    return df[numexpr.evaluate('(x > 5)')]print (ne(df))In [138]: %timeit (ne(df))1 loop, best of 3: 494 ms per loopIn [139]: %timeit df[df.A > 5]1 loop, best of 3: 536 ms per loopIn [140]: %timeit df.query('A > 5')1 loop, best of 3: 781 ms per loopIn [141]: %timeit df[df.eval('A > 5')]1 loop, best of 3: 770 ms per loop

---

import numexprnp.random.seed(125)def ne(x):    x = x.A.values    return x[numexpr.evaluate('(x > 5)')]def be(x):    return x[x.A > 5]def q(x):    return x.query('A > 5')def ev(x):    return x[x.eval('A > 5')]def make_df(n):    df = pd.Dataframe(np.random.randint(10, size=n), columns=['A'])    return dfperfplot.show(    setup=make_df,    kernels=[ne, be, q, ev],    n_range=[2**k for k in range(2, 25)],    logx=True,    logy=True,    equality_check=False,      xlabel='len(df)')