Pandas中Apply函数加速百倍的技巧分享

import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randint(0, 11, size=(1000000, 5)), columns=('a','b','c','d','e'))
def func(a,b,c,d,e):
    if e == 10:
        return c*d
    elif (e < 10) and (e>=5):
        return c+d
    elif e < 5:
        return a+b
%%time
df['new'] = df.apply(lambda x: func(x['a'], x['b'], x['c'], x['d'], x['e']), axis=1)

%%time
# !pip install swifter
import swifter
df['new'] = df.swifter.apply(lambda x : func(x['a'],x['b'],x['c'],x['d'],x['e']),axis=1)
HBox(children=(html(value='Dask Apply'), FloatProgress(value=0.0, max=16.0), HTML(value='')))

%%time
df['new'] = df['c'] * df['d'] #default case e = =10
mask = df['e'] < 10
df.loc[mask,'new'] = df['c'] + df['d']
mask = df['e'] < 5
df.loc[mask,'new'] = df['a'] + df['b']

for col in ('a','b','c','d'):
    df[col] = df[col].astype(np.int16) 
%%time
df['new'] = df['c'] * df['d'] #default case e = =10
mask = df['e'] < 10
df.loc[mask,'new'] = df['c'] + df['d']
mask = df['e'] < 5
df.loc[mask,'new'] = df['a'] + df['b']

%%time
df['new'] = df['c'].values * df['d'].values #default case e = =10
mask = df['e'].values < 10
df.loc[mask,'new'] = df['c'] + df['d']
mask = df['e'].values < 5
df.loc[mask,'new'] = df['a'] + df['b']